Control method and system of personalized intelligent mattress

Abstract

The invention provides a control method and system for a personalized intelligent mattress, and relates to the technical field of intelligent home control, and the method comprises the steps: obtaining human body pressure data and human body temperature data on the intelligent mattress as sample data; preprocessing the sample data; determining a cluster center of the sample data and a membership degree corresponding to the cluster center through a fuzzy C-means clustering method; based on the cluster center and the membership degree, performing human body region division on the intelligent mattress; performing feature extraction according to a human body region division result, and determining data features; according to the data features, sleeping postures are classified; determining human body pressure data of various sleeping postures based on the sleeping posture classification result; determining human body back surface data in an upright state; in combination with the human body back surface data and the human body pressure data of various sleeping postures, performing comfort evaluation on the sleeping postures; and controlling the intelligent mattress through a PID (Proportion Integration Differentiation) controller according to a comfort level evaluation result. The adaptability and comfort of the intelligent mattress can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of smart home control, and particularly to a control method and system for a personalized smart mattress. Background Art

[0002] The control method of a personalized smart mattress is a technology that based on sensors and intelligent algorithms to monitor and adjust the user's sleep state, body shape characteristics and personal preferences in real time. It usually combines pressure sensors and artificial intelligence algorithms to analyze data and dynamically adjust the mattress to optimize the user's sleep quality.

[0003] With the improvement of people's living standards, the attention to sleep quality has increased day by day. Traditional mattresses cannot meet the needs of different individuals. Especially as people age or their health conditions change, the comfort requirements for mattresses also change. A personalized smart mattress can automatically adjust the mattress by real-time monitoring of the user's sleeping posture, body pressure distribution and other physiological data, so as to provide a tailor-made comfortable experience for different users, relieve stress, improve sleep quality, help relieve fatigue, and even contribute to disease prevention and recovery.

[0004] However, in traditional mattress control methods, the adjustment of the mattress usually only relies on single pressure data or temperature data, ignoring the in-depth analysis of the user's physiological data, and unable to perform personalized adjustment according to the sleeping postures of different users. As a result, the adjustment of the mattress cannot truly meet the unique needs of each user. When evaluating comfort, only static data (fixed temperature and pressure) is considered, without considering the change of sleeping posture, resulting in difficulty in maintaining comfort for a long time. Summary of the Invention

[0005] In order to solve the technical problems in traditional mattress control methods, where the adjustment of the mattress usually only relies on single pressure data or temperature data, ignoring the in-depth analysis of the user's physiological data, unable to perform personalized adjustment according to the sleeping postures of different users, resulting in the adjustment of the mattress not truly meeting the unique needs of each user, and when evaluating comfort, only static data (fixed temperature and pressure) is considered without considering the change of sleeping posture, leading to difficulty in maintaining comfort for a long time, the present invention provides a control method and system for a personalized smart mattress.

[0006] The technical solutions provided by the embodiments of the present invention are as follows:

[0007] First aspect:

[0008] A control method for a personalized smart mattress provided by an embodiment of the present invention includes:

[0009] S1: Obtain the human pressure data and human temperature data on the smart mattress as sample data;

[0010] S2: Preprocess the sample data;

[0011] S3: Determine the cluster centers of the sample data and the membership degrees corresponding to the cluster centers through the fuzzy C - means clustering method according to the preprocessed sample data;

[0012] S4: Divide the human body regions of the intelligent mattress based on the cluster centers and the membership degrees;

[0013] S5: Extract features from the preprocessed sample data according to the human body region division result to determine data features;

[0014] S6: Classify the sleeping postures according to the data features;

[0015] S7: Determine the human body pressure data of various sleeping postures based on the sleeping posture classification result;

[0016] S8: Determine the human body back surface data in the upright state;

[0017] S9: Evaluate the comfort of the sleeping postures by combining the human body back surface data and the human body pressure data of various sleeping postures;

[0018] S10: Control the intelligent mattress through a PID controller according to the comfort evaluation result.

[0019] Second aspect:

[0020] A control system of a personalized intelligent mattress provided by an embodiment of the present invention includes: a memory and one or more processors;

[0021] One or more application programs are stored in the memory, and the one or more application programs are adapted to be executed by the one or more processors to implement the above - mentioned control method of the personalized intelligent mattress.

