Intelligent sickbed control method based on matrix pressure sensor modeling

Abstract

The invention relates to the technical field of control, in particular to an intelligent sickbed control method based on matrix pressure sensor modeling. The method comprises the following steps that a matrix type pressure sensor network is arranged in a mattress, and an inflation structure soft bag with an inflation and deflation valve is correspondingly arranged in a blank grid block, so that a matrix type pressure sensing intelligent sickbed is obtained; acquiring pressure data corresponding to each sensing point location of a user in real time by using a matrix type pressure sensing intelligent sickbed, and performing pressure distribution matrix modeling to obtain an intelligent sickbed pressure distribution matrix model; and acquiring an intelligent sickbed pressure matrix mean value and an intelligent sickbed pressure matrix standard deviation, performing pressure difference block division and inflation and deflation amount compensation calculation, and acting on the inflation structure soft package to perform inflation control response and deflation control response so as to execute corresponding intelligent sickbed pressure inflation and deflation control work. According to the invention, real-time monitoring and feedback control of the pressure state of the intelligent sickbed user can be realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of control, in particular to a smart hospital bed control method based on matrix pressure sensor modeling BACKGROUND By arranging multiple matrix pressure sensors on the smart hospital bed mattress, high-precision real-time monitoring of the bed surface pressure distribution can be achieved. The matrix sensor can cover the entire mattress surface, providing comprehensive pressure data to ensure accurate reflection of the patient's body position and pressure changes. Through advanced modeling algorithms in data processing, real-time analysis of sensor data is performed to establish a mathematical model between the patient's body position and the bed surface pressure. This model can effectively identify the patient's dynamic changes and provide a scientific basis for automatic pressure adjustment of the smart hospital bed. This can automatically adjust the height and angle based on real-time monitoring data to optimize patient comfort and safety. However, traditional smart hospital beds often use simple pressure sensors to monitor patient body position and pressure distribution. These sensors rely on a single measurement point during use, making it difficult to adapt to changes in patient size and posture. This makes it difficult to accurately capture patient activity and body position changes on the bed, resulting in the smart hospital bed being unable to adaptively adjust based on real-time pressure conditions in each distribution block, including weak pressure and excessive pressure blocks. SUMMARY

[0002] Therefore, it is necessary to provide a smart hospital bed control method based on matrix pressure sensor modeling to solve at least one of the above technical problems.

[0003] To achieve the above purpose, a smart hospital bed control method based on matrix pressure sensor modeling includes the following steps: Step S1: A matrix pressure sensor network is arranged inside the mattress, which is composed of 300 pressure sensor sub-units arranged in 10 rows and 30 columns, and a corresponding inflatable structure bag with a gas charging valve is arranged in the blank block between each pressure sensor sub-unit in the matrix pressure sensor network to obtain a matrix pressure sensing smart hospital bed. Each pressure sensor sub-unit in the matrix pressure sensing smart hospital bed is used to collect real-time pressure data of the user at each sensing point and perform pressure distribution matrix modeling to obtain a smart hospital bed pressure distribution matrix model. Step S2: Obtain the intelligent hospital bed pressure matrix mean value and the intelligent hospital bed pressure matrix standard deviation using the intelligent hospital bed pressure distribution matrix model, and divide the intelligent hospital bed pressure distribution matrix model into pressure difference blocks based on the intelligent hospital bed pressure matrix mean value and the intelligent hospital bed pressure matrix standard deviation to obtain the intelligent hospital bed pressure weak block and the intelligent hospital bed pressure excessive block; obtain the user real-time body posture data and the user body feature data, and perform air inflation and deflation compensation calculation on the intelligent hospital bed pressure weak block and the intelligent hospital bed pressure excessive block based on the user real-time body posture data and the user body feature data respectively to obtain the intelligent hospital bed pressure weak block adaptive inflation amount and the intelligent hospital bed pressure excessive block adaptive deflation amount; Step S3: The pressure weak block adaptive inflation amount is applied to the inflation valve corresponding to the inflatable structure soft package in the intelligent hospital bed pressure weak block to perform inflation control response, generate intelligent hospital bed inflation valve control instructions, and perform corresponding intelligent hospital bed pressure weak inflation control work; Step S4: The pressure excessive block adaptive deflation amount is applied to the deflation valve corresponding to the inflatable structure soft package in the intelligent hospital bed pressure excessive block to perform deflation control response, generate intelligent hospital bed deflation valve control instructions, and perform corresponding intelligent hospital bed pressure excessive deflation control work.

[0004] Further, step S1 includes the following steps: Step S11: The matrix distribution layout planning is performed in the mattress according to the arrangement mode of 10 rows and 30 columns to design and generate a matrix distribution layout diagram inside the mattress; Step S12: A matrix pressure sensor network is generated by configuring pressure sensor sub-units at each intersection point in the matrix distribution layout diagram inside the mattress and connecting and arranging, wherein the matrix pressure sensor network is composed of 300 pressure sensor sub-units arranged in 10 rows and 30 columns; Step S13: The inflatable structure soft package with inflation and deflation valves is arranged in the blank block separated by each pressure sensor sub-unit in the matrix pressure sensor network to obtain a matrix pressure sensing intelligent hospital bed; Step S14: Real-time user pressure data corresponding to each pressure sensing point is obtained by using each pressure sensor sub-unit in the matrix pressure sensing intelligent hospital bed to collect pressure data corresponding to each sensing point of the user; Step S15: The user real-time pressure data corresponding to each pressure sensing point is subjected to pressure distribution matrix modeling to obtain an intelligent hospital bed pressure distribution matrix model.

[0005] Further, step S2 includes the following steps: Step S21: The pressure data at each distribution point in the intelligent hospital bed pressure distribution matrix model is accumulated and summed to obtain the cumulative total value of the intelligent hospital bed pressure distribution; Step S22: The intelligent hospital bed pressure distribution matrix model is calculated based on the cumulative total value of the intelligent hospital bed pressure distribution to obtain the intelligent hospital bed pressure matrix mean; Step S23: The intelligent hospital bed pressure matrix standard deviation is calculated based on the intelligent hospital bed pressure matrix mean for the pressure data at each distribution point in the intelligent hospital bed pressure distribution matrix model; Step S24: The intelligent hospital bed pressure distribution matrix model is divided into pressure difference blocks based on the intelligent hospital bed pressure matrix mean and the intelligent hospital bed pressure matrix standard deviation to obtain the intelligent hospital bed pressure weak block and the intelligent hospital bed pressure excessive block; Step S25: The user's real-time body posture data and user's body feature data are obtained, and the intelligent hospital bed pressure weak block and the intelligent hospital bed pressure excessive block are compensated based on the user's real-time body posture data and user's body feature data. The pressure weak block and the pressure excessive block are obtained.

[0006] Further, step S24 includes the following steps: Step S241: The intelligent hospital bed pressure matrix mean and the intelligent hospital bed pressure matrix standard deviation are statistically distributed to generate an intelligent hospital bed pressure matrix statistical distribution graph; Step S242: The intelligent hospital bed pressure matrix statistical distribution graph is statistically analyzed to obtain the intelligent hospital bed pressure distribution skewness value and the intelligent hospital bed pressure distribution kurtosis value; Step S243: The intelligent hospital bed pressure distribution skewness value and the intelligent hospital bed pressure distribution kurtosis value are adjusted to obtain the intelligent hospital bed pressure matrix distribution adjustment proportion coefficient; Step S244: The intelligent hospital bed pressure matrix mean and the intelligent hospital bed pressure matrix standard deviation are quantitatively calculated based on the intelligent hospital bed pressure matrix distribution adjustment proportion coefficient to obtain the intelligent hospital bed pressure distribution difference division standard limit; Step S245: The intelligent hospital bed pressure distribution matrix model is divided into pressure difference blocks based on the intelligent hospital bed pressure distribution difference division standard limit to obtain the intelligent hospital bed pressure weak block and the intelligent hospital bed pressure excessive block.

[0007] Further, step S245 includes the following steps: Based on the criteria for classifying pressure distribution differences in intelligent hospital beds, pressure differences are labeled and determined for each pressure value point within the intelligent hospital bed pressure distribution matrix model. If the pressure distribution matrix model contains the first... Line number If the pressure value point corresponding to the column is equal to the boundary of the standard for dividing the pressure distribution difference of the intelligent hospital bed, no processing is performed; if the pressure value point in the intelligent hospital bed pressure distribution matrix model is equal to the boundary of the standard for dividing the pressure distribution difference of the intelligent hospital bed, no processing is performed. Line number If the pressure value point corresponding to a column is less than the threshold of the standard for classifying pressure distribution differences in intelligent hospital beds, then that pressure value point is marked as a point with weak pressure; if the pressure distribution matrix model of the intelligent hospital bed contains a column with a pressure value point less than the threshold of the standard for classifying pressure distribution differences in intelligent hospital beds, then that ... Line number When the pressure value point corresponding to the column is greater than the limit of the standard for dividing the pressure distribution difference of the intelligent hospital bed, the pressure value point is marked as the pressure excessive value point. Obtain the row and column labels of all pressure weak and pressure excessive values ​​in the intelligent hospital bed pressure distribution matrix model to obtain the row and column labels of pressure weak and pressure excessive values. Based on the row and column labels of the weak pressure points, the weak pressure adjacent points are aggregated and classified to obtain the weak pressure adjacent point subset of the smart bed corresponding to each weak zone. Based on the row and column labels of the excessive pressure points, all excessive pressure value points are aggregated and classified into adjacent points of excessive pressure, resulting in a subset of adjacent points of excessive pressure for each excessive pressure zone of the smart hospital bed. Based on the subset of adjacent points with weak pressure in the smart hospital bed, the corresponding pressure value points in the smart hospital bed pressure distribution matrix model are divided into weak pressure block edges to obtain the weak pressure block of the smart hospital bed; based on the subset of adjacent points with excessive pressure in the smart hospital bed, the corresponding pressure value points in the smart hospital bed pressure distribution matrix model are divided into excessive pressure block edges to obtain the excessive pressure block of the smart hospital bed.

[0008] Furthermore, the step of dividing the pressure distribution matrix model of the intelligent hospital bed into edge-connected pressure weak blocks based on the subset of adjacent points with weak pressure of the intelligent hospital bed includes the following steps: Based on the subset of adjacent points with weak pressure in the intelligent hospital bed, the corresponding pressure value points in the intelligent hospital bed pressure distribution matrix model are identified as edge pressure points of the weak partition, so as to obtain the edge pressure point positions of each direction corresponding to the weak pressure adjacent partition in the intelligent hospital bed pressure distribution matrix model. The edge pressure gradient fitting analysis was performed on the edge pressure points at various locations corresponding to the weak pressure adjacent partitions in the intelligent hospital bed pressure distribution matrix model to obtain the edge pressure fitting gradient corresponding to the weak pressure adjacent partitions. Based on the edge pressure fitting gradient, the position of the edge pressure point corresponding to each direction in the pressure weak adjacent partition in the intelligent hospital bed pressure distribution matrix model is analyzed by adjacent point edge connection analysis, and the block edge connection boundary between the edge pressure adjacent points corresponding to each direction in the pressure weak adjacent partition is obtained. According to the block edge connection boundary between the edge pressure adjacent points corresponding to each direction in the pressure weak adjacent partition in the intelligent hospital bed pressure distribution matrix model, the corresponding pressure value points in the intelligent hospital bed pressure distribution matrix model are divided by pressure weak block edge connection, so as to obtain the pressure weak block of the intelligent hospital bed.

