A parametric simulation model design method and system based on intelligent bed

Abstract

The present invention relates to the technical field of parameterized simulation model design, and in particular to a parameterized simulation model design method and system based on a smart bed. The method comprises the following steps: performing internal logic relationship analysis on the functional design requirement data of the smart bed and mapping the functional test boundary parameters between different functional modules to obtain the functional test boundary parameters; performing functional scenario test data collection on the functional test boundary parameters, and then performing scene function execution abnormality identification to obtain scene function execution abnormality data; performing functional test balance point correction on the scene function execution abnormality data to obtain scene function balance point correction data; performing parameterized simulation model design on the scene function balance point correction data and performing automated firmware design to obtain the smart bed scene parameter logic firmware. The present invention makes the parameterized simulation model design technology more perfect by optimizing the parameterized simulation model design technology.

Description

Technical Field

[0001] The present invention relates to the technical field of parametric simulation model design, and in particular to a parametric simulation model design method and system based on an intelligent bed. Background Art

[0002] With the advancement of science and technology, smart beds, as a product that integrates advanced sensors, the Internet of Things and data analysis technologies, have attracted more and more attention. Smart beds provide personalized sleep optimization suggestions by monitoring the user's sleep status, physiological parameters and environmental conditions. This process not only relies on the precise perception ability of the hardware, but also requires data processing and analysis through complex algorithm models. Therefore, it is particularly important to design an effective parametric simulation model. Secondly, with the enhancement of health awareness, the market demand for smart beds continues to grow. People hope to improve sleep quality through scientific means, and parametric simulation models can provide more accurate personalized solutions. By simulating the hardness, temperature regulation and intelligent functions of the mattress, designers can better meet the specific needs of different users, such as the different requirements for the elderly, pregnant women or athletes, thereby improving user satisfaction. Furthermore, with the maturity of artificial intelligence technology, especially in the fields of machine learning and data mining, the parametric simulation model of smart beds can be trained with a large amount of historical data, thereby improving the model's predictive ability and adaptability. Designers can use these technologies to conduct in-depth analysis of users' usage behaviors and preferences, so as to develop more scientific bed design solutions. In addition, simulating different usage scenarios and user behaviors can help designers discover potential problems before the product is launched, so as to optimize it. However, the traditional parametric simulation model design method based on smart beds has the problems of incomplete model scenario testing functions and inaccurate testing. Summary of the invention

[0003] Based on this, it is necessary to provide a parametric simulation model design method and system based on a smart bed to solve at least one of the above technical problems.

[0004] To achieve the above object, a parameterized simulation model design method based on a smart bed is provided, the method comprising the following steps:

[0005] Step S1: Acquire the smart bed function design requirement data; perform internal logic relationship analysis on the smart bed function design requirement data to obtain the internal logic relationship data of the function modules; perform function test boundary parameter mapping between different function modules according to the internal logic relationship data of the function modules to obtain the function test boundary parameters;

[0006] Step S2: collecting function scenario test data for function test boundary parameters to obtain smart bed function scenario test data; performing scene function execution abnormality identification on the smart bed function scenario test data to obtain scene function execution abnormality data; performing function test balance point correction on the scene function execution abnormality data to obtain scene function balance point correction data;

[0007] Step S3: Design a parameterized simulation model for the scene function balance point correction data to obtain a smart bed scene parameter logic optimization model;

[0008] Step S4: Automated firmware design is performed on the smart bed scene parameter logic optimization model to obtain the smart bed scene parameter logic firmware, and the smart bed scene parameter logic firmware is embedded into the smart bed control system to perform smart bed parameterized simulation.

[0009] The present invention first obtains the functional design requirement data of the smart bed, and performs an in-depth internal logical relationship analysis to clarify the mutual connection and dependency between the functional modules. This process not only helps the design team understand the role of each functional module, but also lays the foundation for subsequent functional testing. By processing the internal logical relationship data of the functional module, the functional test boundary parameter mapping between different functional modules can be effectively performed to ensure that the test covers all relevant functions. Ultimately, this link will help identify the interaction of functions and improve the overall design rationality and testability of the system. Based on the functional test boundary parameters obtained in the previous step, the test data of the smart bed functional scene is collected. These scene test data will provide an important basis for evaluating the actual application performance of the smart bed. Then, the collected functional scene test data is anomaly identified. This step aims to find out the potential problems in the execution of the scene function and ensure that the smart bed can work normally in a variety of real use scenarios. Finally, by correcting the functional test balance point, it is ensured that the execution effect of the scene function reaches the predetermined goal, thereby improving the stability and reliability of the smart bed function, thereby improving user experience and product satisfaction. This series of steps not only enhances the market competitiveness of the product, but also helps to create a more intelligent sleep management solution. The parametric simulation model is designed for the scene function balance point correction data obtained in the previous step. The core purpose of this process is to build a scene parameter logic optimization model for the smart bed to achieve efficient optimization of the smart bed function. By modeling complex scene functions in a parametric way, the design team can more clearly analyze how each parameter affects the overall performance of the smart bed. This logic optimization model not only provides a theoretical basis for subsequent development, but also helps designers quickly identify and solve potential problems to ensure the best implementation of the function. In complex application scenarios, the logic optimization model can effectively improve the ability to regulate functional parameters and ultimately promote a more balanced and intelligent user experience. Based on the optimized scene parameter logic model of the smart bed, the design of the automated firmware is carried out. Through this step, the designed parameter logic firmware can be embedded into the control system of the smart bed, so that it can automatically perform parametric simulation. This process will enable the smart bed to have more powerful intelligent control capabilities, thereby achieving more precise dynamic adjustment and scene functions that adapt to user needs. Through the design and implementation of automated firmware, the development team can ensure the real-time response and optimal performance of the system, while also reducing the need for human intervention and enhancing the stability and security of the system. To sum up, this series of steps not only improves the performance and intelligence level of smart beds, but also greatly enhances its market competitiveness, providing users with a more convenient and efficient sleep management experience.Therefore, the present invention is an optimization processing of a traditional parametric simulation model design method based on a smart bed, which solves the problems of incomplete model scene testing function and inaccurate testing in the traditional parametric simulation model design method based on a smart bed, improves the overall comprehensiveness of the scene testing function, and enhances the accuracy of the test.

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

[0011] Step S11: Acquire intelligent bed functional design requirement data;

[0012] Step S12: Decomposing the smart bed functional design requirement data into functional modules to obtain smart bed functional module decomposition data;

[0013] Step S13: Analyze the internal logic relationship of the decomposed data of the intelligent bed functional modules to obtain the internal logic relationship data of the functional modules;

[0014] Step S14: mapping the functional test boundary parameters between different functional modules of the intelligent bed functional module decomposition data according to the internal logical relationship data of the functional modules to obtain the functional test boundary parameters.

[0015] The present invention first obtains the functional design requirement data of the smart bed through step S11. The data is the basis of the entire design process and helps the team to clarify user needs and market expectations. This link not only involves the understanding of product functions, but also includes an in-depth analysis of user scenarios, providing theoretical support for subsequent functional design. In step S12, the obtained functional design requirement data is decomposed into functional modules. This decomposition process can refine complex functional requirements into independent modules, making the design, development and testing of each module clearer and more efficient. This helps the team to clarify the responsibilities and functions between each module and facilitate subsequent management and coordination. The internal logical relationship analysis of the functional module decomposition data is crucial because it ensures that the mutual relationship and dependency between the functional modules are scientifically understood and analyzed. By understanding these internal logical relationships, the team can effectively avoid functional conflicts and incoordination during functional integration and debugging, and optimize the system architecture design. Finally, in step S14, according to the results of the internal logical relationship analysis of the functional modules, the functional test boundary parameter mapping between different functional modules is performed on the smart bed functional module decomposition data. Through this process, the key parameters that need to be tested can be accurately identified, laying a solid foundation for comprehensive functional testing of the smart bed, thereby ensuring high reliability and stability in the interaction and integration between multiple functional modules. This series of steps not only improves the scientific nature of the design process, but also provides guarantees for the normal operation of the final smart bed and user experience.

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

[0017] Step S21: constructing a smart bed simulation test environment according to the functional test boundary parameters to obtain a smart bed simulation test environment;

[0018] Step S22: collecting functional scenario test data for functional test boundary parameters according to the intelligent bed simulation test environment to obtain intelligent bed functional scenario test data;

[0019] Step S23: using a preset function execution specification identification manual to identify scene function execution anomalies on the smart bed function scene test data to obtain scene function execution anomaly data;

[0020] Step S24: performing function test balance point correction on the scene function execution abnormal data to obtain scene function balance point correction data.

[0021] The present invention firstly builds a simulation test environment for a smart bed according to the functional test boundary parameters obtained above through step S21. This environment is established to simulate the real use scenario, so as to provide a safe and controllable experimental space for subsequent tests. In this environment, the design team can effectively evaluate the functional performance of the smart bed and its response under various access conditions and operations, which is crucial to confirming the effectiveness of the design. Next, in step S22, according to the constructed smart bed simulation test environment, the functional scenario test data is collected for the functional test boundary parameters. The data obtained in this process provides a direct basis for subsequent functional verification, ensuring that the design team can obtain real and detailed functional performance information. The collected scenario test data is identified for abnormalities using the preset functional execution specification identification manual, which is a key link to ensure product reliability. Through this process, the team can promptly discover problems in the functional scenario, identify and record various abnormal phenomena, and provide targeted data support for subsequent functional correction and optimization. Finally, in step S24, the functional test balance point is corrected for the identified abnormal data of the scene function execution. This process ensures the coordination and balance between different functions, so that user needs can be better met in practical applications. Through the above series of steps, the functions of smart beds will be more stable and the user experience will be significantly improved, thereby enhancing the market competitiveness of the product.