[0022] The beneficial effects brought by the technical solution provided by the embodiment of the present invention at least include:

[0023] In the embodiment of the present invention, the pressure and temperature data of the user are processed through the fuzzy C - means clustering method. By combining sleeping posture classification and region division, personalized region adjustment is provided for each user, enabling the mattress to more precisely adapt to the physiological needs of the user and providing the best comfort. By comprehensively considering the influence of different sleeping postures, body types, and back pressure distributions on comfort in the comfort evaluation of sleeping postures, the sleep needs of the user are accurately reflected. By combining the PID controller and the simulated annealing algorithm, dynamic adjustment can be performed according to the real - time comfort error to ensure that the comfort of the user is always in the best balance. This intelligent adjustment mechanism can effectively cope with changes in different sleeping postures and health states, improving the adaptability and comfort of the mattress. Description of the Drawings

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0025] Figure 1 It is a schematic flowchart of a control method for a personalized intelligent mattress provided by an embodiment of the present invention;

[0026] Figure 2 It is a schematic structural diagram of a control system for a personalized intelligent mattress provided by an embodiment of the present invention. Detailed implementation manners

[0027] The following will describe the technical solutions in the present invention in conjunction with the drawings.

[0028] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "example" in the present invention should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the use of the word "example" is intended to present concepts in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two.

[0029] To make the technical problems to be solved, technical solutions and advantages of the present invention clearer, the following will be described in detail in conjunction with the drawings and specific embodiments.

[0030] Referring to the attached Figure 1 illustrates a schematic flowchart of a control method for a personalized intelligent mattress provided by an embodiment of the present invention.

[0031] The embodiments of the present invention provide a control method for a personalized intelligent mattress, and the method includes:

[0032] S1: Obtain the human body pressure data and human body temperature data on the intelligent mattress as sample data.

[0033] Among them, the human body pressure data refers to the information reflecting the pressure borne by each part of the human body on the mattress collected by the pressure sensor. These data help to judge the support of the mattress and whether it is evenly distributed. The human body temperature data refers to the temperature change of the user's body surface measured by the temperature sensor, reflecting the heat distribution of the human body and helping to evaluate the temperature control effect and comfort of the mattress.

[0034] In the present invention, the intelligent mattress includes a pressure sensor and an infrared sensor. The human pressure data is obtained through the pressure sensor, and the human body temperature data is obtained through the infrared sensor.

[0035] It should be noted that by obtaining the pressure data and temperature data of the human body, the specific physiological conditions of the user on the mattress can be comprehensively understood, which can provide accurate real-time data for the intelligent adjustment of the mattress, ensuring that the mattress can be dynamically adjusted according to different user needs and changes in sleeping postures.

[0036] In a possible implementation manner, S1 is specifically:

[0037] The human pressure data is obtained through the pressure sensor, and the human body temperature data is obtained through the infrared sensor.

[0038] Among them, the pressure sensor is a sensor that can sense the pressure exerted on an object. In the mattress, the pressure sensor is used to measure the pressure distribution of the human body on the mattress surface, helping to analyze the user's body shape, sleeping posture, and the support condition of the mattress. The infrared sensor is a sensor that can sense the infrared radiation emitted by an object. The infrared sensor determines the temperature change of the human body by measuring the infrared rays radiated by the human body and is commonly used to measure the surface temperature.

[0039] S2: Preprocess the sample data.

[0040] In a possible implementation manner, S2 is specifically:

[0041] Preprocess the sample data including noise reduction:

[0042]

[0043] Among them, MAF represents the sample data after moving average filtering, N represents the size of the filtering window, and x n represents the sample data at the nth moment.

[0044] Among them, the moving average filter (MAF) is a common signal smoothing technique used to remove noise in the data and smooth the data fluctuations, reducing the influence of high-frequency noise by calculating the average value of the data within a certain time window.

[0045] It should be noted that preprocessing the sample data for noise reduction can remove possible environmental noise, sensor errors, or external interferences during the acquisition process, ensuring the accuracy and reliability of the data. Through noise reduction processing, unnecessary signal fluctuations can be avoided from affecting subsequent analysis, making the mattress more accurate in terms of pressure and temperature adjustment.

[0046] S3: Based on the preprocessed sample data, determine the cluster centers of the sample data and the membership degrees corresponding to the cluster centers through the fuzzy C-means clustering method.

