Intelligent bed control method and system based on Internet of Things and control terminal

Abstract

The invention relates to the technical field of intelligent bed control, in particular to an intelligent bed control method and system based on the Internet of Things and a control terminal. The method comprises the following steps: performing posture change analysis on a user sleep posture data set to obtain user sleep posture change data; performing posture pressure mapping on the user sleep posture change data to obtain posture change pressure mapping data; posture stability identification is carried out on the user sleep posture change data, posture multi-point pressure calculation is carried out, and posture stability multi-point pressure data is obtained; performing attitude fatigue degree identification according to the attitude stable multi-point pressure data to obtain attitude fatigue degree data; attitude supporting structure adjustment is conducted on the attitude fatigue degree data, automatic firmware design is conducted, and attitude supporting logic firmware is obtained. The intelligent bed control technology is improved, so that the intelligent bed control technology is more perfect.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent bed control, and particularly to an intelligent bed control method, system and control terminal based on the Internet of Things. Background Art

[0002] With the rapid development of Internet of Things technology, the smart home field has witnessed a revolutionary change. The Internet of Things (IoT) enables various devices to be interconnected through a network, realizing data collection, transmission and processing. Against this backdrop, the intelligent bed, as an important part of family life, has gradually attracted people's attention. The intelligent bed can not only improve the user's sleep quality, but also provide personalized health management and monitoring services. Technically, the core of the intelligent bed lies in the integration of sensors and control systems. Modern intelligent beds are usually equipped with a variety of sensors, such as pressure sensors, temperature and humidity sensors, heart rate monitors, etc. These sensors can real-time monitor the user's sleep state, including data such as sleep depth, turning frequency, heart rate changes, etc. At the same time, with the help of Internet of Things technology, this data can be transmitted to a smart phone or other terminal devices via Wi-Fi or Bluetooth, and users can view their sleep conditions at any time. In addition, an analysis platform based on cloud computing can conduct in-depth analysis on the collected data and provide personalized health suggestions and improvement measures. However, there are problems with a traditional Internet-of-Things-based intelligent bed control method, such as the inability to accurately analyze the fatigue degree of postures and the weak ability to adjust postures. Summary of the Invention

[0003] Based on this, it is necessary to provide an intelligent bed control method, system and control terminal based on the Internet of Things to solve at least one of the above technical problems.

[0004] To achieve the above object, an intelligent bed control method based on the Internet of Things, the method includes the following steps:

[0005] Step S1: Collect data on the user's sleep posture through the electronic monitoring device built in the intelligent bed to obtain a user sleep posture data set; perform posture change analysis on the user sleep posture data set to obtain user sleep posture change data; perform posture pressure mapping on the user sleep posture change data to obtain posture change pressure mapping data;

[0006] Step S2: Identify the posture stability of the user sleep posture change data to obtain user sleep posture stability data; calculate the multi-point pressure of the posture for the user sleep posture stability data to obtain posture stability multi-point pressure data; identify the posture fatigue degree based on the posture stability multi-point pressure data to obtain posture fatigue degree data;

[0007] Step S3: Obtain the intelligent bed material data; adjust the posture support structure according to the intelligent bed material data for the posture fatigue degree data to obtain the bed body posture support structure data;

[0008] Step S4: Based on the bed body posture support structure data, perform automated firmware design to obtain the posture support logic firmware, and send the posture support logic firmware to the Internet of Things control platform to execute the intelligent bed control method.

[0009] Through the intelligent bed with built-in electronic monitoring devices, the present invention comprehensively collects the posture information of users during sleep. The primary task of this process is to establish a detailed dataset of users' sleep postures, which includes various sleep postures and their changes of users over a period of time. Through in-depth analysis of these data, the characteristics of posture changes at different stages of users can be identified, which is crucial for understanding sleep quality and health status. Next, using the posture change pressure mapping technology, the sleep posture can be combined with the weight distribution and the pressure impact on the mattress to generate posture change pressure mapping data. This mapping can help analyze which posture causes physical fatigue or discomfort, thus providing a scientific basis for improving the sleep quality of users. Focusing on the identification of the stability of users' sleep postures, this step aims to judge the stability of users' postures throughout the sleep process. Through the monitoring of sleeping postures, the technology can identify which posture lasts longer and the conversion frequency between different postures observed during the entire sleep cycle. Relying on these data, multi-point pressure calculation of postures is carried out to evaluate the pressure exerted on each body part by different postures. Finally, based on these posture stability multi-point pressure data, the system can identify the fatigue level of users. This not only helps users understand their own sleep quality but also provides practical guidance for improving design and personal health management. This process provides users with actionable insights, enabling them to take measures to optimize their sleep environment and improve overall health. First, obtain the material data of the intelligent bed, which is the key basis for realizing the adjustment of the posture support structure. These data not only include the material type, hardness, breathability, durability, etc. of the bed body but also involve the sleep postures and their fatigue levels of users on different material mattresses. By deeply analyzing the posture fatigue level data, the support effects of specific materials on different body parts of users can be understood. According to these analysis results, the posture support structure of the bed body is optimized and adjusted accordingly, and finally, the bed body posture support structure data is formed. This adjustment can significantly improve sleep quality, reduce physical discomfort and fatigue caused by improper support, enhance the comfort of users during sleep, and thus promote a healthy sleep pattern. Based on the obtained bed body posture support structure data, the intelligent bed will enter the automated firmware design stage. By integrating various sensor data and user feedback, the corresponding posture support logic firmware is designed, which will provide the support strategies required by the intelligent bed in different postures. After the design is completed, this firmware will be sent to the Internet of Things control platform, which represents a major step forward for the intelligent bed towards automation and intelligence. The Internet of Things control platform can receive the feedback from the intelligent bed in real time and make adjustments according to the dynamic needs of users to ensure that the bed body always provides the optimal support during users' sleep. This intelligent control method not only improves the efficiency and accuracy of the use of the bed body but also greatly enhances the user experience, ensuring that users always maintain a comfortable and healthy state during nighttime sleep, and thus improving the overall quality of life.Therefore, the present invention is an improved treatment of a traditional Internet of Things-based intelligent bed control method, which solves the problems that the traditional Internet of Things-based intelligent bed control method cannot accurately analyze the fatigue degree of postures and has a weak ability to adjust postures, improves the accuracy of analyzing the fatigue degree of postures, and enhances the ability to adjust postures.

[0010] Preferably, step S1 includes the following steps:

[0011] Step S11: Collect data on the user's sleep posture through the electronic monitoring device built in the intelligent bed to obtain a user sleep posture data set;

[0012] Step S12: Collect user sleep posture pressure data based on the pressure sensor built in the intelligent bed to obtain user sleep posture pressure data;

[0013] Step S13: Analyze the posture changes in the user sleep posture data set to obtain user sleep posture change data;

[0014] Step S14: Perform posture pressure mapping on the user sleep posture change data according to the user sleep posture pressure data to obtain posture change pressure mapping data.

[0015] The intelligent bed of the present invention uses its built-in electronic monitoring device to comprehensively and meticulously collect data on the user's sleep posture. This process is the basis for obtaining the user's sleep state, helping to establish a user sleep posture dataset, which contains various sleep postures, duration, and rotation frequency, etc. Through this continuous monitoring, the system can record the natural posture changes of the user during the night, thereby helping to analyze the user's sleep patterns and habits. These data can not only reflect the user's basic sleep quality but also provide an important basis for subsequent analysis, allowing doctors or sleep experts to give more targeted health advice and promoting the user's health management and personalized care. The pressure data of the user's sleep posture is collected through the pressure sensors built in the intelligent bed. This step can more precisely understand the impact of different sleep postures on the body. The pressure sensors will record the pressure borne by each part of the body in different postures, thereby generating the pressure data of the user's sleep posture. These data are very important because they will help identify which postures cause physical discomfort, pain, or muscle fatigue. This pressure data combined with the posture data can provide a more comprehensive perspective for subsequent posture change analysis, helping to develop a more personalized sleep improvement plan to enhance the user's overall sleep experience and health. Conducting posture change analysis on the user's sleep posture dataset is a crucial step. By using advanced data analysis techniques, it is possible to meticulously examine the posture changes of the user during the entire night's sleep, including the frequency of posture transitions and the duration of each posture, etc. This analysis can reveal the discomforts or problems that occur to the user during sleep, such as whether they stay in an unfavorable sleep posture for a long time, thus causing a sense of compression or other problems in the body. By understanding these changes, it is possible to help identify potential sleep disorders and then provide improvement suggestions for the user. For example, adjusting the hardness of the mattress or introducing auxiliary devices to encourage the user to adopt a healthier sleep posture, thereby effectively improving sleep quality. Based on the pressure data of the user's sleep posture collected in the previous steps, performing posture-pressure mapping on the user's sleep posture change data is an important integration step. This technology correlates the user's posture changes with the pressure borne in each posture for analysis, thereby generating posture change pressure mapping data. This mapping can clearly identify which sleep postures cause excessive pressure concentration on specific body parts, thereby leading to a decline in sleep quality or causing health problems. Through the visualization of this data, users and health managers can more intuitively understand their sleep conditions and formulate corresponding intervention strategies, not only improving the sleep experience but also helping to maintain long-term physical health.