[0022] Preferably, step S24 includes the following steps:

[0023] Step S241: extracting the test sleep posture from the scene function execution abnormal data to obtain the test scene sleep posture data;

[0024] Step S242: evaluating the roll amplitude of limb joint nodes on the sleep posture data of the test scene to obtain roll amplitude data of the joint nodes;

[0025] Step S243: performing bed adjustment correction on the abnormal data of scene function execution according to the roll amplitude data of the joint nodes to obtain bed adjustment correction data;

[0026] Step S244: performing a flipping behavior simulation on the sleep posture data of the test scene to obtain sleep test flipping simulation data;

[0027] Step S245: performing pressure change analysis on the sleep posture data of the test scene according to the sleep test flip simulation data to obtain sleep flip pressure change data;

[0028] Step S246: performing mattress pressure feedback correction on the abnormal data of scene function execution according to the sleep turning pressure change data to obtain mattress pressure feedback correction data;

[0029] Step S247: Perform function test balance point correction according to the bed adjustment correction data and the mattress pressure feedback correction data to obtain scene function balance point correction data.

[0030] The present invention first extracts the test sleep posture from the abnormal data of the scene function execution through step S241. This process is to collect the performance data of the user in different sleep postures to provide a basis for subsequent analysis. These posture data will help to gain insight into different sleeping habits and their impact on the functions of the smart bed, so that the design team can conduct in-depth analysis on specific issues. Subsequently, in step S242, the roll amplitude of the limb joint nodes is evaluated for the extracted test scene sleep posture data. This evaluation can determine whether there is improper roll in various parts of the user's body during sleep, and then reveal the resulting comfort problems, providing a scientific basis for the adjustment design of the smart bed. In step S243, the bed adjustment is corrected according to the roll amplitude data of the joint nodes. The purpose of this link is to adjust the structure or function of the smart bed to ensure that it can better adapt to different sleep postures and improve the comfort level of the user. In step S244, by simulating the flipping behavior of the test scene sleep posture data, the design team can observe and record the dynamic performance of the user when turning over, which is very important for optimizing the mattress design and hardness configuration. Next, step S245 uses the sleep test flip simulation data to perform pressure change analysis, which will reveal how the mattress contacts the user's body in different turning over scenarios, thereby judging its support and comfort. Subsequently, in step S246, the abnormal data of the scene function execution is corrected for mattress pressure feedback based on the sleep flip pressure change data to ensure that the smart bed can sense and adjust its support status in real time during use. This process is an important part of realizing the dynamic adjustment of the smart bed. Finally, in step S247, the functional test balance point is corrected based on the comprehensive bed adjustment correction data and the mattress pressure feedback correction data. This step ensures that when the user actually uses it, the various functions of the smart bed can be properly and balanced, thereby maximizing the user's comfort and overall sleep quality. Through these orderly correction steps, the smart bed will be able to achieve more efficient and intelligent function optimization, providing users with a more humane sleep solution.

[0031] Preferably, performing bed adjustment correction on abnormal data of scene function execution according to the roll amplitude data of the joint nodes comprises the following steps:

[0032] According to the roll amplitude data of the joint nodes, the abnormal tilt angles of the beds in different joint node areas are extracted from the abnormal data of the scene function execution to obtain the abnormal tilt angle data of the beds;

[0033] According to the abnormal bed tilt angle data, the center of gravity offset angles of different joint node areas are calculated for the joint node roll amplitude data to obtain the joint area center of gravity offset angle data;

[0034] Calculate the pressure distribution of the center of gravity offset angle data of the joint area to obtain the center of gravity offset pressure distribution data;

[0035] The abnormal inclination angle data of the bed is corrected by bed adjustment according to the center of gravity offset angle data of the joint area and the center of gravity offset pressure distribution data to obtain bed adjustment correction data.

[0036] In the process of adjusting and correcting the bed body according to the abnormal data of the scene function execution based on the tilt amplitude data of the joint nodes, the present invention first needs to extract the abnormal tilt angle of the bed in different joint node areas. This process is crucial because it can accurately identify the tilt relationship between various parts of the body and the bed surface when using the smart bed. This precise extraction method will provide necessary data support for subsequent adjustment operations, so that the adjustment can be optimized for the user's body posture in actual use. In the next step, the center of gravity offset angle of different joint node areas is calculated through the abnormal tilt angle data of the bed. This step can help understand the balance state of each joint of the human body on the bed surface under abnormal tilt conditions, thereby identifying potential sources of discomfort. Subsequently, the pressure distribution is calculated for the center of gravity offset angle data of the joint area. This step is crucial because it can reveal the pressure distribution caused by the center of gravity offset and provide data basis for judging the physical discomfort felt by the user. Finally, the abnormal tilt angle of the bed is adjusted and corrected according to the center of gravity offset angle data of the joint area and the corresponding center of gravity offset pressure distribution data. The purpose of this link is to ensure that the smart bed can autonomously adapt to the user's body characteristics and posture during design, thereby achieving dynamic adjustment. By comprehensively considering the inclination and pressure of different joint areas, the smart bed can provide more accurate adjustments, greatly improving the user's sleeping comfort. In summary, this series of correction steps not only enhances the intelligent control capabilities of the smart bed, but also effectively improves the user experience, ensuring that it can be supported and comfortable in all kinds of sleeping postures.

[0037] Preferably, performing mattress pressure feedback correction on abnormal data of scene function execution according to sleep turning pressure change data comprises the following steps:

[0038] Extracting mattress function execution abnormal feedback data under different flipping pressure changes from the scene function execution abnormal data according to the sleep flipping pressure change data, and obtaining mattress function execution abnormal feedback data;

[0039] Performing periodic change analysis on sleep turning pressure change data to obtain turning pressure periodic change data;

[0040] Performing attitude pressure distribution difference analysis on the periodic change data of the rollover pressure to obtain attitude pressure distribution difference data;

[0041] Get the elastic modulus data of the mattress material;

[0042] Calculate the elastic memory recovery capacity of the material based on the elastic modulus data of the mattress material according to the posture pressure distribution difference data, and obtain the elastic memory recovery capacity data of the material;

[0043] The support balance force of the mattress contact surface is calculated according to the posture pressure distribution difference data and the material elastic memory recovery capacity data to obtain the support balance force data of the mattress contact surface;

[0044] The mattress pressure feedback correction of the abnormal feedback data is performed on the mattress function according to the mattress contact surface support balance force data to obtain the mattress pressure feedback correction data.

[0045] The process of the present invention for mattress pressure feedback correction based on sleep turning pressure change data is divided into multiple key steps to ensure that the smart mattress can adapt to the needs of users in real time and provide the best support and comfort. First, by extracting the abnormal feedback data of the mattress function execution under different turning pressure changes, the necessary basic data is provided for subsequent correction. The core of this step is to identify the abnormalities exhibited by the mattress when turning over, and then provide guidance for the improvement of the overall design. Next, the periodic change analysis of the turning pressure change data is performed to obtain the periodic change data of the turning pressure. This analysis can reveal the pressure change pattern applied to the mattress when the user turns over in different time periods, and help understand the relationship between the user's turning behavior and the performance of the mattress. The subsequent step is to perform posture pressure distribution difference analysis on the turning pressure periodic change data, so as to obtain posture pressure distribution difference data. This step is crucial to understanding the pressure distribution of users in different sleeping postures, and can identify the pressure concentration area that causes discomfort. Subsequently, the elastic modulus data of the mattress material is obtained to evaluate the performance characteristics of the mattress material. Combined with the posture pressure distribution difference data, the elastic memory recovery ability data of the mattress material is calculated. This calculation will help us understand whether the mattress can quickly return to its original shape after pressure is applied, which in turn affects the user's comfort. Furthermore, based on the posture pressure distribution difference data and the material elastic memory recovery ability data, the mattress contact surface support balance force is calculated to obtain the mattress contact surface support balance force data. This step ensures that the mattress can maintain good support and balance when the user turns over or changes posture. Finally, based on the mattress contact surface support balance force data, the mattress function execution abnormal feedback data is corrected for mattress pressure feedback, and finally the mattress pressure feedback correction data is obtained. This series of fine correction steps enables the mattress to be adjusted in time during dynamic use, providing users with personalized support and comfort experience, and significantly improving the functionality and user satisfaction of the smart mattress. Through the systematic analysis and correction of the above steps, the smart mattress can effectively solve various problems that arise during use and achieve the best use effect.

[0046] Preferably, calculating the material elastic memory recovery capacity of the mattress material elastic modulus data according to the posture pressure distribution difference data includes the following steps:

[0047] According to the posture pressure distribution difference data, the mattress material elastic modulus data is used to distribute the mattress deformation depression degree in different pressure distribution areas to obtain the mattress deformation depression degree data;

[0048] According to the mattress deformation depression degree data, the deformation stability of the mattress material elastic modulus data is evaluated to obtain the material elastic deformation stability data;

[0049] According to the mattress deformation depression degree data and the material elastic deformation stability data, the rebound attenuation simulation is performed to obtain the mattress rebound attenuation simulation data;

[0050] The material elastic memory recovery capacity is calculated based on the material elastic deformation stability data and the mattress rebound attenuation simulation data to obtain the material elastic memory recovery capacity data.