[0047] Among them, the fuzzy C-means clustering method (FCM) is a clustering algorithm that realizes data grouping by assigning data points to multiple clusters and weighting them according to membership degrees. In FCM, each data point can belong to multiple clusters simultaneously, and each cluster has a membership degree (ranging from 0 to 1). The goal of clustering is to minimize the weighted error of the distance from each data point to the cluster center. The cluster center refers to the center point of each cluster (or class) in the clustering algorithm, usually the weighted average of all data points within the cluster. In FCM, the cluster center is determined based on the membership degrees of the data points and the data characteristics. The membership degree represents the degree to which a data point belongs to a certain cluster, and its value ranges from 0 to 1. A value of 1 indicates complete membership in the cluster, and a value of 0 indicates complete non-membership. A value between 0 and 1 indicates the degree of membership of the point in multiple clusters.

[0048] It should be noted that by processing the preprocessed sample data through the fuzzy C-means clustering method, more flexible and accurate data grouping can be achieved. Different from traditional clustering methods, FCM allows a data point to have different membership degrees in multiple clusters, which makes the clustering more in line with the complexity of the data. This method can effectively capture the data characteristics of different regions or sleeping postures and provide a reliable basis for subsequent mattress area division and comfort evaluation, ensuring the accuracy of personalized adjustment.

[0049] In a possible implementation manner, S3 specifically includes:

[0050] S301: Set the number of clusters and the stopping threshold;

[0051] S302: Initialize the membership degree matrix;

[0052] S303: Calculate the cluster centers:

[0053]

[0054] where c k represents the k-th cluster center, x i represents the i-th data point in the sample data, i = 1, 2,..., n, n represents the total number of data points, u ik represents the membership degree of the i-th data point in the k-th cluster, and m represents the fuzzy factor;

[0055] S303: Calculate the membership degree matrix corresponding to the cluster centers:

[0056]

[0057] Among them, c l represents the l-th cluster center, where l = 1, 2, ..., c, and c represents the total number of clusters;

[0058] S304: Calculate the objective function according to the cluster center and membership degree:

[0059]

[0060] Among them, A represents the objective function, and x iP represents the component of the i-th data point in the P-th dimension, and x iN represents the component of the i-th data point in the N-th dimension, and c kP represents the cluster center of the k-th cluster in the P-th dimension, and c kN represents the cluster center of the k-th cluster in the N-th dimension;

[0061] S305: Determine whether the termination condition is reached; if so, output the cluster center and the membership degree corresponding to the cluster center, otherwise, return to step S303.

[0062] In a possible implementation manner, the termination condition is specifically:

[0063]

[0064] Among them, represents the objective function of the t-th iteration, represents the objective function of the (t - 1)-th iteration, and ε represents the stop threshold.

[0065] S4: Based on the cluster center and membership degree, perform human body area division on the intelligent mattress.

[0066] It should be noted that performing human body area division based on the cluster center and membership degree can accurately match each area of the mattress with the user's body characteristics. The cluster center and membership degree obtained by the fuzzy C-means clustering method can accurately divide the support requirements of each area of the mattress, avoiding the simple practice of uniformly adjusting all areas. Different body parts are optimized according to the actual pressure and temperature requirements, improving the adaptability and comfort of the mattress.

[0067] In a possible implementation manner, S4 specifically includes:

[0068] S401: Determine the center and the central axis according to the cluster center and membership degree;

[0069] S402: Perform human body area division according to the center and the central axis.

[0070] It should be noted that determining the center and central axis based on cluster centers and membership degrees, and then dividing the human body into regions based on this information can more accurately reflect the specific needs of each region. Determining the center and central axis helps to clarify the support requirements of the human body on the mattress, so that fine adjustments can be made according to the pressure and comfort needs of different regions, avoiding a single global adjustment, and being able to optimize different body parts (such as the head, back, buttocks, legs) separately, thereby improving the accuracy of mattress adjustment and enhancing the user's sleep comfort and overall experience.