[0016] Preferably, step S2 includes the following steps:

[0017] Step S21: Calculate the posture change frequency of the user's sleep posture change data to obtain the posture change frequency data;

[0018] Step S22: Identify the stability of the user's sleep posture based on the posture change frequency data to obtain the user's sleep posture stability data;

[0019] Step S23: Calculate the multi-point pressure of the posture based on the posture change pressure mapping data for the user's sleep posture stability data to obtain the multi-point pressure data of the stable posture;

[0020] Step S24: Identify the high / low pressure points of the posture for the multi-point pressure data of the stable posture to obtain the high / low pressure point data of the posture;

[0021] Step S25: Identify the fatigue degree of the posture based on the high / low pressure point data of the posture for the user's sleep posture stability data to obtain the posture fatigue degree data.

[0022] The present invention is an important process for calculating the posture change frequency of the user's sleep posture change data. This step analyzes the frequency history of the user's posture change during the time period through all the posture data collected in the time period. These calculation results can reveal the frequent posture changes of the user during sleep, and help to understand whether the user habitually adjusts his sleeping posture or frequently turns over at night. Understanding the frequency of posture changes can help doctors and health experts identify potential sleep disorders and user discomfort, thereby providing data support for later personalized sleep improvement plans. Based on the analysis of frequency data, users can be guided to change to better sleeping habits and promote their overall health. It is a crucial step to implement posture stability identification based on posture change frequency data. This step determines the posture stability of the user by analyzing the time the user maintains a certain posture during sleep and the frequency of changing postures. The sleep posture stability data obtained by calculation can indicate whether the user has frequent posture changes and short-term stable sleep states during sleep. Stability data has a significant impact on the evaluation of sleep quality, because the lack of good posture stability leads to increased pressure on body parts, which in turn affects the realization of deep sleep. Based on this data, users can better understand their own sleep patterns, and it also provides a scientific basis for formulating optimization measures. The posture multi-point pressure calculation of the user's sleep posture stability data based on the posture change pressure mapping data is an in-depth analysis of the results of the previous steps. By combining pressure mapping with stability, the pressure distribution of different parts of the user's body in different sleeping positions can be accurately measured. This multi-point pressure data helps to understand the pressure characteristics caused to the body during the user's fixed posture, and can effectively identify which postures are beneficial and which cause burden or discomfort. This step not only enables the user's sleep dynamics to be analyzed from a more comprehensive perspective, but also helps to provide users with more scientific sleep adjustment suggestions so that they can get high-quality rest. The process of identifying high / low pressure points for posture stability multi-point pressure data is crucial. By analyzing the pressure data under various postures, the corresponding high-pressure and low-pressure points can be identified. This operation will tell the user which parts are under greater pressure during sleep, causing discomfort or pain, and which parts are relatively comfortable. Identifying high-pressure points can help users understand the source of compression problems and provide data support for improving the sleeping environment. At the same time, the identification of low-pressure points is equally important, providing users with reasonable suggestions to avoid health risks caused by long-term high-pressure points. The process of identifying the posture fatigue level of the user's sleeping posture stability data based on the posture high / low pressure point data is the last step in integrating all the previous analysis results. By combining the identified high-pressure and low-pressure points, the system can evaluate the user's posture fatigue level, which can effectively reveal the impact of the pressure the user endures at night on the body.

[0023] Preferably, step S23 includes the following steps:

[0024] Step S231: Analyze the pressure changes of different joint parts of the user's sleep posture stability data according to the posture change pressure mapping data to obtain the posture joint pressure data;

[0025] Step S232: Calculate the center of gravity offset angle of the posture joint pressure data of different joint parts to obtain the joint center of gravity offset angle data;

[0026] Step S233: Conduct pressure position specificity analysis of different joint parts based on the posture joint pressure data and the joint center of gravity offset angle data to obtain the joint pressure position specificity data;

[0027] Step S234: Calculate the movable radius of different joint parts for the joint pressure position specificity data to obtain the position-related joint movable radius data;

[0028] Step S235: Calculate the posture multi-point pressure of the user's sleep posture stability data based on the joint pressure position specificity data and the position-related joint movable radius data to obtain the posture stability multi-point pressure data.

[0029] It is very important for the present invention to analyze the pressure changes of different joint parts on the user's sleep posture stability data based on the posture change pressure mapping data. This step allows the system to quantify the pressure changes borne by different joint parts in various sleep postures, and can help identify which joints cause discomfort due to continuous pressure. Through the detailed analysis of these pressure data, the system can understand the pressure distribution and changes at specific joints in different sleep postures, thereby providing a scientific basis for further posture adjustment. This process is crucial for optimizing the user's sleep posture, reducing physical discomfort and fatigue during sleep, and helping the user better maintain their physical health. Calculating the center of gravity offset angle of the posture joint pressure data of different joint parts is an important analysis of the user's sleep posture stability and comfort. This calculation process involves the spatial analysis of the pressure effect on the joint center, and identifies the center of gravity offset of each joint in different sleep postures. By calculating the center of gravity offset angle data, the body balance state of the user during the sleep posture change and its impact on the overall comfort can be evaluated. If the center of gravity offset is too large, it means that the posture is not stable enough, and the user's turning over times at night increase, thus affecting the sleep quality. The analysis of these angle data will provide more powerful support for formulating appropriate posture adjustment plans and bedding designs. Based on the posture joint pressure data and the joint center of gravity offset angle data, performing a pressure position specificity analysis of different joint parts can help to deeply understand how the pressure is distributed and concentrated at specific positions of each joint. This analysis reveals the specific characteristics of the pressure on the joints in different postures, and identifies which postures cause excessive pressure on certain specific parts. This analysis can provide important insights for doctors, physical therapists and the users themselves, helping to formulate more targeted improvement plans, reducing pain or discomfort caused by improper postures, and thus optimizing the user's overall sleep experience and health. Based on the joint pressure position specificity data and the position-related joint movable radius data, performing a posture multi-point pressure calculation on the user's sleep posture stability data will help to comprehensively evaluate the overall comfort and stability of the user at night. The posture multi-point pressure data can reflect the comprehensive force-bearing situation of the user at different joint parts, and analyze its support and pressure distribution effects on various parts of the body. This process can not only identify the areas that cause bias pressure or fatigue in a specific posture, but relying on these data, personalized sleep environments or adjustment suggestions can be customized for the user. The ultimate goal of these efforts is to help users optimize their sleep quality through scientific posture assessment, effectively improve their health level and quality of life, and bring a better sleep experience to the users.

[0030] Preferably, step S25 includes the following steps:

[0031] Step S251: Calculate the pressure difference between adjacent joint parts for the high / low pressure point data of the posture, and obtain the pressure difference data between adjacent joint parts;

[0032] Step S252: Analyze the muscle tightness of different joint parts for the user's sleep posture stability data based on the pressure difference data of adjacent joint parts to obtain joint posture muscle tightness data;

[0033] Step S253: Calculate the fatigue index of different joint parts for the joint posture muscle tightness data based on the pressure difference data of adjacent joint parts to obtain the joint posture fatigue index;

[0034] Step S254: Quantify the differences of different joint parts for the joint posture muscle tightness data according to the joint posture fatigue index to obtain joint muscle fatigue difference quantification data;

[0035] Step S255: Identify the posture fatigue degree for the user's sleep posture stability data based on the joint muscle fatigue difference quantification data to obtain the posture fatigue degree data.

[0036] By calculating the pressure difference between adjacent joint parts based on the attitude high-pressure and low-pressure point data, the present invention can intuitively reflect the pressure distribution differences between joints in a specific sleeping posture. This process helps to identify potential problems caused by unbalanced pressure, such as excessive pressure on a certain joint, resulting in fatigue or tightness of the surrounding muscles. Through this pressure difference analysis, the imbalance of joint load during sleep and its impact on muscle state can be accurately captured, providing important basic data for subsequent muscle tightness and fatigue analysis, thus laying an important foundation for improving the user's sleeping posture and sleep quality. Using the pressure difference data between adjacent joint parts for the analysis of the sleep posture stability of the user helps to determine the muscle tightness degree of different joint parts. By combining the pressure difference with the muscle tight state, it can be identified which joints have a sense of tightness due to uneven pressure. This analysis process can not only reveal the muscle response of the user in a specific sleeping posture, but also provide a scientific basis for muscle relaxation strategies and posture adjustment. This will help the user reduce the discomfort caused by muscle tightness, thereby optimizing their sleeping posture and improving the overall sleep experience. According to the pressure difference data between adjacent joint parts, the fatigue index of different joint parts is calculated for the joint attitude muscle tightness data, aiming to quantify the fatigue degree of the joint in a specific sleeping posture. This process can timely detect whether a specific joint is under excessive pressure and thus causes fatigue by comprehensively analyzing the pressure data and the muscle tight level. The calculation of this fatigue index not only allows the user to understand their own physical state in a specific sleeping posture, but also provides effective data for formulating a reasonable recovery plan or treatment plan according to these indicators, providing guarantee for the physical and mental health of the user. By applying the joint attitude fatigue index, the differences between different joint parts of the joint attitude muscle tightness data are quantified, so as to deeply analyze the fatigue conditions and muscle tightness performances of each joint. The result of quantifying the fatigue differences of the joints can clearly point out which joints have significant fatigue due to overuse or improper posture. The quantified result provides a clear direction for subsequent intervention measures, ensuring that the user can timely adjust their sleeping posture or carry out corresponding rehabilitation training, helping to reduce the risk of injury, reduce discomfort during sleep, and improve the overall comfort and sleep quality. Based on the quantified data of joint muscle fatigue differences, the posture fatigue degree of the user's sleep posture stability is identified. The key to this step is to integrate the data obtained in the previous steps to identify the fatigue degree of the user in the current sleeping posture and provide targeted feedback to the user. For example, by identifying the fatigue degree, the user can understand which joints are under higher pressure and fatigue in a specific posture, so as to adjust the sleeping position in a timely manner. In this process, it not only helps to enhance the user's attention to their own sleep quality, but also enables them to have a deeper understanding of sleeping posture adjustment, thus actively improving their own sleep management to ensure more efficient repair and relaxation at night.