[0051] The process of calculating the elastic memory recovery capacity of the material elastic modulus of the mattress according to the posture pressure distribution difference data of the present invention covers multiple important steps to ensure the comfort and support of the mattress during use. First, by analyzing the posture pressure distribution difference data, the degree of deformation depression of the mattress in different pressure distribution areas can be identified. This data reveals the degree of deformation of the mattress in a specific area by monitoring the pressure applied by the user in different sleeping postures. This analysis result provides a basis for subsequent deformation evaluation and helps designers understand the performance of the mattress under load-bearing conditions. After obtaining the mattress deformation depression degree data, the next step is to evaluate the deformation stability of the mattress material elastic modulus. This evaluation aims to determine the ability of the mattress to maintain its support and shape after undergoing a certain deformation. The stability data not only reflects the performance of the material, but also provides an important basis for understanding the durability of the mattress in long-term use. This information is of guiding significance for improving mattress design and material selection, ensuring that users can still get good support under multiple turns and different postures. Next, based on the mattress deformation depression degree data and the material elastic deformation stability data, a rebound attenuation simulation is performed. This step simulates the mattress's ability to recover after the pressure is released, and evaluates its attenuation characteristics by observing the mattress's rebound process. This simulation data is crucial to understanding the comfort and support of the mattress during use, and can reveal the recovery efficiency of the material after experiencing pressure. Finally, the material's elastic memory recovery capacity is calculated by combining the material's elastic deformation stability data and the mattress's rebound attenuation simulation data. This calculation can provide information about the memory effect and recovery ability of the mattress material in long-term use. This series of analyses and calculations not only improves the accuracy of the mattress's performance evaluation, but also ensures the comfort and adaptability of the final product in actual use, bringing users a better sleeping experience. Through these steps, designers and manufacturers can better optimize mattress materials and improve the market competitiveness and user satisfaction of their products.

[0052] Preferably, step S3 comprises the following steps:

[0053] Step S31: normalizing the scene function balance point correction data to obtain scene function balance correction normalized data;

[0054] Step S32: Designing a parameterized simulation model according to the scene function balance correction normalization data to obtain a smart bed scene parameterized simulation model;

[0055] Step S33: Perform dynamic adaptive logic optimization on the smart bed scene parameterized simulation model to obtain a smart bed scene parameter logic optimization model.

[0056] The design and implementation of step S3 of the present invention is intended to improve the balance and adaptability of the smart bed in different usage scenarios. First, step S31 normalizes the scene function balance point correction data, aiming to convert data of different scales and units into a unified standard to obtain scene function balance correction normalized data. This processing step is necessary because the original data has large differences due to measurement methods or environmental factors. Through normalization, the deviation between the data can be eliminated, making subsequent analysis and modeling more reliable and accurate. The normalized data will provide a solid foundation for the construction of the parametric simulation model and ensure the effectiveness of the model. Next, in step S32, a parametric simulation model design is performed based on the scene function balance correction normalized data to create a smart bed scene parametric simulation model. The model simulates the behavior and reaction of the smart bed in different usage environments and scenarios by introducing key parameters and variables. The goal of this stage is to enhance the flexibility of the model through parametric design so that it can adapt to a variety of user needs and usage scenarios. Through the creation of the simulation model, the performance and function realization of the mattress can be deeply analyzed, thereby providing data support and theoretical basis for subsequent practical applications. Finally, step S33 performs dynamic adaptive logic optimization on the smart bed scene parameterized simulation model to obtain the smart bed scene parameter logic optimization model. This process focuses on how to make the model self-adjust and optimize according to real-time feedback and user behavior. Through the introduction of dynamic adaptive logic, the smart bed can evaluate the changes in user needs in real time during use, and quickly make corresponding adjustments to improve the user experience and comfort. Ultimately, these optimizations not only improve the intelligence level of the smart bed, but also enable it to better meet the personalized needs of users in practical applications, ensuring that users can enjoy an ideal sleep experience in different scenarios. Through the interrelationship of these steps, the improvement of the overall design and function will significantly enhance the market competitiveness and user satisfaction of the smart bed.

[0057] Preferably, step S32 includes the following steps:

[0058] Step S321: dividing the scene function balance correction normalized data into a test set and a training set to obtain a scene function balance correction test set and a scene function balance correction training set;

[0059] Step S322: Randomly sample the scene function balance correction training set to obtain a scene function balance sampling training set;

[0060] Step S323: using a random forest algorithm to design an initial parameterized simulation model for the scene function balanced sampling training set to obtain an initial intelligent bed scene parameterized simulation model;

[0061] Step S324: Optimize and test the initial smart bed scene parameterized simulation model according to the scene function balance correction test set to obtain the smart bed scene parameterized simulation model.

[0062] The design of step S32 of the present invention aims to build an efficient and reliable intelligent bed scene parameterized simulation model through a series of precise operations to meet the personalized needs of different users. First, in step S321, the scene function balance correction normalized data is divided into a test set and a training set. This process is crucial because through reasonable division, it can be ensured that the training and testing of the model can be carried out independently on different data sets, thereby improving the generalization ability and authenticity of the model. The training set is used for model learning, while the test set is used to verify the performance of the model on unknown data. This step lays a solid foundation for all subsequent steps. Subsequently, in step S322, the scene function balance correction training set is randomly sampled to obtain a scene function balance sampling training set. This random sampling process is intended to extract representative samples from the training set to ensure that important information is not lost when the data volume is large, while enhancing the robustness and stability of the model. Through random sampling, it is possible to reduce the computational cost while retaining diversity, making the model establishment more efficient and rapid. In step S323, the random forest algorithm is used to design the initial parameterized simulation model for the scene function balance sampling training set. In this process, the introduction of the random forest algorithm enhances the model's complexity processing capability, and through the integration of multiple decision trees, effectively improves the prediction accuracy and classification ability. The construction of the initial parameterized simulation model lays the foundation for subsequent optimization, enabling the model to better adapt to different scene settings in a multidimensional environment. Finally, in step S324, the initial intelligent bed scene parameterized simulation model is optimized and tested according to the scene function balance correction test set. The significance of this step is to ensure that the model not only performs well on the training set, but also performs well in the real scene by comparing with the test set. This optimization test link can adjust and improve the model parameters to make it more effective in practical applications, and finally obtain a more accurate intelligent bed scene parameterized simulation model. The execution of this series of steps not only improves the efficiency of model construction, but also optimizes the performance of the final product, ensuring its competitiveness in the market and user satisfaction.

[0063] Preferably, the present invention further provides a parameterized simulation model design system based on a smart bed, which is used to execute the parameterized simulation model design method based on a smart bed as described above. The parameterized simulation model design system based on a smart bed comprises:

[0064] The function test boundary mapping module is used to obtain the function design requirement data of the smart bed; perform internal logic relationship analysis on the function design requirement data of the smart bed to obtain the internal logic relationship data of the function module; perform function test boundary parameter mapping between different function modules according to the internal logic relationship data of the function module to obtain the function test boundary parameters;

[0065] The function test balance point module is used to collect function scenario test data for function test boundary parameters to obtain smart bed function scenario test data; identify scene function execution anomalies on the smart bed function scenario test data to obtain scene function execution anomaly data; perform function test balance point correction on the scene function execution anomaly data to obtain scene function balance point correction data;

[0066] The model design module is used to design a parameterized simulation model for the scene function balance point correction data to obtain a smart bed scene parameter logic optimization model;

[0067] The automated firmware design module is used to perform automated firmware design on the smart bed scene parameter logic optimization model to obtain the smart bed scene parameter logic firmware, and embed the smart bed scene parameter logic firmware into the smart bed control system to perform smart bed parameterized simulation.

[0068] The beneficial effect of the present invention is that the functional design requirement data of the smart bed is first obtained, and an in-depth internal logical relationship analysis is performed on it to clarify the mutual connection and dependency between the functional modules. This process not only helps the design team understand the role of each functional module, but also lays the foundation for subsequent functional testing. By processing the internal logical relationship data of the functional module, the functional test boundary parameter mapping between different functional modules can be effectively performed to ensure that the test covers all relevant functions. Ultimately, this link will help identify the interaction of functions and improve the overall design rationality and testability of the system. Based on the functional test boundary parameters obtained in the previous step, test data collection for the functional scenarios of the smart bed is carried out. These scenario test data will provide an important basis for evaluating the actual application performance of the smart bed. Next, the collected functional scenario test data is anomaly identified. This step aims to find out potential problems in the execution of the scene function and ensure that the smart bed can work normally in a variety of real use scenarios. Finally, by correcting the functional test balance point, it is ensured that the execution effect of the scene function reaches the predetermined goal, thereby improving the stability and reliability of the smart bed function, thereby improving user experience and product satisfaction. This series of steps not only enhances the market competitiveness of the product, but also helps to create a more intelligent sleep management solution. The parametric simulation model is designed for the scene function balance point correction data obtained in the previous step. The core purpose of this process is to build a scene parameter logic optimization model for the smart bed to achieve efficient optimization of the smart bed function. By modeling complex scene functions in a parametric way, the design team can more clearly analyze how each parameter affects the overall performance of the smart bed. This logic optimization model not only provides a theoretical basis for subsequent development, but also helps designers quickly identify and solve potential problems to ensure the best implementation of the function. In complex application scenarios, the logic optimization model can effectively improve the ability to regulate functional parameters and ultimately promote a more balanced and intelligent user experience. Based on the optimized scene parameter logic model of the smart bed, the design of the automated firmware is carried out. Through this step, the designed parameter logic firmware can be embedded into the control system of the smart bed, so that it can automatically perform parametric simulation. This process will enable the smart bed to have more powerful intelligent control capabilities, thereby achieving more precise dynamic adjustment and scene functions that adapt to user needs. Through the design and implementation of automated firmware, the development team can ensure the real-time response and optimal performance of the system, while also reducing the need for human intervention and enhancing the stability and security of the system. To sum up, this series of steps not only improves the performance and intelligence level of smart beds, but also greatly enhances its market competitiveness, providing users with a more convenient and efficient sleep management experience.Therefore, the present invention is an optimization processing of a traditional parametric simulation model design method based on a smart bed, which solves the problems of incomplete model scene testing function and inaccurate testing in the traditional parametric simulation model design method based on a smart bed, improves the overall comprehensiveness of the scene testing function, and enhances the accuracy of the test. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 A schematic diagram of the steps of a parameterized simulation model design method based on an intelligent bed;

[0070] Figure 2 for Figure 1 Detailed implementation steps of step S2 in FIG.

