A method, system and device based on intelligent vital sign monitoring control

Abstract

The present invention relates to the field of monitoring and control technology, and in particular to a method, system and device based on intelligent vital sign monitoring and control. The method comprises the following steps: by acquiring the pressure and heart rate sensor data of the device, defining the baseline pressure data, and integrating the pressure data to obtain the deformation state of the device; using the deformation state data to identify the spinal posture and estimate the spinal fatigue adjustment time; inferring the user's behavior pattern based on the heart rate data and estimating the behavior time; combining the spinal fatigue adjustment time and the user's behavior time, analyzing and generating the device early warning vibration time data, and transmitting it to the electrical control unit to perform the timed vibration task; finally, acquiring the real-time pressure data after vibration, performing spinal posture identification, analyzing the posture correction strategy, and transmitting it to the electrical control unit for torsion spring elastic control. The present invention can improve the accuracy and authenticity of the user's sitting posture vital sign monitoring.

Description

Technical Field

[0001] The present invention relates to the field of monitoring and control technology, and in particular to a method, system and device based on intelligent vital sign monitoring and control. Background Art

[0002] In order to solve the adverse effects of long-term bad sitting posture of modern people, many researchers and enterprises have begun to pay attention to the development and application of sitting assistive devices. These devices are designed to improve the user's sitting posture, comfort and work efficiency through external support and guidance. However, there are some significant defects in traditional methods. Most traditional sitting assistive devices rely on static physical support, such as chair backs, cushions and waist protectors. These devices are usually unable to monitor the user's sitting status and physical signs in real time and lack the ability to adjust dynamically. Once the user's sitting posture changes during use, the device cannot respond in time, resulting in unsatisfactory sitting assistance effects. Many traditional methods lack an effective feedback mechanism. Users often find it difficult to perceive changes in their posture during long-term sitting. Although some devices are equipped with reminder functions, it is difficult to effectively attract the user's attention due to the low reminder frequency or too single reminder frequency, resulting in a decrease in the user's dependence on sitting posture monitoring. This lack of interactive design makes it easy for users to ignore the importance of correct sitting posture when using the device, which ultimately affects health and work efficiency. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide a method, system and device based on intelligent vital sign monitoring and control to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a control method based on intelligent vital sign monitoring includes the following steps:

[0005] Step S1: Obtain device pressure sensor data and device heart rate sensor data, and define a device pressure reference according to the device pressure sensor data, thereby obtaining device reference pressure data; integrate the device deformation state of the device pressure sensor data based on the device reference pressure data, thereby obtaining device deformation state data;

[0006] Step S2: recognizing the spinal posture of the device user based on the device deformation state data, thereby obtaining the spinal posture data of the device user, and estimating the spinal fatigue adjustment time of the spinal posture data of the device user, thereby obtaining the spinal fatigue adjustment time data;

[0007] Step S3: inferring the user behavior pattern according to the device heart rate sensor data, thereby obtaining the user behavior pattern data; estimating the user behavior time based on the user behavior pattern data, thereby obtaining the user behavior time data;

[0008] Step S4: analyzing the equipment warning vibration time according to the spinal fatigue adjustment time data and the user behavior time data, thereby obtaining the equipment warning vibration time data, and transmitting it to the electrical control unit to execute the equipment timing warning vibration task;

[0009] Step S5: Acquire real-time device pressure sensor data, and perform real-time device user spinal posture recognition based on the real-time device pressure sensor data, thereby obtaining real-time device user spinal posture data; perform spinal posture correction strategy analysis on the real-time device user spinal posture data based on spinal fatigue trend data, thereby obtaining a posture correction strategy, and transmit it to the electrical control unit to execute the device torsion spring elastic control task.

