Control system of intelligent bed and control method thereof

Abstract

The invention relates to the technical field of sickbed control, in particular to a control system of an intelligent bed and a control method thereof. The method comprises the following steps: acquiring structural data of the intelligent bed; carrying out human body fitting area gravity sensor deployment on the intelligent bed structure data to obtain sickbed sensor deployment data; performing gravity sensor data acquisition on the sickbed sensor deployment data to obtain an initial gravity sensor data set; carrying out data matrix processing on the gravity sensor data set to generate a multi-dimensional pressure sensing matrix; acquiring user pain part data and bed board motor initial position data; and performing pressure distribution mode recognition on the multi-dimensional pressure sensing matrix to obtain a uniform distribution mode and a concentrated distribution mode. According to the invention, through the personalized support regulation, global attitude optimization and real-time feedback mechanism of the intelligent bed, the control accuracy and intelligence of the intelligent bed are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of hospital bed control, and in particular to a control system and a control method of an intelligent bed. Background Art

[0002] Early hospital beds mainly relied on manual adjustment, and physical operations were used to achieve the lifting and tilting of the bed to meet the basic comfort needs of patients. With the development of electric control technology, electric hospital beds have been widely used. Users can adjust the bed electrically through buttons or remote controls, which significantly improves the convenience of bed operation. In recent years, with the maturity of technologies such as sensors, the Internet of Things and artificial intelligence, smart beds have been comprehensively upgraded. Modern smart beds can not only be remotely controlled, but also have functions such as automatic adjustment, health monitoring and data analysis. Smart beds that integrate pressure sensors, body temperature monitoring, heart rate detection and other devices can collect patients' physiological data in real time and transmit them to the monitoring system of medical staff through wireless networks, helping doctors to grasp the changes in patients' conditions in a timely manner. In addition, artificial intelligence technology enables smart beds to have adaptive adjustment functions, which can automatically adjust the bed posture according to the patient's body position and condition to optimize the rehabilitation effect. However, the existing smart beds lack accurate perception of the user's pressure distribution, resulting in poor adjustment effect. At the same time, smart beds usually only focus on local support and ignore the coordination of the overall posture, which leads to low accuracy and intelligence of smart bed control. Summary of the invention

[0003] Based on this, it is necessary to provide a control system and a control method of a smart bed to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above object, a control method of a smart bed is provided, the method comprising the following steps: Step S1: Acquire smart bed structure data; deploy gravity sensors in the human body fitting area on the smart bed structure data to obtain bed sensor deployment data; collect gravity sensor data on the bed sensor deployment data to obtain an initial gravity sensor data set; matrix the gravity sensor data set to generate a multi-dimensional pressure perception matrix; Step S2: obtaining the user's pain site data and the bed board motor initial position data; performing pressure distribution pattern recognition on the multi-dimensional pressure sensing matrix to obtain a uniform distribution pattern and a concentrated distribution pattern; performing local support regulation on the user's pain site data based on the bed board motor initial position data through the uniform distribution pattern and the concentrated distribution pattern to generate the user's local area support regulation data; performing ergonomic fit analysis on the user's local area support regulation data to generate bed structure adjustment human body fit data; Step S3: using the bed structure to adjust the human body fit data to perform a part pain analysis on the user's local area support control data to generate local adjustment area part pain data; based on the local adjustment area part pain data, the user's local area support control data is globally optimized and controlled to generate the user's global area support control data; Step S4: Encode the user's global area support and control data and the user's local area support and control data as data instructions to generate bed motor support and control instructions; perform functional testing on the bed motor support and control instructions to generate bed motor support and control test data; perform system integration of the bed motor support and control instructions based on the bed motor support and control test data to execute intelligent bed control operations.

[0005] The present invention ensures a comprehensive understanding of the overall structure of the bed and the user's weight distribution by acquiring the structure data of the smart bed and deploying gravity sensors. This data collection provides the necessary foundation and lays a solid foundation for subsequent analysis and control. The generated multi-dimensional pressure sensing matrix can monitor the changes in the patient's gravity distribution on the bed in real time, which helps to quickly identify uneven pressure distribution and early detect potential health problems, such as the risk of pressure sores. The data collection of the gravity sensor provides a real-time feedback mechanism for the smart bed, which can continuously update the user's pressure state and realize dynamic regulation. Combining the user's pain site data with the initial position of the bed motor, personalized local support regulation is realized to ensure that the user's specific needs are met and the comfort is improved. By identifying the uniform distribution mode and the concentrated distribution mode, the user's needs can be analyzed more accurately and the adjustment strategy of the bed can be optimized. Through ergonomic fit analysis, the adjusted bed structure can better adapt to the user's body curve, reduce the body pressure caused by an unsuitable bed body, and thus improve the patient's satisfaction and rehabilitation effect. Analyzing the pain in the local area of ​​the user can provide specific pain feedback to help medical staff understand the patient's physical condition. By performing global posture optimization on the pain data of the local adjustment area, the overall support of the user can be coordinated, the use experience of the bed can be improved, and pain and discomfort can be reduced. By accurately adjusting the global support of the bed, it can help patients maintain the best posture during the rehabilitation process. By encoding the global and local support control data of the user, the accuracy and reliability of the bed motor execution instructions are ensured, and the intelligence level of the system is improved. Functional testing before the execution of the control instructions can discover potential problems in advance, ensure the safety and stability of the bed during use, and reduce the occurrence rate of failures. By analyzing the test data of the bed motor support control, system integration is achieved, the coordinated operation of each module is ensured, the comprehensive performance of the smart bed is improved, and strong support is provided for subsequent medical services. Therefore, the present invention improves the accuracy and intelligence of the smart bed control through personalized support control, global posture optimization and real-time feedback mechanism of the smart bed.

[0006] Preferably, step S1 comprises the following steps: Step S11: Acquire smart bed structure data; Step S12: segmenting the smart bed structure data into human body fitting areas to generate smart bed human body fitting area data; deploying regional gravity sensors based on the smart bed human body fitting area data to obtain bed sensor deployment data; Step S13: performing gravity sensor data collection on the bed sensor deployment data based on a preset time interval to obtain an initial gravity sensor data set; performing data preprocessing on the initial gravity sensor data set to generate a standard gravity sensor data set, wherein the data preprocessing includes data cleaning, data denoising, outlier processing, and data standardization; Step S14: grouping the standard gravity sensor data set according to the smart bed human body fitting area data to generate a regionalized pressure data set; matrixing the regionalized pressure data set to generate a multi-dimensional pressure perception matrix.

[0007] The present invention obtains the structure data of the smart bed to provide basic data for subsequent pressure perception, ensuring that the system can effectively identify the needs of different patients. The human body fitting area segmentation in step S12 can accurately identify the contact area of ​​the bed, optimize the layout of the sensor, and ensure the effectiveness and accuracy of data acquisition. By deploying gravity sensors in the fitting area, the patient's posture changes on the bed can be monitored in real time, providing a basis for personalized care and improving the quality of nursing services. Step S13 ensures that the gravity sensor collects data at preset time intervals and generates a standardized data set through data preprocessing, which helps to eliminate data noise and outliers and enhance the reliability of the data. By grouping and matrixing the standard gravity sensor data set, a multidimensional pressure perception matrix is ​​generated, so that the system can perform more sophisticated pressure analysis and patient posture monitoring. By real-time monitoring of the patient's posture and pressure distribution, the system can issue an alarm in time when the patient develops pressure sores or other safety risks, thereby improving the patient's safety and comfort. The generated multidimensional pressure perception matrix provides quantitative data support for medical personnel, helping them to formulate more accurate nursing plans and improve the overall nursing level.

[0008] Preferably, matrixing the regionalized pressure data set comprises the following steps: Performing regional sensor layout analysis on the regionalized pressure data set to generate a regional sensor layout table, wherein the regional sensor layout table includes regional sensor numbers and regional sensor position data; Perform time series collection on the regionalized pressure data set to obtain a regionalized pressure data collection time series; perform missing value detection on the regionalized pressure data collection time series, and when it is detected that the time series of the regionalized pressure data set is missing, the regionalized pressure data collection time series is supplemented to generate a time series pressure data set; Generate regional pressure vectors for regional sensor numbers to generate regional pressure vector sets; use time series pressure data sets to sort the regional pressure vector sets to generate a time-regional pressure matrix; expand the time-regional pressure matrix into a multi-dimensional pressure perception matrix through regional sensor position data to generate a multi-dimensional pressure perception matrix.

[0009] The present invention analyzes the layout of regional sensors, and the generated regional sensor layout table provides the number and location information of the sensor, which helps to reasonably plan the installation location of the sensor, ensures that all key areas are covered, and improves the effectiveness of data acquisition. Time series acquisition ensures the real-time and continuity of regional pressure data, so that the system can monitor the patient's posture changes and the pressure distribution on the mattress, and timely reflect the patient's status. Through the missing value detection and completion mechanism, the integrity and continuity of the time series pressure data set are guaranteed, thereby improving the accuracy of data analysis and avoiding decision-making errors caused by missing data. The generation of regional pressure vectors and the vector sorting process enable data from sensors in different regions to be integrated and compared to form a unified time-region pressure matrix, which is convenient for subsequent data analysis and processing. By expanding the time-region pressure matrix to generate a multidimensional pressure perception matrix, the system can provide richer pressure distribution information and support more complex analysis and model construction, such as pressure distribution change trend analysis and anomaly detection. The system can track the patient's pressure distribution in real time, help nursing staff identify potential health risks, such as pressure sores, so that timely intervention measures can be taken to enhance the initiative and effectiveness of patient care. The multi-dimensional stress perception matrix provides quantitative basic data for medical decision-making, helping medical personnel to develop personalized care plans and thus improve the quality of nursing services.