[0071] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0072] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0073] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0074] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0075] To achieve this, please refer to Figure 1 to Figure 2 , a parameterized simulation model design method based on an intelligent bed, the method comprising the following steps:

[0076] Step S1: Acquire the smart bed function design requirement data; perform internal logic relationship analysis on the smart bed function design requirement data to obtain the internal logic relationship data of the function modules; perform function test boundary parameter mapping between different function modules according to the internal logic relationship data of the function modules to obtain the function test boundary parameters;

[0077] Step S2: collecting function scenario test data for function test boundary parameters to obtain smart bed function scenario test data; performing scene function execution abnormality identification on the smart bed function scenario test data to obtain scene function execution abnormality data; performing function test balance point correction on the scene function execution abnormality data to obtain scene function balance point correction data;

[0078] Step S3: Design a parameterized simulation model for the scene function balance point correction data to obtain a smart bed scene parameter logic optimization model;

[0079] Step S4: Automated firmware design is performed on the smart bed scene parameter logic optimization model to obtain the smart bed scene parameter logic firmware, and the smart bed scene parameter logic firmware is embedded into the smart bed control system to perform smart bed parameterized simulation.

[0080] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of a parameterized simulation model design method based on a smart bed of the present invention. In this example, the parameterized simulation model design method based on a smart bed includes the following steps:

[0081] Step S1: Acquire the smart bed function design requirement data; perform internal logic relationship analysis on the smart bed function design requirement data to obtain the internal logic relationship data of the function modules; perform function test boundary parameter mapping between different function modules according to the internal logic relationship data of the function modules to obtain the function test boundary parameters;

[0082] In the embodiment of the present invention, in this step, the functional design demand data of the smart bed is collected by a survey method, including interviews with patients, doctors and nursing staff, to ensure a comprehensive understanding of the needs of all parties. A questionnaire survey method is used to formulate a questionnaire containing specific functions such as comfort, health monitoring, and intelligent adjustment to collect quantitative and qualitative data. The collected data is coded, and the functional requirements are prioritized using the analytic hierarchy process (AHP) to clarify the key functions. When the internal logical relationship analysis of the demand data is performed, a cause-and-effect relationship diagram is constructed to clarify the mutual influence between the functions. The "internal logical relationship data of the functional module" is sorted out using a graphical tool to provide a basis for subsequent module design. According to this data, parameter mapping is performed between different functional modules, and the "functional test boundary parameters" are formed in combination with the logical relationship between the modules to ensure that the interaction of each module meets the original design intention. According to the internal logical relationship data of the functional module, the functional test boundary parameter mapping between different functional modules is implemented. This process uses the boundary value analysis method and the equivalence class partitioning method. First, the input and output parameters of each functional module are determined, and then each functional module is tested to find out the performance of its function under boundary conditions to ensure that the functional module can operate normally under different conditions. For different functions of the smart bed (such as intelligent adjustment, environmental monitoring, etc.), set corresponding boundary parameters, such as temperature adjustment range, upper and lower limits of humidity perception, etc. The test process records the response of all functional modules, analyzes the impact of the interaction between modules, and finally obtains the functional test boundary parameters to provide a basis for the next step of scene test data collection.

[0083] Step S2: collecting function scenario test data for function test boundary parameters to obtain smart bed function scenario test data; performing scene function execution abnormality identification on the smart bed function scenario test data to obtain scene function execution abnormality data; performing function test balance point correction on the scene function execution abnormality data to obtain scene function balance point correction data;

[0084] In the embodiment of the present invention, different functional scenarios are first set, and experimental design methods such as orthogonal design are used for comprehensive testing to ensure the performance of each functional module under different conditions. For each functional scenario, key performance indicators such as reaction time, accuracy, etc. are recorded to form "smart bed functional scenario test data". On this basis, statistical process control (SPC) technology is used to identify abnormalities in the scenario test data, analyze whether there are abnormal values ​​beyond the preset range in the data, and generate "scenario function execution abnormal data". Next, multivariate regression analysis is used to correct the balance point of the functional test and identify the key parameters affecting the function execution by combining abnormal data and normal test results. The "scenario function balance point correction data" is obtained by calculation to provide a scientific basis for subsequent design optimization. After the scene function test data is collected, the scene function execution abnormality identification is implemented. This step uses an anomaly detection algorithm, such as an isolation forest algorithm, to analyze the collected scene function test data and identify data points that are significantly deviated from the normal operating mode. In the specific operation, each test data is input into the isolation forest model, and the abnormal score of each data is calculated, and the data below the set threshold is marked as abnormal. By analyzing these abnormal data, we can find out the potential causes of abnormal function execution, which involve factors such as hardware failure, software logic errors or improper user operation. For the identified abnormal data of scene function execution, the functional test balance point correction is performed. The correction process adopts feedback control theory, and adjusts the parameter settings of each functional module of the smart bed by analyzing the difference between abnormal data and normal data. In the specific implementation, reasonable control targets are set, and parameters are adjusted based on the collected abnormal data, and the PID control algorithm is used to dynamically adjust the functional parameters. For example, if the temperature adjustment function of the smart bed responds too slowly in a specific scenario, its adjustment gain can be adjusted through the PID control algorithm to improve the response speed. After correction, the scene test is performed again to verify whether the adjusted function achieves the expected effect and ensure that the smart bed can operate stably in various scenarios. Finally, all corrected data will be integrated into the control system of the smart bed to achieve more efficient automatic adjustment function.

[0085] Step S3: Design a parameterized simulation model for the scene function balance point correction data to obtain a smart bed scene parameter logic optimization model;

[0086] In an embodiment of the present invention, after the correction data of the scene function balance point is collected, a parameterized simulation model is designed. The process first requires a systematic analysis of the collected correction data to identify the logical relationship between the parameters. Apply system identification theory and select a suitable modeling method, such as a state space model or a transfer function model, to construct a parameterized simulation model. In a specific implementation, the least squares method is used to optimize the model parameters by a data fitting method to minimize the error between the output of the model and the output of the actual test data. The implementation steps include: first, the correction data is divided into a training set and a test set, the training set is used for estimating the model parameters, and the test set is used for verifying the model. The training set is used to construct a parameterized simulation model to extract key parameters, such as the adjustment speed, sensitivity, and stability of the smart bed. After the model is built, the root mean square error (RMSE) is used as the model accuracy evaluation standard by comparing the output of the test set with the model prediction result, and the model parameters are further optimized to achieve higher accuracy. The finally obtained smart bed scene parameter logic optimization model realizes effective prediction of the dynamic response of the smart bed in various usage scenarios.

[0087] Step S4: Automated firmware design is performed on the smart bed scene parameter logic optimization model to obtain the smart bed scene parameter logic firmware, and the smart bed scene parameter logic firmware is embedded into the smart bed control system to perform smart bed parameterized simulation.

[0088] In the embodiment of the present invention, after completing the design of the intelligent bed scene parameter logic optimization model, the automated firmware design is carried out to integrate the optimization model into the intelligent bed control system. The process first converts the algorithm logic of the optimization model into firmware code, using an embedded programming language such as C language or C++ to achieve efficient algorithm execution. The specific implementation steps include: refining the algorithm in the parameterized simulation model into a specific instruction set, including the reading, calculation and response output process of each parameter. In the implementation process, the structure of the designed firmware includes an initialization module, a parameter reading module, a logic control module and a response output module. The initialization module is responsible for the environmental parameter collection when the system starts, and the parameter reading module obtains real-time data from the sensor and passes it to the logic control module. The logic control module calculates the parameters according to the optimization model and adjusts the various functions of the intelligent bed through the control strategy, such as adjusting the hardness of the mattress, the tilt angle and environmental monitoring. The response output module feeds back the adjustment results to the control system to achieve real-time control. After sufficient testing and verification, the intelligent bed scene parameter logic firmware is embedded in the intelligent bed control system to ensure that the intelligent bed can efficiently perform parameterized simulation in actual use.

[0089] Preferably, step S1 comprises the following steps:

[0090] Step S11: Acquire intelligent bed functional design requirement data;

[0091] Step S12: Decomposing the smart bed functional design requirement data into functional modules to obtain smart bed functional module decomposition data;

[0092] Step S13: Analyze the internal logic relationship of the decomposed data of the intelligent bed functional modules to obtain the internal logic relationship data of the functional modules;

[0093] Step S14: mapping the functional test boundary parameters between different functional modules of the intelligent bed functional module decomposition data according to the internal logical relationship data of the functional modules to obtain the functional test boundary parameters.