[0009] Further, step S25 includes the following steps: Step S251: acquiring real-time body posture data and user body feature data of the user; Step S252: performing feature three-dimensional corner point detection on the real-time body posture data and user body feature data of the user to obtain a user body posture feature three-dimensional corner point set and a user body feature three-dimensional corner point set; Step S253: performing user body state simulation modeling according to the user body posture feature three-dimensional corner point set and the user body feature three-dimensional corner point set to generate an intelligent hospital bed user body state real-time simulation model; Step S254: performing user use simulation force field coupling analysis on the intelligent hospital bed user body state real-time simulation model and the intelligent hospital bed pressure distribution matrix model to generate an intelligent hospital bed user real-time use simulation coupling dynamic field; Step S255: based on the intelligent hospital bed user real-time use simulation coupling dynamic field, compensating the inflation and deflation amount of the pressure weak block and the pressure excessive block of the intelligent hospital bed respectively to obtain the adaptive inflation amount of the pressure weak block and the adaptive deflation amount of the pressure excessive block.

[0010] Further, step S254 includes the following steps: Setting the user real-time posture synchronous response of the intelligent hospital bed user body state real-time simulation model to generate different sleep posture response conditions of the intelligent hospital bed user; Based on the different sleep posture response conditions of the intelligent hospital bed user, the pressure distribution matrix of the intelligent hospital bed is optimized to obtain the pressure distribution matrix sub-model corresponding to the different sleep postures of the intelligent hospital bed user; Constructing a force field coupling model for the pressure distribution matrix sub-model corresponding to the different sleep postures of the intelligent hospital bed user and the intelligent hospital bed user body state real-time simulation model to generate an intelligent hospital bed user real-time comprehensive stress force field coupling model; Performing dynamic coupling force field simulation analysis on the intelligent hospital bed user real-time comprehensive stress force field coupling model to generate an intelligent hospital bed user real-time use simulation coupling dynamic field.

[0011] Further, step S255 comprises the following steps: Based on the real-time use of the intelligent hospital bed user, the inflation structure soft package at each pressure point in the pressure weak block and the pressure excessive block of the intelligent hospital bed is respectively analyzed in structure bearing and limit load, and the inflation structure bearing pressure and the inflation structure limit load pressure corresponding to each pressure point in the pressure weak block and the pressure excessive block are obtained; Based on the inflation structure bearing pressure and the inflation structure limit load pressure corresponding to each pressure point in the pressure weak block and the pressure excessive block, the target pressure adaptive calculation formula is used to respectively calculate the target pressure of each pressure point in the pressure weak block and the pressure excessive block of the intelligent hospital bed, and the inflation structure target adaptive pressure corresponding to each pressure point in the pressure weak block and the pressure excessive block is obtained; The gas flow characteristic data of the inflation structure is obtained, and the gas flow ratio response analysis is performed on the corresponding inflation structure soft package based on the gas flow characteristic data of the inflation structure, and the inflation structure gas flow ratio coefficient is obtained; Based on the inflation structure target adaptive pressure corresponding to each pressure point in the pressure weak block and the inflation structure gas flow ratio coefficient, the inflation amount compensation calculation is performed on each pressure point in the pressure weak block of the intelligent hospital bed, and the pressure weak block adaptive inflation amount is obtained; Based on the inflation structure target adaptive pressure corresponding to each pressure point in the pressure excessive block and the inflation structure gas flow ratio coefficient, the deflation amount compensation calculation is performed on each pressure point in the pressure excessive block of the intelligent hospital bed, and the pressure excessive block adaptive deflation amount is obtained.

[0012] Further, the target pressure adaptive calculation formula is specifically: ; ; In the formula, is the inflation structure target adaptive pressure corresponding to the first pressure point in the pressure weak block, is the inflation structure target adaptive pressure corresponding to the first pressure point in the pressure excessive block, is the horizontal coordinate of the first pressure point in the pressure weak block, is the vertical coordinate of the first pressure point in the pressure weak block, is the inflation structure bearing pressure of the first pressure point in the pressure weak block, The weighting parameter represents the influence of the pressure borne by the inflatable structure in the low-pressure zone on the target pressure. The size of the area where the pressure is relatively weak. This represents the minimum pressure corresponding to the area with relatively weak pressure. The weighting parameter is the one that minimizes the integral effect of pressure. The first in the weak pressure block pressure point The ultimate load pressure of the inflatable structure. The weighting parameter represents the influence of the ultimate load pressure of the inflatable structure on the target pressure in the area with weak pressure. For the first block with excessive pressure The x-coordinate of each pressure point For the first block with excessive pressure The ordinate of each pressure point For the first block with excessive pressure pressure point The inflatable structure can withstand pressure. The weighting parameter represents the influence of the pressure borne by the inflatable structure within the excessively high-pressure area on the target pressure. The size of the area where the pressure is too high. This represents the maximum pressure within the area experiencing excessive pressure. The weighting parameter is the integral effect of maximum pressure. For the first block with excessive pressure pressure point The ultimate load pressure of the inflatable structure. The weighting parameter represents the influence of the ultimate load pressure of the inflatable structure within the excessively high-pressure zone on the target pressure. Correction coefficients for adapting the pressure to the target inflatable structure in areas with weak pressure. Correction coefficients for the pressure of the inflatable structure corresponding to the excessively high pressure area.

[0013] The beneficial effects of this invention are: The intelligent sickbed control method based on matrix pressure sensor modeling has the beneficial effects that, compared with the prior art, the 10-row 30-column matrix distribution layout is implemented in the mattress, which lays a structural foundation for the design of the intelligent sickbed mattress. This systematic arrangement enables the pressure sensors to be evenly distributed inside the mattress, ensuring that each area can be effectively monitored. The matrix layout not only improves the space utilization rate but also makes the subsequent sensor configuration and data acquisition more efficient. Under the guidance of the layout diagram, the design team can intuitively identify the position of each pressure sensor and form a coherent monitoring network throughout the mattress. This design optimizes the user's comfort experience, enabling the mattress to accurately adapt to changes in different patient body types and postures, thereby better capturing real-time patient activity and body position changes on the bed and laying a foundation for subsequent processing. By arranging the inflatable structure soft package with a corresponding inflation and deflation valve in the blank grid block between each pressure sensor subunit in the matrix pressure sensor network, the functionality of the mattress is further improved. This inflatable soft package can dynamically adjust its hardness and shape according to real-time pressure data, ensuring that users achieve ideal support in different sleeping positions. This design not only provides a comfortable sleep experience but also effectively reduces physical stress and discomfort caused by long-term static posture. The flexibility of the inflatable structure enables the mattress to adapt to the individual needs of different users, significantly improving user satisfaction and health levels. At the same time, by using each pressure sensor subunit in the matrix pressure sensor intelligent sickbed to collect real-time pressure data at each sensing point and perform pressure distribution matrix modeling, this process ensures high frequency and high accuracy of the data, enabling the mattress to better capture real-time patient activity and body position changes on the bed. The established matrix model can visualize the pressure distribution of the user at different postures, helping users intuitively understand their sleep pressure conditions. By analyzing the pressure distribution matrix, it can identify which areas have excessive or insufficient pressure, and then achieve precise adjustment, thereby providing data support for subsequent pressure adjustment. Secondly, by performing matrix mean statistical calculation on the intelligent sickbed pressure distribution matrix model, the pressure matrix mean of the intelligent sickbed is obtained, which provides an important reference standard for the pressure distribution of the entire mattress, helping users understand the average pressure level of each area. Mean statistics help identify which areas have relatively high or low pressure and provide guidance for subsequent pressure adjustment.By calculating the standard deviation of the pressure matrix based on the average pressure matrix of the smart hospital bed, the standard deviation of the pressure matrix is obtained, which provides important information about the consistency of pressure distribution for the mattress. A smaller standard deviation means that the pressure distribution is more uniform, while a larger standard deviation indicates that there may be large pressure fluctuations in some areas. This statistical analysis enables the smart hospital bed mattress to accurately identify potential pressure abnormal areas and provides a data basis for subsequent pressure difference block division, allowing the mattress to achieve more intelligent pressure management. By dividing the pressure difference block based on the average pressure matrix and the standard deviation of the smart hospital bed pressure matrix, the pressure weak block and the pressure excessive block are identified. This step enables the mattress to manage pressure distribution in a more refined manner. Through block division, the smart hospital bed can clearly identify the specific areas that need to be adjusted. The pressure weak block needs to be strengthened, while the pressure excessive block needs to be reduced. Such intelligent division not only improves the mattress's ability to adapt to changes in user posture, but also effectively avoids physical discomfort caused by uneven pressure. This analysis result lays the foundation for subsequent air compensation calculation, allowing the mattress to dynamically adjust to meet user needs. By obtaining real-time body posture data and user body feature data, and based on the real-time body posture data and user body feature data, the air compensation calculation for the smart hospital bed pressure weak block and the smart hospital bed pressure excessive block is performed. This step enables the smart hospital bed to accurately adjust the pressure state of each block based on individual differences. Based on real-time data, the compensation calculation can ensure that each user can obtain the best support in different sleeping positions, greatly improving the personalized adaptability of the mattress. This dynamic adjustment mechanism not only enhances the user's comfort experience, but also effectively prevents physical problems caused by excessive or insufficient pressure. This comprehensive pressure adjustment process enables the smart hospital bed to improve sleep quality while achieving real-time pressure state self-adaptive adjustment in each distribution block. Then, by identifying the pressure weak block, the smart hospital bed generates an air valve control instruction based on the corresponding area's inflation control response. The key of this control mechanism is that it can adjust the hardness and support force of the mattress in real time to ensure that the user obtains the best support during sleep. The immediate response of the inflation control can effectively reduce the uneven pressure caused by changes in user posture during sleep, thereby avoiding discomfort caused by insufficient local pressure.Finally, for the gas control of the excessively stressed blocks, the gas control is also realized through the corresponding gas valve control instructions, and the key of the process is to effectively reduce the pressure of the local area, so as to avoid the discomfort such as numbness or pain caused by excessive pressure. The realization of the gas control enables the mattress to continuously monitor and adjust after the user falls asleep, so as to ensure that the user remains in a comfortable state during the whole sleep process. The dynamic pressure adjustment not only improves the sleep quality of the user, but also is completed without disturbing the user, thereby improving the use experience of the intelligent hospital bed and enabling the user to enjoy a more personalized and intelligent sleep experience. BRIEF DESCRIPTION OF DRAWINGS

[0014] Other characteristics, objects and advantages of the present application will become more apparent from the following detailed description of non-restrictive embodiments, made with reference to the attached drawings: Figure 1 The step flow diagram of the intelligent hospital bed control method based on the matrix type pressure sensor modeling of the present application; Figure 2 The detailed step flow diagram of step S1 in the present application; Figure 1 The detailed step flow diagram of step S2 in the present application; Figure 3 The detailed step flow diagram of step S2 in the present application; Figure 1 The detailed step flow diagram of step S2 in the present application; DETAILED DESCRIPTION

[0015] The technical method of the present application will be described clearly and completely below with reference to the attached drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor belong to the protection scope of the present application.