[0010] Preferably, step S2 comprises the following steps: Step S21: obtaining the user's pain location data and the bed board motor initial position data; performing pressure distribution pattern recognition on the multi-dimensional pressure sensing matrix to obtain the user's pressure distribution pattern data, wherein the user's pressure distribution pattern data includes a uniform distribution pattern and a concentrated distribution pattern; performing a bed board motor dynamic adjustment on the bed board motor initial position data according to the uniform distribution pattern and the concentrated distribution pattern, thereby generating a bed board motor dynamic adjustment strategy; Step S22: performing local support demand analysis on the user's pain site data according to the bed board motor dynamic adjustment strategy to generate user's local area support demand data; performing local support regulation based on the user's local area support demand data to generate user's local area support regulation data; Step S23: Calculate the bed adjustment support height based on the user's local area support control data to obtain bed adjustment support height data; cluster the bed adjustment support height data into discrete points to generate a bed structure adjustment support curve; Step S24: Performing ergonomic fit analysis on the support curve of the bed structure adjustment to generate bed structure adjustment human body fit data.

[0011] By acquiring the user's pain site data, the system can accurately identify the patient's needs, provide data support for subsequent support demand analysis, and improve the personalization and effectiveness of medical services. The pressure distribution pattern recognition in step S21 enables the system to analyze the user's pressure distribution, identify the uniform distribution pattern and the concentrated distribution pattern, help understand the patient's state on the bed, and provide a scientific basis for the dynamic adjustment of the bed board. The bed board motor is dynamically adjusted according to the pressure distribution pattern, and a dynamic adjustment strategy for the bed board motor is generated, which can effectively respond to the different needs of patients, improve the adaptability of the bed board, and reduce discomfort. Step S22 generates local area support demand data for the user by analyzing the local support demand, ensuring that the bed board adjustment can meet the support demand of the patient's specific parts and improve the patient's comfort. Support regulation is performed based on the user's local area support demand data, and regulation data is generated, so that the bed board can intelligently adapt to the changes of the patient and enhance the use experience of the bed. Step S23 calculates the support height of the bed adjustment, and performs discrete point clustering to generate a support curve for the bed structure adjustment to ensure that the bed board height is consistent with the patient's physiological structure, thereby providing the best support. Through ergonomic fit analysis, we generate data on the fit of the bed structure to ensure that the bed design matches the user's body shape, maximizing comfort and reducing body pressure points. Through systematic adjustment and analysis, we improve the overall quality of care, reduce complications caused by bed discomfort, and improve the patient's recovery experience.

[0012] Preferably, step S21 includes the following steps: Step S211: obtaining the user's pain location data and the bed board motor initial position data; Step S212: extracting pressure distribution space features from the multi-dimensional pressure sensing matrix to obtain pressure distribution space feature data; performing spatial heat map conversion on the pressure distribution space feature data to generate a pressure distribution space heat map; performing regional color distribution on the pressure distribution space heat map to generate regional pressure color distribution data; Step S213: performing adjacent color scale coding difference calculation on the regional pressure color distribution data to obtain an adjacent pixel color scale data set; performing averaging on the adjacent pixel color scale data set to generate regional pixel color scale mean data; comparing the regional pixel color scale mean data with a preset standard color scale mean threshold, and when the regional pixel color scale mean data is greater than the preset standard color scale mean threshold, a concentrated distribution mode is generated; Step S214: When the regional pixel color level mean data is less than or equal to the preset standard color level mean threshold, a uniform distribution pattern is generated; the bed board motor position is dynamically adjusted based on the bed board motor initial position data according to the uniform distribution pattern and the concentrated distribution pattern, thereby generating a bed board motor dynamic adjustment strategy.

[0013] The present invention provides important basic data for subsequent analysis by obtaining the user's pain site data and the initial position data of the bed motor, ensuring that it can be adjusted according to the specific needs of the patient. The pressure distribution space feature extraction of the multidimensional pressure perception matrix in step S212 can effectively identify the pressure distribution state of different regions and help understand the pressure distribution of the patient on the bed. Through the pressure distribution space heat map conversion, the pressure distribution feature data is visualized as a heat map, and the intensity and area of ​​the pressure distribution are intuitively displayed, which is convenient for nursing staff to quickly assess the patient's pressure condition. The generated regional pressure color distribution data provides detailed information on the pressure distribution in the region, which helps to identify the pressure concentration area that causes discomfort or risk to the patient. Step S213 further refines the pressure distribution information through adjacent color scale coding difference calculation and averaging processing, forming regional pixel point color scale mean data, providing an accurate basis for pattern recognition. According to the comparison of the regional pixel point color scale mean data with the preset standard color scale mean threshold, the system can intelligently identify the concentrated distribution mode and uniform distribution mode of pressure. This provides a basis for the dynamic adjustment of the bed board, ensuring that the support can be adjusted in time according to the different needs of the patient. Based on different distribution patterns, the initial position of the bed motor is dynamically adjusted to generate a dynamic adjustment strategy for the bed motor, which enables adaptive adjustment of the bed under different pressure conditions and improves the comfort of the bed. By identifying and dynamically adjusting the pressure distribution pattern, more personalized care can be provided to patients, reducing health risks caused by uneven pressure and improving the overall care effect.

[0014] Preferably, dynamically adjusting the position of the bed board motor according to the uniform distribution mode and the concentrated distribution mode includes: Based on the uniform distribution mode, the motor position is leveled for the initial position data of the bed board motor to generate the bed board motor position leveling data; the motor load is monitored according to the bed board motor position leveling data to generate the bed board motor load leveling monitoring data; Load balance the bed board motor load monitoring data to generate load balance data for the motor; use the load balance data for the motor to make the motor output power consistent, thereby generating a uniformly distributed motor control strategy; Based on the centralized distribution mode, the multi-dimensional pressure sensing matrix is ​​divided into pressure areas to generate high-pressure area data and normal-pressure area data; the initial position data of the bed board motor is raised according to the high-pressure area data to generate the motor position adjustment data of the high-pressure area; the initial position data of the bed board motor is lowered according to the normal-pressure area data to generate the motor position adjustment data of the normal-pressure area; The motor power is adaptively adjusted through the motor position adjustment data of the high-pressure area and the motor position adjustment data of the normal pressure area, thereby generating a centralized distribution motor control strategy; the uniform distribution motor control strategy and the centralized distribution motor control strategy are integrated to generate a dynamic adjustment strategy for the bed board motor.

[0015] The present invention can effectively reduce the shaking or instability of the bed board during use and improve the patient's sense of security and comfort by leveling the motor position and generating the leveling data of the bed board motor position. The leveling load of the bed board motor is monitored and the load information is obtained in time, which can effectively identify the load condition of the bed board and ensure that the load distribution of the bed board in different states is balanced, thereby reducing equipment loss and failure risks. The generated uniform distribution motor control strategy can ensure that the output power of the motor remains consistent in the uniform distribution mode, further improve the support effect of the bed board, and enhance the patient's comfort. Based on the centralized distribution mode, the multi-dimensional pressure perception matrix is ​​divided into pressure areas, and the high pressure area and the normal pressure area can be clearly identified, providing basic data for subsequent motor adjustment to ensure the scientificity and pertinence of the adjustment. Through different adjustment strategies for high pressure areas and normal pressure areas, the motor position adjustment data of the high pressure area and the motor position adjustment data of the normal pressure area are generated, and the intelligent adjustment of the motor position is realized, thereby optimizing the bed board support in a targeted manner and reducing the pain of the patient in the high pressure area. Adaptive motor power adjustment based on the motor position adjustment data in high-pressure areas and normal-pressure areas can ensure that the motor can flexibly adjust power output according to the real-time pressure distribution, thereby improving the efficiency and comfort of the bed board. The uniformly distributed motor control strategy and the centralized distributed motor control strategy are integrated to generate a unified bed board motor dynamic adjustment strategy to ensure that the bed board can respond promptly and effectively under different pressure modes. The entire process can provide personalized support for each patient through real-time monitoring and response to the user's actual needs, significantly improving the patient's comfort and satisfaction in bed.

[0016] Preferably, step S24 includes the following steps: Step S241: performing a 3D human body scan according to the human body fitting area data of the smart bed to generate 3D human body scan data; extracting human body features from the 3D human body scan data to generate body feature data, wherein the human body features include part shape, volume and curvature; Step S242: constructing a three-dimensional human body model through the intelligent bed structure data and the body feature data to generate three-dimensional human body model data; performing a human body-bed contact surface analysis on the three-dimensional human body model data to generate fitting model simulation data; Step S243: performing finite element analysis on the fitting model simulation data to generate contact surface finite element analysis result data; performing three-dimensional human body fitting curve fitting on the contact surface finite element analysis result data according to the bed structure adjustment support curve to generate fitting curve data; Step S244: Calculate the curve overlap between the fit curve data and the bed structure adjustment support curve to generate bed structure adjustment human body fit data.

[0017] The data generated by the 3D scanning of the human body in the present invention makes it more accurate to extract the user's body features, including information such as part shape, volume and curvature. This provides real basic data for subsequent model construction and contact surface analysis. The constructed three-dimensional human body model can truly reflect the user's body shape characteristics, which is helpful for accurate analysis of the human body-bed contact surface. This fitting model simulation data provides a scientific basis for optimizing the bed board design. By performing finite element analysis on the contact surface, the support structure of the bed can be identified and optimized to ensure that the user obtains higher comfort and safety during use and reduce the potential risk of pressure sores. The finite element analysis results of the contact surface are fitted with the support curve of the bed structure adjustment, and the generated fit curve data can quantify the support effect of the bed board and guide subsequent structural adjustments. By calculating the overlap between the fit curve and the support curve of the bed structure adjustment, the generated bed structure adjustment human body fit data provides feedback basis for the dynamic adjustment of the bed board, which helps to achieve more personalized bed board adjustment. Accurate fit evaluation provides important reference data for nursing staff, which can help them adjust the bed according to the user's physical characteristics and needs, thereby improving the quality of nursing services.

[0018] Preferably, step S3 comprises the following steps: Step S31: using the bed structure to adjust the human body fit data to collect comfort feedback on the user's local area support control data to obtain local area adjustment feedback data; Step S32: recording the user's body posture for the local area adjustment feedback data to generate local area adjustment posture data; performing a part pain analysis on the local area adjustment feedback data according to the local area adjustment posture data to generate local adjustment area part pain data; Step S33: performing global posture optimization and control on the user's local area support control data based on the local adjustment area pain data, thereby generating the user's global area support control data.