[0094] In the embodiment of the present invention, firstly, the functional design requirement data of the smart bed are systematically collected through methods such as literature research, user interviews and market surveys. These data include the user's expected functions for the smart bed, the shortcomings of existing products and the industry development trend. Specifically, a questionnaire survey is used to collect information from potential users, covering functional requirements such as sleep monitoring, adjusting the sleep environment, and providing health feedback. By classifying and sorting the collected data, a demand database can be established to ensure that all functional requirements are saved in a structured form, laying the foundation for the subsequent functional module decomposition. In addition, a qualitative analysis method is used to deeply analyze user feedback to identify specific problems encountered by users when using the smart bed, which will be used as key considerations in the design process. Based on the obtained functional design requirement data, the functional decomposition method is used to systematically disassemble the requirements. First, the main functional modules of the smart bed are defined, such as: sleep monitoring module, adjustment control module, user interaction module and data processing module. Then, for each functional module, its specific sub-functions are further identified. For example, the sleep monitoring module can be subdivided into heart rate monitoring, breathing monitoring, sleep stage analysis, etc. During the decomposition process, a top-down approach is adopted to ensure that each sub-function matches the overall requirements and cross-validate when necessary. Finally, the functional modules and their sub-functions are represented in the form of a hierarchical tree structure so that logical relationship analysis and test boundary parameter mapping can be performed in subsequent steps. After the functional module decomposition is completed, the internal logical relationship between each functional module and its sub-function is analyzed by causal analysis. The specific steps include first establishing a dependency matrix between functional modules to clarify which functional modules are independent of each other and which modules have interactive effects. Then, the priority and trigger conditions of each module are determined by logical reasoning. For example, the output data of the sleep monitoring module will affect the decision-making process of the regulation control module. At the same time, the directed graph model in graph theory can be introduced to represent the dependency relationship between functional modules so as to more intuitively understand the logical flow between modules. During the analysis process, the logical relationships and interactions of all modules need to be clearly recorded so that subsequent functional tests and parameter mapping can be effectively designed based on these relationships. Based on the internal logical relationship data of the functional modules obtained in step S13, the mapping of functional test boundary parameters is carried out. First, the input and output parameters of each functional module are determined to clarify which parameters need to be boundary tested. For example, in the sleep monitoring module, the heart rate monitoring range is 60 to 100 beats per minute, and any data outside this range needs special processing. Next, the boundary value analysis method is used to test the input and output parameters of each module to ensure the stability of the system and the accuracy of the function under extreme conditions. By constructing a parameter mapping table, the test boundary conditions of each functional module are listed to ensure that the interface parameters between all functional modules are consistent and effective in actual operation.In addition, specific test standards and expected results are set to subsequently verify the collaborative working capabilities between modules and ultimately achieve efficient functional integration of the smart bed.

[0095] Preferably, step S2 comprises the following steps:

[0096] Step S21: constructing a smart bed simulation test environment according to the functional test boundary parameters to obtain a smart bed simulation test environment;

[0097] Step S22: collecting functional scenario test data for functional test boundary parameters according to the intelligent bed simulation test environment to obtain intelligent bed functional scenario test data;

[0098] Step S23: using a preset function execution specification identification manual to identify scene function execution anomalies on the smart bed function scene test data to obtain scene function execution anomaly data;

[0099] Step S24: performing function test balance point correction on the scene function execution abnormal data to obtain scene function balance point correction data.

[0100] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0101] Step S21: constructing a smart bed simulation test environment according to the functional test boundary parameters to obtain a smart bed simulation test environment;

[0102] In an embodiment of the present invention, the construction of a simulation test environment for a smart bed first requires determining the required test parameters. These parameters include the functional boundaries of the smart bed, such as the bed's lifting height, tilt angle, intensity and mode of the massage function, and environmental factors such as temperature and humidity. The construction process uses sensor data acquisition and environmental simulation equipment to ensure that each functional parameter can be fully simulated in actual operation. First, high-precision sensors are used to monitor the various functions of the bed to provide real-time feedback on its status. Then, combined with computer vision technology, multiple cameras are configured to monitor the environment in real time to ensure that the impact of environmental factors on the functions of the smart bed is accurately recorded. Finally, data fusion technology is used to integrate sensor data with visual data to form a complete simulation test environment for a smart bed. Through these steps, an environment is created that can comprehensively test the various functions of the smart bed, laying the foundation for subsequent functional scenario test data collection.

[0103] Step S22: collecting functional scenario test data for functional test boundary parameters according to the intelligent bed simulation test environment to obtain intelligent bed functional scenario test data;

[0104] In an embodiment of the present invention, after the intelligent bed simulation test environment is constructed, the collection of functional scenario test data begins. First, a specific test scenario is defined, including a static sleep state, a dynamic adjustment state, and a specific environmental stimulus (such as noise or light changes). Using a preset test protocol, the various parameters of the intelligent bed are gradually adjusted, and the corresponding function execution is recorded in each state. Through a real-time monitoring system, the state data of the intelligent bed in each scenario is obtained and stored as time series data to ensure the continuity and integrity of the data. At the same time, data acquisition software is used to automatically record response data during user interaction, such as pressure changes of the mattress, changes in the sleeper's body position, etc. For each test scenario, a statistical analysis method is used to calculate the mean and variance of each function to evaluate the performance of the intelligent bed in different scenarios, and finally a comprehensive functional scenario test data set is formed to provide a basis for subsequent abnormality identification.

[0105] Step S23: using a preset function execution specification identification manual to identify scene function execution anomalies on the smart bed function scene test data to obtain scene function execution anomaly data;

[0106] In an embodiment of the present invention, after the function scenario test data is collected, the scene function execution anomaly identification is performed. This step uses a preset function execution specification identification manual, which lists in detail the standard execution parameters of each function. First, the collected function scenario test data is compared with the standard parameters in the identification manual to identify deviations and anomalies that occur during the test process. To achieve this process, a rule-based anomaly detection algorithm is used to compare the actual value and standard value of each parameter item by item. If the deviation of a parameter is detected to exceed the preset threshold range, it is marked as abnormal data. At the same time, combined with the cluster analysis method in machine learning, the abnormal data is classified to identify abnormal patterns. Finally, all the scene function execution abnormal data are summarized to form a detailed abnormality report to provide a basis for subsequent function correction.

[0107] Step S24: performing function test balance point correction on the scene function execution abnormal data to obtain scene function balance point correction data.

[0108] In an embodiment of the present invention, the function test balance point is corrected for the identified scene function execution abnormal data. First, the distribution characteristics of the abnormal data are analyzed, and the main factors affecting the execution of the smart bed function are determined by regression analysis. Based on these analyses, a correction model is established, which takes into account the relationship between environmental factors and functional parameters. An optimization algorithm, such as a genetic algorithm or a particle swarm optimization algorithm, is used to search for the best function execution parameters so that the adjusted function output can meet the standards in the specification identification manual. In this process, parameter adjustment and function testing need to be performed iteratively for multiple times to ensure that each adjustment can approach the ideal functional state. After sufficient testing and adjustment, the scene function balance point correction data finally obtained will be used for the subsequent optimization of the smart bed function, to achieve the stability and reliability of the smart bed in different scenarios, and to provide guarantee for the final user experience.

[0109] Preferably, step S24 comprises the following steps:

[0110] Step S241: extracting the test sleep posture from the scene function execution abnormal data to obtain the test scene sleep posture data;

[0111] Step S242: evaluating the roll amplitude of limb joint nodes on the sleep posture data of the test scene to obtain roll amplitude data of the joint nodes;

[0112] Step S243: performing bed adjustment correction on the abnormal data of scene function execution according to the roll amplitude data of the joint nodes to obtain bed adjustment correction data;

[0113] Step S244: performing a flipping behavior simulation on the sleep posture data of the test scene to obtain sleep test flipping simulation data;

[0114] Step S245: performing pressure change analysis on the sleep posture data of the test scene according to the sleep test flip simulation data to obtain sleep flip pressure change data;

[0115] Step S246: performing mattress pressure feedback correction on the abnormal data of scene function execution according to the sleep turning pressure change data to obtain mattress pressure feedback correction data;

[0116] Step S247: Perform function test balance point correction according to the bed adjustment correction data and the mattress pressure feedback correction data to obtain scene function balance point correction data.