[0016] To achieve the above-mentioned purpose, please refer to Figures 1 to 3 The present application provides an intelligent hospital bed control method based on matrix type pressure sensor modeling, which comprises the following steps: Step S1: A matrix type pressure sensor network is arranged inside the mattress, wherein the matrix type pressure sensor network is composed of 300 pressure sensor subunits arranged in 10 rows and 30 columns, and an air structure soft package with a gas charging valve is arranged in the blank block between each pressure sensor subunit in the matrix type pressure sensor network, so as to obtain a matrix type pressure sensing intelligent hospital bed; each pressure sensor subunit in the matrix type pressure sensing intelligent hospital bed is used to collect the pressure data of the user at each sensing point in real time and to model the pressure distribution matrix, so as to obtain an intelligent hospital bed pressure distribution matrix model; Step S2: obtain the intelligent hospital bed pressure matrix mean value and the intelligent hospital bed pressure matrix standard deviation by using the intelligent hospital bed pressure distribution matrix model, and divide the pressure difference blocks of the intelligent hospital bed pressure distribution matrix model based on the intelligent hospital bed pressure matrix mean value and the intelligent hospital bed pressure matrix standard deviation, to obtain the intelligent hospital bed pressure weak block and the intelligent hospital bed pressure excessive block; obtain the user real-time body posture data and the user body feature data, and based on the user real-time body posture data and the user body feature data, respectively, compensate the intelligent hospital bed pressure weak block and the intelligent hospital bed pressure excessive block to obtain the pressure weak block adaptive inflation amount and the pressure excessive block adaptive deflation amount; Step S3: the pressure weak block adaptive inflation amount is applied to the inflation valve corresponding to the inflation structure soft package in the intelligent hospital bed pressure weak block to generate an intelligent hospital bed inflation valve control instruction for performing corresponding intelligent hospital bed pressure weak inflation control work; Step S4: the pressure excessive block adaptive deflation amount is applied to the deflation valve corresponding to the inflation structure soft package in the intelligent hospital bed pressure excessive block to generate an intelligent hospital bed deflation valve control instruction for performing corresponding intelligent hospital bed pressure excessive deflation control work.

[0017] In the embodiment of the application, please refer to Figure 1 The method comprises the following steps: Step S1: a matrix pressure sensor network is arranged inside the mattress, wherein the matrix pressure sensor network is composed of 300 pressure sensor subunits arranged in 10 rows and 30 columns, and the inflation structure soft package with the inflation and deflation valve is arranged in the blank block between each pressure sensor subunit in the matrix pressure sensor network, to obtain a matrix pressure sensing intelligent hospital bed; the pressure data corresponding to each sensing point of the user is collected by each pressure sensor subunit in the matrix pressure sensing intelligent hospital bed in real time, and the pressure distribution matrix modeling is performed, to obtain an intelligent hospital bed pressure distribution matrix model; In this embodiment of the invention, when planning the matrix distribution layout inside the mattress, the overall size of the mattress is first determined to ensure that it can accommodate a 10-row, 30-column arrangement. By accurately measuring the available space inside the mattress, a matrix distribution layout diagram is drawn using CAD software. The spacing between each sensor position must be evenly distributed to ensure the accuracy of pressure sensing. Based on the matrix distribution layout diagram generated by the previous design, pressure sensor sub-units are configured at each intersection. Each pressure sensor sub-unit selects a suitable pressure sensor, such as a thin-film or strain gauge sensor, and connects it to a main control unit through a dedicated connector. All sensors are arranged in a 10-row, 30-column structure to ensure that their arrangement is uniform and stable in both the horizontal and vertical directions. The cables are routed through the edge of the mattress to connect and generate a matrix pressure sensor network. By placing inflatable pouches with inflation / deflation valves in the blank grid areas (i.e., the blank grid areas after the "grid" division) between the pressure sensor subunits in the previously connected matrix pressure sensor network, and selecting highly elastic inflation materials, and installing air valves in each pouch, precise control of the gas inside the mattress can be achieved. A heat-fusion process is used to connect the air valves to the pouches to ensure their sealing and durability. The inflation and deflation speeds must be considered during the design, thus obtaining a matrix-type pressure-sensing smart hospital bed. Simultaneously, by using each pressure sensor subunit in the previously deployed matrix-type pressure-sensing smart hospital bed, real-time pressure data corresponding to each sensing point within the smart hospital bed is collected from the user. A high-precision analog-to-digital converter ensures that the pressure data from each sensor can be accurately read and promptly sent to the main control unit. Then, based on the real-time user pressure data corresponding to each pressure sensing point, mathematical modeling software is used to model the pressure distribution matrix. Finite element analysis is used to process the pressure data, and an algorithm is used to convert the real-time data from each pressure sensor into a corresponding pressure distribution matrix. For example... ,in For the first Line number The pressure value of the sensor, The number of rows, To determine the number of columns, the modeling process needs to consider factors such as user weight, center of gravity position, and mattress firmness to ensure that the model accurately reflects the user's actual usage and ultimately yields a smart hospital bed pressure distribution matrix model.

[0018] Step S2: obtaining the intelligent hospital bed pressure matrix mean value and the intelligent hospital bed pressure matrix standard deviation by using the intelligent hospital bed pressure distribution matrix model, and dividing the intelligent hospital bed pressure distribution matrix model into pressure difference blocks based on the intelligent hospital bed pressure matrix mean value and the intelligent hospital bed pressure matrix standard deviation to obtain the intelligent hospital bed pressure weak block and the intelligent hospital bed pressure excessive block; obtaining the user real-time body posture data and the user body feature data, and performing air inflation and air deflation compensation calculation on the intelligent hospital bed pressure weak block and the intelligent hospital bed pressure excessive block based on the user real-time body posture data and the user body feature data respectively to obtain the intelligent hospital bed pressure weak block adaptive air inflation amount and the intelligent hospital bed pressure excessive block adaptive air deflation amount; In the embodiment of the application, by traversing the pressure data at each distribution point in the previously modeled intelligent hospital bed pressure distribution matrix model, the pressure values of each point are recorded and summed up, so as to cumulatively calculate the centralized cumulative total value of the entire pressure distribution, and by performing mean value statistical calculation on the pressure values of each distribution point in the intelligent hospital bed pressure distribution matrix model, the number of elements in the matrix is determined, and the total value is divided by the number of elements to calculate the mean value, which can be realized by a matrix operation tool, for example The mean value reflects the overall pressure level of the intelligent hospital bed, so as to obtain the intelligent hospital bed pressure matrix mean value. After calculating the intelligent hospital bed pressure matrix mean value, the pressure data at each distribution point in the intelligent hospital bed pressure distribution matrix model is calculated for standard deviation, and the process of calculating the standard deviation includes first calculating the sum of squares of the difference between each pressure data point and the mean value, then dividing the sum of squares by the number of data points minus one, and finally taking the square root, for example The result of the standard deviation will be used to measure the dispersion degree of the pressure data, so as to obtain the intelligent hospital bed pressure matrix standard deviation. At the same time, by combining the previously quantitatively calculated intelligent hospital bed pressure matrix mean value and intelligent hospital bed pressure matrix standard deviation, the corresponding intelligent hospital bed pressure distribution matrix model is divided into pressure difference blocks, and first the standard limit value is determined, for example which is set as the standard corresponding to the pressure weak block and the pressure excessive block, wherein the pressure weak block is specifically , and the pressure excessive block is specifically The pressure values in the matrix are compared with the thresholds, and the pressure points are classified according to the comparison results, and are respectively marked as pressure weak and pressure excessive areas, so that the intelligent hospital bed pressure weak block and the intelligent hospital bed pressure excessive block are divided. Then, by using a high-precision sensor and a camera system, the user's body posture and body feature data are captured in real time, a deep learning algorithm is used to process the collected images, the user's body parts are identified, the data such as pressure and acceleration fed back by the sensor are obtained, the joint angle, height, weight and other body feature parameters are obtained, in the data collection process, the sensor is ensured to be in good contact with the user, so as to obtain accurate body posture information and convert it into a standardized numerical form, so as to obtain the user's real-time body posture data and body feature data. And, by combining the previously obtained real-time body posture data and body feature data of the user, compensation calculation of the specific amount of inflation and deflation of the previously identified intelligent hospital bed pressure weak block and intelligent hospital bed pressure excessive block is carried out, so as to calculate the inflation and deflation amount of each area by analyzing the posture change of the user and combining the characteristics of each block, using a fluid dynamics model or a pressure model, calculating the required inflation amount for the weak area and the deflation amount for the excessive area, this process can be realized by an algorithm, ensuring accurate control of gas flow, so that the pressure of each block is kept within a proper range, and finally the adaptive inflation amount of the pressure weak block and the adaptive deflation amount of the pressure excessive block are obtained.

[0019] Step S3: The pressure weak block adaptive inflation amount is applied to the inflation valve corresponding to the inflation structure soft package in the intelligent hospital bed pressure weak block to generate an intelligent hospital bed inflation valve control instruction to perform corresponding intelligent hospital bed pressure weak inflation control work; In the embodiment of the application, the pressure weak block adaptive inflation amount obtained by the previous compensation calculation is applied to the inflation valve corresponding to the inflation structure soft package of each pressure point in the intelligent hospital bed pressure weak block to generate an intelligent hospital bed inflation valve control instruction in response, and the inflation control sends the generated instruction to the inflation valve driving system to ensure that the inflation valve is opened and inflates the inflation structure soft package corresponding to each pressure point in the weak block. The control process adopts a PID control algorithm to monitor the inflation amount change in real time to maintain the set adaptive inflation amount, the valve control instruction is sent out through a circuit control module to ensure the accuracy of the inflation process, the system state is fed back in real time, and the inflation amount is continuously adjusted according to the change of the user's weight and posture to realize dynamic adaptation, and finally the corresponding intelligent hospital bed pressure weak inflation control work is performed.

[0020] Step S4: Apply the appropriate venting amount to the venting valve corresponding to the inflatable structure soft pack in the excessive pressure area of ​​the smart bed to control the venting, and generate a control command for the smart bed venting valve to execute the corresponding venting control work for excessive pressure in the smart bed.

[0021] In this embodiment of the invention, the previously calculated overpressure block is adjusted to apply the corresponding deflation volume to the deflation valves of the inflatable structure soft packs at each pressure point within the overpressure block of the smart bed. This triggers a deflation control response, generating a control command for the smart bed's deflation valves. The deflation control process also involves sending the generated command to the deflation valve drive system to ensure the deflation valves open and deflate the inflatable structure soft packs at each pressure point within the overpressure block. During this process, a similar PID control strategy is employed to monitor the deflation volume in real time, maintaining the pressure within a suitable range. The valve control dynamically adjusts the opening and closing state of the deflation valves based on feedback data from the pressure sensor, achieving automated pressure regulation of the smart bed and ultimately executing the corresponding overpressure deflation control operation.

[0022] Furthermore, as an embodiment of the present invention, reference is made to... Figure 2 As shown, Figure 1 A detailed flowchart of step S1 is shown below. In this embodiment, step S1 includes the following steps: Step S11: Design and generate a matrix distribution layout diagram of the mattress interior by arranging the mattress in a 10-row, 30-column pattern. In this embodiment of the invention, when planning the matrix distribution layout inside the mattress, the overall size of the mattress is first determined to ensure that it can accommodate a 10-row, 30-column arrangement. By accurately measuring the available space inside the mattress, a matrix distribution layout diagram is drawn using CAD software. The spacing between each sensor position must be evenly distributed to ensure the accuracy of pressure sensing. In the design, the size of the sensors and cable wiring are taken into account, and sufficient space is reserved to avoid interference, thereby ensuring that subsequent pressure data acquisition is carried out smoothly. Finally, the corresponding matrix distribution layout diagram inside the mattress is designed and generated.

[0023] Step S12: By configuring pressure sensor sub-units at each intersection of the matrix distribution layout diagram inside the mattress and connecting them, a matrix pressure sensor network is generated, wherein the matrix pressure sensor network consists of 300 pressure sensor sub-units arranged in 10 rows and 30 columns. In this embodiment of the invention, pressure sensor sub-units are configured at each intersection point according to the previously designed internal matrix distribution layout diagram of the mattress. Each pressure sensor sub-unit selects a suitable pressure sensor, such as a thin-film or strain gauge sensor, and connects it to a main control unit through a dedicated connector. All sensors are arranged in a 10-row, 30-column structure to ensure that their arrangement in the horizontal and vertical directions is uniform and stable. The cables are routed through the edge of the mattress to reduce the impact on the use of the mattress and to ensure the reliability of power supply and data transmission. Finally, the connection and arrangement generate a matrix pressure sensor network.