[0019] The present invention can obtain the user's comfort feedback on a specific area by using the human body fit data to collect feedback on the local area support regulation. This provides intuitive data support for subsequent regulation. The user's body posture is recorded so that the impact of the local area adjustment is comprehensively analyzed. The generated local area adjustment posture data can reflect the user's physical response under different support conditions, providing a basis for further optimization. The local area adjustment posture data is analyzed for the position pain, and the discomfort or pain of the user under a specific adjustment can be identified, helping the nursing staff to understand the user's needs and feelings in a timely manner. Based on the pain data of the local adjustment area, the global posture can be optimized and regulated. This regulation not only focuses on a specific part, but also considers the overall comfort, avoiding discomfort in other parts due to local adjustment. Through real-time feedback and pain analysis, the nursing staff can carry out targeted support regulation according to the specific situation of the user, thereby improving the overall quality and effect of nursing. This step supports personalized support regulation based on the feedback of each user, meets the differences in comfort and support requirements of different users, and improves user satisfaction. Through the analysis of the feedback data of the local area adjustment, data-based decision support can be provided for the dynamic adjustment of the smart bed, reducing the error of manual judgment. Timely pain feedback and posture recording can help the medical team identify and improve potential discomfort early and prevent health problems caused by improper support.

[0020] Preferably, step S4 comprises the following steps: Step S41: encapsulating the user's global area support control data and the user's local area support control data to generate a bed motor support control encapsulation data packet; Step S42: performing instruction encoding on the bed motor support control encapsulation data packet to generate a bed motor support control instruction; Step S43: Perform a functional test on the bed motor support control instructions to generate bed motor support control test data; perform system integration on the bed motor support control instructions according to the bed motor support control test data to execute the intelligent bed control operation.

[0021] The present invention helps to centrally manage different types of data and improve the efficiency and consistency of data processing by encapsulating the global and local area support control data of the user. By encoding the instructions for the encapsulated data packet, the generated bed motor support control instructions are more concise and efficient, making the subsequent execution process smoother. Functional testing is performed on the basis of the generated instructions to ensure the correctness and effectiveness of the instructions and avoid equipment failure or user discomfort caused by erroneous instructions. Through feedback on the test data, the instructions can be systematically integrated and optimized to ensure the efficiency and accuracy of the smart bed when executing control operations. Stable execution of motor support control instructions can significantly improve the user's comfort and sense of security on the bed and reduce unexpected situations caused by equipment failure. By analyzing the test data of the bed motor support control, the equipment status and execution effect can be monitored in real time, and the operation strategy can be adjusted in time to meet user needs. The encapsulated data packet and test data provide a rich information basis, which can provide a basis for future improvements and decisions, and support the continuous optimization of the smart bed. The system integration step ensures the compatibility between different hardware and software modules, and improves the stability and reliability of the entire smart bed system.

[0022] In this specification, a control system of a smart bed is provided, which is used to execute the control method of the smart bed, and the control system of the smart bed includes: The gravity sensing module is used to obtain the structure data of the smart bed; deploy gravity sensors in the human body fitting area of ​​the smart bed structure data to obtain the bed sensor deployment data; collect gravity sensor data on the bed sensor deployment data to obtain the initial gravity sensor data set; matrix the gravity sensor data set to generate a multi-dimensional pressure sensing matrix; The pressure recognition module is used to obtain the user's pain site data and the bed motor initial position data; perform pressure distribution pattern recognition on the multi-dimensional pressure perception matrix to obtain a uniform distribution pattern and a concentrated distribution pattern; perform local support regulation on the user's pain site data based on the bed motor initial position data through a uniform distribution pattern and a concentrated distribution pattern to generate user local area support regulation data; perform ergonomic fit analysis on the user's local area support regulation data to generate bed structure adjustment human body fit data; The global adjustment module is used to use the bed structure to adjust the human body fit data to perform a part pain analysis on the user's local area support control data to generate local adjustment area part pain data; based on the local adjustment area part pain data, the user's local area support control data is globally optimized and controlled to generate the user's global area support control data; The control integration module is used to encode data instructions for the user's global area support and control data and the user's local area support and control data to generate bed motor support and control instructions; perform functional testing on the bed motor support and control instructions to generate bed motor support and control test data; and perform system integration of the bed motor support and control instructions based on the bed motor support and control test data to execute intelligent bed control operations.

[0023] The beneficial effect of the present invention is that by collecting the structural information of the smart bed, data support is ensured for subsequent operations. Gravity sensors are reasonably deployed on the smart bed to generate bed sensor deployment data to help monitor the patient's weight distribution. The initial data set is collected through the gravity sensor to obtain the patient's pressure distribution information. The gravity sensor data set is processed and the data is converted into a multidimensional pressure perception matrix for subsequent analysis. The user's pain site information and the initial settings of the bed board are collected as the basis for regulation. The multidimensional pressure perception matrix is ​​analyzed to identify the uniform distribution mode and the concentrated distribution mode to help understand the user's pressure situation. Based on the identified mode and initial position data, the bed board is adjusted to meet the user's local support needs. By analyzing the local support regulation data, the bed structure adjustment human body fit data is generated to ensure the matching degree between the bed and the user's body. The bed structure adjustment human body fit data is used to evaluate the user's pain in different parts to form pain data in the local adjustment area. The user's support regulation is optimized based on the pain data, and the global area support regulation data is generated to improve the overall comfort. The user's global and local support regulation data are encoded to generate specific motor support regulation instructions. Perform functional tests on the generated instructions to ensure their reliability in actual applications and generate test data. Perform system integration of the instructions based on the test data to ensure that the smart bed can correctly perform control operations. Through precise support and regulation, the discomfort caused by the patient's illness is reduced and the overall user experience is improved. In combination with the user's specific needs and pressure data, the support method of the bed board is dynamically adjusted to enhance the adaptability of the bed. The intelligent system can reduce the burden on nursing staff so that they can focus on more important patient care work. The system's data collection and analysis capabilities provide a reliable basis for subsequent bed design and improvement, and promote continuous optimization. Functional testing and system integration ensure the effective execution of instructions, reduce system failure rate, and improve use stability. Therefore, the present invention improves the accuracy and intelligence of smart bed control through personalized support regulation, global posture optimization and real-time feedback mechanism of the smart bed. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A schematic diagram of a process flow of a control method for a smart bed; Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart; Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG. Figure 4 for Figure 1 Detailed implementation steps of step S4 in FIG. The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0025] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0026] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0027] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0028] To achieve this, please refer to Figures 1 to 4 , a control method for a smart bed, the method comprising the following steps: Step S1: Acquire smart bed structure data; deploy gravity sensors in the human body fitting area on the smart bed structure data to obtain bed sensor deployment data; collect gravity sensor data on the bed sensor deployment data to obtain an initial gravity sensor data set; matrix the gravity sensor data set to generate a multi-dimensional pressure perception matrix; Step S2: obtaining the user's pain site data and the bed board motor initial position data; performing pressure distribution pattern recognition on the multi-dimensional pressure sensing matrix to obtain a uniform distribution pattern and a concentrated distribution pattern; performing local support regulation on the user's pain site data based on the bed board motor initial position data through the uniform distribution pattern and the concentrated distribution pattern to generate the user's local area support regulation data; performing ergonomic fit analysis on the user's local area support regulation data to generate bed structure adjustment human body fit data; Step S3: using the bed structure to adjust the human body fit data to perform a part pain analysis on the user's local area support control data to generate local adjustment area part pain data; based on the local adjustment area part pain data, the user's local area support control data is globally optimized and controlled to generate the user's global area support control data; Step S4: Encode the user's global area support and control data and the user's local area support and control data as data instructions to generate bed motor support and control instructions; perform functional testing on the bed motor support and control instructions to generate bed motor support and control test data; perform system integration of the bed motor support and control instructions based on the bed motor support and control test data to execute intelligent bed control operations.

[0029] The present invention ensures a comprehensive understanding of the overall structure of the bed and the user's weight distribution by acquiring the structure data of the smart bed and deploying gravity sensors. This data collection provides the necessary foundation and lays a solid foundation for subsequent analysis and control. The generated multi-dimensional pressure sensing matrix can monitor the changes in the patient's gravity distribution on the bed in real time, which helps to quickly identify uneven pressure distribution and early detect potential health problems, such as the risk of pressure sores. The data collection of the gravity sensor provides a real-time feedback mechanism for the smart bed, which can continuously update the user's pressure state and realize dynamic regulation. Combining the user's pain site data with the initial position of the bed motor, personalized local support regulation is realized to ensure that the user's specific needs are met and the comfort is improved. By identifying the uniform distribution mode and the concentrated distribution mode, the user's needs can be analyzed more accurately and the adjustment strategy of the bed can be optimized. Through ergonomic fit analysis, the adjusted bed structure can better adapt to the user's body curve, reduce the body pressure caused by an unsuitable bed body, and thus improve the patient's satisfaction and rehabilitation effect. Analyzing the pain in the local area of ​​the user can provide specific pain feedback to help medical staff understand the patient's physical condition. By performing global posture optimization on the pain data of the local adjustment area, the overall support of the user can be coordinated, the use experience of the bed can be improved, and pain and discomfort can be reduced. By accurately adjusting the global support of the bed, it can help patients maintain the best posture during the rehabilitation process. By encoding the global and local support control data of the user, the accuracy and reliability of the bed motor execution instructions are ensured, and the intelligence level of the system is improved. Functional testing before the execution of the control instructions can discover potential problems in advance, ensure the safety and stability of the bed during use, and reduce the occurrence rate of failures. By analyzing the test data of the bed motor support control, system integration is achieved, the coordinated operation of each module is ensured, the comprehensive performance of the smart bed is improved, and strong support is provided for subsequent medical services. Therefore, the present invention improves the accuracy and intelligence of the smart bed control through personalized support control, global posture optimization and real-time feedback mechanism of the smart bed.