[0010] The present invention can establish a reference state for the device by acquiring pressure sensing data, and this reference state will help to monitor the changes in the user's sitting posture in the future and provide accurate data reference. The deformation state integration based on the reference pressure data can monitor the changes in sitting posture in real time and timely identify whether the user maintains a good sitting posture. This dynamic monitoring can significantly improve the adaptability and effectiveness of the device. By analyzing the deformation state data of the device, the user's spinal posture can be accurately identified. This data is crucial for adjusting the user's sitting posture and helps to reduce the pressure on the spine and back. By estimating the fatigue adjustment time using the spinal posture data, personalized sitting posture adjustment suggestions can be provided to help users rest or adjust within the best time, thereby improving comfort and reducing fatigue. Inferring the user's behavior pattern based on the heart rate sensor data can provide the device with more information about the user's current state, which is of great significance for adjusting the feedback and reminder mechanism of the device. Estimating the user's behavior time helps the device to provide feedback and prompts in time when the user needs to adjust the sitting posture or take a rest, thereby enhancing the responsiveness of the device. By integrating the spinal fatigue adjustment time data and the user's behavior time data, a reasonable warning vibration time can be set. This warning mechanism can effectively remind users to pay attention to changes in sitting posture and avoid maintaining a bad sitting posture for a long time. The warning information is transmitted to the electrical control unit to achieve timed warning vibration, further enhancing the interactivity of the device and making the user pay more attention to their sitting posture. By obtaining real-time pressure sensing data, the device can continuously monitor the user's sitting posture after the warning vibration. This real-time feedback can prompt and adjust in time when the user's sitting posture changes. According to the spinal fatigue trend data, the corresponding posture correction strategy can be formulated to help users better adjust their sitting posture, reduce spinal pressure, and prevent potential health problems. The posture correction strategy is transmitted to the electrical control unit to perform specific elastic control tasks, further enhancing the functionality of the device and making it more efficient in protecting the user's health. In summary, the above steps construct a sitting posture assistance system that can provide timely feedback and adjustment through dynamic acquisition and real-time analysis of data. Such a design not only improves the device's ability to monitor and adjust the user's sitting posture, but also enhances the user's sense of participation and dependence, thereby more effectively improving the user's sitting posture, improving work efficiency and comfort, and ultimately helping to protect the user's spinal health.

[0011] Optionally, step S1 specifically includes:

[0012] Step S11: Acquire device pressure sensor data and device heart rate sensor data;

[0013] Step S12: performing pressure sensing division according to the device pressure sensing data, thereby obtaining the device torsion spring pressure sensing data and the device interaction pressure sensing data;

[0014] Step S13: Perform Fourier transform on the device torsion spring pressure sensing data to obtain the device torsion spring pressure spectrum, and perform high-frequency torsion spring pressure statistics based on the device torsion spring pressure spectrum to obtain high-frequency torsion spring pressure data; define the torsion spring pressure benchmark based on the high-frequency torsion spring pressure data to obtain the device torsion spring pressure benchmark data;

[0015] Step S14: performing interactive pressure time series analysis on the interactive pressure sensing data of the device to obtain interactive pressure time series data, and performing long-term interactive pressure statistics on the interactive pressure time series data to obtain long-term interactive pressure data; defining an interactive pressure benchmark according to the long-term interactive pressure data to obtain the interactive pressure benchmark data of the device;

[0016] Step S15: performing equipment pressure benchmark integration on the equipment torsion spring pressure benchmark data and the equipment interactive pressure benchmark data, thereby obtaining equipment benchmark pressure data;

[0017] Step S16: integrating the equipment deformation state of the equipment pressure sensing data based on the equipment baseline pressure data, thereby obtaining equipment deformation state data.

[0018] The present invention can timely grasp the working status of the equipment and the physiological status of the user by acquiring pressure sensing and heart rate data in real time, and can provide necessary basic data for subsequent data analysis and processing, which is helpful to form a comprehensive equipment performance evaluation system. By dividing the pressure sensing data into torsion spring pressure and interaction pressure, different types of data can be analyzed in a targeted manner to provide more accurate monitoring and analysis results. Through classification processing, the subsequent analysis steps can be simplified and the efficiency and accuracy of data processing can be improved. Fourier transform can convert time domain data into frequency domain data, help identify and analyze the frequency components of pressure changes, and provide a deep understanding of the equipment status. Through high-frequency torsion spring pressure statistics, the working performance of the equipment under high-frequency conditions can be identified to ensure the reliability of the equipment in complex working environments. Time series analysis can reveal the law of interaction pressure changes over time and identify potential usage patterns or abnormal situations. Statistics of long-term interaction pressure data help to understand the performance change trend of the equipment over a long period of time, and provide a basis for subsequent maintenance and improvement. Integrating the torsion spring compression and interactive compression data to form a comprehensive equipment benchmark compression data is helpful to comprehensively evaluate the working status of the equipment, which provides more reliable basic data support for subsequent decision-making, and helps to optimize equipment design and predict failures. By integrating the benchmark compression data, the deformation state of the equipment can be effectively monitored, potential structural problems can be identified in a timely manner, and the reliability of the equipment under various working conditions can be improved, the failure rate can be reduced, the service life of the equipment can be extended, and the overall performance can be improved.