[0024] Step S13: By arranging corresponding inflatable structural soft packs with inflation and deflation valves in the blank grid blocks that are divided between each pressure sensor subunit in the matrix pressure sensor network, a matrix pressure sensing smart hospital bed is obtained. In this embodiment of the invention, an inflatable structural soft pack with inflation / deflation valves is arranged in the blank grid blocks between each pressure sensor subunit in the previously connected matrix pressure sensor network (i.e., the blank grid blocks after the "grid" division). A highly elastic inflation material is selected, and an air valve is installed in each soft pack to achieve precise control of the gas inside the mattress. The air valve is connected to the soft pack using a hot-melt process to ensure its sealing and durability. The inflation and deflation speeds need to be considered during the design so that the firmness and comfort of the mattress can be quickly adjusted according to different user needs, ultimately resulting in a matrix pressure sensing intelligent hospital bed.

[0025] Step S14: Use each pressure sensor subunit in the matrix pressure sensing smart hospital bed to collect the pressure data of the user at each sensing point in real time, and obtain the real-time pressure data of the user at each pressure sensing point. In this embodiment of the invention, each pressure sensor subunit in the previously deployed matrix-type pressure-sensing smart bed collects pressure data corresponding to each sensing point of the user in real time. By using a high-precision analog-to-digital converter, it is ensured that the pressure data of each sensor can be accurately read and sent to the main control unit in a timely manner. During the data transmission process, wireless or wired communication is used to ensure the stability and real-time performance of the data transmission. The collected pressure data is visualized through monitoring software, and finally, the real-time pressure data of the user corresponding to each pressure sensing point is obtained.

[0026] Step S15: Model the pressure distribution matrix of the real-time user pressure data corresponding to each pressure sensing point to obtain the intelligent hospital bed pressure distribution matrix model.

[0027] In this embodiment of the invention, pressure distribution matrix is ​​modeled using mathematical modeling software based on the real-time user pressure data collected from each pressure sensing point. The pressure data is then processed using finite element analysis, and an algorithm transforms the real-time data from each pressure sensor into a corresponding pressure distribution matrix. For example... ,in For the first Line number The pressure value of the sensor, The number of rows, To determine the number of columns, the modeling process needs to consider factors such as user weight, center of gravity position, and mattress firmness to ensure that the model accurately reflects the user's actual usage and ultimately yields a smart hospital bed pressure distribution matrix model.

[0028] Furthermore, as an embodiment of the present invention, reference is made to... Figure 3 As shown, Figure 1 A detailed flowchart of step S2 is shown below. In this embodiment, step S2 includes the following steps: Step S21: Perform a concentrated summation of the pressure data at each distribution point within the intelligent hospital bed pressure distribution matrix model to obtain the total concentrated distribution value of the intelligent hospital bed pressure. In this embodiment of the invention, the pressure data at each distribution point within the previously modeled intelligent bed pressure distribution matrix is ​​traversed to record the pressure values ​​at each point and sum them up, thereby accumulating and calculating the total cumulative value of the entire pressure distribution. This process can be implemented using a programming language (such as Python or MATLAB). A loop structure is used to traverse the matrix, and an accumulator variable is used to add the pressure values ​​at each distribution point, ensuring comprehensive processing of the data from all distribution points. Finally, the cumulative total value of the concentrated pressure distribution of the intelligent hospital bed is obtained.

[0029] Step S22: Calculate the mean of the intelligent bed pressure distribution matrix model based on the cumulative total value of the concentrated distribution of intelligent bed pressure, and obtain the mean of the intelligent bed pressure matrix; In this embodiment of the invention, after obtaining the cumulative total value of the concentrated distribution of pressure in the intelligent hospital bed, the mean value of the pressure at each distribution point within the intelligent hospital bed pressure distribution matrix model is calculated to determine the number of elements in the matrix. The mean value is then calculated by dividing the total value by the number of elements. This process can be implemented using matrix operation tools, such as the mean function in the NumPy library, to directly calculate the mean value of the entire pressure matrix. This mean reflects the overall pressure level of the smart hospital beds, ultimately yielding the mean of the smart hospital bed pressure matrix.

[0030] Step S23: Based on the intelligent hospital bed pressure matrix mean, the pressure data at each distribution point in the intelligent hospital bed pressure distribution matrix model is calculated by matrix standard deviation statistical calculation, and the intelligent hospital bed pressure matrix standard deviation is obtained. In the embodiment of the application, after the intelligent hospital bed pressure matrix mean is calculated, the standard deviation of the pressure data at each distribution point in the intelligent hospital bed pressure distribution matrix model is calculated. The standard deviation calculation process includes first calculating the sum of squares of the difference between each pressure data point and the mean, then dividing the sum of squares by the number of data points minus one, and finally taking the square root, for example This calculation can use statistical analysis tools to ensure accurate calculation of the standard deviation. The result of the standard deviation will be used to measure the dispersion of the pressure data, and finally the intelligent hospital bed pressure matrix standard deviation is obtained.

[0031] Step S24: Based on the intelligent hospital bed pressure matrix mean and the intelligent hospital bed pressure matrix standard deviation, the intelligent hospital bed pressure distribution matrix model is divided into pressure difference blocks to obtain the intelligent hospital bed pressure weak block and the intelligent hospital bed pressure excessive block. In the embodiment of the application, the corresponding intelligent hospital bed pressure distribution matrix model is divided into pressure difference blocks by combining the previously quantitatively calculated intelligent hospital bed pressure matrix mean and intelligent hospital bed pressure matrix standard deviation. First, the standard limit value is determined, for example This is set as the standard corresponding to the pressure weak block and the pressure excessive block, where the pressure weak block is specifically And the pressure excessive block is specifically Each pressure value in the matrix is compared with these thresholds, and the pressure points are classified according to the comparison results. This step is realized by logical judgment, and each pressure value is classified using conditional statements to form two blocks, which are identified as the pressure weak and pressure excessive regions, respectively. Finally, the intelligent hospital bed pressure weak block and the intelligent hospital bed pressure excessive block are obtained.

[0032] Step S25: Obtain user real-time body posture data and user body feature data, and based on the user real-time body posture data and the user body feature data, respectively, the intelligent hospital bed pressure weak block and the intelligent hospital bed pressure excessive block are calculated for air charging and discharging compensation, and the pressure weak block adaptive air charging amount and the pressure excessive block adaptive air discharging amount are obtained.

[0033] In the embodiment of the present application, by using high-precision sensors and camera systems, the body posture and body feature data of the user are captured in real time, the collected images are processed using deep learning algorithms to identify the parts of the user's body, and the joint angle, height, weight and other body feature parameters are obtained through the data feedback of the sensors such as pressure, acceleration, etc. During the data collection process, the sensor is in good contact with the user to obtain accurate body posture information and convert it into a standardized numerical form, so as to obtain the real-time body posture data and body feature data of the user. At the same time, by combining the real-time body posture data and body feature data of the user obtained previously, the compensation calculation of the specific amount of inflation and deflation of the previously identified weak pressure block and the overlarge pressure block of the intelligent hospital bed is carried out, so as to calculate the inflation and deflation amount of each region by analyzing the posture change of the user and combining the characteristics of each block, using the fluid dynamics model or the pressure model, calculating the required inflation amount for the weak region and the deflation amount for the overlarge region. This process can be realized by algorithm, ensuring accurate control of gas flow, so that the pressure of each block is kept within a proper range, and finally the adaptive inflation amount of the weak pressure block and the adaptive deflation amount of the overlarge pressure block are obtained.

[0034] Further, step S24 comprises the following steps: Step S241: According to the intelligent hospital bed pressure matrix mean value and the intelligent hospital bed pressure matrix standard deviation, a statistical distribution graph is drawn to generate an intelligent hospital bed pressure matrix statistical distribution graph; In the embodiment of the present application, by combining the intelligent hospital bed pressure matrix mean value and the intelligent hospital bed pressure matrix standard deviation calculated previously, the hist() function of Matplotlib is used to draw a histogram of the pressure matrix to show the distribution of the pressure data, and a normal distribution curve is superimposed to intuitively display the distribution characteristics of the pressure matrix, and finally an intelligent hospital bed pressure matrix statistical distribution graph is drawn.

[0035] Step S242: The intelligent hospital bed pressure matrix statistical distribution graph is subjected to skewness and kurtosis statistical analysis to obtain the intelligent hospital bed pressure distribution skewness value and the intelligent hospital bed pressure distribution kurtosis value; In the embodiment of the present application, the skewness and kurtosis of the pressure data at each distribution point are analyzed by using the skew() and kurtosis() functions of the SciPy library on the generated intelligent hospital bed pressure matrix statistical distribution graph, the skewness value is used to judge the symmetry of the distribution, and the kurtosis value reflects the sharpness of the distribution, the calculation results are recorded to provide the basis data for subsequent adjustment, wherein the skewness value greater than zero indicates that the distribution is right-skewed, and the skewness value less than zero indicates that the distribution is left-skewed; and the kurtosis value greater than three indicates that the distribution is relatively sharp, and the kurtosis value less than three indicates that the distribution is relatively flat, and finally the intelligent hospital bed pressure distribution skewness value and the intelligent hospital bed pressure distribution kurtosis value are obtained.

[0036] Step S243: adjusting the proportion coefficient according to the intelligent hospital bed pressure distribution skewness value and the intelligent hospital bed pressure distribution kurtosis value to obtain the intelligent hospital bed pressure matrix distribution adjustment proportion coefficient. In the embodiment of the present application, by combining the previously analyzed intelligent hospital bed pressure distribution skewness value and intelligent hospital bed pressure distribution kurtosis value, a formula is set to calculate the adjustment proportion coefficient, so as to realize the weighted average of the skewness value and the kurtosis value to obtain a comprehensive adjustment coefficient, which reflects the overall characteristics of the pressure distribution, if the skewness value deviates significantly from zero or the kurtosis value deviates significantly from three, it indicates that the pressure distribution is uneven and needs to be adjusted, and the specific calculation formula can be: adjustment proportion coefficient = a*skewness value + b*(kurtosis value-3), wherein a and b are weight parameters, and finally the intelligent hospital bed pressure matrix distribution adjustment proportion coefficient is obtained.

[0037] Step S244: quantitatively calculating the pressure difference division limit based on the intelligent hospital bed pressure matrix distribution adjustment proportion coefficient and the intelligent hospital bed pressure matrix mean value and the intelligent hospital bed pressure matrix standard deviation to obtain the intelligent hospital bed pressure distribution difference division standard limit. In the embodiment of the present application, the mean value and the standard deviation of the pressure matrix are re-evaluated by combining the previously quantitatively calculated intelligent hospital bed pressure matrix distribution adjustment proportion coefficient, so as to set the standard limit of the pressure difference division, determine a reasonable pressure range by using the mean value ± k*standard deviation (k is the intelligent hospital bed pressure matrix distribution adjustment proportion coefficient), record the range, form the standard limit of the pressure distribution difference division, and finally obtain the intelligent hospital bed pressure distribution difference division standard limit.

[0038] Step S245: dividing the pressure difference block based on the intelligent hospital bed pressure distribution difference division standard limit and the intelligent hospital bed pressure distribution matrix model to obtain the intelligent hospital bed pressure weak block and the intelligent hospital bed pressure excessive block.

[0039] In this embodiment of the invention, the intelligent hospital bed pressure distribution matrix model is divided into regions by combining the previously determined standard boundary for dividing the pressure distribution difference of the intelligent hospital bed. Using a predefined algorithm, the pressure matrix data is traversed, and regions where the pressure value falls into different intervals are marked as weak blocks (i.e., all adjacent pressure points with specific pressure values ​​less than the standard boundary) or excessive blocks (i.e., all adjacent pressure points with specific pressure values ​​greater than the standard boundary). A method combining matrix operations and conditional judgments can be used, and the numpy.where() function is used for efficient processing to complete the block division. The block division results are then visualized, and finally, weak intelligent hospital bed pressure blocks and excessive intelligent hospital bed pressure blocks are obtained.