[0037] Preferably, step S3 includes the following steps:

[0038] Step S31: Obtain the intelligent bed material data;

[0039] Step S32: Adjust the softness and hardness of the bed body contact surface for the posture fatigue degree data according to the intelligent bed material data to obtain the softness and hardness adjustment data of the bed body contact surface;

[0040] Step S33: Adjust the posture support structure for the posture fatigue degree data according to the softness and hardness adjustment data of the bed body contact surface to obtain the bed body posture support structure data.

[0041] The acquisition of the intelligent bed material data in the present invention is the first step in the entire dynamic adjustment of the sleep experience. The key to this step lies in thoroughly understanding the material characteristics of the mattress and the bed frame, including factors such as the density, elasticity, breathability, and durability of the material. By collecting and analyzing these material data, the system can comprehensively judge the adaptability of the bed body to different parts of the user's body and its impact, and then provide a scientific basis for subsequent adjustments. These effective data help to identify the support performance of different materials for different sleeping postures, ensuring that users can obtain balanced support during sleep and reducing the risk of physical discomfort. In-depth material data analysis lays a theoretical foundation for achieving a personalized sleep experience, thereby improving the sleep quality. Based on the acquisition of the intelligent bed material data, the softness and hardness of the bed body contact surface are adjusted for the posture fatigue degree data. This step emphasizes the importance of the softness and hardness of the mattress in the user's sleep state. By analyzing the posture fatigue degree, the system can understand the needs of the user's different sleeping postures for the bed body contact surface. For example, some postures require a softer contact surface to relieve joint pressure, while other postures are more suitable for harder support. According to these data, the system will make targeted softness and hardness adjustments so that the bed body contact surface can effectively adapt to the physiological characteristics and sleep needs of the user. The finally obtained softness and hardness adjustment data of the bed body contact surface will provide a direct solution for optimizing the user's comfort and support, and reducing muscle fatigue and discomfort caused by improper postures. According to the softness and hardness adjustment data of the bed body contact surface, the posture support structure is adjusted for the posture fatigue degree data. This step aims to improve the support performance of the bed body to further meet the personalized sleep needs of the user. When the softness and hardness of the bed body contact surface are adjusted, the system will conduct a detailed analysis in combination with the user's posture fatigue data to evaluate whether the current support structure still meets the physiological tolerance of the user during sleep. If it is found that the support of certain specific parts is insufficient, the system will make intelligent adjustments, such as changing the height, density, and other characteristics of the support points, to ensure that the user's body can be better supported, thereby reducing the occurrence of posture fatigue. This series of adjustments can not only effectively improve the user's comfort, but also improve their sleep quality in the long term, ensuring better repair and recovery at night.

[0042] Preferably, step S33 includes the following steps:

[0043] Step S331: Calculate the elastic deformation strength of the softness and hardness adjustment data of the bed contact surface to obtain the contact surface elastic deformation strength data;

[0044] Step S332: Calculate the vertical pressure of the contact surface of different joint postures for the posture fatigue degree data to obtain the vertical pressure data of the joint posture contact surface;

[0045] Step S333: Calculate the fatigue relief support angle of different joint postures for the vertical pressure data of the joint posture contact surface to obtain the fatigue relief support angle data;

[0046] Step S334: Adjust the deformation support adaptation of the contact surface elastic deformation strength data according to the vertical pressure data of the joint posture contact surface to obtain the deformation support adaptation data;

[0047] Step S335: Adjust the posture support structure according to the fatigue relief support angle data and the deformation support adaptation data to obtain the bed posture support structure data.

[0048] The present invention calculates the elastic deformation strength of the softness and hardness adjustment data of the bed body contact surface, thereby obtaining the elastic deformation strength data of the contact surface. Through this calculation, the system can deeply understand the deformation ability of the mattress when affected by the user's body weight and posture, that is, the deformation degree of the mattress under specific pressure conditions. The acquisition of this data is crucial for understanding the elastic characteristics of the bed body material, because sufficient elastic deformation strength can ensure that the bed body maintains an appropriate amount of deformation when supporting the user's body weight, without generating excessive pressure or reaction force. Therefore, by optimizing the elastic deformation strength, the system can effectively extend the service life of the bed body, provide better comfort and support, and reduce the fatigue caused by the mismatch between the sleep posture and the mattress characteristics. The data on the degree of posture fatigue is analyzed in detail, and the vertical pressure on the contact surface for different joint postures is calculated. The core of this calculation is to evaluate the pressure level borne by specific joints of the user in different sleeping postures. By scientifically calculating the vertical pressure on the contact surface, the system can obtain the force condition of each joint in a specific posture, which is of great significance for judging whether there are potential problems such as pressure concentration and uneven joint load. Effective pressure data can not only help users understand their physiological state in various postures, but also provide accurate basis for subsequent adjustment of the support structure to ensure the comfort and overall health of users during sleep. According to the data on the degree of posture fatigue, the vertical pressure on the contact surface for different joint postures is calculated to evaluate the force distribution on the bed body contact surface in each posture. By calculating the vertical pressure data of the joint posture contact surface, it can be identified which parts bear too high or too low pressure under specific sleeping postures. Such analysis is very important because uneven pressure distribution is likely to cause local fatigue and discomfort in the body. Mastering these pressure data helps the system to prioritize the joints that generate fatigue due to long-term compression in the subsequent adjustment of the support structure, ensuring that the user's body is well supported, improving the comfort of sleep and effectively preventing potential health problems. By calculating the vertical pressure data of the joint posture contact surface, the relief support angle for different joint postures is determined. This calculation aims to identify the most suitable support angle for the user's body in a specific position, thereby effectively relieving the fatigue caused by improper posture. A scientific and reasonable support angle can better disperse the pressure application points, reduce the pressure borne by specific joints during sleep, and thus reduce muscle discomfort and fatigue problems. This adjustment will further optimize the user's experience in bed, make the use of bridging materials more efficient, and at the same time enhance the overall support effect, ensuring that the user can maintain a good posture and relaxed muscle state during the whole night's deep sleep. According to the vertical pressure data of the joint posture contact surface, the elastic deformation strength data of the contact surface is adjusted for deformation support adaptation. The purpose of this step is to coordinate the elasticity of the bed body contact surface and the sensitivity of the pressure application area to ensure that the mattress can provide the best rebound and adaptation ability at each touch point.Through the adaptive adjustment of the deformation support, the system can optimize for high-pressure and low-pressure areas, enabling the relevant support materials to effectively adjust their elastic response to match the user's body needs under different sleeping postures. The finally obtained deformation support adaptation data can provide a direct basis for creating a personalized bed support solution, thereby improving the user's sleep comfort and reducing physical fatigue caused by the mismatch of the bed structure. Based on the fatigue relief support angle data and the deformation support adaptation data, the system adjusts the posture support structure, which is a key step in realizing a personalized sleep environment. By using mathematical models and algorithms, the system can accurately calculate the optimal support structure for each joint, enabling the bed to provide just the right support during the user's sleep. This adjustment of the support structure can ensure that the mattress maintains the optimal shape in different changing sleeping postures, promoting an even distribution of pressure throughout the body. This can not only effectively relieve muscle fatigue caused by exercise but also improve the overall sleep quality, enabling the user to experience a more comfortable and relaxing sleep state. The optimized bed posture support structure data will provide a solid foundation for achieving the best sleep experience, ensuring long-term health and comfort.

[0049] Preferably, step S4 includes the following steps:

[0050] Step S41: Perform ensemble learning on the bed posture support structure data through the random forest algorithm to obtain posture support adjustment learning data;

[0051] Step S42: Conduct logical iterative training and optimization on the posture support adjustment learning data to obtain posture support learning logic optimization data;

[0052] Step S43: Based on the posture support learning logic optimization data, perform automated firmware design to obtain posture support logic firmware, and send the posture support logic firmware to the Internet of Things control platform to execute the intelligent bed control method.