[0071] In the present invention, the position of the data point with the largest membership is selected to determine the horizontal and vertical central axes. In the horizontal direction, the left and right clusters are usually background clusters, and the middle cluster represents the torso. The position with the largest membership in the middle cluster is selected as the torso central axis. In the vertical direction, the middle cluster corresponds to the waist, the upper cluster is the chest, and the lower cluster is the buttocks. The position with the largest membership in the vertical middle cluster is selected as the waist central axis. The intersection of the horizontal and vertical central axes is taken as the final center. According to the intersection and the central axis, the body area is divided into the torso area and the limb area, and further divided into sub-areas such as the left chest, right chest, left hip, right hip, left leg, and right leg.

[0072] S5: According to the human body area division result, feature extraction is performed on the preprocessed sample data to determine data features.

[0073] It should be noted that feature extraction based on the results of human body area division can deeply explore the specific data characteristics of each area of ​​the mattress, providing an accurate basis for personalized adjustment. By extracting left-right symmetry features, chest-hip symmetry features, etc., the system can understand the pressure requirements, temperature changes, etc. of each area, thereby achieving regional optimization and adjustment. This method can ensure that the mattress can be finely adjusted according to the needs of different parts of the body, avoiding simple and unified adjustment methods, and improving user comfort and sleep quality.

[0074] In a possible implementation, the human body segmentation result specifically includes: a left chest area, a right chest area, a left hip area, a right hip area, a left leg area, and a right leg area.

[0075] The data features specifically include: left-right symmetry, chest-hip symmetry, and leg symmetry.

[0076] Among them, the left-right symmetry feature refers to whether the pressure or temperature distribution on the left and right sides of the human body on the mattress is symmetric. Since the left and right parts of the human body are usually symmetric, the left-right symmetry feature is used to evaluate whether the support and comfort on both sides of the mattress are balanced, ensuring uniform support on both sides. The chest-hip symmetry feature refers to whether the pressure distribution or support characteristics in the chest and hip areas of the human body are symmetric. The chest and hips are important areas of the human body, and the chest-hip symmetry feature evaluates whether these areas receive appropriate support, especially the impact on the hardness and comfort of the mattress. The leg symmetry feature refers to whether the pressure and temperature distribution in the two leg areas of the human body are symmetric. This feature helps to judge whether the support for both legs by the mattress is balanced, ensuring the comfort and support of the legs and avoiding discomfort or pressure concentration.

[0077] S5 is specifically as follows:

[0078] Through the following formula, feature extraction is performed on the preprocessed sample data to determine the data features:

[0079] T D-RL =(C R +H R )-(C L +H L )

[0080] T D-CH =(C R +C L )-(H R +H L )

[0081] L D-RL =|L R -L L |

[0082] Among them, T D-RL represents the left-right symmetry feature, T C-CH represents the chest-hip symmetry feature, C R represents the right chest area, H R represents the right hip area, C L represents the left chest area, H L represents the left hip area, L D-RL represents the leg symmetry feature, L R represents the right leg area, L L represents the left leg area.

[0083] S6: According to the data features, perform sleep posture classification.

[0084] It should be noted that classifying sleeping postures based on data characteristics can accurately identify different types of sleeping postures according to the user's body characteristics and the pressure and temperature distribution of the mattress. This can help the system understand the user's sleeping habits, and then optimize the support requirements of the mattress for different sleeping postures. Through classification, the mattress can dynamically adjust the hardness, temperature, etc. of each area, so that each sleeping posture can obtain the best comfort, thus significantly improving the user's sleep quality and overall comfort experience.

[0085] In the present invention, the data characteristics are marked as supine, left lateral lying, right lateral lying, and prone, and a support vector machine is used for sleeping posture classification.

[0086] S7: Based on the sleeping posture classification result, determine the human body pressure data for each type of sleeping posture.

[0087] Among them, the sleeping posture classification results are: supine, left lateral lying, right lateral lying, and prone.

[0088] It should be noted that based on the sleeping posture classification result, determining the human body pressure data for each type of sleeping posture can provide a basis for personalized sleep health monitoring. By analyzing the pressure changes in each sleeping posture, the deformation of the corresponding area of the mattress in each sleeping posture can be determined, providing a basis for comfort estimation.

[0089] S8: Determine the human body back surface data in the upright state.

[0090] By collecting the back surface data in the upright state through a 3D scanner, the pressure distribution and support points of the human back in the natural standing position can be accurately understood, which helps to evaluate the health status of the spine and back and provides a basis for comfort estimation.