[0019] Optionally, step S16 is specifically:

[0020] Step S161: Calculating the device pressure offset based on the device pressure sensing data, thereby obtaining the device torsion spring pressure offset and the device interactive pressure offset;

[0021] Step S162: performing compression offset statistics on the torsion spring compression data of the device, thereby obtaining the torsion spring compression data of the high-offset device and the torsion spring compression data of the low-offset device;

[0022] Step S163: performing pressure offset statistics on the device interaction pressure offset, thereby obtaining high-offset device interaction pressure data and low-offset device interaction pressure data;

[0023] Step S164: performing compression time-series correlation on the torsion spring compression data of the high-offset device and the interactive compression data of the high-offset device, thereby obtaining the deformation data of the working state; performing compression time-series correlation on the torsion spring compression data of the low-offset device and the interactive compression data of the low-offset device, thereby obtaining the deformation data of the standby state;

[0024] Step S165: Merge the deformation data of the working state and the deformation data of the standby state to obtain the equipment deformation state data.

[0025] The present invention can accurately understand the pressure state of the device under different working conditions by calculating the offset of the device pressure sensing data based on the device baseline pressure data. This calculation lays the foundation for subsequent performance analysis and helps to discover abnormal pressure changes of the device during use. Statistics on the pressure offset of the device torsion spring can help identify which devices perform under high and low pressure conditions. Devices with high offsets may indicate potential structural defects or material fatigue, while devices with low offsets may indicate that they are in good condition. Through this classification, subsequent maintenance and detection work can be more targeted. Statistics on the interactive pressure offset of the device are equally important because the interaction between the devices will affect the overall performance. By analyzing the interactive data of high offset and low offset, it is possible to identify which device combinations may cause efficiency reduction or failure risks when working, thereby providing data support for the optimal configuration of the device. Time-series correlation of high-offset torsion springs and interactive pressure data can reveal the dynamic behavior of the device under different working conditions. This analysis helps to understand the deformation mode of the device in actual use, and then identify potential fault warning signals. The deformation data in the standby state can be used as a baseline for normal operation to provide a comparative reference for equipment performance monitoring. By combining the deformation data of the working state and the deformation data of the standby state, comprehensive deformation state data of the equipment can be obtained. This data can not only be used to monitor the operating status of the equipment in real time, but also can be used for historical data analysis to optimize equipment design, improve reliability, and reduce maintenance costs. At the same time, the formed data set provides a basis for the subsequent training of machine learning or intelligent prediction algorithms, which helps to realize intelligent equipment management.

[0026] Optionally, step S2 specifically includes:

[0027] Step S21: extracting working state deformation features from the equipment deformation state data, thereby obtaining working state deformation data;

[0028] Step S22: integrating the pressure distribution of the equipment in working state according to the deformation data in working state, thereby obtaining the pressure distribution data of the equipment in working state, and selecting the pressure center of the equipment in working state for the pressure distribution data in working state, thereby obtaining the pressure center data of the equipment in working state;

[0029] Step S23: Calculate the left and right pressure difference of the equipment part based on the pressure distribution data of the equipment working state, so as to obtain the left and right pressure difference data of the equipment part;

[0030] Step S24: recognizing the user's spinal posture according to the device pressure center data in the working state and the left and right pressure difference data of the device parts, thereby obtaining the device user's spinal posture data;

[0031] Step S25: Estimating the spinal fatigue adjustment time based on the device user's spinal posture data, thereby obtaining spinal fatigue adjustment time data.