[0117] In the embodiment of the present invention, the embodiment of testing the extraction of sleep posture adopts a sensor array arranged on the surface of the smart bed to capture the user's sleep posture in real time. In the specific implementation, the sensor works together with the accelerometer and the pressure sensor to monitor different parts of the user's body. The data collected by the sensor is transmitted to the central processing unit for data cleaning and preprocessing to remove noise and outliers. Then, the user's sleep posture is identified from the processed data through the feature extraction algorithm to form a set of structured sleep posture data, including the position, angle and pressure distribution information of each part of the body on the bed. These data provide a basis for the subsequent evaluation of the roll amplitude of the limb joint node. The embodiment of the evaluation of the roll amplitude of the limb joint node utilizes a multidimensional data analysis method, especially based on the principal component analysis (PCA) technology. First, the sleep posture data extracted in step S241 is input into the PCA model and dimensionality reduction is performed to highlight the main features. Then, the roll amplitude of each joint node is evaluated by calculating the relative position change of each joint node at different time points. The roll amplitude data of the joint node is generated by combining the three-dimensional coordinates of the joint position using the geometric distance calculation formula. This data is used to analyze the user's sleep quality and potential physical discomfort. The embodiment of the bed adjustment correction first constructs a correction model based on the roll amplitude data of the joint nodes obtained in step S242. The model is established using a linear regression analysis method to determine the optimal adjustment angle of each joint through the relationship between historical data and the roll amplitude. After the adjustment system receives the calculated target adjustment angle, it physically adjusts the bed through the electric regulator. After the adjustment is completed, the posture data is collected again to verify the adjustment effect to ensure that the joint nodes are restored to the appropriate tilt angle to optimize the user's comfort. The embodiment of the flipping behavior simulation uses dynamic simulation technology. First, based on the user's sleeping posture data in step S241, a model with real physical characteristics is constructed. The model simulates the mechanical behavior of the user during the flipping process, including changes in the center of gravity, friction effects, etc., by analyzing the physical engine. Through multiple simulations, the motion trajectory of each joint node during the flipping process and its related mechanical data are obtained to form the sleep test flipping simulation data. These data provide the necessary basis for pressure change analysis. The embodiment of the pressure change analysis uses finite element analysis (FEA) technology to perform in-depth analysis on the flipping simulation data generated in step S244. In the specific steps, the pressure applied by each joint during the flipping process is combined with the material properties of the mattress to establish a pressure distribution model. Through numerical calculation, the pressure change applied by the mattress to the user during the flipping process is evaluated, and a pressure change graph is drawn. This process can identify the pressure concentration area in the flipping process, providing a basis for the subsequent mattress pressure feedback correction. The embodiment of the mattress pressure feedback correction relies on feedback control theory, and combines the pressure change data obtained in step S245 to construct an adaptive control model.This model dynamically adjusts the pressure of the mattress by monitoring the pressure distribution on the mattress in real time and using the proportional-integral-differential (PID) control algorithm. Specifically, the system adjusts the pressure of the airbag inside the mattress in real time according to the difference between the actual detected pressure value and the ideal pressure value, ensuring that the mattress can provide appropriate support when the user flips over to reduce discomfort and improve sleep quality. The embodiment of the functional test balance point correction combines the bed adjustment correction data and the mattress pressure feedback correction data obtained in the previous steps for comprehensive analysis. First, through cluster analysis, the adjustment data of different users are classified to find the optimal adjustment balance point suitable for different body types. Then, the decision tree algorithm is used to generate an adjustment strategy based on the user's specific feedback and historical data to ensure that the smart bed can always maintain the best support effect in different sleeping postures. Finally, the scene function balance point correction data is output to provide a basis for further optimization and personalized adjustment of the smart bed.

[0118] Preferably, performing bed adjustment correction on abnormal data of scene function execution according to the roll amplitude data of the joint nodes comprises the following steps:

[0119] According to the roll amplitude data of the joint nodes, the abnormal tilt angles of the beds in different joint node areas are extracted from the abnormal data of the scene function execution to obtain the abnormal tilt angle data of the beds;

[0120] According to the abnormal bed tilt angle data, the center of gravity offset angles of different joint node areas are calculated for the joint node roll amplitude data to obtain the joint area center of gravity offset angle data;

[0121] Calculate the pressure distribution of the center of gravity offset angle data of the joint area to obtain the center of gravity offset pressure distribution data;

[0122] The abnormal inclination angle data of the bed is corrected by bed adjustment according to the center of gravity offset angle data of the joint area and the center of gravity offset pressure distribution data to obtain bed adjustment correction data.

[0123] In the embodiment of the present invention, in this step, the roll amplitude data of the joint nodes need to be obtained first, and the data comes from the sensors of the bed. These sensors are arranged at different joint node positions, such as the head, back and legs. The roll amplitude data of each joint node is analyzed, and the standard deviation and mean method are used to judge the tilt state of the bed in each area. By setting a threshold, when the roll amplitude exceeds the threshold, it can be identified as abnormal. Then, according to the identified abnormal data, the abnormal tilt angle of each joint node is calculated. Using the abnormal tilt angle data of the bed, the center of gravity offset angle of the joint area is calculated next. First, the center of gravity position of each joint area is defined, and the center of gravity of each joint area is calculated by the known bed geometry parameters and joint tilt angle, and the plane geometry principle is applied. After obtaining the center of gravity offset angle data of the joint area, the pressure distribution caused by the center of gravity offset is calculated next. First, it is necessary to establish a pressure distribution model between the bed and the contact surface of the human body according to the material properties of the bed and the data of the pressure sensor. By using the finite element analysis method, the pressure distribution equation of the bed at different center of gravity positions is established. The specific steps include dividing the bed into multiple small units, calculating the pressure value of each unit at each center of gravity offset angle, and then finding the pressure distribution of the entire bed. Finally, the bed is adjusted and corrected according to the center of gravity offset angle data and the center of gravity offset pressure distribution data of the joint area. First, a correction algorithm is set, usually using a PID control algorithm, to monitor the status of each joint of the bed in real time. According to the center of gravity offset angle, adjust the angle of each joint of the bed to achieve the center of gravity returning to the ideal position. During the correction process, based on the calculated pressure distribution data, evaluate whether the pressure distribution of each joint after adjustment is reasonable. If the pressure distribution is uneven, continue to fine-tune the angles of each joint until the preset pressure distribution state is reached. Through iterative adjustment, the bed adjustment correction data is finally obtained, and these data are recorded in the system to ensure that the bed can be maintained in the best condition in future use.

[0124] Preferably, performing mattress pressure feedback correction on abnormal data of scene function execution according to sleep turning pressure change data comprises the following steps:

[0125] Extracting mattress function execution abnormal feedback data under different flipping pressure changes from the scene function execution abnormal data according to the sleep flipping pressure change data, and obtaining mattress function execution abnormal feedback data;

[0126] Performing periodic change analysis on sleep turning pressure change data to obtain turning pressure periodic change data;

[0127] Performing attitude pressure distribution difference analysis on the periodic change data of the rollover pressure to obtain attitude pressure distribution difference data;

[0128] Get the elastic modulus data of the mattress material;

[0129] Calculate the elastic memory recovery capacity of the material based on the elastic modulus data of the mattress material according to the posture pressure distribution difference data, and obtain the elastic memory recovery capacity data of the material;

[0130] The support balance force of the mattress contact surface is calculated according to the posture pressure distribution difference data and the material elastic memory recovery capacity data to obtain the support balance force data of the mattress contact surface;

[0131] The mattress pressure feedback correction of the abnormal feedback data is performed on the mattress function according to the mattress contact surface support balance force data to obtain the mattress pressure feedback correction data.

[0132] In the embodiment of the present invention, in this step, according to the sleep flip pressure change data, it is first necessary to extract the abnormal data of the scene function execution. By analyzing the flip pressure change, the pressure distribution under different flip states is determined. The specific operation includes first collecting the pressure data of the user when sleeping on the mattress, and using the sensor to record the pressure change curve during each flip. After the data collection is completed, the signal processing technology is applied, and the low-pass filter is used to eliminate the noise effect to ensure that the data is clear and reliable. Subsequently, the user-defined threshold algorithm is used to determine when the function execution abnormality occurs, and then the relevant feedback data is extracted. This process can effectively identify the fault or uneven support phenomenon of the mattress during the flip process, and provide basic data for subsequent analysis. In this step, the periodic change analysis is performed on the acquired sleep flip pressure change data. First, the pressure change data is analyzed in the frequency domain using Fourier transform to identify the periodic characteristics of the pressure change. The result of Fourier transform can reveal the main frequency component of the pressure change, thereby determining the periodic change characteristics of the pressure during the flip process. In addition, a time domain analysis method, such as an autocorrelation function, is used to further confirm the periodicity of the pressure change, and the mean and standard deviation of the period are calculated to determine the stability of the pressure during the flip process. This analysis can provide an important basis for the stability of mattress performance and lay a data foundation for the subsequent posture pressure distribution difference analysis. In this stage, the posture pressure distribution difference analysis is performed on the pressure data obtained by periodic changes. First, the extracted pressure data is classified according to different postures, and the pressure distribution characteristics under each posture are calculated respectively. The multidimensional pressure data is reduced to two or three dimensions using the principal component analysis (PCA) method to more intuitively observe the changes in pressure distribution. Then, the statistical analysis method is used to calculate the mean, variance and other indicators of the pressure distribution under each posture, and the pressure distribution differences under different postures are compared to form posture pressure distribution difference data. These data can reflect the user's comfort and support in different postures, and provide a necessary basis for the subsequent calculation of the elastic memory recovery ability of the material. When obtaining the elastic modulus data of the mattress material, the physical properties of the mattress material must be determined first. Through laboratory testing, the dynamic mechanical analysis (DMA) technology is used to measure the storage modulus and loss modulus of the mattress material under different frequency and temperature conditions, so as to calculate the elastic modulus of the material. This process involves applying a known stress to the material, measuring its deformation, calculating the stress-strain relationship of the material using Hooke's law, and finally obtaining its elastic modulus. The elastic modulus data obtained in this way can provide the necessary physical parameters for the subsequent calculation of material recovery capacity. When calculating the elastic memory recovery capacity of the mattress material, it is first necessary to combine the posture pressure distribution difference data with the material elastic modulus data. By establishing a formula that reflects the relationship between material stress and strain, combining the actual pressure changes under posture with the material properties, and applying the nonlinear fitting method, the material recovery capacity curve is obtained.This curve can finally obtain the elastic memory recovery capacity data of the material by analyzing the energy loss of the material during compression and relaxation. This step can not only quantify the performance of the material, but also reflect the support effect and comfort changes of the mattress during actual use. When calculating the support balance force of the mattress contact surface, it is necessary to comprehensively use the posture pressure distribution difference data and the material elastic memory recovery capacity data. By establishing a mechanical model and applying the principle of static balance, the pressure distribution of each contact point is weighted averaged to determine the support force on the contact surface. The specific method is to use finite element analysis (FEA) technology to establish a grid model on the mattress contact surface and calculate the balance force distribution under different postures through numerical simulation. At the same time, combined with the recovery capacity of the material, the calculation model is adjusted to reflect the deformation characteristics of the material under pressure to ensure the accuracy of the calculation results. This calculation can provide a quantitative basis for the support performance of the mattress and help improve the design and optimization of the mattress. When performing mattress pressure feedback correction, the mattress contact surface support balance force data obtained in the previous step is first combined with the abnormal feedback data of the mattress function execution. By setting the feedback control algorithm, the pressure distribution of the mattress is adjusted in real time to achieve the correction of uneven support. In specific implementation, the PID control algorithm can be used to dynamically adjust the airbags or mechanical components of the mattress according to the deviation between the current pressure feedback and the set target, ensuring that the mattress can provide uniform support when the user flips over. Finally, the corrected mattress pressure feedback correction data is output to provide users with a more comfortable sleeping experience and improve the overall functionality and adaptability of the smart bed.