[0040] Furthermore, step S245 includes the following steps: Based on the criteria for classifying pressure distribution differences in intelligent hospital beds, pressure differences are labeled and determined for each pressure value point within the intelligent hospital bed pressure distribution matrix model. If the pressure distribution matrix model contains the first... Line number If the pressure value point corresponding to the column is equal to the boundary of the standard for dividing the pressure distribution difference of the intelligent hospital bed, no processing is performed; if the pressure value point in the intelligent hospital bed pressure distribution matrix model is equal to the boundary of the standard for dividing the pressure distribution difference of the intelligent hospital bed, no processing is performed. Line number If the pressure value point corresponding to a column is less than the threshold of the standard for classifying pressure distribution differences in intelligent hospital beds, then that pressure value point is marked as a point with weak pressure; if the pressure distribution matrix model of the intelligent hospital bed contains a column with a pressure value point less than the threshold of the standard for classifying pressure distribution differences in intelligent hospital beds, then that ... Line number When the pressure value point corresponding to the column is greater than the limit of the standard for dividing the pressure distribution difference of the intelligent hospital bed, the pressure value point is marked as the pressure excessive value point. In this embodiment of the invention, by combining the specific numerical values ​​of the standard boundary for dividing the pressure distribution differences of the intelligent hospital bed obtained from previous analysis, the abnormal pressure points of each pressure value point in the intelligent hospital bed pressure distribution matrix model are marked and determined accordingly, so as to set a standard boundary value. This value is determined based on experimental data or theoretical models and is used to distinguish between normal and abnormal pressure distributions. Based on this standard boundary value, the model is traversed through the pressure distribution matrix model of the intelligent hospital bed. Line number For each pressure value point in the column, compare the pressure value of each point with the standard limit value. During the traversal, if the first... Line number If the value of the column pressure numerical point is equal to the standard limit, the point remains in the original state and does not need to be further processed; if the pressure value is less than the standard limit, the point is marked as "weak pressure" and the row and column indexes thereof are recorded for subsequent processing, so as to obtain the weak pressure numerical point position; and if the pressure value is greater than the standard limit, the point is marked as "excessive pressure" and the row and column indexes thereof are recorded, so as to obtain the excessive pressure numerical point position, which ensures that the state of all pressure numerical points is accurately identified and lays a foundation for subsequent classification and aggregation.

[0041] Preferably, the row and column labels corresponding to all the weak pressure numerical point positions and the excessive pressure numerical point positions in the intelligent hospital bed pressure distribution matrix model are obtained respectively to obtain the weak pressure point position row and column labels and the excessive pressure point position row and column labels. In the embodiment of the present application, the row and column labels of all the numerical points marked as "weak pressure" and "excessive pressure" are extracted respectively to create two lists respectively by using the row and column indexes of the weak pressure and excessive pressure points identified in the previous step, and the row and column labels of all the weak pressure points and the excessive pressure points are stored in the lists. The process is realized by traversing the previous marking results, and all the row and column indexes meeting the conditions are recorded in the corresponding lists. These row and column labels will be used in the subsequent aggregation and classification steps to accurately locate the specific position in the pressure distribution matrix during the classification process, and finally the weak pressure point position row and column labels and the excessive pressure point position row and column labels are obtained.

[0042] Preferably, the weak pressure adjacent point positions of all the weak pressure numerical points are aggregated and classified based on the weak pressure point position row and column labels to obtain the intelligent hospital bed weak pressure adjacent point position subsets corresponding to the weak pressure sub-regions. In the embodiment of the present application, the row and column adjacent point positions of all the weak pressure numerical points are aggregated and classified based on the weak pressure point position row and column labels. The concept of adjacency matrix in graph theory is adopted, the weak pressure numerical points are regarded as nodes in the graph, and the connection relationship between the nodes is defined by the adjacent relationship in the pressure distribution matrix. All the points marked as weak pressure are traversed by double loops, and it is checked whether the four adjacent points above, below, left and right of each point also belong to the weak pressure sub-region. If the row and column labels corresponding to the adjacent points differ by one value, they are classified into the same subset, so as to divide multiple subsets, each of which contains a group of weak pressure point sets adjacent to each other in the pressure distribution matrix. This process realizes the effective division of the weak pressure sub-regions, and finally the intelligent hospital bed weak pressure adjacent point position subsets corresponding to the weak pressure sub-regions are obtained.

[0043] Preferably, the excessive pressure adjacent point positions of all the excessive pressure numerical points are aggregated and classified based on the excessive pressure point position row and column labels to obtain the intelligent hospital bed excessive pressure adjacent point position subsets corresponding to the excessive pressure sub-regions. In the embodiment of the present application, the same is true for the previously identified excessive pressure point position label. All excessive pressure value points are aggregated and classified by row and column adjacent points. The adjacent relationship is still used to aggregate and classify the excessive pressure point position label. An empty list is used to store all the excessive pressure adjacent point subsets. In the loop traversal process, for each point marked as excessive pressure, check whether its adjacent upper, lower, left and right points also belong to the excessive pressure sub-region. If so, these adjacent points are included in the same subset. This process not only effectively identifies the excessive pressure region, but also helps the subsequent division of the excessive pressure block, and finally obtains the intelligent hospital bed excessive pressure adjacent point subset corresponding to each excessive partition.

[0044] Preferably, based on the intelligent hospital bed pressure weak adjacent point subset, the corresponding pressure value points in the intelligent hospital bed pressure distribution matrix model are divided by the edge connection of the pressure weak block to obtain the intelligent hospital bed pressure weak block; based on the intelligent hospital bed pressure excessive adjacent point subset, the corresponding pressure value points in the intelligent hospital bed pressure distribution matrix model are divided by the edge connection of the pressure excessive block to obtain the intelligent hospital bed pressure excessive block.

[0045] In the embodiment of the present application, the intelligent hospital bed pressure weak adjacent point subset obtained by the previous aggregation and division is used to divide the corresponding pressure value points in the intelligent hospital bed pressure distribution matrix model by the edge connection of the pressure weak block, so as to determine the edge position of these points by traversing each aggregated subset. In the traversal process, the minimum row and column index and the maximum row and column index of the points in each subset are recorded, thereby defining the boundary of each pressure weak block. In specific implementation, a flag matrix can be used to mark the points belonging to the weak block, and then these points are traversed to ensure that all pressure weak regions are correctly divided, thereby connecting the intelligent hospital bed pressure weak block obtained by division. Similarly, based on the pressure excessive adjacent point subset, the corresponding pressure value points in the intelligent hospital bed pressure distribution matrix model are divided by the edge connection of the pressure excessive block, and the boundary points are also recorded, thereby connecting to form the complete range of the pressure excessive block, and finally obtaining the intelligent hospital bed pressure excessive block.

[0046] Further, the edge connection division of the pressure weak block based on the intelligent hospital bed pressure weak adjacent point subset includes the following steps: The edge pressure point position of the pressure weak partition is identified based on the intelligent hospital bed pressure weak adjacent point subset, so as to obtain the edge pressure point position of each direction corresponding to the pressure weak adjacent partition in the intelligent hospital bed pressure distribution matrix model. In the embodiment of the present application, by combining each weak pressure point in the subset of weakly adjacent points of the intelligent hospital bed pressure obtained through previous analysis, the corresponding pressure value points in the intelligent hospital bed pressure distribution matrix model are matched and determined to determine the corresponding weakly adjacent distribution range in the intelligent hospital bed pressure distribution matrix model, and the specific position of the maximum edge pressure node at each position in the corresponding weakly adjacent distribution range is identified, and finally the edge pressure point position at each position corresponding to the weakly adjacent partition in the intelligent hospital bed pressure distribution matrix model is obtained.

[0047] Preferably, the edge pressure gradient fitting analysis is performed on the edge pressure point position at each position corresponding to the weakly adjacent partition in the intelligent hospital bed pressure distribution matrix model, and the edge pressure fitting gradient corresponding to the weakly adjacent partition is obtained. In the embodiment of the present application, by performing the fitting analysis of the edge pressure gradient on the edge pressure point position at each position corresponding to the weakly adjacent partition in the intelligent hospital bed pressure distribution matrix model identified previously, the least square method is used to process the pressure data of the edge pressure point at each position, a mathematical model of pressure value and spatial position is established, then the pressure gradient change at the specific position is calculated to analyze the pressure change at different positions, and the edge pressure fitting gradient is obtained. This gradient can effectively reflect the strength and trend of pressure change, and finally the edge pressure fitting gradient corresponding to the weakly adjacent partition is obtained.

[0048] Preferably, based on the edge pressure fitting gradient, the adjacent point edge connection analysis is performed on the edge pressure point position at each position corresponding to the weakly adjacent partition in the intelligent hospital bed pressure distribution matrix model, and the block edge connection boundary between the adjacent edge pressure points at each position corresponding to the weakly adjacent partition is obtained. In the embodiment of the present application, by combining the edge pressure fitting gradient obtained through previous fitting analysis, the adjacent point position between the edge pressure points at each position corresponding to the weakly adjacent partition in the intelligent hospital bed pressure distribution matrix model is analyzed by using the connected component algorithm in graph theory, and the specific operation is as follows: the edge pressure point is taken as a node, the fitting obtained pressure gradient is taken as a weight, a connected graph is constructed, the connected boundary between the adjacent edge pressure points is identified by traversing the nodes in the graph, the adjacent edge points belonging to the same block are marked, and thus the boundary of the weak pressure area is effectively delimited, and finally the block edge connection boundary between the adjacent edge pressure points at each position corresponding to the weakly adjacent partition is obtained.

[0049] Preferably, according to the block edge connection boundary between the adjacent edge pressure points at each position corresponding to the weakly adjacent partition, the pressure weak block of the intelligent hospital bed pressure distribution matrix model is obtained by performing pressure weak block edge connection division on the corresponding pressure value points.

[0050] In the embodiment of the present application, after the block edge connected boundary between the edge pressure adjacent points corresponding to the weak pressure adjacent partition is identified, the corresponding pressure value points in the intelligent hospital bed pressure distribution matrix model are divided based on the connected boundary. The specific operation is to classify the pressure value points in the pressure distribution matrix according to the boundary information, and all the pressure points falling in the same block are classified according to their adjacent relationship, and these adjacent pressure points form a complete weak pressure block, so as to effectively mark and separate the uneven area of the pressure distribution of the intelligent hospital bed. This process ensures that the intelligent hospital bed can accurately respond to the user's pressure distribution demand, and finally connects and divides the weak pressure block of the intelligent hospital bed.

[0051] Further, step S25 includes the following steps: Step S251: acquiring real-time body posture data and user body feature data of the user; In the embodiment of the present application, the body posture and body feature data of the user are captured in real time by using high-precision sensors and camera systems, the collected images are processed by using a deep learning algorithm, the body parts of the user are recognized, the data such as pressure and acceleration fed back by the sensors are obtained, the joint angle, height, weight and other body feature parameters are obtained, in the data acquisition process, the sensors are ensured to be in good contact with the user, so as to obtain accurate body information and convert it into a standardized numerical form, form a complete user data set, and finally obtain the real-time body posture data and body feature data of the user.

[0052] Step S252: performing feature three-dimensional corner point detection on the real-time body posture data and body feature data of the user to obtain a user body posture feature three-dimensional corner point set and a user body feature three-dimensional corner point set; In the embodiment of the present application, on the basis of the acquired user body posture data and body feature data, feature three-dimensional corner point detection is performed by using three-dimensional reconstruction technology, so as to identify the key joint positions of the user by applying an image processing algorithm (such as edge detection and feature matching), and a three-dimensional space coordinate transformation algorithm is used to map the identified two-dimensional corner points to a three-dimensional coordinate system, to generate a three-dimensional corner point set of the user body posture feature. At the same time, combined with the body feature data of the user, the body feature three-dimensional corner point set is extracted through statistical analysis, to ensure the accuracy and integrity of the corner point set, and finally the user body posture feature three-dimensional corner point set and the user body feature three-dimensional corner point set are obtained.