[0030] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of a control method of a smart bed of the present invention. In this example, the control method of the smart bed includes the following steps: Step S1: Acquire smart bed structure data; deploy gravity sensors in the human body fitting area on the smart bed structure data to obtain bed sensor deployment data; collect gravity sensor data on the bed sensor deployment data to obtain an initial gravity sensor data set; matrix the gravity sensor data set to generate a multi-dimensional pressure perception matrix; In the embodiment of the present invention, detailed structural data of each component of the smart bed is obtained through a sensor network and related measuring equipment. The data content includes: bed size (length, width, height, edge curve, etc.), support structure (bed material, support leg design, bed slope, etc.), motor configuration (motor quantity, specifications, power, etc.), sensor interface (sensor installation position, connection method, etc.), laser rangefinder and three-dimensional scanner and other technologies are used to ensure the acquisition of high-precision bed structure data. The acquired structural data is stored in the database to facilitate subsequent data processing and analysis. According to the bed structure and user requirements, a suitable gravity sensor is selected to ensure that its sensitivity and measurement range are suitable for use in the bed. The sensor needs to have: high precision: can accurately measure small weight changes of less than 1 kg. Fast response: can complete data collection in a short time. Design the specific deployment position of the sensor to ensure that it is evenly distributed throughout the bed surface to obtain pressure changes in different areas. Common deployment positions include: head of bed, foot of bed, middle of bed and bedside. According to the user's lying posture, focus on the support areas of shoulders, back, waist, buttocks and legs. According to the design plan, fix the gravity sensor in the specified position and use a fixing clamp or adhesive to ensure its stability. After the sensor is deployed, calibrate it to ensure the measurement accuracy of the sensor. The calibration process requires a reference standard weight. Build a data acquisition system, including the connection between the data collector and the gravity sensor, to ensure that the data can be transmitted to the computer or storage device in real time. Use wireless transmission or wired transmission to select the most suitable connection solution according to the needs. Start the data acquisition system to collect data from the deployed gravity sensor. Within a specific time after the user lies down, the system continuously records the gravity data of the sensor. The recorded gravity data should include information such as timestamp, sensor number, and sensor output value. Store the collected initial gravity sensor data set in a local or cloud database for subsequent analysis. Convert the initial gravity sensor data set to a unified data structure. The data is usually organized into a time series format for subsequent processing. Matrix the collected gravity data to integrate the data from different sensors into a multidimensional matrix, usually with rows representing timestamps and columns representing the readings of each sensor. The dimensions of the multi-dimensional pressure sensing matrix can be adjusted according to the number of sensors and sampling time to ensure that all relevant data are covered. The data in the matrix is ​​normalized so that the readings of different sensors can be standardized, which is helpful for subsequent analysis and comparison.

[0031] Step S2: obtaining the user's pain site data and the bed board motor initial position data; performing pressure distribution pattern recognition on the multi-dimensional pressure sensing matrix to obtain a uniform distribution pattern and a concentrated distribution pattern; performing local support regulation on the user's pain site data based on the bed board motor initial position data through the uniform distribution pattern and the concentrated distribution pattern to generate the user's local area support regulation data; performing ergonomic fit analysis on the user's local area support regulation data to generate bed structure adjustment human body fit data; In an embodiment of the present invention, the user's pain location information is collected by questionnaire or interview, including: pain location (such as back, waist, legs, etc.), pain intensity (using a 1-10 scoring system), pain type (such as tingling, dull pain, soreness, etc.), recording the user's pain location data, and sorting and storing the data. Through the control system of the smart bed, the initial position data of the current bed board motor is obtained, including: the inclination angle of the bed board, the height setting of the bed board, and the motor state (such as running or standby). The acquired initial position data is stored in the database as the basis for subsequent regulation. The multidimensional pressure perception matrix is ​​cleaned to remove noise and outliers to ensure the accuracy of the data. The pressure data is processed by interpolation or other data smoothing techniques to improve the accuracy of pattern recognition. The pressure distribution pattern is identified by machine learning or pattern recognition algorithms (such as K-means clustering, support vector machine, etc.), and the process includes: extracting effective features from the multidimensional pressure perception matrix, such as pressure peak, distribution range, etc. The recognition model is trained using historical pressure data so that it can be classified into uniform distribution mode and concentrated distribution mode. Perform pattern recognition on the current pressure data to determine whether it belongs to the uniform distribution mode or the concentrated distribution mode, and output the corresponding results. The uniform distribution mode and concentrated distribution mode obtained by identification are stored in the database for reference in subsequent support control. Based on the initial position data of the bed board motor, a support control algorithm is designed, which specifically includes: for the uniform distribution mode, keep the motor position of the bed board unchanged or make fine adjustments to maintain the existing support distribution. For the concentrated distribution mode, according to the user's pain site data, adjust the position of the bed board motor to enhance the support felt by the user. The specific control method includes: raising the height of the bed board area where the pain site is located, adjusting the inclination angle of the pain site to reduce pressure, and generating the user's local area support control data, and the record includes: the adjusted motor position data and the adjusted angle and height. Using the user's local area support control data, an ergonomic fitting model is established. The model should consider: the load-bearing characteristics of different parts of the human body and the pressure tolerance of the pain site. The adjusted bed board motor position is simulated by simulation software to generate a pressure distribution map of the contact surface between the user and the bed. Analyze the pressure distribution of the contact surface, calculate the fit data, and evaluate its comfort and support effect, mainly including: the uniformity of pressure distribution and the pressure changes in the affected area. Record the results of ergonomic fit analysis, generate the human body fit data for bed structure adjustment, and archive it.

[0032] Step S3: using the bed structure to adjust the human body fit data to perform a part pain analysis on the user's local area support control data to generate local adjustment area part pain data; based on the local adjustment area part pain data, the user's local area support control data is globally optimized and controlled to generate the user's global area support control data; In an embodiment of the present invention, the following data are collected and integrated: Bed structure adjustment human body fit data: reflects the support of the bed board to the user's body. User local area support control data: records the adjustment of the user's local support, including motor position, angle, height, etc. Through user feedback, the user's pain in different local areas is recorded and analyzed, and the data content includes: pain intensity (such as using a 1-10 scoring system), pain type (such as tingling, dull pain, soreness, etc.), pain duration (changes within a specific time after adjustment), and local adjustment area pain data is generated, including pain intensity and location. Statistical methods (such as variance analysis, correlation analysis, etc.) are used to analyze the relationship between the pain data and the fit data, identify the support area closely related to the pain, and generate a report to indicate which adjustments cause or relieve the user's pain. Based on the local adjustment area pain data, identify the area with stronger pain. Mark the local area that needs to be optimized for global posture control. Use optimization algorithms (such as genetic algorithms, particle swarm optimization, etc.) to perform global posture optimization on the user's local area support control data: set the optimization goal to minimize the user's pain and improve comfort. Ensure the structural safety and stability of the bed board and do not exceed the physical limitations of the equipment. Iterate the optimization of the global support control data, the process includes: adjusting the overall height and angle of the bed board to achieve the best support distribution. Consider the influence of adjacent areas to ensure that local optimization does not cause increased pain in other parts. Based on the output of the optimization algorithm, generate the user's global area support control data, including: optimized motor position and tilt angle, adjusted support strategy (such as regional increase or decrease in support, etc.).

[0033] Step S4: Encode the user's global area support and control data and the user's local area support and control data as data instructions to generate bed motor support and control instructions; perform functional testing on the bed motor support and control instructions to generate bed motor support and control test data; perform system integration of the bed motor support and control instructions based on the bed motor support and control test data to execute intelligent bed control operations.

[0034] In an embodiment of the present invention, support control data of the global area and the local area of ​​the user are collected. According to a predetermined coding rule, the collected data is converted into an instruction format. This format includes specific parameters, such as motor speed, position, load, etc., to generate a bed motor support control instruction, and perform format verification to ensure that the instruction is correct. The bed motor support control instruction is input into the test environment. Run the instruction, observe the response and behavior of the bed motor, and record relevant data. Compare the actual results with the expected results, analyze whether there is a deviation, generate bed motor support control test data, record the execution and effect of the instruction, and evaluate whether its function is normal. Analyze the test data and identify any parameters or functions that need to be adjusted. According to the analysis results, optimize and modify the motor support control instruction. Perform system integration testing of the instruction in an integrated environment to ensure compatibility with other systems of the smart bed. Ensure that the instruction can effectively interact with the user interface and provide real-time feedback. Complete system integration to form an efficient and reliable smart bed control instruction system. Input the final bed motor support control instruction into the smart bed control system. Start the smart bed control operation, monitor the execution process, and ensure that all instructions are completed smoothly. Collect data generated during the execution process, conduct real-time monitoring and analysis to ensure that all functions of the bed are normal. Achieve effective control of the smart bed and generate relevant operation data for subsequent evaluation and improvement.

[0035] Preferably, step S1 comprises the following steps: Step S11: Acquire smart bed structure data; Step S12: segmenting the smart bed structure data into human body fitting areas to generate smart bed human body fitting area data; deploying regional gravity sensors based on the smart bed human body fitting area data to obtain bed sensor deployment data; Step S13: performing gravity sensor data collection on the bed sensor deployment data based on a preset time interval to obtain an initial gravity sensor data set; performing data preprocessing on the initial gravity sensor data set to generate a standard gravity sensor data set, wherein the data preprocessing includes data cleaning, data denoising, outlier processing, and data standardization; Step S14: grouping the standard gravity sensor data set according to the smart bed human body fitting area data to generate a regionalized pressure data set; matrixing the regionalized pressure data set to generate a multi-dimensional pressure perception matrix.