[0133] Preferably, calculating the material elastic memory recovery capacity of the mattress material elastic modulus data according to the posture pressure distribution difference data includes the following steps:

[0134] According to the posture pressure distribution difference data, the mattress material elastic modulus data is used to distribute the mattress deformation depression degree in different pressure distribution areas to obtain the mattress deformation depression degree data;

[0135] According to the mattress deformation depression degree data, the deformation stability of the mattress material elastic modulus data is evaluated to obtain the material elastic deformation stability data;

[0136] According to the mattress deformation depression degree data and the material elastic deformation stability data, the rebound attenuation simulation is performed to obtain the mattress rebound attenuation simulation data;

[0137] The material elastic memory recovery capacity is calculated based on the material elastic deformation stability data and the mattress rebound attenuation simulation data to obtain the material elastic memory recovery capacity data.

[0138] In an embodiment of the present invention, first, according to the posture pressure distribution difference data, the pressure on the mattress surface is monitored using sensor technology to obtain pressure data in different areas. In specific implementation, multiple pressure sensors are evenly arranged on the mattress surface to record the pressure distribution under different weights and postures. Subsequently, the obtained pressure data is normalized to eliminate the influence between different individuals and obtain a standardized pressure distribution map. Using the relationship between pressure and deformation, the relevant formulas in elastic mechanics (such as Hooke's law) are used to calculate the deformation depression degree of the mattress according to the pressure in different areas. This process involves an interpolation algorithm, such as bilinear interpolation, to improve the spatial resolution of the deformation data, and finally generate a two-dimensional or three-dimensional distribution map of the mattress deformation depression degree. After obtaining the deformation depression degree data of the mattress, the elastic deformation stability of the material is evaluated. In specific implementation, a dynamic load test method is used to simulate the influence of different weights and dynamic postures on the mattress. By applying different pressure distribution patterns and recording the mattress deformation after each application, the difference between it and the initial state is compared. Then, the time series analysis method is used to evaluate the resilience and stability of the deformation. The difference between the maximum and minimum deformations is calculated, and the stability of the mattress material during multiple loading and unloading processes is evaluated by combining material properties such as Poisson's ratio and elastic modulus. The obtained deformation data is used to construct stability indicators, such as the deformation recovery rate (RecoveryRate), to quantify the deformation stability of the mattress. According to the obtained mattress deformation depression degree data and the material elastic deformation stability data, the rebound attenuation simulation is performed. In the specific implementation, the numerical simulation technology is used to establish the dynamic model of the mattress under different pressures and deformations, and the finite element analysis (FEA) method is used to simulate the rebound process of the mattress. After setting the initial deformation state and applying the simulated pressure, the rebound process of the mattress is observed and its deformation data changing with time is recorded. The exponential decay model is used to fit the rebound process, and the rebound attenuation coefficient is calculated. It is combined with the deformation stability data to obtain the rebound attenuation simulation data of the mattress after multiple uses, forming a complete rebound characteristic curve. After obtaining the material elastic deformation stability data and the mattress rebound attenuation simulation data, the elastic memory recovery capacity of the material is calculated. In the specific implementation, the weighted average method is used to calculate the comprehensive recovery capacity by combining the rebound attenuation coefficient and deformation recovery rate obtained in the previous steps. First, the memory recovery capacity index formula is set, the rebound attenuation coefficient and the deformation recovery rate are weightedly combined, and the elastic modulus of the material is considered to obtain a comprehensive memory recovery capacity index. Then, through the test data under different pressures and deformations, a linear regression analysis method is used to establish a relationship model between recovery capacity and external pressure, thereby obtaining the memory recovery capacity data of the mattress during use. This data will provide a theoretical basis for the optimal design of mattress materials.

[0139] Preferably, step S3 comprises the following steps:

[0140] Step S31: normalizing the scene function balance point correction data to obtain scene function balance correction normalized data;

[0141] Step S32: Designing a parameterized simulation model according to the scene function balance correction normalization data to obtain a smart bed scene parameterized simulation model;

[0142] Step S33: Perform dynamic adaptive logic optimization on the smart bed scene parameterized simulation model to obtain a smart bed scene parameter logic optimization model.

[0143] In an embodiment of the present invention, in step S31, the correction data of the scene function balance point is first collected, including the user's physiological parameters (such as weight, height, heart rate, etc.) and environmental parameters (such as room temperature, humidity, noise, etc.). These data are normalized to eliminate the influence of different dimensions on data analysis. The specific method is to use Min-Max Normalization to convert each data item to the [0,1] interval. In this process, the maximum and minimum values ​​of each feature in the data set are first determined, and then the above conversion is performed on each data point. The normalized data will be used for the subsequent parametric simulation model design to ensure that each feature is compared on the same scale to avoid model deviation caused by dimensional differences. In step S32, the parametric simulation model is designed based on the normalized scene function balance correction data. In this step, the model is established using the multivariate linear regression method. First, the relationship between the response variable (such as the user's comfort score) and the independent variable (such as weight, room temperature, mattress hardness, etc.) is determined. In step S33, the designed smart bed scene parametric simulation model is dynamically adaptively logically optimized. The genetic algorithm (GA) is used to optimize the model. First, the fitness function is defined, which evaluates the performance of the model based on user feedback and comfort scores. The new generation of model parameters is generated through selection, crossover and mutation operations.

[0144] Preferably, step S32 includes the following steps:

[0145] Step S321: dividing the scene function balance correction normalized data into a test set and a training set to obtain a scene function balance correction test set and a scene function balance correction training set;

[0146] Step S322: Randomly sample the scene function balance correction training set to obtain a scene function balance sampling training set;

[0147] Step S323: using a random forest algorithm to design an initial parameterized simulation model for the scene function balanced sampling training set to obtain an initial intelligent bed scene parameterized simulation model;

[0148] Step S324: Optimize and test the initial smart bed scene parameterized simulation model according to the scene function balance correction test set to obtain the smart bed scene parameterized simulation model.

[0149] In an embodiment of the present invention, in the process of processing the scene function balance correction normalization data, it is first necessary to divide the data set into a training set and a test set. In the specific implementation process, the scene function balance correction normalization data is first preprocessed to ensure the integrity and accuracy of the data. Next, a random partitioning method is used to divide the data into a training set at a ratio of 80% and a test set at a ratio of 20%. In order to ensure the representativeness of the data, a stratified sampling method is used to ensure that the data ratio of each category in the training set and the test set is the same as the overall data. This process can ensure the effectiveness of the training model and the reliability of the test model. After completing the division of the training set, the scene function balance correction training set is randomly sampled to generate a scene function balance sampling training set. In the specific implementation, a sampling method without replacement is used to randomly select 70% of the samples from the training set to construct a new training set. This process generates a random number index from the training set by implementing a simple random number generation algorithm, and selects samples accordingly. This method can effectively reduce the size of the training set and reduce the computational complexity, while maintaining the diversity and representativeness of the samples, thereby helping to improve the training efficiency of the model. After obtaining the scene function balanced sampling training set, the random forest algorithm is used to design the initial parameterized simulation model for the training set. In the specific implementation, the feature variables and target variables are first defined. Then, multiple decision trees are constructed by setting hyperparameters such as the number of trees and the maximum depth of the random forest. Each decision tree forms a powerful integrated learning model by randomly sampling and feature selection on the training set. The model training process involves calculating the information gain of each feature and dividing it on the nodes of the tree. Finally, the output of the initial intelligent bed scene parameterized simulation model is obtained by voting on the results of these decision trees. This model can more accurately reflect the multi-dimensional scene requirements of the intelligent bed. After the initial intelligent bed scene parameterized simulation model is constructed, the model needs to be optimized and tested according to the scene function balance correction test set. In the implementation process, the test set is first input into the initial model for prediction, and the performance of the model on the test set is recorded, including evaluation indicators such as accuracy, recall rate and F1 score. Next, the model error is analyzed to identify the shortcomings of the model in specific scenarios, such as overfitting or underfitting. To this end, a cross-validation method can be used to optimize the model's hyperparameters by training and testing the training set multiple times. After the model is optimized, the model's performance on the test set is re-evaluated to obtain the final intelligent bed scenario parameterized simulation model. This process ensures that the model's performance can meet the expected results in actual applications and improves the functional adaptability and scenario responsiveness of the intelligent bed.