[0053] Step S253: performing user body posture simulation modeling according to the user body posture feature three-dimensional corner point set and the user body feature three-dimensional corner point set, to generate a real-time simulation model of the user body posture of the intelligent hospital bed; In the embodiment of the present application, the user body posture simulation modeling is performed by combining the previously detected user body feature three-dimensional angle point set and the user body feature three-dimensional angle point set, so as to construct a three-dimensional model of the user by using the bone animation technology in computer graphics, simulate the motion range and position relationship of each joint, at the same time, simulate the center of gravity and stress of the user in different postures by using the physical engine, ensure the reality of the model, and generate a dynamic adjustable user body posture real-time change simulation model, so that the model data can be updated in real time according to the posture change of the user, and finally generate an intelligent bed user body posture real-time simulation model.

[0054] Step S254: coupling analysis of the intelligent bed user body posture real-time simulation model and the intelligent bed pressure distribution matrix model is performed by using the user simulation force field, so as to generate an intelligent bed user real-time use simulation coupling dynamic field; In the embodiment of the present application, after the intelligent bed user body posture real-time simulation model is completed, the coupling analysis is performed on the intelligent bed pressure distribution matrix model, so as to evaluate how the user weight is distributed in each area of the intelligent bed in a specific body posture by using the finite element analysis (FEA) method to apply different use situation simulation to the simulation model, and obtain the stress characteristics of the intelligent bed under different pressure distributions by force field analysis, generate a simulation coupling dynamic field of the user real-time use process of the intelligent bed, ensure that the mattress can obtain the corresponding pressure stress distribution in real time under different user postures, and finally generate an intelligent bed user real-time use simulation coupling dynamic field.

[0055] Step S255: based on the intelligent bed user real-time use simulation coupling dynamic field, compensation calculation of the air charging and discharging amount is performed on the intelligent bed pressure weak block and the intelligent bed pressure excessive block respectively, to obtain the adaptive air charging amount of the pressure weak block and the adaptive air discharging amount of the pressure excessive block.

[0056] In the embodiment of the present application, based on the intelligent bed user real-time use simulation coupling dynamic field obtained by the coupling analysis, that is, the corresponding pressure stress distribution of the intelligent bed user in different postures, compensation calculation of the air charging and discharging amount is performed on the intelligent bed pressure weak block and the intelligent bed pressure excessive block respectively, to calculate the adaptive air charging amount and air discharging amount of each area according to the coupling dynamic field data, perform air charging amount compensation calculation on the area with insufficient pressure by using the fluid dynamics model, ensure that the pressure can be restored to the set standard, calculate the adaptive air discharging amount for the area with excessive pressure, and realize real-time dynamic adjustment by adjusting the air pressure of the air bag inside the intelligent bed, ensure that the user obtains balanced support and comfort during sleep, and finally obtain the adaptive air charging amount of the pressure weak block and the adaptive air discharging amount of the pressure excessive block.

[0057] Further, step S254 includes the following steps: The user real-time posture synchronization response setting of the intelligent sickbed user body posture real-time simulation model is performed to generate different sleep posture response conditions of the intelligent sickbed user; In the embodiment of the present application, after the construction of the intelligent sickbed user body posture real-time simulation model is completed, the physiological characteristic data of the user, including height, weight and specific sleep habits, need to be collected first, so as to monitor the body posture changes of the user in real time through embedded sensors, such as accelerometers and gyroscopes, and the data is transmitted to the central processing unit through wireless connection. The real-time posture of the user is analyzed using a machine learning algorithm, and the generated posture information is input into the intelligent sickbed user body posture real-time simulation model constructed by simulation to generate corresponding user response conditions of the patient user in different sleep postures, and finally the different sleep posture response conditions of the intelligent sickbed user are set.

[0058] Preferably, the pressure distribution matrix model of the intelligent sickbed is optimized based on the different sleep posture response conditions of the intelligent sickbed user to obtain the corresponding pressure distribution matrix sub-model of the intelligent sickbed user in different sleep postures; In the embodiment of the present application, the pressure distribution matrix model of the intelligent sickbed is optimized after the different sleep posture response conditions of the user are obtained. In the specific operation, the finite element analysis method is adopted to simulate the pressure distribution of the user's weight in different postures by establishing a pressure distribution matrix, and the pressure data of each region is monitored in real time through the matrix pressure sensor arranged on the surface of the mattress. The collected data will be sent into the pressure optimization algorithm. This algorithm based on machine learning technology can adjust the pressure distribution according to real-time feedback to generate a pressure distribution matrix sub-model corresponding to the user's posture, ensuring the maximum comfort and support of the user in different postures. Finally, the corresponding pressure distribution matrix sub-model of the intelligent sickbed user in different sleep postures is obtained.

[0059] Preferably, the force field coupling model is constructed for the corresponding pressure distribution matrix sub-model of the intelligent sickbed user in different sleep postures and the intelligent sickbed user body posture real-time simulation model to generate a real-time comprehensive stress force field coupling model of the intelligent sickbed user; In the embodiment of the present application, the force field coupling model of the user of the smart hospital bed is established by fusing the previously optimized pressure distribution matrix sub-model of the user of the smart hospital bed in different sleeping postures and the corresponding real-time simulation model of the body posture of the user of the smart hospital bed, so as to integrate the data of the corresponding pressure distribution matrix and the simulation model in different sleeping postures by using a computer simulation software, form a multi-dimensional force field model, establish the boundary conditions of the force field by algorithm calculation combined with the information fed back by the actual sensor, and obtain the force field coupling model of the real-time comprehensive stress of the user by using a nonlinear dynamics method to process the interaction of each point in the force field. The model can accurately reflect the specific stress distribution of the user in different sleeping postures, and finally generate the real-time comprehensive stress force field coupling model of the user of the smart hospital bed.

[0060] Preferably, the real-time comprehensive stress force field coupling model of the user of the smart hospital bed is subjected to dynamic coupling force field simulation analysis to generate the real-time use simulation coupling dynamic field of the user of the smart hospital bed.

[0061] In the embodiment of the present application, the real-time comprehensive stress force field coupling model of the user of the smart hospital bed is subjected to dynamic coupling force field simulation analysis to generate the real-time use simulation coupling dynamic field of the user of the smart hospital bed.

[0062] Further, the step S255 comprises the following steps: Based on the real-time use simulation coupling dynamic field of the user of the smart hospital bed, the structural bearing and limit load analysis are performed on the inflatable structure soft package at each pressure point in the weak pressure block and the excessive pressure block of the smart hospital bed, respectively, to obtain the corresponding inflatable structure bearing pressure and limit load pressure of each pressure point in the weak pressure block and the excessive pressure block. In the embodiment of the present application, the structural bearing and limit load analysis are performed on the weak pressure block and the excessive pressure block of the smart hospital bed based on the real-time use simulation coupling dynamic field of the user of the smart hospital bed obtained through the previous coupling analysis, to model the inflatable structure soft package at each pressure point by using a finite element analysis software, set boundary conditions and loading conditions according to the weight and use posture of the user, analyze the actual bearing capacity and limit load of each pressure point by applying mechanics theory, output the bearing pressure value and limit load value of each pressure point according to the simulation result, and finally obtain the corresponding inflatable structure bearing pressure of each pressure point in the weak pressure block and the excessive pressure block. and the air-filled structure limit load pressure .

[0063] Preferably, the target pressure of each pressure point in the pressure weak block and the pressure excessive block of the intelligent hospital bed is calculated by using a target pressure adaptive calculation formula based on the air-filled structure bearing pressure corresponding to each pressure point in the pressure weak block and the pressure excessive block and the air-filled structure limit load pressure, and the air-filled structure target adaptive pressure corresponding to each pressure point in the pressure weak block and the pressure excessive block is obtained. In the embodiment of the present application, a suitable target pressure adaptive calculation formula is constructed by combining the air-filled structure bearing pressure corresponding to each pressure point in the pressure weak block, the air-filled structure limit load pressure, the air-filled structure bearing pressure corresponding to each pressure point in the pressure excessive block, the air-filled structure limit load pressure, the horizontal coordinate of the pressure point, the vertical coordinate of the pressure point, the area size, the corresponding influence weight parameter and the related parameter, and the target pressure of each pressure point in the pressure weak block and the pressure excessive block of the intelligent hospital bed is calculated, so as to quantitatively calculate the target adaptive pressure of each pressure point by inputting the bearing pressure and the limit load of each pressure point, and the result is stored after calculation, so as to be used for real-time adjustment of inflation and deflation, to ensure that the mattress can automatically adapt to the needs of the user during use, and finally obtain the air-filled structure target adaptive pressure corresponding to each pressure point in the pressure weak block and the pressure excessive block.

[0064] Preferably, the air-filled structure gas flow characteristic data is obtained, and the corresponding air-filled structure soft package is subjected to gas flow ratio response analysis based on the air-filled structure gas flow characteristic data, and the air-filled structure gas flow ratio coefficient is obtained. In the embodiment of the present application, the air-filled structure gas flow characteristic data is obtained by using laboratory equipment, a fluid dynamics model is used to analyze the flow behavior of gas inside the air-filled structure, the pressure change in the inflation and deflation process is recorded, the speed, flow and pressure change data of gas flow under different pressure states are collected, and the collected data is analyzed by using a data processing tool to calculate the gas flow ratio, and the air-filled structure gas flow ratio coefficient under different operating conditions is obtained, to ensure the balance of inflation and deflation, and to serve as a basis for subsequent inflation and deflation amount calculation, and finally the air-filled structure gas flow ratio coefficient is obtained.

[0065] Preferably, the inflation amount compensation calculation of each pressure point in the pressure weak block of the intelligent hospital bed is performed based on the air-filled structure target adaptive pressure corresponding to each pressure point in the pressure weak block and the air-filled structure gas flow ratio coefficient, and the pressure weak block adaptive inflation amount is obtained. In this embodiment of the invention, by combining the target matching pressure of the inflation structure corresponding to each pressure point in the pressure-weak block obtained from previous analysis and the gas flow ratio coefficient of the inflation structure, the inflation volume compensation calculation is performed on the actual pressure at the corresponding point in the pressure-weak block of the smart hospital bed. The difference between the target matching pressure and the actual measured pressure is multiplied by the flow ratio coefficient using a mathematical formula to calculate the inflation volume required for each pressure point. This compensation calculation takes into account the dynamic characteristics of gas flow to ensure that the inflation structure can quickly reach the target pressure within an appropriate time, and finally obtains the matching inflation volume for the pressure-weak block.

[0066] Preferably, the gas release compensation is calculated for each pressure point in the excessive pressure block of the smart hospital bed based on the target matching pressure of the inflation structure corresponding to each pressure point in the excessive pressure block and the gas flow ratio coefficient of the inflation structure, so as to obtain the matching gas release volume for the excessive pressure block.

[0067] In this embodiment of the invention, the actual pressure at the corresponding point in the excessive pressure block of the smart hospital bed is compensated by combining the target matching pressure of the inflation structure corresponding to each pressure point in the excessive pressure block obtained by the previous analysis and the gas flow ratio coefficient of the inflation structure. The difference between the target matching pressure and the actual measured pressure is multiplied by the flow ratio coefficient using a mathematical formula to calculate the required amount of air release for each pressure point. This compensation calculation also takes into account the dynamic characteristics of gas flow to ensure that the inflation structure can release air to reach the target pressure within an appropriate time, and finally obtains the air release amount adapted to the excessive pressure block.