[0053] The present invention applies the random forest algorithm to perform ensemble learning on the data of the bed body attitude support structure, which is crucial for improving the adaptive ability of the smart bed. Random forest is an ensemble learning method that judges data by constructing multiple decision trees, thereby increasing the prediction accuracy and robustness of the model. At this stage, by analyzing the bed body support structure data obtained in the early stage, the algorithm can identify the features that have the greatest impact on the user's posture and integrate them into the attitude support adjustment learning data. This data not only reflects the requirements of different sleeping postures for the bed body support system but also reveals the preferences of users in different sleep states, thus providing a data basis for subsequent optimization. The beneficial effect of this step is to improve the comprehensive performance of the model, make the smart bed more accurate in understanding and adapting to user needs, and lay a scientific foundation for realizing personalized sleep adjustment. Logically iterative training optimization is performed on the attitude support adjustment learning data, and this process aims to improve the learning efficiency and application effect of the algorithm. After being processed by the random forest algorithm, the obtained learning data needs to be further logically optimized to construct a more accurate and adaptable model. At this stage, the system will continuously compare with real data, and through the iterative process, it will correct the support structure in real time and identify the factors that are most strongly correlated with the user's posture and comfort. Through the optimization of logical iterative training, the system can eliminate potential errors and uncertainties, provide a more reliable basis for the final support adjustment strategy, and ensure that each user can enjoy the best support and comfortable experience on the smart bed. This optimization process directly improves the adaptability and intelligence level of the bed body, thereby further promoting the development and practicality of smart bed technology. Automatically designing the firmware based on the attitude support learning logic optimization data is an important part of the highly intelligent implementation of the smart bed system. The attitude support logic firmware generated in this step is essentially the concretization of the learning and optimization results, aiming to realize the automatic adjustment function of the smart bed through programming. The firmware design will integrate all control logics and algorithms based on the optimized data, enabling the smart bed to respond to the needs and environmental changes of users in real time. At the same time, the generated firmware will be sent to the Internet of Things control platform to achieve linkage with the smart home system. This process enables the smart bed to cooperate with other smart devices to form a comprehensive and efficient sleep management system, thereby greatly improving the user's sleep quality and overall life experience. Through the above steps, the smart bed has not only become a passive piece of furniture but an intelligent device that actively participates in the user's health and comfort.

[0054] Preferably, the control terminal includes: a memory, a processor, and an Internet-of-Things-based smart bed control program stored on the memory and executable on the processor. When the Internet-of-Things-based smart bed control program is executed by the processor, it implements the Internet-of-Things-based smart bed control method described in any one of the above.

[0055] Preferably, the present invention further provides an Internet of Things-based intelligent bed control system for executing the Internet of Things-based intelligent bed control method described above. The Internet of Things-based intelligent bed control system includes:

[0056] An attitude change module for collecting data on the user's sleep posture through an electronic monitoring device built into the intelligent bed to obtain a user sleep posture data set; performing attitude change analysis on the user sleep posture data set to obtain user sleep posture change data; and performing attitude pressure mapping on the user sleep posture change data to obtain attitude change pressure mapping data;

[0057] An attitude fatigue analysis module for identifying the attitude stability of the user's sleep posture change data to obtain user sleep posture stability data; calculating the attitude multi-point pressure of the user sleep posture stability data to obtain attitude stability multi-point pressure data; and identifying the attitude fatigue degree based on the attitude stability multi-point pressure data to obtain attitude fatigue degree data;

[0058] A support adjustment module for obtaining intelligent bed material data; adjusting the attitude support structure according to the intelligent bed material data based on the attitude fatigue degree data to obtain bed body attitude support structure data;

[0059] An automatic execution module for designing an automatic firmware based on the bed body attitude support structure data to obtain an attitude support logic firmware, and sending the attitude support logic firmware to the Internet of Things control platform to execute the intelligent bed control method.

[0060] The beneficial effects of the present invention are as follows. Through the intelligent bed with the help of built-in electronic monitoring devices, the posture information of the user during sleep is comprehensively collected. The primary task in this process is to establish a detailed dataset of the user's sleep postures, which includes various sleep postures and their changes of the user over a period of time. By deeply analyzing these data, the characteristics of the user's posture changes at different stages can be identified, which is crucial for understanding sleep quality and health status. Next, using the posture change pressure mapping technology, the sleep posture can be combined with the weight distribution and the pressure impact on the mattress to generate the posture change pressure mapping data. This mapping helps to analyze which posture causes physical fatigue or discomfort, thus providing a scientific basis for improving the user's sleep quality. Focusing on the identification of the stability of the user's sleep posture, this step aims to judge the stability of the user's posture during the entire sleep process. Through the monitoring of the sleeping posture, the technology can identify which posture lasts longer and the conversion frequency between different postures observed during the entire sleep cycle. Relying on these data, the multi-point pressure calculation of the posture is carried out to evaluate the pressure exerted on each body part by different postures. Finally, based on these posture stability multi-point pressure data, the system can identify the user's fatigue level. This not only helps the user to understand their own sleep quality, but also provides practical guidance for improving the design and personal health management. This process provides the user with actionable insights, enabling them to take measures to optimize their sleep environment and improve their overall health level. First, obtain the material data of the intelligent bed, which is the key basis for realizing the adjustment of the posture support structure. These data not only include the material type, hardness, breathability, durability, etc. of the bed body, but also involve the sleep postures and their fatigue levels of the user on different material mattresses. By deeply analyzing the posture fatigue level data, the support effect of a specific material on different parts of the user's body can be understood. According to these analysis results, the posture support structure of the bed body is optimized and adjusted accordingly, and finally the bed body posture support structure data is formed. This adjustment can significantly improve sleep quality, reduce physical discomfort and fatigue caused by improper support, enhance the comfort of the user during sleep, and thus promote a healthy sleep pattern. Based on the obtained bed body posture support structure data, the intelligent bed will enter the automated firmware design stage. By integrating various sensor data and user feedback, the corresponding posture support logic firmware is designed, which will provide the support strategies required by the intelligent bed in different postures. After the design is completed, the firmware will be sent to the Internet of Things control platform, which represents a major step forward for the intelligent bed towards automation and intelligence. The Internet of Things control platform can receive the feedback from the intelligent bed in real time and make adjustments according to the dynamic needs of the user to ensure that the bed body always provides the optimal support during the user's sleep. This intelligent control method not only improves the efficiency and accuracy of the bed body use, but also greatly enhances the user experience, ensuring that the user always maintains a comfortable and healthy state during the night sleep, and thus improving the overall quality of life.Therefore, the present invention is an improved treatment of a traditional Internet of Things-based intelligent bed control method, which solves the problems that the traditional Internet of Things-based intelligent bed control method cannot accurately analyze the fatigue degree of the posture and has a weak ability to adjust the posture, improves the accuracy of analyzing the fatigue degree of the posture, and enhances the ability to adjust the posture. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 is a schematic flow chart of the steps of an Internet of Things-based intelligent bed control method;

[0062] Figure 2 is Figure 1 a detailed implementation step flow chart of step S2 in

[0063] The realization, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0064] The technical method of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative work belong to the scope of protection of the present invention.

[0065] In addition, the accompanying drawings are only schematic diagrams of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus their repeated description will be omitted. Some of the block diagrams shown in the 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 in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0066] It should be understood that although the terms "first", "second", etc. may be used here to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit can be called the second unit, and similarly the second unit can be called the first unit. The term "and / or" used here includes any and all combinations of one or more of the listed related items.

[0067] To achieve the above object, please refer to Figures 1 to 2 , an Internet of Things-based intelligent bed control method, the method includes the following steps:

[0068] Step S1: Use the electronic monitoring device built into the smart bed to collect data on the user's sleep posture, obtaining a user sleep posture dataset; perform posture change analysis on the user sleep posture dataset to obtain user sleep posture change data; perform posture pressure mapping on the user sleep posture change data to obtain posture change pressure mapping data;

[0069] Step S2: Perform posture stability identification on the user sleep posture change data to obtain user sleep posture stability data; perform multi-point posture pressure calculation on the user sleep posture stability data to obtain multi-point posture stability pressure data; perform posture fatigue degree identification based on the multi-point posture stability pressure data to obtain posture fatigue degree data;

[0070] Step S3: Obtain the smart bed material data; adjust the posture support structure according to the smart bed material data for the posture fatigue degree data to obtain the bed body posture support structure data;

[0071] Step S4: Based on the bed body posture support structure data, perform automated firmware design to obtain posture support logic firmware, and send the posture support logic firmware to the Internet of Things control platform to execute the smart bed control method.

[0072] In the embodiment of the present invention, refer to Figure 1 As described, it is a schematic diagram of the step flow of a smart bed control method based on the Internet of Things of the present invention. In this example, the smart bed control method based on the Internet of Things includes the following steps:

[0073] Step S1: Use the electronic monitoring device built into the smart bed to collect data on the user's sleep posture, obtaining a user sleep posture dataset; perform posture change analysis on the user sleep posture dataset to obtain user sleep posture change data; perform posture pressure mapping on the user sleep posture change data to obtain posture change pressure mapping data;

[0074] In the embodiments of the present invention, through the electronic monitoring device built in the smart bed, high-precision sensors are used to collect real-time data on the user's sleep posture. The device includes an acceleration sensor and a pressure sensor, which can capture the user's movement trajectory on the bed and the pressure values at each contact point respectively. The data collection frequency is set to 20 times per second to ensure continuous and detailed posture information is obtained. Next, the collected data is input into the posture recognition algorithm, and the Dynamic Time Warping (DTW) technique is used to analyze the user's sleep posture to identify the posture changes in different sleep stages. By analyzing, a user's sleep posture data set is obtained, including the posture types and their change trends in each time period. Finally, based on the analysis results of the data set, the Principal Component Analysis (PCA) method is used to perform dimensionality reduction on the posture changes, so as to extract the user's sleep posture change data, including the frequently changing posture types and their occurrence frequencies.