[0032] The present invention can obtain more accurate and detailed working state deformation data by extracting the features of the equipment deformation state data. These data can reflect the deformation of the equipment in actual use, avoiding errors caused by environmental factors or human factors. Analysis of the deformation characteristics of the equipment can help identify potential performance problems, such as material fatigue, structural damage, etc., which is convenient for early maintenance and optimized design. Integrating the working state deformation data can clearly show the pressure distribution of the equipment during use, which helps to identify which parts are subjected to excessive pressure. This helps to optimize the design of the equipment and reduce local force concentration, thereby improving the durability and safety of the equipment. By selecting the pressure center of the equipment, the pressure point of the user when using the equipment can be accurately grasped, providing basic data for subsequent posture recognition and health analysis. Calculating the pressure difference between the left and right parts of the equipment can effectively identify asymmetric pressure distribution, which is of great significance for detecting whether the user's posture is healthy and whether there is physical discomfort. By analyzing the pressure difference between the left and right parts, personalized usage suggestions can be provided to users to help users adjust their sitting posture or usage habits to reduce potential spinal injury risks. By using the pressure center data and pressure difference data to identify the spinal posture, the user's sitting or standing posture can be monitored in real time, and bad postures can be corrected in time to avoid spinal fatigue and injury. Through the posture recognition system, users can be warned of improper postures to help them develop good sitting and living habits, thereby improving their overall health. By estimating the spinal fatigue adjustment time, users can arrange their work and rest time reasonably, avoid spinal fatigue caused by long-term static postures, and thus improve work efficiency and quality of life. Based on the estimation results, the device can provide users with adjustment suggestions or automatically adjust their postures to improve user comfort and satisfaction.

[0033] Optionally, step S24 is specifically:

[0034] Step S241: calculating the relative position of the user's body center of gravity in the working state according to the data of the pressure center of the device in the working state, thereby obtaining the relative position data of the user's body center of gravity, and dividing the relative position data of the user's body center of gravity according to the position of the body center of gravity in the working state of the device, thereby obtaining the relative position state data of the upper limb center of gravity and the relative position state data of the lower limb center of gravity;

[0035] Step S242: performing pressure difference clustering calculation based on the left and right pressure difference data of the equipment part, so as to obtain the left and right pressure balanced equipment part status data and the left and right pressure uneven equipment part status data;

[0036] Step S243: performing device state intersection operation on the upper limb center of gravity relative position state data and the left and right pressure-balanced device part state data, thereby obtaining the user's spine longitudinal tilt device state data; performing device state intersection operation on the lower limb center of gravity relative position state data and the left and right pressure-balanced device part state data, thereby obtaining the user's spine natural device state data; performing device state intersection operation on the lower limb center of gravity relative position state data and the left and right pressure-uneven device part state data, thereby obtaining the user's spine lateral tilt device state data;

[0037] Step S244: constructing a user spine posture recognition model based on the user spine longitudinal tilt device state data, the user spine natural device state data, and the user spine lateral tilt device state data;

[0038] Step S245: performing device user spine posture recognition on the working state deformation data through the user spine posture recognition model, thereby obtaining device user spine posture data.

[0039] The present invention can obtain more accurate relative position data of the user's center of gravity by calculating the center of gravity of the user through the data of the center of pressure of the device. This is very important for evaluating the balance and stability of the user, especially in scenes such as sports and rehabilitation. The division of the center of gravity of the upper limbs and lower limbs enables the device to perform a more detailed analysis according to the force conditions of different parts of the body, thereby optimizing the design and use of the device. By calculating the pressure difference, the balanced state of the left and right forces of the user on the device can be clearly determined, which helps to timely discover incorrect user postures or device design defects and prevent sports injuries. According to the data of balanced and uneven pressure on the left and right, the device can adjust its working mode to adapt to the needs of different users, thereby improving the comfort of use. Through the intersection operation, the center of gravity state of the upper and lower limbs and the pressure balance are comprehensively considered, and the longitudinal, natural and lateral tilt states of the user's spine can be more comprehensively evaluated. This multi-dimensional evaluation method makes data analysis more accurate and scientific. Based on different spinal status data, personalized posture adjustment suggestions are provided to help users improve their postures and prevent spinal problems. Building a user spinal posture recognition model can realize intelligent analysis of the user's spinal posture and improve the efficiency and accuracy of data processing. The model can be used in a variety of scenarios, including medical health, sports training, rehabilitation therapy, etc., and has strong applicability and practical value. Through the real-time recognition of the user's spinal posture by the model, the user can get feedback in time and adjust the posture at any time. Long-term data accumulation and analysis can help track changes in the user's spinal health and provide a basis for disease prevention.