[0036] In an embodiment of the present invention, the structural data of the smart bed, including the size, shape, material and functional components of the bed, is obtained by using a 3D scanner or CAD (computer-aided design) software. The structural data is converted into a software format suitable for analysis, such as STL or OBJ format, to ensure compatibility in subsequent processing. Image processing technology (such as threshold segmentation and contour detection) is used to process the bed structure data to identify the human body fitting area (such as the mattress area). The coordinates and dimensions of each fitting area are recorded to generate the human body fitting area data of the smart bed. According to the characteristics of the human body fitting area, a suitable gravity sensor (such as a piezoelectric sensor or a strain gauge) is selected. According to the human body fitting area data, the optimal deployment position of the gravity sensor is determined in the bed design to ensure that the pressure changes can be accurately monitored in different body positions, and the bed sensor deployment data is generated, including the specific position of each sensor and its corresponding area. Gravity sensor data is collected for the bed sensor deployment data at a preset time interval (such as once per second), and the original gravity data output by the sensor is recorded. Duplicate, missing or invalid data points are removed. A filter (such as a Kalman filter or a mean filter) is used to reduce the noise in the sensor data. Identify and handle outliers (e.g., by standard deviation or IQR). Standardize the processed data for subsequent analysis. Aggregate the cleaned and processed data into a data set in a standard format for easy storage and analysis. Group the standard gravity sensor data set according to the smart bed body fit area data, and divide the data according to different areas (such as head, torso, legs, etc.). Create a pressure data set for each area to record the gravity change information in the area. Convert the regionalized pressure data set into a matrix form to form a multi-dimensional pressure perception matrix for subsequent data analysis and visualization. Ensure that each dimension of the matrix corresponds to a different area and time point, thereby providing a full range of pressure distribution information.

[0037] Preferably, matrixing the regionalized pressure data set comprises the following steps: Performing regional sensor layout analysis on the regionalized pressure data set to generate a regional sensor layout table, wherein the regional sensor layout table includes regional sensor numbers and regional sensor position data; Perform time series collection on the regionalized pressure data set to obtain a regionalized pressure data collection time series; perform missing value detection on the regionalized pressure data collection time series, and when it is detected that the time series of the regionalized pressure data set is missing, the regionalized pressure data collection time series is supplemented to generate a time series pressure data set; Generate regional pressure vectors for regional sensor numbers to generate regional pressure vector sets; use time series pressure data sets to sort the regional pressure vector sets to generate a time-regional pressure matrix; expand the time-regional pressure matrix into a multi-dimensional pressure perception matrix through regional sensor position data to generate a multi-dimensional pressure perception matrix.

[0038] In an embodiment of the present invention, the specific position of each sensor on the smart bed is identified by collecting the sensor position information in all regionalized pressure data sets. According to the spatial distribution characteristics of the sensors, the layout of the sensors is analyzed to ensure that they cover all key pressure monitoring areas. A regional sensor layout table is created, which includes the following information: Regional sensor number: a unique identifier for each sensor. Regional sensor location data: the specific location coordinates of each sensor on the bed (such as x, y coordinates). The layout table can be in a spreadsheet or database format to facilitate subsequent data processing and analysis. Based on the regionalized pressure data set collected previously, the pressure data of each regional sensor at different time points is recorded to form a time series. Ensure that the frequency of the time series is consistent (such as once per second) to facilitate subsequent analysis. Perform missing value detection on the regionalized pressure data collection time series to identify whether there is missing pressure data in a specific time period. Use methods (such as linear interpolation and mean filling) to process missing values ​​to ensure the integrity of the time series. By completing the missing values, a complete time series pressure data set is generated to ensure that each time point has a corresponding pressure value record. According to the number in the regional sensor layout table, a regional pressure vector is generated for each regional sensor. Each regional pressure vector contains the pressure values ​​of all sensors in the region at a specific time point, forming a vector set. The pressure vectors of all regional sensors are aggregated to form a regional pressure vector set. Each vector corresponds to a specific time point. Using the time series pressure data set, the regional pressure vector set is sorted to ensure that all vectors are arranged in time order. The generated time-regional pressure matrix will include the time dimension and the pressure data of the regional sensors. The sorted regional pressure vector set is organized into a matrix format, where the rows represent the time points and the columns represent the pressure values ​​of sensors in different regions. The time-regional pressure matrix is ​​expanded using the regional sensor location data to consider the impact of sensor location on pressure distribution. Through the location data, additional dimensions (such as coordinate location, sensor type) can be added to each sensor location for subsequent analysis. The expanded matrix is ​​organized into a multidimensional pressure perception matrix to provide a comprehensive understanding of different regions, different times and their spatial distribution. This matrix will provide support for subsequent data analysis, visualization and health monitoring decisions.

[0039] As an example of the present invention, refer to Figure 2As shown, in this example, step S2 includes: Step S21: obtaining the user's pain location data and the bed board motor initial position data; performing pressure distribution pattern recognition on the multi-dimensional pressure sensing matrix to obtain the user's pressure distribution pattern data, wherein the user's pressure distribution pattern data includes a uniform distribution pattern and a concentrated distribution pattern; performing a bed board motor dynamic adjustment on the bed board motor initial position data according to the uniform distribution pattern and the concentrated distribution pattern, thereby generating a bed board motor dynamic adjustment strategy; Step S22: performing local support demand analysis on the user's pain site data according to the bed board motor dynamic adjustment strategy to generate user's local area support demand data; performing local support regulation based on the user's local area support demand data to generate user's local area support regulation data; Step S23: Calculate the bed adjustment support height based on the user's local area support control data to obtain bed adjustment support height data; cluster the bed adjustment support height data into discrete points to generate a bed structure adjustment support curve; Step S24: Performing ergonomic fit analysis on the support curve of the bed structure adjustment to generate bed structure adjustment human body fit data.

[0040] In an embodiment of the present invention, the user's pain site data is obtained through user feedback, medical records or smart mattress sensor collection, and the specific pain point location and its related characteristics (such as pain level, duration) are recorded. The data format should be clear to ensure that each pain point can be accurately identified and located. Collect the initial position data of the bed board motor and record the positions of various components of the bed board at the beginning (such as the height of the head, foot, and side of the bed). Ensure that the position data corresponds to the pain site data for subsequent adjustments. Apply machine learning or deep learning algorithms (such as clustering algorithms or pattern recognition algorithms) to analyze the multidimensional pressure perception matrix and identify different pressure distribution patterns. The identified patterns include uniform distribution patterns (relatively uniform pressure distribution, suitable for users without obvious pain points) and concentrated distribution patterns (pressure concentration in specific areas, corresponding to the user's pain site). Generate user pressure distribution pattern data based on the recognition results, mark it as a uniform distribution pattern or a concentrated distribution pattern, and associate it with the user's pain site data. Based on the user pressure distribution pattern data, analyze the initial position data of the bed board motor and formulate a dynamic adjustment strategy for the bed board motor. For example, if a concentrated distribution pattern is identified, it is possible to consider lifting or lowering a specific area of ​​the bed board to reduce the pressure on the painful area. According to the dynamic adjustment strategy of the bed board motor and the user's painful area data, the user's local support needs are analyzed and the areas that need to be strengthened are identified. The specific demand data of each area that needs support is recorded, including information such as support strength, support area and adjustment direction. The analysis results are integrated to generate the user's local area support demand data for subsequent support regulation. Based on the user's local area support demand data, the corresponding local support regulation operation is performed to adjust the hardness, support height and other parameters of the mattress or bed board, generate the user's local area support regulation data, and record the specific parameter changes after regulation. According to the user's local area support regulation data, the adjusted support height data of the bed is calculated to ensure the comfort and effectiveness of the support. A mathematical model or optimization algorithm is used to consider the characteristics of the user's painful area and adjust the support height of each area. Discrete point clustering is performed on the bed adjustment support height data, and a clustering algorithm (such as K-means) is used to analyze the change trend of the support height to generate a bed structure adjustment support curve. The clustering results are recorded for subsequent analysis. Based on the support curve of the bed structure adjustment, the ergonomic fit analysis of the user's mattress support effect is performed. The adaptability of the mattress support to the user's body is evaluated, and the fit data is calculated, taking into account the user's physiological characteristics and pain sites. The analysis results are sorted out to generate the human body fit data of the bed structure adjustment, providing a quantitative evaluation of the mattress comfort. This data can be used to further optimize the mattress design and support strategy to improve the user experience.

[0041] Preferably, step S21 includes the following steps: Step S211: obtaining the user's pain location data and the bed board motor initial position data; Step S212: extracting pressure distribution space features from the multi-dimensional pressure sensing matrix to obtain pressure distribution space feature data; performing spatial heat map conversion on the pressure distribution space feature data to generate a pressure distribution space heat map; performing regional color distribution on the pressure distribution space heat map to generate regional pressure color distribution data; Step S213: performing adjacent color scale coding difference calculation on the regional pressure color distribution data to obtain an adjacent pixel color scale data set; performing averaging on the adjacent pixel color scale data set to generate regional pixel color scale mean data; comparing the regional pixel color scale mean data with a preset standard color scale mean threshold, and when the regional pixel color scale mean data is greater than the preset standard color scale mean threshold, a concentrated distribution mode is generated; Step S214: When the regional pixel color level mean data is less than or equal to the preset standard color level mean threshold, a uniform distribution pattern is generated; the bed board motor position is dynamically adjusted based on the bed board motor initial position data according to the uniform distribution pattern and the concentrated distribution pattern, thereby generating a bed board motor dynamic adjustment strategy.