[0075] Step S2: Identify the stability of the user's sleep posture changes to obtain the user's sleep posture stability data; calculate the multi-point pressure of the posture for the user's sleep posture stability data to obtain the multi-point pressure data of the stable posture; identify the degree of posture fatigue according to the multi-point pressure data of the stable posture to obtain the degree of posture fatigue data;

[0076] In the embodiments of the present invention, the stability of the obtained user's sleep posture changes is identified. The Hurst exponent analysis method is adopted to judge the stability by calculating the self-similarity of the user's posture changes. The posture change data is converted into a time series, and by calculating the value of the Hurst exponent, the user's sleep posture stability data in a specific time period is obtained, and the stable and unstable posture regions are identified. Subsequently, multi-point pressure calculation is performed on the posture stability data. The specifically used algorithm is a distributed pressure sensor network to ensure that the pressure data measured at different positions is accurately integrated. In this process, the pressure values at each measurement point are calculated by the method of weighted average, so as to obtain the multi-point pressure data of the stable posture, which describes the overall pressure distribution of the user in different postures. According to the obtained multi-point pressure data of the stable posture, a fuzzy logic algorithm is used to identify the degree of posture fatigue, evaluate the fatigue condition of the user during sleep, and finally generate the degree of posture fatigue data, providing guidance helpful for improving the user's sleep quality.

[0077] Step S3: Obtain the smart bed material data; adjust the posture support structure according to the smart bed material data for the degree of posture fatigue data to obtain the bed body posture support structure data;

[0078] In the embodiments of the present invention, material data is obtained from the sensor system of the intelligent bed, mainly including the density, elastic modulus, damping characteristics, etc. of the mattress. These data are collected in real time by embedded sensors to ensure the accuracy and timeliness of the material information. Then, based on the obtained attitude fatigue degree data, the support structure of the bed body is adjusted by using the Finite Element Analysis (FEA) technology. This analysis process regards the bed body as a multi-physical field coupling problem, and by inputting the physical characteristics of different materials, the stress conditions under different postures are simulated. On this basis, combined with the fatigue degree data, an optimized design of the support structure is carried out to ensure that the bed body provides the best support effect when the user's posture changes. Finally, the bed body attitude support structure data is generated, which details the position of the optimized support points and the mechanical parameters required for each support point.

[0079] Step S4: Based on the bed body attitude support structure data, an automated firmware design is carried out to obtain the attitude support logic firmware, and the attitude support logic firmware is sent to the Internet of Things control platform to execute the intelligent bed control method.

[0080] In the embodiments of the present invention, based on the bed body attitude support structure data, an automated firmware design is carried out. Using the object-oriented design method, each parameter of the attitude support structure is converted into a function module in a programmable logic controller (PLC). During the design process, a state machine model is used to describe the different support states of the bed body and the corresponding control logic. For each support state, corresponding control instructions are written, including the rotation speed, angle adjustment of the motor, and real-time feedback mechanism. These instructions are optimized through a scheduling algorithm to ensure a rapid response when receiving the user's posture change signal. After the design is completed, the attitude support logic firmware is uploaded to the Internet of Things control platform to achieve the dynamic control of the intelligent bed. The platform has a real-time data transmission function to ensure that the interaction between the bed body and the user can be completed within milliseconds, thereby improving the overall user experience and sleep quality.

[0081] Preferably, step S1 includes the following steps:

[0082] Step S11: The data of the user's sleep posture is collected through the electronic monitoring device built in the intelligent bed to obtain the user's sleep posture data set;

[0083] Step S12: Based on the pressure sensor built in the intelligent bed, the user's sleep posture pressure data is collected to obtain the user's sleep posture pressure data;

[0084] Step S13: The attitude change analysis is carried out on the user's sleep posture data set to obtain the user's sleep posture change data;

[0085] Step S14: Perform pose-pressure mapping on the user's sleep pose change data based on the user's sleep pose pressure data to obtain pose change pressure mapping data.

[0086] In the embodiment of the present invention, data collection of the user's sleep pose is performed by an electronic monitoring device built in the smart bed. This device integrates high-precision motion sensors, including an accelerometer and a gyroscope, and can monitor the user's body position and motion state in real time in a three-dimensional space. The sensors collect data at a frequency of 20 times per second to ensure continuous pose change information is obtained. The data is subjected to preliminary filtering to remove noise and errors, ensuring the accuracy and effectiveness of the data. Finally, all pose information is integrated into a user sleep pose data set, recording the pose type, timestamp, and its corresponding motion trajectory at each time point, forming a complete time series, providing a basis for subsequent analysis. Data collection of the user's sleep pose pressure is performed based on the pressure sensors built in the smart bed. The pressure sensors are distributed in different areas of the mattress to monitor the pressure changes at each contact point of the user's body in real time. The data collection process adopts a time synchronization mechanism to ensure the correlation between the pose data and the pressure data. By designing a reasonable pressure threshold, the user's weight distribution and its change trend are identified. The collected pressure data is subjected to data smoothing to eliminate instantaneous fluctuations and interference signals, and finally user sleep pose pressure data is generated, recording the pressure distribution in different time periods, providing an important basis for subsequent pose change analysis. Pose change analysis is performed on the user sleep pose data set, and the dynamic time warping (DTW) algorithm is used to identify and compare the changes in different sleep poses. This algorithm can process pose data with offsets on the time axis by measuring the distance between time series. During the analysis process, the user's sleep pose data is divided into multiple time windows, and the frequency and mode of pose changes within each window are calculated respectively. At the same time, a clustering algorithm is used to classify different sleep poses, combining similar poses together, thereby obtaining the user's sleep pose change data. This process provides the pose change trajectory of the user during the entire sleep cycle, helping to identify common pose types and their durations. Perform pose-pressure mapping on the user's sleep pose change data based on the user's sleep pose pressure data. First, align the pressure data with the pose change data to ensure data consistency through timestamp matching. Next, apply linear regression analysis to map the pressure distribution information to the corresponding pose changes and calculate the pressure performance of each pose. This process generates pose change pressure mapping data, characterizing the pressure distribution characteristics under different poses, and helping to identify the support effect and comfort of the user in different sleep poses. The final mapping result provides data support for optimizing the support strategy of the smart bed and further improving the user's sleep quality.

[0087] Preferably, step S2 includes the following steps:

[0088] Step S21: Calculate the posture change frequency of the user's sleep posture change data to obtain the posture change frequency data;

[0089] Step S22: Identify the posture stability of the user's sleep posture change data based on the posture change frequency data to obtain the user's sleep posture stability data;

[0090] Step S23: Calculate the multi-point pressure of the posture based on the posture change pressure mapping data for the user's sleep posture stability data to obtain the multi-point pressure data of the posture stability;

[0091] Step S24: Identify the high / low pressure points of the posture for the multi-point pressure data of the posture stability to obtain the high / low pressure point data of the posture;

[0092] Step S25: Identify the posture fatigue degree of the user's sleep posture stability data based on the high / low pressure point data of the posture to obtain the posture fatigue degree data.

[0093] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0094] Step S21: Calculate the posture change frequency of the user's sleep posture change data to obtain the posture change frequency data;

[0095] In the embodiment of the present invention, the posture change frequency of the user's sleep posture change data is calculated. First, the posture change data is divided into multiple windows according to time periods, and each window contains data of a certain duration (for example, 5 minutes). Within each window, calculate the number of posture changes that the user has made during this time period. To ensure accuracy, signal processing methods are used to filter the posture change signal to remove interference and noise. Then, count the number of posture changes within each window and calculate the change frequency per minute. Finally, integrate the frequency data of each window to generate the posture change frequency data, record the change frequency of the user's posture within each time period, so as to provide basic data for subsequent stability identification.

[0096] Step S22: Identify the posture stability of the user's sleep posture change data based on the posture change frequency data to obtain the user's sleep posture stability data;

[0097] In the embodiments of the present invention, the attitude stability of the user's sleep attitude change data is identified according to the attitude change frequency data. The threshold judgment method is adopted. First, a frequency threshold is set, which is usually obtained through statistical analysis of historical data. The calculated attitude change frequency is compared with the set threshold. When the frequency is lower than the threshold, it is judged that the attitude is stable. In order to enhance the accuracy of recognition, the moving average method is further introduced to smooth the frequency data, thereby reducing the influence of short-term fluctuations on the judgment result. Finally, the user's sleep attitude stability data is generated, clearly recording which time periods the attitude is stable and the duration of each period, providing a basis for subsequent multi-point pressure calculation.

[0098] Step S23: Calculate the multi-point pressure of the user's sleep attitude stability according to the attitude change pressure mapping data to obtain the multi-point pressure data of the attitude stability.

[0099] In the embodiments of the present invention, according to the attitude change pressure mapping data, the multi-point pressure of the user's sleep attitude stability is calculated. First, combined with the obtained pressure mapping data, the pressure distribution characteristics of the user in different postures are identified. Next, the pressure data in each stable posture is associated with the attitude change data, and the pressure of multiple contact points is calculated by the weighted average method to obtain the overall multi-point pressure data. This process also considers the center of gravity position of the user's body and the relative pressure of each contact point to ensure that the generated multi-point pressure data of the attitude stability accurately reflects the overall pressure distribution of the user in the stable posture, providing a necessary basis for subsequent high / low pressure point identification.

[0100] Step S24: Identify the high / low pressure points of the attitude from the multi-point pressure data of the attitude stability to obtain the high / low pressure point data of the attitude.