[0091] S9: Combine the human body back surface data and the human body pressure data for each type of sleeping posture to evaluate the comfort of the sleeping posture.

[0092] It should be noted that by combining the human body back surface data and the human body pressure data for each type of sleeping posture, the pressure impact of different sleeping postures on various parts of the body can be more comprehensively understood, so as to evaluate the load degree on important parts such as the spine and back during sleep, effectively identify the compression and discomfort of different sleeping postures on the body, and then provide data support for personalized sleep comfort optimization.

[0093] In a possible implementation manner, S9 specifically includes:

[0094] S901: Combine the human body back surface data and the human body pressure data for each type of sleeping posture to determine the back shape from the shoulder to the hip and the deformation of the corresponding area of the mattress;

[0095] S902: Calculate the comfort index of the sleeping posture:

[0096]

[0097] Among them, CL represents the comfort index, r(α,β) represents the similarity between vectors α and β, α represents the back shape from the shoulder to the hip, and β represents the deformation of the corresponding area of the mattress;

[0098] S903: Calculate the discomfort index of the sleeping position:

[0099]

[0100] Among them, DL represents the discomfort index;

[0101] S903: According to the comfort index and the discomfort index, evaluate the comfort of the sleeping position.

[0102] When CL = 1, DL = 0, and the comfort of the sleeping position is comfortable;

[0103] When CL = 0, DL = 0.5, and the comfort of the sleeping position is moderately uncomfortable;

[0104] When CL = -1, DL = 1, and the comfort of the sleeping position is very uncomfortable.

[0105] S10: According to the comfort evaluation result, control the intelligent mattress through a PID controller.

[0106] Among them, the PID controller (Proportional-Integral-Derivative Controller) is a commonly used feedback controller. It adjusts the proportional (P), integral (I), and derivative (D) control quantities to perform real-time adjustment on the system. In the application of the intelligent mattress, the PID controller adjusts the angle, hardness, and support area of the mattress in real time according to the comfort evaluation result to optimize the sleeping position and improve comfort.

[0107] It should be noted that by adjusting the state of the mattress through intelligent control, the hardness and angle of the mattress can be automatically optimized according to the real-time comfort evaluation result, improving the comfort of the user, providing a personalized sleep experience. The PID controller can accurately and dynamically respond to body changes, ensure the best comfort level is maintained throughout the sleep process, reduce the physical pressure caused by mattress discomfort, and thus improve sleep quality.

[0108] In a possible implementation manner, the comfort evaluation result specifically includes: comfortable, moderately uncomfortable, and very uncomfortable;

[0109] S10 specifically includes:

[0110] S1001: According to the comfort evaluation result, calculate the comfort error:

[0111] e(t) = CL target-CL current

[0112] Among them, e(t) represents the current comfort error, and CL target represents the desired comfort, and CL current represents the current comfort.

[0113] S1002: Optimize the PID controller through the simulated annealing algorithm.

[0114] Optimizing the PID controller through the simulated annealing algorithm specifically includes:

[0115] S10021: Define the optimization objective:

[0116]

[0117] Among them, E current represents the current optimization objective function, and T represents the upper limit of integration.

[0118] S10022: Initialize the PID controller parameters;

[0119] Define the control parameters of simulated annealing. Among them, the control parameters include the initial temperature, the cooling rate, and the stopping temperature;

[0120] S10023: Optimize the PID control parameters:

[0121] K′ p = K p + ΔK p × f(T)

[0122] K′ i = K i + ΔK i × f(T)

[0123] K′ d = K d + ΔK d × f(T)

[0124] Among them, K′ p , K′ i and K′ d respectively represent the optimized proportional gain, integral gain, and derivative gain. K p represents the proportional gain, K i represents the integral gain, K d represents the derivative gain, ΔK p , ΔK i and ΔK d respectively represent the perturbations of the proportional gain, integral gain, and derivative gain, and f(T) represents the temperature-related function.

[0125] f(T) is a temperature-related function. Generally, as the temperature decreases, the amplitude of the perturbation also decreases. Its role is to scale the perturbation according to the current temperature, thereby controlling the breadth and precision of the search.

[0126] S10024: Update the objective function based on the new PID control parameters

[0127]

[0128] Among them, E new represents the new optimized objective function.

[0129] S10025: Calculate the change in the objective function:

[0130] ΔE = E new - E current

[0131] Among them, ΔE represents the change in temperature.