[0042] In an embodiment of the present invention, specific information of the user's body pain part, such as the location, degree and characteristics of the pain, is collected by means of sensors or user input. Such data can be obtained through the built-in pressure sensor of the smart bed, and combined with user feedback, the pain part data is further verified and corrected. The initial position of the bed board motor at the beginning is recorded, including the position parameters such as the height and angle of each adjustment area, to ensure that these data are consistent with the subsequent adjustment process. Using a multi-dimensional pressure sensing matrix, the pressure distribution characteristics of the area where the user contacts the mattress are extracted to generate spatial characteristic data of the pressure distribution. The spatial characteristic data reflects the pressure difference in different parts of the user's body, such as the support strength of the back, shoulders and waist. The extracted pressure distribution spatial characteristic data is converted into a pressure distribution spatial heat map. The spatial heat map is to convert the pressure value into a color display, in which the depth of the color corresponds to different pressure intensities, usually red represents a high pressure area, and blue represents a low pressure area. According to the generated spatial heat map, the color distribution of each area is analyzed, and the regional pressure color distribution data is extracted and generated. This process uses color coding to intuitively display the pressure size of each area through color, which is convenient for subsequent analysis and processing. The color scale difference of adjacent pixels in the regional pressure color distribution data is calculated to extract the color scale data set of adjacent pixels. The color scale encoding reflects the difference between the pressure values. By calculating the color scale difference of adjacent pixels, the degree of pressure change in space can be identified. The extracted adjacent pixel color scale data set is averaged, the average color scale of the regional pixel is calculated, and the regional pixel color scale mean data is generated. This mean data can reflect the overall change trend of the pressure in the entire region. The generated regional pixel color scale mean data is compared with the preset standard color scale mean threshold. When the regional pixel color scale mean data is greater than the preset standard color scale mean threshold, it means that the pressure concentration in the region is high, and a concentrated distribution pattern is generated. If the regional pixel color scale mean data is less than or equal to the preset standard color scale mean threshold, it is judged that the pressure is distributed relatively evenly in space, and a uniform distribution pattern is generated. According to the identified pressure distribution pattern (concentrated distribution pattern or uniform distribution pattern), the initial position data of the bed board motor is dynamically adjusted. Specifically, for the concentrated distribution mode, support can be added or the height can be adjusted in the area where the user's pressure is concentrated, while in the uniform distribution mode, the existing support state is maintained or slightly adjusted. Finally, a dynamic adjustment strategy for the bed board motor is generated and applied to the bed board motor control system to adjust the position of the bed board motor in real time to adapt to the user's needs and provide a more comfortable experience.

[0043] Preferably, dynamically adjusting the position of the bed board motor according to the uniform distribution mode and the concentrated distribution mode includes: Based on the uniform distribution mode, the motor position is leveled for the initial position data of the bed board motor to generate the bed board motor position leveling data; the motor load is monitored according to the bed board motor position leveling data to generate the bed board motor load leveling monitoring data; Load balance the bed board motor load monitoring data to generate load balance data for the motor; use the load balance data for the motor to make the motor output power consistent, thereby generating a uniformly distributed motor control strategy; Based on the centralized distribution mode, the multi-dimensional pressure sensing matrix is ​​divided into pressure areas to generate high-pressure area data and normal-pressure area data; the initial position data of the bed board motor is raised according to the high-pressure area data to generate the motor position adjustment data of the high-pressure area; the initial position data of the bed board motor is lowered according to the normal-pressure area data to generate the motor position adjustment data of the normal-pressure area; The motor power is adaptively adjusted through the motor position adjustment data of the high-pressure area and the motor position adjustment data of the normal pressure area, thereby generating a centralized distribution motor control strategy; the uniform distribution motor control strategy and the centralized distribution motor control strategy are integrated to generate a dynamic adjustment strategy for the bed board motor.

[0044] In the embodiment of the present invention, when the uniform distribution mode is identified, the various positions of the motor are adjusted based on the initial position data of the bed board motor to make it reach a horizontal state. At this time, the bed board motor position leveling data is generated to ensure that the pressure on all areas of the bed board is relatively uniform, and the user's body does not have a local support point that is too high or too low. According to the bed board motor position leveling data, the load of the motor is monitored, the load of the motor in the leveling state is collected, and the bed board motor leveling load monitoring data is generated. The purpose of load monitoring is to ensure that in the leveling state, there will not be too large differences in the loads between the various motors, thereby ensuring the smooth operation of the system. According to the bed board motor leveling load monitoring data, the loads of various motors are balanced and the leveling motor load balancing data is generated. Through load balancing, it is ensured that the output power of the motors is the same in the leveling state, avoiding overloading or underloading of a motor. Finally, the leveling motor load balancing data is used to make the output power of the motors consistent, thereby generating a uniformly distributed motor control strategy to ensure that the bed board remains stable in the uniform distribution mode. When a concentrated distribution pattern is identified, the multi-dimensional pressure sensing matrix is ​​first divided into pressure areas to distinguish high-pressure areas and normal-pressure areas of the user's body, and high-pressure area data and normal-pressure area data are generated. High-pressure areas are usually concentrated in certain parts of the user's body, such as the waist or back, while normal-pressure areas are distributed in other areas. According to the high-pressure area data, the initial position data of the bed board motor is raised to generate high-pressure area motor position adjustment data. The purpose of the position raising is to reduce the pressure of the user's body on the part by increasing the support force of the high-pressure area, making it more comfortable. At the same time, according to the normal-pressure area data, the initial position data of the bed board motor is lowered to generate normal-pressure area motor position adjustment data. The position lowering is to reduce the support force of the normal-pressure area so that the bed board can better fit the user's body and avoid excessive support. According to the high-pressure area motor position adjustment data and the normal-pressure area motor position adjustment data, the power of the motors in each area is adaptively adjusted to ensure that each motor can provide appropriate support force under different pressure areas, thereby generating a concentrated distribution motor control strategy. The uniform distribution motor control strategy is integrated with the centralized distribution motor control strategy, combined with the user's current pressure distribution pattern, to ensure that the bed motor can respond dynamically in various situations and adapt to the user's needs. Finally, through strategy integration, a dynamic adjustment strategy for the bed motor is generated. This adjustment strategy can adjust the position and power of the bed motor in real time, so that the smart bed can provide personalized support and comfort in different usage scenarios (such as when the user is resting or adjusting posture).

[0045] Preferably, step S24 includes the following steps: Step S241: performing a 3D human body scan according to the human body fitting area data of the smart bed to generate 3D human body scan data; extracting human body features from the 3D human body scan data to generate body feature data, wherein the human body features include part shape, volume and curvature; Step S242: constructing a three-dimensional human body model through the intelligent bed structure data and the body feature data to generate three-dimensional human body model data; performing a human body-bed contact surface analysis on the three-dimensional human body model data to generate fitting model simulation data; Step S243: performing finite element analysis on the fitting model simulation data to generate contact surface finite element analysis result data; performing three-dimensional human body fitting curve fitting on the contact surface finite element analysis result data according to the bed structure adjustment support curve to generate fitting curve data; Step S244: Calculate the curve overlap between the fit curve data and the bed structure adjustment support curve to generate bed structure adjustment human body fit data.

[0046] In an embodiment of the present invention, accurate three-dimensional morphological data of the user's whole body is obtained by a high-precision 3D scanning device (such as a laser scanner or an optical scanner), especially a high-resolution scan of the pain area, to ensure that the details of the area are intact. Multi-angle scanning technology is used in combination with a variety of optical sensors to capture the whole body data of the user in different postures, ensuring that the smart bed can provide effective support even in different body positions of the user. The acquired 3D scanning data is subjected to multi-level data processing, including mesh reconstruction, point cloud noise reduction, redundant data removal and other steps to ensure that the geometric data of the human body model has high precision and low error. A high-order curvature analysis algorithm is used to extract the geometric features of key parts from the 3D scanning data, such as the local shape, volume, curvature, etc. of the pain area, so as to accurately simulate the morphology of the user's body. A specific anatomical feature extraction model (such as a deep learning model based on a convolutional neural network) is used to automatically identify the detailed features of the pain area, thereby providing basic data for the personalized adjustment of the smart bed. A high-precision meshing algorithm is used to construct a three-dimensional human body model of the user based on the body feature data and the smart bed structure data. The model not only includes the external geometric morphology of the human body, but also considers the distribution of internal soft tissues for more accurate pressure distribution simulation. By comparing the user's body feature data with the standard anatomical model, the key points and surfaces in the model are adjusted to accurately reflect the user's physical condition and generate personalized three-dimensional human body model data. In the process of model construction, it is necessary to combine the hardware structure of the smart bed, take into account the distribution of sensors in different parts of the bed and the stress characteristics of the bed board structure, so as to ensure that the model can adapt to the actual bed structure. Based on the contact area between the three-dimensional human body model and the surface of the bed, the nonlinear contact mechanics analysis method is used to simulate the pressure distribution of the contact surface between the user and the bed in different positions, and generate fitting model simulation data. Using the contact surface pressure data and the multi-dimensional pressure sensing matrix, dynamic simulation is performed to analyze the changes in the support effect of the bed on the body under dynamic conditions such as user movement and turning over. The contact force simulation algorithm is used to calculate the stress and strain distribution of each contact point, and identify whether there is an excessive or insufficient support area in the pain area, so as to provide data basis for further adjustment. Based on the fitting model simulation data, a high-precision finite element model is constructed, the three-dimensional human body model and the smart bed model are meshed, and the mesh division of the contact surface area is refined to improve the accuracy of stress analysis. The stress-strain equations are applied to simulate the pressure response of different parts of the human body, especially the local stress concentration in the affected area. Through this simulation, it can be determined which parts are under excessive pressure and whether they will cause new discomfort or injury. Multi-scale finite element analysis technology is used to consider the different elastic and mechanical properties of the human skin, muscle and bone layers to generate stress distribution data for each layer of the structure, ensuring that the adjustment not only meets the pressure requirements of surface contact, but also takes into account the support of deep tissues. Combined with the support curve of the bed structure adjustment, the stress data generated by the finite element analysis is curve fitted, and the human body fit curve data is generated through nonlinear regression analysis.This curve reflects the contact and support degree between the bed and the user's body. Use an adaptive fitting algorithm (such as RBF kernel function) to dynamically adjust the fitting curve to ensure that the error between the pressure data and the support curve is minimized, so as to obtain the most optimized fit data. Based on the bed structure, the support curve and the fit curve are adjusted, and a multi-dimensional curve coincidence calculation algorithm (such as coincidence analysis based on Mahalanobis distance) is used to evaluate the support effect of the bed in different areas and generate curve coincidence data. The coincidence of different areas is evaluated in sections, and the support curve is locally fitted with the actual human body fit curve to identify whether the bed provides sufficient support in key areas (such as pain areas or joints). When the curve coincidence is lower than the preset threshold, feedback data is generated for readjusting the bed support, especially for more precise regulation of the pain area. The curve coincidence data is integrated to generate the bed structure adjustment human body fit data. This data includes the coincidence score, support priority and adjustment suggestions of each area to help the bed to be further refined. Based on the fit data, the support strategies of various parts of the smart bed can be adjusted in real time, so that the bed can still maintain efficient fit in dynamic situations (such as when the user turns over, sits up, etc.), ensuring comfort and safety.