[0101] In the embodiments of the present invention, the high / low pressure points of the attitude are identified from the multi-point pressure data of the attitude stability. First, the discrimination thresholds of the high-pressure point and the low-pressure point are set, and these thresholds are set according to historical pressure data and user individual differences. Next, a classification algorithm is used to analyze the pressure data, identify the pressure values of each contact point, and compare them with the set thresholds. When the pressure value of a certain contact point is higher than the high-pressure threshold, it is marked as a high-pressure point; on the contrary, if it is lower than the low-pressure threshold, it is marked as a low-pressure point. By traversing all contact points, the high / low pressure point data of the attitude is generated, clearly recording the positions of the high-pressure and low-pressure points in different sleep postures, providing support for subsequent fatigue degree identification.

[0102] Step S25: Identify the fatigue degree of the user's sleep attitude according to the high / low pressure point data of the attitude to obtain the fatigue degree data of the attitude.

[0103] In the embodiments of the present invention, based on the attitude high / low pressure point data, the attitude fatigue degree of the user's sleep attitude stability data is identified. First, by combining the identified high-pressure and low-pressure points, the comprehensive evaluation method is used to associate the pressure data with the user's stability data. Specifically, the time period in which the high-pressure points are located is analyzed to evaluate the fatigue status of the user during this time period. To quantify the fatigue degree, a fatigue scoring system is constructed, and the score is based on the duration and frequency of the high-pressure points. The longer the duration and the higher the frequency, the higher the fatigue score. Finally, the attitude fatigue degree data is generated, clearly recording the fatigue level of the user during sleep due to the influence of high-pressure points, providing a basis for further optimizing the support strategy of the intelligent bed.

[0104] Preferably, step S23 includes the following steps:

[0105] Step S231: Analyze the pressure changes of different joint parts of the user's sleep attitude stability data according to the attitude change pressure mapping data to obtain the attitude joint pressure data;

[0106] Step S232: Calculate the center of gravity offset angle of the attitude joint pressure data of different joint parts to obtain the joint center of gravity offset angle data;

[0107] Step S233: Perform pressure position specificity analysis of different joint parts according to the attitude joint pressure data and the joint center of gravity offset angle data to obtain the joint pressure position specificity data;

[0108] Step S234: Calculate the movable radius of different joint parts for the joint pressure position specificity data to obtain the position-related joint movable radius data;

[0109] Step S235: Perform attitude multi-point pressure calculation on the user's sleep attitude stability data according to the joint pressure position specificity data and the position-related joint movable radius data to obtain the attitude stability multi-point pressure data.

[0110] In the embodiments of the present invention, based on the attitude change pressure mapping data, the pressure change analysis of the user's sleep attitude stability data for different joint parts is carried out to obtain the attitude joint pressure data. First, the attitude change pressure mapping data is associated with the joint parts of the user to identify the main joints of the body, such as the shoulder joint, elbow joint, hip joint, knee joint, etc. By extracting the pressure values of each joint at different attitudes point by point and using the interpolation method to smooth the data, the influence of instantaneous fluctuations on the results can be eliminated. Then, the average pressure values of each joint in different time periods are calculated and compared with the standard pressure values to generate the attitude joint pressure data. These data can reflect in detail the pressure distribution of different joint parts and provide a basis for subsequent analysis. The center of gravity offset angle calculation is carried out on the attitude joint pressure data of different joint parts to obtain the joint center of gravity offset angle data. First, for each joint part, the geometric center algorithm is used to calculate the center of gravity position of the pressure it receives. According to the pressure data of each joint part, the centroid formula is used to calculate the centroid coordinates of this part. Then, combined with the standard position and attitude of the user's body, the offset angle of the center of gravity relative to the standard position is calculated. Trigonometric functions are used for angle conversion to generate the joint center of gravity offset angle data. These data are helpful for analyzing the pressure change and the stability of the center of gravity of the joint at different attitudes and providing support for subsequent pressure position specificity analysis. According to the attitude joint pressure data and the joint center of gravity offset angle data, the pressure position specificity analysis of different joint parts is carried out to obtain the joint pressure position specificity data. First, the pressure data of each joint is associated with the corresponding center of gravity offset angle data to evaluate the distribution characteristics of the pressure. The principal component analysis (PCA) method is used to reduce the dimension of the pressure data, extract the main features of the pressure data, and identify the pressure concentration areas of specific joint parts at different attitudes. According to the analysis results, the joint pressure position specificity data is generated, which indicates which joint parts have a more concentrated pressure distribution at a specific attitude and reflects the attitude characteristics of the user during sleep. The movable radius calculation of different joint parts is carried out on the joint pressure position specificity data to obtain the position-associated joint movable radius data. First, the movable radius is defined as the maximum movement range of the joint within the range of maintaining an effective pressure distribution. By setting a fixed pressure threshold, it is judged the pressure change that the joint can withstand under this threshold. Then, based on the pressure data and position characteristics, the geometric modeling method is used to calculate the movable range of each joint. By establishing a spatial model corresponding to the joint pressure distribution, the movable radius of each joint part is determined. This data can provide a basis for subsequent attitude multi-point pressure calculation to ensure pressure adjustment within the tolerable range. According to the joint pressure position specificity data and the position-associated joint movable radius data, the attitude multi-point pressure calculation is carried out on the user's sleep attitude stability data to obtain the attitude stable multi-point pressure data.First, integrate the joint pressure position-specific data with the movable radius data to identify the pressure characteristics and their adjustable ranges of each joint in a specific posture. Next, use multivariate regression analysis to establish a pressure calculation model by combining the pressure characteristics and movement radii of each joint. Through this model, calculate the total pressure exerted by each joint and its distribution under the condition of maintaining a stable posture. Finally, generate multi-point pressure data for posture stability, clearly record the pressure changes at different joint positions, and provide data support for optimizing the support strategy of the intelligent bed.

[0111] Preferably, step S25 includes the following steps:

[0112] Step S251: Calculate the pressure difference between adjacent joint parts for the high / low pressure point data of the posture to obtain the pressure difference data of adjacent joint parts;

[0113] Step S252: Analyze the muscle tightness of different joint parts for the user's sleep posture stability data based on the pressure difference data of adjacent joint parts to obtain the joint posture muscle tightness data;

[0114] Step S253: Calculate the fatigue index of different joint parts for the joint posture muscle tightness data based on the pressure difference data of adjacent joint parts to obtain the joint posture fatigue index;

[0115] Step S254: Quantify the differences of different joint parts for the joint posture muscle tightness data based on the joint posture fatigue index to obtain the joint muscle fatigue difference quantification data;

[0116] Step S255: Identify the posture fatigue degree for the user's sleep posture stability data based on the joint muscle fatigue difference quantification data to obtain the posture fatigue degree data.

[0117] In the embodiments of the present invention, the pressure difference of adjacent joint parts is calculated for the posture high / low voltage point data to obtain the pressure difference data of adjacent joint parts. First, the high-pressure and low-pressure points of each joint are identified and used as the basis for analysis. Next, by calculating the pressure difference between adjacent joints (such as the shoulder joint and the elbow joint, the hip joint and the knee joint), using the absolute value difference formula, that is, subtracting the pressure values of adjacent joints, the pressure difference data is obtained. The specific method includes establishing a pressure difference matrix to facilitate the identification of the pressure change trend between different joints. Through this process, the generated pressure difference data of adjacent joint parts provides a key basis for subsequent muscle tightness analysis. According to the pressure difference data of adjacent joint parts, the muscle tightness analysis of different joint parts is carried out on the user's sleep posture stability data to obtain the joint posture muscle tightness data. First, the joint parts with large pressure changes are determined using the pressure difference data, assuming that there is muscle tightness in these parts. Then, using the method of linear regression analysis, the correlation analysis is carried out between the pressure difference data and the user's muscle tightness perception (which can be obtained through self-report or sensor feedback), and the tightness degree index is calculated. The generated joint posture muscle tightness data can provide the necessary input for subsequent fatigue index calculation, revealing the tension state of different joints during sleep. According to the pressure difference data of adjacent joint parts, the fatigue index calculation of different joint parts is carried out on the joint posture muscle tightness data to obtain the joint posture fatigue index. First, the obtained joint posture muscle tightness data is combined and analyzed with the pressure difference data. Using the fatigue index calculation formula, the muscle tightness degree and the pressure difference are weighted and synthesized to reflect the fatigue degree of muscles in different joints. Specifically, the weights of different joints are set, and the weighted average method is used to obtain the fatigue index of each joint. This process will help to quantify the fatigue level of each joint and provide support for subsequent analysis. The finally generated joint posture fatigue index will be used to evaluate the overall fatigue state of the user. According to the joint posture fatigue index, the difference quantification of different joint parts is carried out on the joint posture muscle tightness data to obtain the joint muscle fatigue difference quantification data. First, the fatigue indexes of each joint are sorted, and the average fatigue value of each joint is calculated. Then, the analysis of variance method is used to compare the fatigue indexes of each joint to determine which joints have significant fatigue differences. By calculating the standard deviation and the mean difference, the difference quantification data of each joint relative to the overall fatigue level is obtained. This data can specifically reflect which joints show significant tightness due to fatigue, providing a quantitative basis for subsequent fatigue degree identification. According to the joint muscle fatigue difference quantification data, the posture fatigue degree identification is carried out on the user's sleep posture stability data to obtain the posture fatigue degree data. First, the joint muscle fatigue difference quantification data is combined with the user's posture stability data, and the influence of muscle fatigue degree on the overall sleep posture is evaluated through correlation analysis.Next, a grading method is adopted to quantify the fatigue level into different grades (such as mild, moderate, and severe fatigue), and the fatigue state of the user in different postures is determined by combining the aforementioned data. The finally generated posture fatigue level data will provide a basis for the adaptive control strategy of the smart bed, enabling the bed body to adjust when necessary to improve the user's sleep quality.