[0132] S10026: According to the change in the objective function, determine whether to accept the new PID controller parameters; if so, enter step S10027, otherwise return to step S10023.

[0133] Specifically, determining whether to accept the new PID controller parameters is as follows:

[0134] Determine whether to accept the new PID controller parameters according to the following probability:

[0135]

[0136] Among them, P represents the acceptance probability, and T represents the current temperature.

[0137] S10027: Update the temperature:

[0138] T new = α × T

[0139] Among them, T represents the updated temperature, T represents the current temperature, and α represents the cooling rate.

[0140] S10028: Determine whether the updated temperature has reached the stop temperature; if so, output the optimal PID control parameters, otherwise return to step S10023.

[0141] S1003: Output the control signal according to the optimized PID controller:

[0142]

[0143] Among them, u(t) represents the control signal, and K p represents the proportional gain, and K iRepresents the integral gain, K d Represents the differential gain, and d represents the differential operator.

[0144] S1004: Control the intelligent mattress according to the control signal.

[0145] In the present invention, the intelligent mattress includes an airbag adjustment module and a support module. Among them, the support module includes an electric drive, a linkage mechanism, and a support frame. The intelligent mattress controls the inflation and deflation of the airbag through the airbag adjustment module to adjust the hardness of the mattress, and controls the electric drive to drive the linkage mechanism through the support module to adjust the angle of the mattress, so that the support area of the mattress reaches the best state.

[0146] The beneficial effects brought by the technical solution provided by the embodiment of the present invention at least include:

[0147] In the embodiment of the present invention, through the fuzzy C-means clustering method, the pressure and temperature data of the user are processed, combined with the sleep posture classification and area division, to provide personalized area adjustment for each user, so that the mattress can more accurately adapt to the physiological needs of the user and provide the best comfort. By comprehensively considering the influence of different sleep postures, body types, and back pressure distributions on comfort in the comfort evaluation of sleep postures, it can accurately reflect the sleep needs of the user. Combining the PID controller and the simulated annealing algorithm, it can dynamically adjust according to the real-time comfort error to ensure that the comfort of the user is always in the best balance. This intelligent adjustment mechanism can effectively cope with the changes in different sleep postures and health states, and improve the adaptability and comfort of the mattress.

[0148] Refer to the attached Figure 2 illustrates a schematic structural diagram of a control system of a personalized intelligent mattress provided by the present invention.

[0149] The present invention also provides a control system 30 of a personalized intelligent mattress, including: a memory 303 and one or more processors 301.

[0150] One or more application programs are stored in the memory 303, and one or more application programs are adapted to be executed by one or more processors 301 to implement the control method of the personalized intelligent mattress in the method embodiment.

[0151] The control system 30 of the personalized intelligent mattress includes: a processor 301 and a memory 303. Among them, the processor 301 and the memory 303 are connected, such as connected through a bus 302.

[0152] The structure of the control system 30 of the personalized intelligent mattress does not constitute a limitation to the embodiment of the present invention.

[0153] The processor 301 can be a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logical blocks, modules, and circuits described in connection with the disclosure of the present invention. The processor 301 can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0154] The bus 302 can include a path for transmitting information between the above components. The bus 302 can be a PCI bus, an EISA bus, etc. The bus 302 can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity of representation, only a thick line is shown in the figure, but it does not mean that there is only one bus or one type of bus.

[0155] The memory 303 can be a ROM or other types of static storage devices that can store static information and instructions, a RAM, or other types of dynamic storage devices that can store information and instructions. It can also be an EEPROM, a CD-ROM, or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0156] It should be noted that the control system 30 of the personalized intelligent mattress can implement the above-mentioned control method of the personalized intelligent mattress and can achieve the same or similar technical effects. To avoid repetition, the present invention will not elaborate further.

[0157] The beneficial effects brought by the technical solution provided by the embodiments of the present invention at least include:

[0158] In the embodiments of the present invention, through the fuzzy C-means clustering method, the pressure and temperature data of the user are processed. Combining the sleep posture classification and region division, personalized region adjustment is provided for each user, so that the mattress can more accurately adapt to the physiological needs of the user and provide the best comfort. By evaluating the comfort of the sleep posture, comprehensively considering the influence of different sleep postures, body types, and back pressure distributions on comfort, it can accurately reflect the sleep needs of the user. Combining the PID controller and the simulated annealing algorithm, it can dynamically adjust according to the real-time comfort error to ensure that the comfort of the user is always in the best balance. This intelligent adjustment mechanism can effectively cope with changes in different sleep postures and health states, and improve the adaptability and comfort of the mattress.