[0047] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes: Step S31: using the bed structure to adjust the human body fit data to collect comfort feedback on the user's local area support control data to obtain local area adjustment feedback data; Step S32: recording the user's body posture for the local area adjustment feedback data to generate local area adjustment posture data; performing a part pain analysis on the local area adjustment feedback data according to the local area adjustment posture data to generate local adjustment area part pain data; Step S33: performing global posture optimization and control on the user's local area support control data based on the local adjustment area pain data, thereby generating the user's global area support control data.

[0048] In the embodiment of the present invention, the human body fit data is adjusted by the bed structure, and the smart bed first performs support regulation for the local area of ​​the user. The support regulation includes fine-tuning of each module of the bed (such as the bed board and the motor), especially fine-tuning for the area of ​​the pain site. The support regulation is based on the real-time feedback mechanism, and the appropriate support force is gradually applied by adjusting the hardness, angle and height of the bed board. The support effect of different areas is monitored in real time by the pressure sensor, and it is ensured that the adjustment will not cause secondary pressure damage. In the process of local support regulation, the user's real-time feedback data is collected by embedded sensors. These sensors can monitor the user's micro-movements, pressure changes and the reaction of the skin contact surface to generate comfort feedback data. At the same time, the system will also ask the user's subjective comfort feeling, and use voice interaction or touch screen interface to let the user actively feedback whether the regulated area is comfortable or whether there is a pain area. Through multi-dimensional data fusion technology, the user's subjective feelings are fused with sensor data to generate local area adjustment feedback data. The collected local area adjustment feedback data is analyzed to record the user's body posture after adjustment, including details such as local limb position, spinal curvature, and pressure distribution. Using posture sensors and 3D scanning equipment, the user's posture changes are dynamically captured to generate local area posture adjustment data. Body posture recording not only focuses on the user's static posture, but also captures the user's dynamic behaviors such as turning over and moving in bed, ensuring that the bed support can provide appropriate adjustments under different user postures. According to the local area posture adjustment data, the user's local area is deeply analyzed for pain. Using the pressure distribution matrix and the user's subjective feedback, the pain concentration area is identified and analyzed in detail. Through the machine learning algorithm, the user's pain data is matched with his body posture to determine the parts that are prone to pain in a specific posture. This analysis can distinguish different types of pain causes such as insufficient bone support, muscle pressure concentration, and soft tissue compression, and generate local adjustment area pain data. In the process of pain analysis, combined with biomechanical modeling technology, the stress concentration of the pain area is calculated, thereby providing a basis for further support regulation. Based on the local adjustment area pain data, the system automatically optimizes the user's global posture. Through the intelligent algorithm, the support structure of the entire bed is adjusted, so that not only the local area is properly supported, but also the posture of the whole body is reasonably optimized. The system will make global posture balance adjustments based on the pain data, such as adjusting the overall tilt angle of the bed, the hardness distribution of the mattress, and the position of the support points to ensure that each part is evenly and appropriately supported and to avoid excessive pressure concentration in a single part. Using a multi-region feedback fusion algorithm, the system can process pain data from multiple parts at the same time, comprehensively balance the support requirements of different regions, and achieve overall optimization and control. Through global posture optimization and control, the user's global regional support control data is generated.These data include detailed information such as support strength, angle adjustment, pressure distribution, etc. in each area, providing data support for subsequent dynamic support. Global support data can be called by the control system of the smart bed in real time to ensure that the bed can quickly adjust the support of the corresponding area every time the user changes posture, thereby improving the overall comfort of the user. In addition, the data can also be used for long-term monitoring and optimization. As time goes by, the bed system will continue to self-learn and adjust, gradually improving the accuracy of support adjustment.

[0049] As an example of the present invention, refer to Figure 4 As shown, in this example, step S4 includes: Step S41: encapsulating the user's global area support control data and the user's local area support control data to generate a bed motor support control encapsulation data packet; Step S42: performing instruction encoding on the bed motor support control encapsulation data packet to generate a bed motor support control instruction; Step S43: Perform a functional test on the bed motor support control instructions to generate bed motor support control test data; perform system integration on the bed motor support control instructions according to the bed motor support control test data to execute the intelligent bed control operation.

[0050] In an embodiment of the present invention, the previously generated global area support control data of the user is fused with the local area support control data of the user. The fusion process combines the support requirements of all regions of the body with the adjustment parameters of the local special regions, ensuring that the support control of the bed can take care of the overall situation and make optimization adjustments for the local areas that are painful or require special support. On the basis of data fusion, the global and local support control data are encapsulated and processed using a standardized data encapsulation protocol to generate a bed motor support control encapsulation data packet. The contents of the encapsulation data packet include: motor action instructions (such as rising, falling, translation, etc.), support strength and angle adjustment parameters of each region, pressure distribution and dynamic feedback data of posture adjustment. The format of the encapsulation data packet follows the motor control communication protocol to ensure that it can be efficiently decoded and executed by the hardware and software modules of the bed control system. The generated bed motor support control encapsulation data packet is encoded. The encoding process uses a specific bed motor control instruction set to ensure that each support control data can correspond to a specific motor action. The contents of instruction coding include: control codes of each motor, such as motor number, direction of movement, target position, etc.; adjustment instructions for support strength, using precise control parameters to set the power output of the motor; trigger conditions of system feedback (for example, triggering motor action when pressure sensor data reaches a certain threshold). Instruction coding adopts an optimized binary coding format so that instructions can be efficiently transmitted to the motor control module to ensure fast and error-free execution. After completing instruction coding, the system generates bed motor support control instructions. These instructions are the core of the specific execution of intelligent bed control operations and are sent directly to the bed motor module through the instruction transmission channel. After the instructions are generated, the system will perform functional tests to verify the validity and accuracy of the bed motor support control instructions. The test process includes: simulation execution: the system simulates the execution of bed motor support control instructions in a virtual environment to verify whether the instructions can adjust the motor position, support strength, etc. as expected. Physical test: execute the generated instructions on the actual bed, monitor the actual operation of the motor, detect whether the instructions accurately control the motor action, and ensure that the user will not be affected by incorrect operation. Real-time feedback: Through pressure sensors and position sensors, real-time data of motor operation during the test is collected to generate bed motor support control test data for subsequent instruction optimization. According to the bed motor support control test data, the motor support control instructions are system integrated to ensure seamless connection between the overall control system of the bed and the motor control module. The steps of system integration include: integrating the tested and verified motor control instructions with the intelligent control system of the bed (including central control unit, sensor network, user interface, etc.). Through the distributed control network, ensure that all motor modules can receive and execute the instructions issued by the system in real time. Continuously monitor the feedback during the execution of instructions to ensure the accuracy of instruction execution and handle any abnormal situations in real time.After the integration is completed, the system will officially perform the intelligent bed control operation, and adjust the various motors of the bed according to the user's real-time needs and posture changes, providing accurate and comfortable support adjustments. The intelligent bed can dynamically adjust the support strength, angle and pressure distribution of various parts of the user's body through a series of automated instructions, ensuring that the bed user can get the best support effect regardless of the posture.

[0051] In this specification, a control system of a smart bed is provided, which is used to execute the control method of the smart bed, and the control system of the smart bed includes: The gravity sensing module is used to obtain the structure data of the smart bed; deploy gravity sensors in the human body fitting area of ​​the smart bed structure data to obtain the bed sensor deployment data; collect gravity sensor data on the bed sensor deployment data to obtain the initial gravity sensor data set; matrix the gravity sensor data set to generate a multi-dimensional pressure sensing matrix; The pressure recognition module is used to obtain the user's pain site data and the bed motor initial position data; perform pressure distribution pattern recognition on the multi-dimensional pressure perception matrix to obtain a uniform distribution pattern and a concentrated distribution pattern; perform local support regulation on the user's pain site data based on the bed motor initial position data through a uniform distribution pattern and a concentrated distribution pattern to generate user local area support regulation data; perform ergonomic fit analysis on the user's local area support regulation data to generate bed structure adjustment human body fit data; The global adjustment module is used to use the bed structure to adjust the human body fit data to perform a part pain analysis on the user's local area support control data to generate local adjustment area part pain data; based on the local adjustment area part pain data, the user's local area support control data is globally optimized and controlled to generate the user's global area support control data; The control integration module is used to encode data instructions for the user's global area support and control data and the user's local area support and control data to generate bed motor support and control instructions; perform functional testing on the bed motor support and control instructions to generate bed motor support and control test data; and perform system integration of the bed motor support and control instructions based on the bed motor support and control test data to execute intelligent bed control operations.

[0052] The beneficial effect of the present invention is that by collecting the structural information of the smart bed, data support is ensured for subsequent operations. Gravity sensors are reasonably deployed on the smart bed to generate bed sensor deployment data to help monitor the patient's weight distribution. The initial data set is collected through the gravity sensor to obtain the patient's pressure distribution information. The gravity sensor data set is processed and the data is converted into a multidimensional pressure perception matrix for subsequent analysis. The user's pain site information and the initial settings of the bed board are collected as the basis for regulation. The multidimensional pressure perception matrix is ​​analyzed to identify the uniform distribution mode and the concentrated distribution mode to help understand the user's pressure situation. Based on the identified mode and initial position data, the bed board is adjusted to meet the user's local support needs. By analyzing the local support regulation data, the bed structure adjustment human body fit data is generated to ensure the matching degree between the bed and the user's body. The bed structure adjustment human body fit data is used to evaluate the user's pain in different parts to form pain data in the local adjustment area. The user's support regulation is optimized based on the pain data, and the global area support regulation data is generated to improve the overall comfort. The user's global and local support regulation data are encoded to generate specific motor support regulation instructions. Perform functional tests on the generated instructions to ensure their reliability in actual applications and generate test data. Perform system integration of the instructions based on the test data to ensure that the smart bed can correctly perform control operations. Through precise support and regulation, the discomfort caused by the patient's illness is reduced and the overall user experience is improved. In combination with the user's specific needs and pressure data, the support method of the bed board is dynamically adjusted to enhance the adaptability of the bed. The intelligent system can reduce the burden on nursing staff so that they can focus on more important patient care work. The system's data collection and analysis capabilities provide a reliable basis for subsequent bed design and improvement, and promote continuous optimization. Functional testing and system integration ensure the effective execution of instructions, reduce system failure rate, and improve use stability. Therefore, the present invention improves the accuracy and intelligence of smart bed control through personalized support regulation, global posture optimization and real-time feedback mechanism of the smart bed.