[0118] Preferably, step S3 includes the following steps:

[0119] Step S31: Obtain the smart bed material data;

[0120] Step S32: Adjust the softness and hardness of the bed body contact surface according to the smart bed material data to obtain the adjusted data of the softness and hardness of the bed body contact surface;

[0121] Step S33: Adjust the posture support structure according to the adjusted data of the softness and hardness of the bed body contact surface to obtain the bed body posture support structure data.

[0122] In the embodiments of the present invention, the process of obtaining the intelligent bed material data includes measuring and recording the physical properties of the bed body materials. First, sensors are used to detect the materials of the mattress and the bed frame, and physical parameters such as density, elastic modulus, and compressive strength are collected. These data are sorted to form an intelligent bed material data set. This data set will include the characteristics of different materials (such as memory foam, latex, rigid foam, etc.), thus providing a necessary basis for subsequent softness and hardness adjustment. The data acquisition process needs to ensure consistent environmental conditions to exclude the influence of temperature and humidity changes on material properties. The output of this step is the intelligent bed material data that accurately reflects the material characteristics of the bed body, providing a data basis for the operations in the subsequent steps. According to the intelligent bed material data, the softness and hardness of the bed body contact surface are adjusted for the posture fatigue degree data to obtain the softness and hardness adjustment data of the bed body contact surface. First, the correlation between the obtained material data and the posture fatigue degree data is analyzed, and the regression analysis method is used to determine the influence degree of different materials on the user's fatigue feeling. By establishing a mathematical model and combining the linear relationship between the fatigue degree index and the material characteristics, the optimal softness and hardness of each material in different postures are calculated. According to these calculation results, the softness and hardness of the bed body contact surface are adjusted accordingly. The specific methods include adjusting the inflation pressure of the mattress or replacing the material layer with different hardness. Finally, the adjusted softness and hardness parameters are recorded to form the softness and hardness adjustment data of the bed body contact surface, providing data support for the next support structure adjustment. According to the softness and hardness adjustment data of the bed body contact surface, the posture support structure is adjusted for the posture fatigue degree data to obtain the bed body posture support structure data. First, based on the softness and hardness adjustment data generated in step S32, the demand of the user's sleep posture for the support structure is re-evaluated. The finite element analysis method is used to model the support structure of the bed body. By simulating the deformation of the bed body under different pressure conditions, the support effect of the current support structure on the user is evaluated. Combining the fatigue degree data, the pressure distribution of the user in different postures is analyzed, and the optimal configuration of the support structure is determined. By adjusting the position and shape of the support points, the overall support structure of the bed body is optimized to ensure that the pressure can be effectively dispersed and the user's fatigue feeling can be reduced. Finally, the output bed body posture support structure data will include the optimized parameters of each support point, providing basic data for the control system of the intelligent bed and enhancing the user's sleep experience.

[0123] Preferably, step S33 includes the following steps:

[0124] Step S331: Calculate the elastic deformation strength of the softness and hardness adjustment data of the bed body contact surface to obtain the contact surface elastic deformation strength data;

[0125] Step S332: Calculate the vertical pressure of the contact surface in different joint postures for the posture fatigue degree data to obtain the vertical pressure data of the joint posture contact surface;

[0126] Step S333: Calculate the fatigue relief support angles for different joint postures based on the vertical pressure data of the joint posture contact surfaces to obtain fatigue relief support angle data;

[0127] Step S334: Adjust the deformation support adaptation of the contact surface elastic deformation intensity data according to the vertical pressure data of the joint posture contact surfaces to obtain deformation support adaptation data;

[0128] Step S335: Adjust the posture support structure according to the fatigue relief support angle data and the deformation support adaptation data to obtain the bed body posture support structure data.

[0129] In the embodiments of the present invention, the elastic deformation strength of the softness and hardness adjustment data of the bed body contact surface is calculated to obtain the elastic deformation strength data of the contact surface. This step first needs to calculate the deformation under the applied pressure using the elastic mechanics formula based on the physical properties of the contact surface material, including Young's modulus and Poisson's ratio. Specifically, during implementation, first record the hardness and thickness of each material, and then measure the deformation degree of the contact surface under the action of pressure by applying a standardized vertical pressure. Using the stress-strain curve and combining the linear elastic characteristics of the material, determine its elastic deformation strength under different pressures. Finally, the generated elastic deformation strength data of the contact surface will be used to evaluate the bearing capacity of the contact surface and provide necessary material response information for subsequent steps. Calculate the vertical pressure of the contact surface for different joint postures based on the posture fatigue degree data to obtain the vertical pressure data of the joint posture contact surface. First, analyze the joint positions of the user in different sleeping postures, and based on the posture fatigue degree data, determine the force distribution of each joint in contact with the bed surface. By comprehensively analyzing the forces applied in various directions to the contact surface, calculate the vertical pressure of each joint part to obtain the vertical pressure data of the contact surface of each joint. These data will help understand the force conditions of different joints in specific postures and lay a foundation for subsequent support angle calculations. Perform calculations on the relief support angles for different joint postures based on the vertical pressure data of the joint posture contact surface to obtain the fatigue relief support angle data. This step first analyzes the force conditions of each joint in a specific posture based on the vertical pressure data of the contact surface using mechanical principles. By establishing a model and applying the static equilibrium equation, determine the optimal support angle of the joint under a specific pressure to reduce the sense of fatigue. During implementation, use geometric and trigonometric methods to calculate the ideal angular relationship between the support structure and the joint position. The fatigue relief support angle data formed by these calculation results will provide specific basis for the adaptation adjustment of the support structure to ensure good support for the user during sleep. Based on the vertical pressure data of the joint posture contact surface, perform deformation support adaptation adjustment on the elastic deformation strength data of the contact surface to obtain deformation support adaptation data. First, combine the elastic deformation strength data of the contact surface with the vertical pressure data to analyze the deformation characteristics of the contact surface under different pressure conditions. Using the known elastic theory, calculate the deformation of each material under the current pressure through formulas to determine the adaptability of the contact surface. Specifically, during implementation, compare the force conditions of each joint with the elastic deformation strength of the material to calculate the optimal support capacity of each contact point. Finally, the formed deformation support adaptation data will be used to optimize the support structure of the bed to ensure that the contact surface can effectively support under the action of pressure. Based on the fatigue relief support angle data and the deformation support adaptation data, adjust the posture support structure to obtain the bed body posture support structure data. First, combine the fatigue relief support angle with the deformation support adaptation data to analyze the adaptability of the current support structure to the user.By constructing a mathematical model of the support structure and using a numerical optimization algorithm, the shape and position of the support points are gradually adjusted to achieve the best mechanical balance. During specific implementation, parametric adjustment is performed on each support point, and combined with the force conditions of each point, to ensure a uniform pressure distribution in different postures. The finally obtained data of the bed body posture support structure will be used to control the support system of the intelligent bed in real time, improving the user's comfort and sleep quality.

[0130] Preferably, step S4 includes the following steps:

[0131] Step S41: Perform ensemble learning on the data of the bed body posture support structure through the random forest algorithm to obtain posture support adjustment learning data;

[0132] Step S42: Perform logical iterative training optimization on the posture support adjustment learning data to obtain posture support learning logic optimization data;

[0133] Step S43: Based on the posture support learning logic optimization data, perform automated firmware design to obtain posture support logic firmware, and send the posture support logic firmware to the Internet of Things control platform to execute the intelligent bed control method.

[0134] In the embodiments of the present invention, the random forest algorithm is used to perform ensemble learning on the data of the bed attitude support structure to obtain attitude support adjustment learning data. Specifically, during implementation, the collected attitude support structure data is first divided into multiple subsets, and a part of the data is randomly selected for training to ensure the diversity and representativeness of each subset. The random forest algorithm constructs multiple decision trees and votes on the results of each tree to obtain the final prediction result. During this process, by maximizing the accuracy of each tree on the training data, the robustness and accuracy of the overall model are improved. Finally, the output attitude support adjustment learning data contains the best adaptation information of different sleeping postures and related support structures, providing a basis for subsequent logical iterative training. Logical iterative training optimization is performed on the attitude support adjustment learning data to generate attitude support learning logic optimization data. First, through feature selection on the initially obtained learning data, the feature variables strongly correlated with the support effect are extracted. On this basis, logical regression or other iterative optimization algorithms are used to gradually adjust and optimize the model parameters to improve the adaptability of the model to different users and different postures. In specific operations, the cross-validation method is adopted to repeatedly test and update the model parameters to ensure that the prediction error can be reduced in each iteration. Finally, after multiple iterations, the formed attitude support learning logic optimization data will effectively improve the intelligent adjustment ability of the support structure, providing an accurate basis for automated firmware design. Automated firmware design is performed based on the attitude support learning logic optimization data to generate attitude support logic firmware and send it to the Internet of Things control platform. During the implementation process, first, the decision rules extracted from the learning logic optimization data are analyzed and converted into specific parameters for firmware design. These parameters include the response mechanism of the support structure, the adjustment range, and the interface design for interaction with the user. Then, an automated firmware development tool is used to generate the corresponding firmware code according to the optimized logical structure. After the firmware is completed, it is uploaded to the control platform through the Internet of Things communication protocol to ensure that the smart bed can achieve automated adjustment under different environments and user requirements. Finally, the attitude support logic firmware sent to the Internet of Things control platform has real-time performance and adaptability, and can perform dynamic adjustment according to the real-time feedback of the user, improving the user's sleep experience.