[0159] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily conceive of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

[0160] The following points need to be explained:

[0161] (1) The drawings of the embodiments of the present invention only relate to the structures involved in the embodiments of the present invention, and other structures can refer to the general design.

[0162] (2) For clarity, in the drawings used to describe the embodiments of the present invention, the thickness of the layers or regions is enlarged or reduced, that is, these drawings are not drawn to actual scale. It can be understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element can be "directly" on or under the other element or there can be intermediate elements.

[0163] (3) Without conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other to obtain new embodiments.

[0164] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A control method for a personalized smart mattress, characterized in that: include: S1: Obtain human body pressure data and human body temperature data on the smart mattress as sample data; S2: preprocessing the sample data; S3: Determine the cluster center of the sample data and the degree of membership corresponding to the cluster center by using the fuzzy C-means clustering method according to the preprocessed sample data; S4: dividing the smart mattress into human body regions based on the cluster centers and the membership degrees; S5: According to the human body area division result, feature extraction is performed on the preprocessed sample data to determine the data features; S6: classifying sleeping postures according to the data features; S7: determining human body pressure data of various sleeping positions based on the sleeping position classification results; S8: determining the back surface data of the human body in an upright state; S9: Combining the human back surface data and the human pressure data of various sleeping positions, evaluating the comfort of the sleeping position; S10: According to the comfort evaluation result, the smart mattress is controlled by a PID controller.

2. The control method of the personalized smart mattress according to claim 1, characterized in that: The S1 is specifically: The human body pressure data is obtained through a pressure sensor, and the human body temperature data is obtained through an infrared sensor.

3. The control method of the personalized smart mattress according to claim 1, characterized in that: The S2 is specifically: The sample data is preprocessed including noise reduction.

4. The control method of the personalized smart mattress according to claim 1, characterized in that: The S3 specifically includes: S301: Setting the number of clusters and the stop threshold; S302: Initialize the membership matrix; S303: Calculate cluster center; S303: Calculate the membership matrix corresponding to the cluster center; S304: Calculating an objective function according to the cluster center and the membership degree; S305: Determine whether the termination condition is met; if so, output the cluster center and the membership degree corresponding to the cluster center; otherwise, return to step S303.

5. The control method of the personalized smart mattress according to claim 1, characterized in that: The S4 specifically includes: S401: Determine a center and a central axis according to the cluster center and the membership degree; S402: Divide the human body into regions according to the center and the central axis.

6. The control method of the personalized intelligent mattress according to claim 1, characterized in that: The human body segmentation result specifically includes: a left chest area, a right chest area, a left hip area, a right hip area, a left leg area, and a right leg area; The data features specifically include: left-right symmetry, chest-hip symmetry, and leg symmetry; The S5 is specifically: Perform feature extraction on the preprocessed sample data to determine the data features.

7. The control method of the personalized smart mattress according to claim 1, characterized in that: The S9 specifically includes: S901: Determine the back shape from the shoulder to the buttocks and the deformation of the corresponding area of ​​the mattress by combining the human back surface data and the human pressure data of various sleeping positions; S902: Calculate the comfort index of sleeping posture; S903: Calculate the sleeping posture discomfort index; S903: Evaluate the comfort of the sleeping posture according to the comfort index and discomfort index.

8. The control method of the personalized smart mattress according to claim 1, characterized in that: The comfort evaluation results specifically include comfortable, moderately uncomfortable and very uncomfortable; The S10 specifically includes: S1001: Calculating a comfort error according to the comfort evaluation result; S1002: Optimizing the PID controller by simulated annealing algorithm; S1003: Output a control signal according to the optimized PID controller. S1004: Controlling the smart mattress according to the control signal.

9. A control system for a personalized smart mattress, characterized in that: include: memory and one or more processors; One or more application programs are stored in the memory, and the one or more application programs are suitable for being executed by the one or more processors to implement the control method of the personalized smart mattress according to any one of claims 1 to 8.

Images