[0150] Preferably, the present invention further provides a parameterized simulation model design system based on a smart bed, which is used to execute the parameterized simulation model design method based on a smart bed as described above. The parameterized simulation model design system based on a smart bed comprises:

[0151] The function test boundary mapping module is used to obtain the function design requirement data of the smart bed; perform internal logic relationship analysis on the function design requirement data of the smart bed to obtain the internal logic relationship data of the function module; perform function test boundary parameter mapping between different function modules according to the internal logic relationship data of the function module to obtain the function test boundary parameters;

[0152] The function test balance point module is used to collect function scenario test data for function test boundary parameters to obtain smart bed function scenario test data; identify scene function execution anomalies on the smart bed function scenario test data to obtain scene function execution anomaly data; perform function test balance point correction on the scene function execution anomaly data to obtain scene function balance point correction data;

[0153] The model design module is used to design a parameterized simulation model for the scene function balance point correction data to obtain a smart bed scene parameter logic optimization model;

[0154] The automated firmware design module is used to perform automated firmware design on the smart bed scene parameter logic optimization model to obtain the smart bed scene parameter logic firmware, and embed the smart bed scene parameter logic firmware into the smart bed control system to perform smart bed parameterized simulation.

[0155] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0156] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A parametric simulation model design method based on an intelligent bed, characterized in that: The following steps are involved: Step S1: Acquire the functional design requirement data of the smart bed; perform internal logic relationship analysis on the functional design requirement data of the smart bed to obtain the internal logic relationship data of the functional module; Mapping the functional test boundary parameters between different functional modules according to the internal logical relationship data of the functional modules to obtain the functional test boundary parameters; Step S2: collecting function scenario test data for the function test boundary parameters to obtain smart bed function scenario test data; performing scene function execution abnormality identification on the smart bed function scenario test data to obtain scene function execution abnormality data; Performing function test balance point correction on the scene function execution abnormal data to obtain scene function balance point correction data; wherein step S2 includes: Step S21: constructing a smart bed simulation test environment according to the functional test boundary parameters to obtain a smart bed simulation test environment; Step S22: collecting functional scenario test data for functional test boundary parameters according to the intelligent bed simulation test environment to obtain intelligent bed functional scenario test data; Step S23: using a preset function execution specification identification manual to identify scene function execution anomalies on the smart bed function scene test data to obtain scene function execution anomaly data; Step S24: performing function test balance point correction on the scene function execution abnormal data to obtain scene function balance point correction data; wherein step S24 includes: Step S241: extracting the test sleep posture from the scene function execution abnormal data to obtain the test scene sleep posture data; Step S242: evaluating the roll amplitude of limb joint nodes on the sleep posture data of the test scene to obtain roll amplitude data of the joint nodes; Step S243: performing bed adjustment correction on the abnormal data of scene function execution according to the roll amplitude data of the joint nodes to obtain bed adjustment correction data; Step S244: performing a flipping behavior simulation on the sleep posture data of the test scene to obtain sleep test flipping simulation data; Step S245: performing pressure change analysis on the sleep posture data of the test scene according to the sleep test flip simulation data to obtain sleep flip pressure change data; Step S246: performing mattress pressure feedback correction on the abnormal data of scene function execution according to the sleep turning pressure change data to obtain mattress pressure feedback correction data; Step S247: performing function test balance point correction according to the bed adjustment correction data and the mattress pressure feedback correction data to obtain scene function balance point correction data; Step S3: Design a parameterized simulation model for the scene function balance point correction data to obtain a smart bed scene parameter logic optimization model; Step S4: Automated firmware design is performed on the smart bed scene parameter logic optimization model to obtain the smart bed scene parameter logic firmware, and the smart bed scene parameter logic firmware is embedded into the smart bed control system to perform smart bed parameterized simulation.

2. The parameterized simulation model design method based on the intelligent bed according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire intelligent bed functional design requirement data; Step S12: Decomposing the smart bed functional design requirement data into functional modules to obtain smart bed functional module decomposition data; Step S13: Analyze the internal logic relationship of the decomposed data of the intelligent bed functional modules to obtain the internal logic relationship data of the functional modules; Step S14: mapping the functional test boundary parameters between different functional modules of the intelligent bed functional module decomposition data according to the internal logical relationship data of the functional modules to obtain the functional test boundary parameters.

3. The parameterized simulation model design method based on the smart bed according to claim 1, characterized in that: Correcting the abnormal data of the scene function according to the roll amplitude data of the joint nodes includes the following steps: According to the roll amplitude data of the joint nodes, the abnormal tilt angles of the beds in different joint node areas are extracted from the abnormal data of the scene function execution to obtain the abnormal tilt angle data of the beds; According to the abnormal bed tilt angle data, the center of gravity offset angles of different joint node areas are calculated for the joint node roll amplitude data to obtain the joint area center of gravity offset angle data; Calculate the pressure distribution of the center of gravity offset angle data of the joint area to obtain the center of gravity offset pressure distribution data; The abnormal inclination angle data of the bed is corrected by bed adjustment according to the center of gravity offset angle data of the joint area and the center of gravity offset pressure distribution data to obtain bed adjustment correction data.

4. The parameterized simulation model design method based on the intelligent bed according to claim 1 is characterized in that: The mattress pressure feedback correction for abnormal data of the scene function according to the sleep turning pressure change data includes the following steps: Extracting mattress function execution abnormal feedback data under different flipping pressure changes from the scene function execution abnormal data according to the sleep flipping pressure change data, and obtaining mattress function execution abnormal feedback data; Performing periodic change analysis on sleep turning pressure change data to obtain turning pressure periodic change data; Performing attitude pressure distribution difference analysis on the periodic change data of the rollover pressure to obtain attitude pressure distribution difference data; Get the elastic modulus data of the mattress material; Calculate the elastic memory recovery capacity of the material based on the elastic modulus data of the mattress material according to the posture pressure distribution difference data, and obtain the elastic memory recovery capacity data of the material; The support balance force of the mattress contact surface is calculated according to the posture pressure distribution difference data and the material elastic memory recovery capacity data to obtain the support balance force data of the mattress contact surface; The mattress pressure feedback correction of the abnormal feedback data is performed on the mattress function according to the mattress contact surface support balance force data to obtain the mattress pressure feedback correction data.

5. The parameterized simulation model design method based on the intelligent bed according to claim 4 is characterized in that: Calculating the material elastic memory recovery capacity of the mattress material elastic modulus data according to the posture pressure distribution difference data includes the following steps: According to the posture pressure distribution difference data, the mattress material elastic modulus data is used to distribute the mattress deformation depression degree in different pressure distribution areas to obtain the mattress deformation depression degree data; According to the mattress deformation depression degree data, the deformation stability of the mattress material elastic modulus data is evaluated to obtain the material elastic deformation stability data; According to the mattress deformation depression degree data and the material elastic deformation stability data, the rebound attenuation simulation is performed to obtain the mattress rebound attenuation simulation data; The material elastic memory recovery capacity is calculated based on the material elastic deformation stability data and the mattress rebound attenuation simulation data to obtain the material elastic memory recovery capacity data.

6. The method for designing a parameterized simulation model based on an intelligent bed according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: normalizing the scene function balance point correction data to obtain scene function balance correction normalized data; Step S32: Designing a parameterized simulation model according to the scene function balance correction normalization data to obtain a smart bed scene parameterized simulation model; Step S33: Perform dynamic adaptive logic optimization on the smart bed scene parameterized simulation model to obtain a smart bed scene parameter logic optimization model.

7. The method for designing a parameterized simulation model based on an intelligent bed according to claim 6, characterized in that: Step S32 The following steps are involved: Step S321: dividing the scene function balance correction normalized data into a test set and a training set to obtain a scene function balance correction test set and a scene function balance correction training set; Step S322: Randomly sample the scene function balance correction training set to obtain a scene function balance sampling training set; Step S323: using a random forest algorithm to design an initial parameterized simulation model for the scene function balanced sampling training set to obtain an initial intelligent bed scene parameterized simulation model; Step S324: Optimize and test the initial smart bed scene parameterized simulation model according to the scene function balance correction test set to obtain the smart bed scene parameterized simulation model.

8. A parametric simulation model design system based on an intelligent bed, characterized in that: Used to execute the parameterized simulation model design method based on the smart bed as claimed in claim 1, the parameterized simulation model design system based on the smart bed comprises: The function test boundary mapping module is used to obtain the function design requirement data of the smart bed; perform internal logic relationship analysis on the function design requirement data of the smart bed to obtain the internal logic relationship data of the function module; perform function test boundary parameter mapping between different function modules according to the internal logic relationship data of the function module to obtain the function test boundary parameters; The function test balance point module is used to collect function scenario test data for function test boundary parameters to obtain smart bed function scenario test data; identify scene function execution anomalies on the smart bed function scenario test data to obtain scene function execution anomaly data; perform function test balance point correction on the scene function execution anomaly data to obtain scene function balance point correction data; The model design module is used to design a parameterized simulation model for the scene function balance point correction data to obtain a smart bed scene parameter logic optimization model; The automated firmware design module is used to perform automated firmware design on the smart bed scene parameter logic optimization model to obtain the smart bed scene parameter logic firmware, and embed the smart bed scene parameter logic firmware into the smart bed control system to perform smart bed parameterized simulation.

Images