[0135] Preferably, the control terminal includes: a memory, a processor, and an Internet of Things-based smart bed control program stored on the memory and executable on the processor. When the Internet of Things-based smart bed control program is executed by the processor, it implements the Internet of Things-based smart bed control method as described above.

[0136] Preferably, the present invention also provides an Internet of Things-based smart bed control system for executing the Internet of Things-based smart bed control method as described above. The Internet of Things-based smart bed control system includes:

[0137] The posture change module is used to collect data on the user's sleep posture through the electronic monitoring device built in the smart bed to obtain the user's sleep posture dataset; perform posture change analysis on the user's sleep posture dataset to obtain the user's sleep posture change data; perform posture pressure mapping on the user's sleep posture change data to obtain the posture change pressure mapping data;

[0138] The posture fatigue analysis module is used to identify the posture stability of the user's sleep posture change data to obtain the user's sleep posture stability data; perform multi-point posture pressure calculation on the user's sleep posture stability data to obtain the multi-point posture stability pressure data; identify the posture fatigue degree according to the multi-point posture stability pressure data to obtain the posture fatigue degree data;

[0139] The support adjustment module is used to obtain the smart bed material data; adjust the posture support structure according to the smart bed material data for the posture fatigue degree data to obtain the bed body posture support structure data;

[0140] The automatic execution module is used to perform automatic firmware design based on the bed body posture support structure data to obtain the posture support logic firmware, and send the posture support logic firmware to the Internet of Things control platform to execute the smart bed control method.

[0141] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the application document are intended to be included in the present invention.

[0142] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can 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 these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. A smart bed control method based on the Internet of Things, characterized in that: The following steps are involved: Step S1: collecting data on the user's sleeping posture through the electronic monitoring device built into the smart bed to obtain a user's sleeping posture data set; performing posture change analysis on the user's sleeping posture data set to obtain user's sleeping posture change data; performing posture pressure mapping on the user's sleeping posture change data to obtain posture change pressure mapping data; Step S2: performing posture stabilization identification on the user's sleeping posture change data to obtain the user's sleeping posture stabilization data; performing posture multi-point pressure calculation on the user's sleeping posture stabilization data to obtain posture stabilization multi-point pressure data; performing posture fatigue degree identification based on the posture stabilization multi-point pressure data to obtain posture fatigue degree data; Step S3: Acquire the material data of the smart bed; adjust the posture support structure of the posture fatigue degree data according to the material data of the smart bed to obtain the posture support structure data of the bed; Step S4: Perform automated firmware design based on the bed posture support structure data to obtain posture support logic firmware, and send the posture support logic firmware to the Internet of Things control platform to execute the smart bed control method.

2. The method for controlling an intelligent bed based on the Internet of Things according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: collecting data on the user's sleeping posture through the electronic monitoring device built into the smart bed to obtain a user's sleeping posture data set; Step S12: collecting the user's sleeping posture pressure data based on the built-in pressure sensor of the smart bed to obtain the user's sleeping posture pressure data; Step S13: performing posture change analysis on the user's sleeping posture data set to obtain the user's sleeping posture change data; Step S14: performing posture pressure mapping on the user's sleeping posture change data according to the user's sleeping posture pressure data to obtain posture change pressure mapping data.

3. The method for controlling an intelligent bed based on the Internet of Things according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: Calculating the posture change frequency of the user's sleeping posture change data to obtain posture change frequency data; Step S22: performing posture stabilization identification on the user's sleeping posture change data according to the posture change frequency data to obtain the user's sleeping posture stabilization data; Step S23: performing posture multi-point pressure calculation on the user's sleep posture stabilization data according to the posture change pressure mapping data to obtain posture stabilization multi-point pressure data; Step S24: identifying high / low pressure points of the multi-point pressure data of the posture stabilization to obtain high / low pressure point data of the posture; Step S25: identifying the posture fatigue degree of the user's sleeping posture stability data according to the posture high / low pressure point data to obtain posture fatigue degree data.

4. The method for controlling an intelligent bed based on the Internet of Things according to claim 3, characterized in that: Step S23 includes the following steps: Step S231: analyzing the pressure changes of different joints of the user's sleep posture stability data according to the posture change pressure mapping data to obtain posture joint pressure data; Step S232: calculating the center of gravity offset angle of the posture joint pressure data of different joint parts to obtain joint center of gravity offset angle data; Step S233: performing pressure position specificity analysis of different joint parts according to the posture joint pressure data and the joint gravity center offset angle data to obtain joint pressure position specificity data; Step S234: calculating movable radius of different joint parts for the joint pressure position-specific data to obtain position-related joint movable radius data; Step S235: performing posture multi-point pressure calculation on the user's sleeping posture stabilization data according to the joint pressure position-specific data and the position-associated joint movable radius data to obtain posture stabilization multi-point pressure data.

5. The method for controlling an intelligent bed based on the Internet of Things according to claim 3, characterized in that: Step S25 includes the following steps: Step S251: Calculate the pressure difference of the adjacent joints based on the posture high / low pressure point data to obtain the pressure difference data of the adjacent joints; Step S252: performing muscle tension analysis of different joints on the user's sleep posture stability data according to the pressure difference data of adjacent joints to obtain joint posture muscle tension data; Step S253: calculating fatigue indexes of different joint parts based on the joint posture muscle tension data according to the pressure difference data of adjacent joint parts, and obtaining joint posture fatigue indexes; Step S254: quantifying the differences of the joint posture muscle tension data at different joints according to the joint posture fatigue index to obtain joint muscle fatigue difference quantification data; Step S255: identifying the posture fatigue degree of the user's sleeping posture stability data according to the joint and muscle fatigue difference quantification data to obtain posture fatigue degree data.

6. The method for controlling an intelligent bed based on the Internet of Things according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: Obtaining smart bed material data; Step S32: adjusting the hardness of the bed contact surface based on the posture fatigue degree data according to the material data of the smart bed to obtain the hardness adjustment data of the bed contact surface; Step S33: adjusting the posture support structure of the posture fatigue degree data according to the hardness adjustment data of the bed contact surface to obtain the posture support structure data of the bed.

7. The method for controlling an intelligent bed based on the Internet of Things according to claim 6, characterized in that: Step S33 includes the following steps: Step S331: Calculate the elastic deformation strength of the bed contact surface hardness adjustment data to obtain the contact surface elastic deformation strength data; Step S332: calculating the vertical pressure of the contact surface of different joint postures for the posture fatigue degree data to obtain the vertical pressure data of the contact surface of the joint posture; Step S333: calculating the fatigue relief support angles of different joint postures for the vertical pressure data of the joint posture contact surface to obtain fatigue relief support angle data; Step S334: performing deformation support adaptation adjustment on the contact surface elastic deformation strength data according to the joint posture contact surface vertical pressure data to obtain deformation support adaptation data; Step S335: adjusting the posture support structure according to the fatigue relief support angle data and the deformation support adaptation data to obtain the bed posture support structure data.

8. The method for controlling an intelligent bed based on the Internet of Things according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: performing integrated learning on the bed posture support structure data through a random forest algorithm to obtain posture support adjustment learning data; Step S42: performing logic iterative training optimization on the posture support adjustment learning data to obtain posture support learning logic optimization data; Step S43: Perform automated firmware design based on the posture support learning logic optimization data to obtain the posture support logic firmware, and send the posture support logic firmware to the Internet of Things control platform to execute the smart bed control method.

9. A control terminal, characterized in that: The control terminal includes: a memory, a processor, and an IoT-based smart bed control program stored in the memory and executable on the processor. When the IoT-based smart bed control program is executed by the processor, the IoT-based smart bed control method as described in any one of claims 1 to 8 is implemented.

10. An intelligent bed control system based on the Internet of Things, characterized in that: For executing the smart bed control method based on the Internet of Things as claimed in claim 1, the smart bed control system based on the Internet of Things comprises: The posture change module is used to collect data on the user's sleeping posture through the electronic monitoring device built into the smart bed to obtain a user's sleeping posture data set; perform posture change analysis on the user's sleeping posture data set to obtain user's sleeping posture change data; perform posture pressure mapping on the user's sleeping posture change data to obtain posture change pressure mapping data; The posture fatigue analysis module is used to identify the posture stabilization of the user's sleeping posture change data to obtain the user's sleeping posture stabilization data; perform posture multi-point pressure calculation on the user's sleeping posture stabilization data to obtain posture stabilization multi-point pressure data; perform posture fatigue degree identification based on the posture stabilization multi-point pressure data to obtain posture fatigue degree data; The support adjustment module is used to obtain the material data of the smart bed; the posture support structure is adjusted according to the posture fatigue degree data of the smart bed material data to obtain the bed posture support structure data; The automated execution module is used to perform automated firmware design based on the bed posture support structure data, obtain the posture support logic firmware, and send the posture support logic firmware to the Internet of Things control platform to execute the smart bed control method.

Images