[0053] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0054] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A control method for a smart bed, characterized in that: The following steps are involved: Step S1: Acquire smart bed structure data; deploy gravity sensors in the human body fitting area on the smart bed structure data to obtain bed sensor deployment data; The gravity sensor data is collected for the bed sensor deployment data to obtain an initial gravity sensor data set; the gravity sensor data set is matrixed to generate a multi-dimensional pressure perception matrix; Step S2: obtaining the user's pain location data and the bed motor initial position data; The pressure distribution pattern of the multi-dimensional pressure sensing matrix is ​​recognized to obtain a uniform distribution pattern and a concentrated distribution pattern; based on the initial position data of the bed motor, the local support control of the user's pain site data is performed through the uniform distribution pattern and the concentrated distribution pattern to generate the user's local area support control data; Conduct ergonomic fit analysis on the user's local area support control data to generate human body fit data for bed structure adjustment; Step S3: using the bed structure to adjust the human body fit data to perform a pain analysis on the user's local area support control data to generate local adjustment area pain data; Based on the pain data of the local adjustment area, the user's local area support control data is globally optimized and controlled, thereby generating the user's global area support control data; Step S4: Encoding the user's global area support control data and the user's local area support control data to generate a bed motor support control instruction; Perform functional tests on the bed motor support control instructions and generate bed motor support control test data; The bed motor support control instructions are systematically integrated according to the bed motor support control test data to execute the intelligent bed control operation.

2. The control method of the smart bed according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire smart bed structure data; Step S12: segmenting the smart bed structure data into human body fitting areas to generate smart bed human body fitting area data; deploying regional gravity sensors based on the smart bed human body fitting area data to obtain bed sensor deployment data; Step S13: performing gravity sensor data collection on the bed sensor deployment data based on a preset time interval to obtain an initial gravity sensor data set; performing data preprocessing on the initial gravity sensor data set to generate a standard gravity sensor data set, wherein the data preprocessing includes data cleaning, data denoising, outlier processing, and data standardization; Step S14: grouping the standard gravity sensor data set according to the smart bed human body fitting area data to generate a regionalized pressure data set; matrixing the regionalized pressure data set to generate a multi-dimensional pressure perception matrix.

3. The control method of the smart bed according to claim 2, characterized in that: Matrixing a regionalized pressure dataset involves the following steps: Performing regional sensor layout analysis on the regionalized pressure data set to generate a regional sensor layout table, wherein the regional sensor layout table includes regional sensor numbers and regional sensor position data; Perform time series collection on the regionalized pressure data set to obtain a regionalized pressure data collection time series; perform missing value detection on the regionalized pressure data collection time series, and when it is detected that the time series of the regionalized pressure data set is missing, the regionalized pressure data collection time series is supplemented to generate a time series pressure data set; Generate regional pressure vectors for regional sensor numbers to generate regional pressure vector sets; use time series pressure data sets to sort the regional pressure vector sets to generate a time-regional pressure matrix; expand the time-regional pressure matrix into a multi-dimensional pressure perception matrix through regional sensor position data to generate a multi-dimensional pressure perception matrix.

4. The control method of the smart bed according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: obtaining the user's pain location data and the bed board motor initial position data; performing pressure distribution pattern recognition on the multi-dimensional pressure sensing matrix to obtain the user's pressure distribution pattern data, wherein the user's pressure distribution pattern data includes a uniform distribution pattern and a concentrated distribution pattern; performing a bed board motor dynamic adjustment on the bed board motor initial position data according to the uniform distribution pattern and the concentrated distribution pattern, thereby generating a bed board motor dynamic adjustment strategy; Step S22: performing local support demand analysis on the user's pain site data according to the bed board motor dynamic adjustment strategy to generate user's local area support demand data; performing local support regulation based on the user's local area support demand data to generate user's local area support regulation data; Step S23: Calculate the bed adjustment support height based on the user's local area support control data to obtain bed adjustment support height data; cluster the bed adjustment support height data into discrete points to generate a bed structure adjustment support curve; Step S24: Performing ergonomic fit analysis on the support curve of the bed structure adjustment to generate bed structure adjustment human body fit data.

5. The control method of the smart bed according to claim 4, characterized in that: Step S21 includes the following steps: Step S211: obtaining the user's pain location data and the bed board motor initial position data; Step S212: extracting pressure distribution space features from the multi-dimensional pressure sensing matrix to obtain pressure distribution space feature data; performing spatial heat map conversion on the pressure distribution space feature data to generate a pressure distribution space heat map; performing regional color distribution on the pressure distribution space heat map to generate regional pressure color distribution data; Step S213: performing adjacent color scale coding difference calculation on the regional pressure color distribution data to obtain an adjacent pixel color scale data set; performing averaging on the adjacent pixel color scale data set to generate regional pixel color scale mean data; comparing the regional pixel color scale mean data with a preset standard color scale mean threshold, and when the regional pixel color scale mean data is greater than the preset standard color scale mean threshold, a concentrated distribution mode is generated; Step S214: When the regional pixel color level mean data is less than or equal to the preset standard color level mean threshold, a uniform distribution pattern is generated; the bed board motor position is dynamically adjusted based on the bed board motor initial position data according to the uniform distribution pattern and the concentrated distribution pattern, thereby generating a bed board motor dynamic adjustment strategy.

6. The control method of the smart bed according to claim 5, characterized in that: Dynamic adjustment of the bed motor position according to the uniform distribution mode and the concentrated distribution mode includes: Based on the uniform distribution mode, the motor position is leveled for the initial position data of the bed board motor to generate the bed board motor position leveling data; the motor load is monitored according to the bed board motor position leveling data to generate the bed board motor load leveling monitoring data; Load balance the bed board motor load monitoring data to generate load balance data for the motor; use the load balance data for the motor to make the motor output power consistent, thereby generating a uniformly distributed motor control strategy; Based on the centralized distribution mode, the multi-dimensional pressure sensing matrix is ​​divided into pressure areas to generate high-pressure area data and normal-pressure area data; the initial position data of the bed board motor is raised according to the high-pressure area data to generate the motor position adjustment data of the high-pressure area; the initial position data of the bed board motor is lowered according to the normal-pressure area data to generate the motor position adjustment data of the normal-pressure area; The motor power is adaptively adjusted through the motor position adjustment data of the high-pressure area and the motor position adjustment data of the normal pressure area, thereby generating a centralized distribution motor control strategy; the uniform distribution motor control strategy and the centralized distribution motor control strategy are integrated to generate a dynamic adjustment strategy for the bed board motor.

7. The control method of the smart bed according to claim 4, characterized in that: Step S24 includes the following steps: Step S241: performing a 3D human body scan according to the human body fitting area data of the smart bed to generate 3D human body scan data; extracting human body features from the 3D human body scan data to generate body feature data, wherein the human body features include part shape, volume and curvature; Step S242: constructing a three-dimensional human body model through the intelligent bed structure data and the body feature data to generate three-dimensional human body model data; performing a human body-bed contact surface analysis on the three-dimensional human body model data to generate fitting model simulation data; Step S243: performing finite element analysis on the fitting model simulation data to generate contact surface finite element analysis result data; performing three-dimensional human body fitting curve fitting on the contact surface finite element analysis result data according to the bed structure adjustment support curve to generate fitting curve data; Step S244: Calculate the curve overlap between the fit curve data and the bed structure adjustment support curve to generate bed structure adjustment human body fit data.

8. The control method of the smart bed according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: using the bed structure to adjust the human body fit data to collect comfort feedback on the user's local area support control data to obtain local area adjustment feedback data; Step S32: recording the user's body posture for the local area adjustment feedback data to generate local area adjustment posture data; performing a part pain analysis on the local area adjustment feedback data according to the local area adjustment posture data to generate local adjustment area part pain data; Step S33: performing global posture optimization and control on the user's local area support control data based on the local adjustment area pain data, thereby generating the user's global area support control data.

9. The control method of the smart bed according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: encapsulating the user's global area support control data and the user's local area support control data to generate a bed motor support control encapsulation data packet; Step S42: performing instruction encoding on the bed motor support control encapsulation data packet to generate a bed motor support control instruction; Step S43: Perform a functional test on the bed motor support control instructions to generate bed motor support control test data; perform system integration on the bed motor support control instructions according to the bed motor support control test data to execute the intelligent bed control operation.

10. A control system for an intelligent bed, characterized in that: For executing the control method of the smart bed as claimed in claim 1, the control system of the smart bed comprises: The gravity sensing module is used to obtain the structure data of the smart bed; deploy gravity sensors in the human body fitting area of ​​the smart bed structure data to obtain the bed sensor deployment data; collect gravity sensor data on the bed sensor deployment data to obtain the initial gravity sensor data set; matrix the gravity sensor data set to generate a multi-dimensional pressure sensing matrix; The pressure recognition module is used to obtain the user's pain site data and the bed motor initial position data; perform pressure distribution pattern recognition on the multi-dimensional pressure perception matrix to obtain a uniform distribution pattern and a concentrated distribution pattern; perform local support regulation on the user's pain site data based on the bed motor initial position data through a uniform distribution pattern and a concentrated distribution pattern to generate user local area support regulation data; perform ergonomic fit analysis on the user's local area support regulation data to generate bed structure adjustment human body fit data; The global adjustment module is used to use the bed structure to adjust the human body fit data to perform a part pain analysis on the user's local area support control data to generate local adjustment area part pain data; based on the local adjustment area part pain data, the user's local area support control data is globally optimized and controlled to generate the user's global area support control data; The control integration module is used to encode data instructions for the user's global area support and control data and the user's local area support and control data to generate bed motor support and control instructions; perform functional testing on the bed motor support and control instructions to generate bed motor support and control test data; and perform system integration of the bed motor support and control instructions based on the bed motor support and control test data to execute intelligent bed control operations.

Images