[0068] Furthermore, the specific formula for calculating the target pressure adaptation is as follows: ; ; In the formula, The first in the weak pressure block pressure point The corresponding inflatable structure target adaptation pressure, For the first block with excessive pressure pressure point The corresponding inflatable structure target adaptation pressure, The first in the weak pressure block The x-coordinate of each pressure point The first in the weak pressure block The ordinate of each pressure point The first in the weak pressure block pressure point The inflatable structure can withstand pressure. The weighting parameter represents the influence of the pressure borne by the inflatable structure in the low-pressure zone on the target pressure. Area size of the pressure weak block, Minimum pressure in the pressure weak block, Integral influence weight parameter of the minimum pressure, Limit load pressure of the i-th pressure point in the pressure weak block, Limit load pressure of the i-th pressure point in the pressure weak block, Limit load pressure of the i-th pressure point in the pressure weak block, Integral influence weight parameter of the limit load pressure of the i-th pressure point in the pressure weak block, Horizontal coordinate of the i-th pressure point in the pressure excessive block, Horizontal coordinate of the i-th pressure point in the pressure excessive block, Horizontal coordinate of the i-th pressure point in the pressure excessive block, Horizontal coordinate of the i-th pressure point in the pressure excessive block, Limit load pressure of the i-th pressure point in the pressure excessive block, Limit load pressure of the i-th pressure point in the pressure excessive block, Limit load pressure of the i-th pressure point in the pressure excessive block, Integral influence weight parameter of the limit load pressure of the i-th pressure point in the pressure excessive block, Area size of the pressure excessive block, Maximum pressure in the pressure excessive block, Integral influence weight parameter of the maximum pressure, Limit load pressure of the i-th pressure point in the pressure excessive block, Limit load pressure of the i-th pressure point in the pressure excessive block, Limit load pressure of the i-th pressure point in the pressure excessive block, Integral influence weight parameter of the limit load pressure of the i-th pressure point in the pressure excessive block, Correction coefficient of the target adaptive pressure of the air structure corresponding to the pressure weak block, Correction coefficient of the target adaptive pressure of the air structure corresponding to the pressure excessive block.

[0069] The application obtains a target pressure fitting calculation formula by using a specific mathematical model and verification, which is used for target pressure fitting calculation of each pressure point in the weak pressure block and the overlarge pressure block of the intelligent hospital bed. The target pressure fitting calculation formula can obtain the bearing pressure and the limit load of the corresponding point inflation structure according to the weight, sleeping posture and other factors of the user by calculating the fitting pressure of each pressure point in the weak pressure block and the overlarge pressure block respectively, realizes the individualized pressure regulation, and thus improves the use comfort. Through the analysis of the bearing pressure and the limit load of the inflation structure, the weak points of the structure under different use conditions can be identified, and the bearing capacity and safety of the intelligent hospital bed can be ensured within the normal use range. In combination with the gas flow ratio coefficient, the intelligent hospital bed can adjust the inflation amount and the deflation amount in real time to cope with the change of the body position of the user in the use process, and thus guarantees the continuous comfortable experience. Through the analysis of the flow characteristic data, the design of the inflation structure can be optimized to ensure the smooth flow of the gas in the inflation process, and thus the overall response speed and performance are improved. Secondly, through the fitting of the weak pressure and the overlarge pressure, the balanced distribution of the pressure can be maintained in the use process, the use discomfort and fatigue caused by the uneven pressure are reduced, and through the continuous acquisition of the pressure data in the use process, long-term tracking and analysis can be carried out to provide data support for the future design iteration, realize the continuous optimization of the intelligent hospital bed, and determine the limit load of each pressure point to warn the user before the user exceeds the safe range, and thus the safety of the user is ensured. Through the fitting calculation of each pressure point, the air pressure of the mattress can be further adjusted and optimized according to the feedback of the user to ensure the comfort in the long-term use. Therefore, the formula fully considers the horizontal coordinate of the first pressure point in the weak pressure block the corresponding target fitting pressure of the inflation structure of the first pressure point in the weak pressure block the corresponding target fitting pressure of the inflation structure of the first pressure point in the overlarge pressure block the horizontal coordinate of the first pressure point in the weak pressure block the vertical coordinate of the first pressure point in the weak pressure block the inflation structure bearing pressure of the first pressure point in the weak pressure block the influence weight parameter of the inflation structure bearing pressure in the weak pressure block on the target pressure the area size of the weak pressure block the corresponding minimum pressure in the weak pressure block the minimum pressure integral influence weight parameter the inflation structure bearing pressure of the first pressure point in the overlarge pressure block the inflation structure bearing pressure of the first pressure point in the overlarge pressure block the inflation structure bearing pressure of the first pressure point in the overlarge pressure block the inflation structure bearing pressure of the first pressure point in the overlarge pressure block the inflation structure bearing pressure of the first pressure point in the overlarge pressure block the inflation structure bearing pressure of the first pressure point in the overlarge pressure block​​ pressure point Ultimate load pressure of inflatable structure The weighting parameter for the influence of the ultimate load pressure of the inflatable structure on the target pressure in the weak pressure block. The pressure is too high in the first block The x-coordinate of each pressure point The pressure is too high in the first block The ordinate of each pressure point The pressure is too high in the first block pressure point The inflatable structure bears pressure The weighting parameter for the influence of the pressure-bearing structure of the inflatable structure within the excessively high-pressure area on the target pressure. The size of the area with excessive pressure The maximum pressure corresponding to the block with excessive pressure. The influence of the maximum pressure integral on the weighting parameter The pressure is too high in the first block pressure point Ultimate load pressure of inflatable structure The weighting parameter for the influence of the ultimate load pressure of the inflatable structure in the excessively high pressure block on the target pressure. Correction coefficient for the target pressure of the inflatable structure corresponding to the weak pressure block. Correction coefficient for the target pressure of the inflatable structure corresponding to the excessive pressure block. Among them, by combining the first in the weak pressure block The x-coordinate of each pressure point The first block with relatively weak pressure The ordinate of each pressure point The first block with relatively weak pressure pressure point The inflatable structure bears pressure The weighting parameter for the influence of the bearing pressure of the inflatable structure in the weak pressure block on the target pressure. Size of the area with weak pressure The minimum pressure corresponding to the weak pressure block The minimum pressure integral affects the weighting parameter. The first block with relatively weak pressure pressure point Ultimate load pressure of inflatable structure And the weighting parameter for the influence of the ultimate load pressure of the inflatable structure on the target pressure in the weak pressure block. This constitutes the first in a low-pressure block pressure point Corresponding inflatable structure target adaptation pressure Functional relationship , the longitudinal coordinate of the first pressure point in the pressure excessive block , the longitudinal coordinate of the first pressure point in the pressure excessive block , the longitudinal coordinate of the first pressure point in the pressure excessive block , the longitudinal coordinate of the first pressure point in the pressure excessive block , the longitudinal coordinate of the first pressure point in the pressure excessive block , the longitudinal coordinate of the first pressure point in the pressure excessive block , the longitudinal coordinate of the first pressure point in the pressure excessive block , the longitudinal coordinate of the first pressure point in the pressure excessive block , the longitudinal coordinate of the first pressure point in the pressure excessive block , the longitudinal coordinate of the first pressure point in the pressure excessive block , the longitudinal coordinate of the first pressure point in the pressure excessive block , the longitudinal coordinate of the first pressure point in the pressure excessive block , the longitudinal coordinate of the first pressure point in the pressure excessive block , the longitudinal coordinate of the first pressure point in the pressure excessive block , the longitudinal coordinate of the first pressure point in the pressure excessive block , the longitudinal coordinate of the first pressure point in the pressure excessive block , the longitudinal coordinate of the first pressure point in the pressure excessive block , the longitudinal coordinate of the first pressure point in the pressure excessive block , the longitudinal coordinate of the first pressure point in the pressure excessive block , the longitudinal coordinate of the first pressure point in the pressure excessive block , the longitudinal coordinate of the first pressure point in the pressure excessive block , the longitudinal coordinate of the first pressure point in the pressure excessive block

[0070] The above description is merely that of this application, to enable a person skilled in the art to understand or implement it. Many modifications in materials, methods, and details can be made by those skilled in the art without departing from the spirit and scope of the application. Therefore, the present application is not intended to be limited to the examples described herein but on the contrary, is intended to cover any and all alternatives, modifications, equivalents, and / or alternatives falling within the scope of the present application. Accordingly, the application will not be limited to the examples shown herein, but is intended to cover any and all alternatives, modifications, equivalents, and / or alternatives falling within the scope of the principles and novel features disclosed herein.

Claims

1. A smart bed control method based on modeling of a matrix pressure sensor, characterized by, The method comprises the following steps: Step S1: arranging a matrix pressure sensor network in the mattress, wherein the matrix pressure sensor network is composed of 300 pressure sensor subunits arranged in 10 rows and 30 columns, and a corresponding inflatable structure soft package with inflation and deflation valves is arranged in the blank block between each pressure sensor subunit in the matrix pressure sensor network to obtain a matrix pressure sensing intelligent hospital bed; Real-time pressure data of the user at each sensing point is collected by each pressure sensor subunit in the matrix pressure sensing intelligent hospital bed, and a pressure distribution matrix model is established to obtain an intelligent hospital bed pressure distribution matrix model; Step S2: obtaining the intelligent hospital bed pressure matrix mean value and the intelligent hospital bed pressure matrix standard deviation based on the intelligent hospital bed pressure distribution matrix model, and dividing the intelligent hospital bed pressure distribution matrix model into pressure difference blocks based on the intelligent hospital bed pressure matrix mean value and the intelligent hospital bed pressure matrix standard deviation to obtain an intelligent hospital bed pressure weak block and an intelligent hospital bed pressure excessive block; obtaining real-time body posture data and user body feature data of the user, and performing inflation and deflation compensation calculation on the intelligent hospital bed pressure weak block and the intelligent hospital bed pressure excessive block based on the real-time body posture data and the user body feature data to obtain an adaptive inflation amount of the pressure weak block and an adaptive deflation amount of the pressure excessive block; Step S3: performing inflation control response on the inflation valve corresponding to the inflatable structure soft package in the intelligent hospital bed pressure weak block by applying the adaptive inflation amount of the pressure weak block to the inflation valve to generate an intelligent hospital bed inflation valve control instruction to perform corresponding intelligent hospital bed pressure weak inflation control work; Step S4: performing deflation control response on the deflation valve corresponding to the inflatable structure soft package in the intelligent hospital bed pressure excessive block by applying the adaptive deflation amount of the pressure excessive block to the deflation valve to generate an intelligent hospital bed deflation valve control instruction to perform corresponding intelligent hospital bed pressure excessive deflation control work.

2. The smart hospital bed control method based on modeling of a matrix pressure sensor according to claim 1, characterized in that, Step S1 comprises the following steps: Step S11: arranging the matrix distribution layout in the mattress according to a 10-row and 30-column arrangement to design and generate a matrix distribution layout diagram in the mattress; Step S12: configuring a pressure sensor subunit at each intersection in the matrix distribution layout diagram in the mattress and connecting and arranging to generate a matrix pressure sensor network, wherein the matrix pressure sensor network is composed of 300 pressure sensor subunits arranged in 10 rows and 30 columns; Step S13: arranging a corresponding inflatable structure soft package with inflation and deflation valves in the blank block between each pressure sensor subunit in the matrix pressure sensor network to obtain a matrix pressure sensing intelligent hospital bed; Step S14: collecting real-time pressure data of the user at each sensing point by each pressure sensor subunit in the matrix pressure sensing intelligent hospital bed to obtain real-time pressure data of the user at each pressure sensing point; Step S15: establishing a pressure distribution matrix model based on the real-time pressure data of the user at each pressure sensing point to obtain an intelligent hospital bed pressure distribution matrix model.

3. The smart hospital bed control method based on modeling of a matrix pressure sensor according to claim 1, characterized in that, Step S2 comprises the following steps: Step S21: The pressure data at each distribution point in the intelligent hospital bed pressure distribution matrix model is accumulated and summed to obtain an intelligent hospital bed pressure accumulation distribution cumulative value. Step S22: Based on the intelligent hospital bed pressure accumulation distribution cumulative value, the intelligent hospital bed pressure distribution matrix model is calculated to obtain the intelligent hospital bed pressure matrix mean value. Step S23: Based on the intelligent hospital bed pressure matrix mean value, the pressure data at each distribution point in the intelligent hospital bed pressure distribution matrix model is calculated to obtain the intelligent hospital bed pressure matrix standard deviation. Step S24: Based on the intelligent hospital bed pressure matrix mean value and the intelligent hospital bed pressure matrix standard deviation, the intelligent hospital bed pressure distribution matrix model is divided into pressure difference blocks to obtain the intelligent hospital bed pressure weak block and the intelligent hospital bed pressure excessive block. Step S25: Real-time body posture data and user body feature data are obtained, and based on the real-time body posture data and the user body feature data, the intelligent hospital bed pressure weak block and the intelligent hospital bed pressure excessive block are compensated for inflation and deflation to obtain the intelligent hospital bed pressure weak block inflation and the intelligent hospital bed pressure excessive block deflation.

4. The smart hospital bed control method based on modeling of a matrix pressure sensor according to claim 3, characterized in that, Step S24 includes the following steps: Step S241: According to the intelligent hospital bed pressure matrix mean value and the intelligent hospital bed pressure matrix standard deviation, a statistical distribution graph is drawn to generate an intelligent hospital bed pressure matrix statistical distribution graph; Step S242: The intelligent hospital bed pressure matrix statistical distribution graph is analyzed to obtain the intelligent hospital bed pressure distribution skewness value and the intelligent hospital bed pressure distribution kurtosis value; Step S243: According to the intelligent hospital bed pressure distribution skewness value and the intelligent hospital bed pressure distribution kurtosis value, an adjustment proportion coefficient is calculated to obtain the intelligent hospital bed pressure matrix distribution adjustment proportion coefficient; Step S244: Based on the intelligent hospital bed pressure matrix distribution adjustment proportion coefficient, the intelligent hospital bed pressure matrix mean value and the intelligent hospital bed pressure matrix standard deviation are quantitatively calculated to obtain the intelligent hospital bed pressure distribution difference division standard limit; Step S245: Based on the intelligent hospital bed pressure distribution difference division standard limit, the intelligent hospital bed pressure distribution matrix model is divided into pressure difference blocks to obtain the intelligent hospital bed pressure weak block and the intelligent hospital bed pressure excessive block.

5. The smart hospital bed control method based on modeling of a matrix pressure sensor according to claim 4, characterized in that, Step S245 includes the following steps: Based on the intelligent hospital bed pressure distribution difference division standard limit, each pressure value point in the intelligent hospital bed pressure distribution matrix model is marked and determined. If the pressure value point corresponding to the first row and the first column in the intelligent hospital bed pressure distribution matrix model is equal to the intelligent hospital bed pressure distribution difference division standard limit, no processing is performed. If the pressure value point corresponding to the first row and the first column in the intelligent hospital bed pressure distribution matrix model is less than the intelligent hospital bed pressure distribution difference division standard limit, the pressure value point is marked and determined as a weak pressure value point. If the pressure value point corresponding to the first row and the first column in the intelligent hospital bed pressure distribution matrix model is greater than the intelligent hospital bed pressure distribution difference division standard limit, the pressure value point is marked and determined as an excessive pressure value point. row column is equal to the intelligent hospital bed pressure distribution difference division standard limit, no processing is performed. If the pressure value point corresponding to the first row and the first column in the intelligent hospital bed pressure distribution matrix model is less than the intelligent hospital bed pressure distribution difference division standard limit, the pressure value point is marked and determined as a weak pressure value point. If the pressure value point corresponding to the first row and the first column in the intelligent hospital bed pressure distribution matrix model is greater than the intelligent hospital bed pressure distribution difference division standard limit, the pressure value point is marked and determined as an excessive pressure value point. row column is equal to the intelligent hospital bed pressure distribution difference division standard limit, no processing is performed. If the pressure value point corresponding to the first row and the first column in the intelligent hospital bed pressure distribution matrix model is less than the intelligent hospital bed pressure distribution difference division standard limit, the pressure value point is marked and determined as a weak pressure value point. If the pressure value point corresponding to the first row and the first column in the intelligent hospital bed pressure distribution matrix model is greater than the intelligent hospital bed pressure distribution difference division standard limit, the pressure value point is marked and determined as an excessive pressure value point. row column is equal to the intelligent hospital bed pressure distribution difference division standard limit, no processing is performed. If the pressure value point corresponding to the first row and the first column in The row and column labels of all pressure weak numerical points and pressure excessive numerical points in the intelligent hospital bed pressure distribution matrix model are obtained to obtain the pressure weak point row and column label and the pressure excessive point row and column label; Based on the pressure weak point row and column label, all pressure weak numerical points are classified into pressure weak adjacent point subsets corresponding to each weak partition; Based on the pressure excessive point row and column label, all pressure excessive numerical points are classified into pressure excessive adjacent point subsets corresponding to each excessive partition; The weak pressure adjacent point subset of the smart hospital bed is used to perform weak pressure block edge connection division on the corresponding pressure value points in the smart hospital bed pressure distribution matrix model, to obtain a weak pressure block of the smart hospital bed.

6. The smart hospital bed control method based on modeling of a matrix pressure sensor according to claim 5, characterized in that, The weak pressure adjacent point subset of the smart hospital bed is used to perform weak pressure block edge connection division on the corresponding pressure value points in the smart hospital bed pressure distribution matrix model, to obtain a weak pressure block of the smart hospital bed. The weak pressure adjacent point subset of the smart hospital bed is used to perform weak pressure block edge connection division on the corresponding pressure value points in the smart hospital bed pressure distribution matrix model, to obtain a weak pressure block of the smart hospital bed. The weak pressure adjacent point subset of the smart hospital bed is used to perform weak pressure block edge connection division on the corresponding pressure value points in the smart hospital bed pressure distribution matrix model, to obtain a weak pressure block of the smart hospital bed. The weak pressure adjacent point subset of the smart hospital bed is used to perform weak pressure block edge connection division on the corresponding pressure value points in the smart hospital bed pressure distribution matrix model, to obtain a weak pressure block of the smart hospital bed. Step S25 includes the following steps:

7. The smart hospital bed control method based on modeling of a matrix pressure sensor according to claim 3, characterized by, Step S251: Obtain real-time body posture data and body feature data of the user; Step S252: Perform feature three-dimensional corner point detection on the real-time body posture data and body feature data of the user, to obtain a user body posture feature three-dimensional corner point set and a user body feature three-dimensional corner point set; Step S253: Perform user body state simulation modeling according to the user body posture feature three-dimensional corner point set and the user body feature three-dimensional corner point set, to generate a smart hospital bed user body state real-time simulation model; Step S254: Perform user use simulation force field coupling analysis on the smart hospital bed user body state real-time simulation model and the smart hospital bed pressure distribution matrix model, to generate a smart hospital bed user real-time use simulation coupling dynamic field; Step S255: Based on the smart hospital bed user real-time use simulation coupling dynamic field, perform inflation and deflation amount compensation calculation on the weak pressure block and the excessive pressure block of the smart hospital bed respectively, to obtain an adaptive inflation amount of the weak pressure block and an adaptive deflation amount of the excessive pressure block. Step S254 includes the following steps:

8. The smart hospital bed control method based on modeling of a matrix pressure sensor according to claim 7, characterized in that, Perform user real-time posture synchronous response setting on the smart hospital bed user body state real-time simulation model, to generate different sleep posture response conditions of the smart hospital bed user; ​ The pressure distribution matrix model of the smart hospital bed is optimized based on different sleep posture response conditions of the smart hospital bed user, to obtain a pressure distribution matrix sub-model corresponding to the smart hospital bed user in different sleep postures; A force field coupling model is constructed by coupling the pressure distribution matrix sub-model corresponding to the smart hospital bed user in different sleep postures with the real-time body posture simulation model of the smart hospital bed user, to generate a real-time comprehensive stress force field coupling model of the smart hospital bed user. The real-time comprehensive stress force field coupling model of the smart hospital bed user is subjected to dynamic coupling force field simulation analysis, to generate a real-time use simulation coupling dynamic field of the smart hospital bed user. 9.The smart hospital bed control method based on modeling of a matrix pressure sensor of claim 7, wherein, Step S255 includes the following steps: Based on the real-time use simulation coupling dynamic field of the smart hospital bed user, the structure bearing and ultimate load of the inflatable structure soft package at each pressure point in the weak pressure block and the excessive pressure block of the smart hospital bed are analyzed, to obtain the corresponding inflatable structure bearing pressure and inflatable structure ultimate load pressure of each pressure point in the weak pressure block and the excessive pressure block; Based on the corresponding inflatable structure bearing pressure and inflatable structure ultimate load pressure of each pressure point in the weak pressure block and the excessive pressure block, the target pressure of each pressure point in the weak pressure block and the excessive pressure block of the smart hospital bed is calculated by using a target pressure adaptation calculation formula, to obtain the corresponding inflatable structure target adaptation pressure of each pressure point in the weak pressure block and the excessive pressure block; The gas flow characteristic data of the inflatable structure is obtained, and the corresponding inflatable structure soft package is subjected to gas flow ratio response analysis based on the gas flow characteristic data, to obtain the gas flow ratio coefficient of the inflatable structure; Based on the corresponding inflatable structure target adaptation pressure and gas flow ratio coefficient of each pressure point in the weak pressure block, the inflatable amount of each pressure point in the weak pressure block of the smart hospital bed is calculated, to obtain the adaptive inflation amount of the weak pressure block; Based on the corresponding inflatable structure target adaptation pressure and gas flow ratio coefficient of each pressure point in the excessive pressure block, the deflation amount of each pressure point in the excessive pressure block of the smart hospital bed is calculated, to obtain the adaptive deflation amount of the excessive pressure block.

10. The smart hospital bed control method based on modeling of a matrix pressure sensor according to claim 9, wherein, The target pressure adaptation calculation formula is specifically as follows: ； ； In the formula, The first in the weak pressure block pressure point The corresponding inflatable structure target adaptation pressure, For the first block with excessive pressure pressure point The corresponding inflatable structure target adaptation pressure, The first in the weak pressure block The x-coordinate of each pressure point The first in the weak pressure block The ordinate of each pressure point The first in the weak pressure block pressure point The inflatable structure can withstand pressure. The weighting parameter represents the influence of the pressure borne by the inflatable structure in the low-pressure zone on the target pressure. The size of the area where the pressure is relatively weak. This represents the minimum pressure corresponding to the area with relatively weak pressure. The weighting parameter is the one that minimizes the integral effect of pressure. The first in the weak pressure block pressure point The ultimate load pressure of the inflatable structure. The weighting parameter represents the influence of the ultimate load pressure of the inflatable structure on the target pressure in the area with weak pressure. For the first block with excessive pressure The x-coordinate of each pressure point For the first block with excessive pressure The ordinate of each pressure point For the first block with excessive pressure pressure point The inflatable structure can withstand pressure. The weighting parameter represents the influence of the pressure borne by the inflatable structure within the excessively high-pressure area on the target pressure. The size of the area where the pressure is too high. This represents the maximum pressure within the area experiencing excessive pressure. The weighting parameter is the integral effect of maximum pressure. For the first block with excessive pressure pressure point The ultimate load pressure of the inflatable structure. The weighting parameter represents the influence of the ultimate load pressure of the inflatable structure within the excessively high-pressure zone on the target pressure. Correction coefficients for adapting the pressure to the target inflatable structure in areas with weak pressure. Correction coefficients for the pressure of the inflatable structure corresponding to the excessively high pressure area.

Images