[0040] Optionally, step S25 is specifically:

[0041] Step S251: integrating the time series distribution of the user's spinal posture according to the device user's spinal posture data, thereby obtaining the user's spinal posture time series data;

[0042] Step S252: performing lateral spinal posture time statistics and longitudinal spinal posture time statistics on the user's spinal posture time series data, thereby obtaining lateral spinal posture time data and longitudinal spinal posture time data, and merging the lateral spinal posture time data and longitudinal spinal posture time data by time period, thereby obtaining bad spinal posture time data;

[0043] Step S253: calculating the time proportion of the user's bad spinal posture on the user's spinal posture time series data according to the bad spinal posture time data, thereby obtaining the user's bad spinal posture time proportion data;

[0044] Step S254: performing spinal fatigue trend analysis based on the user's bad spinal posture time proportion data, thereby obtaining spinal fatigue trend data;

[0045] Step S255: obtaining the spinal fatigue degree rule through the expert experience database, and performing spinal fatigue time threshold statistics according to the spinal fatigue degree rule, thereby obtaining spinal fatigue time threshold data;

[0046] Step S256: Estimate the spinal fatigue adjustment time of the spinal fatigue trend data according to the spinal fatigue time threshold data, thereby obtaining the spinal fatigue adjustment time data.

[0047] The present invention can obtain a more comprehensive user posture performance by integrating the time series data of the user's spinal posture, which is convenient for subsequent analysis. Real-time collection and integration of data helps to timely detect the user's posture changes, ensuring that warnings or guidance can be given when bad postures occur. Through independent statistics of the lateral and longitudinal postures, the user's posture deviation can be analyzed more carefully, and the frequency and duration of specific bad postures can be identified. Time period merging can more effectively identify which postures belong to bad spinal postures, providing data support for subsequent intervention measures. Calculating the time proportion of bad spinal postures can help users and doctors evaluate their posture health status and facilitate the formulation of improvement strategies. Based on the user's posture proportion data, personalized improvement suggestions can be provided to help users optimize their daily activities. Spinal fatigue trend analysis provides dynamic monitoring of the user's spinal health status, which can help users understand the changing trend of their spinal fatigue. Through trend analysis, potential spinal fatigue problems can be identified in time, so as to take preventive measures. Obtaining fatigue degree rules through the expert experience database can achieve standardized evaluation of spinal fatigue, making the analysis results more scientific. The statistical time threshold provides a basis for users to set a reasonable spinal fatigue warning line, helping users to understand when they should rest or adjust their postures. By estimating the fatigue adjustment time, users can clearly know when spinal adjustment or rest is needed, which helps reduce the occurrence of spinal fatigue. The estimated adjustment time also provides a basis for the evaluation of the effectiveness of subsequent improvement measures and can test the effectiveness of the intervention measures taken.

[0048] Optionally, step S3 specifically includes:

[0049] Step S31: performing heart rate fluctuation statistics on the device heart rate sensor data, thereby obtaining the user's short heart rate fluctuation data and the user's long heart rate fluctuation data;

[0050] Step S32: identifying the user's temporary use mode according to the user's short heart rate fluctuation data, thereby obtaining the user's temporary use mode data; identifying the user's deep use mode according to the user's long and slow heart rate fluctuation data, thereby obtaining the user's deep use mode data;

[0051] Step S33: merging the user temporary usage pattern data and the user deep usage pattern data to obtain user behavior pattern data;

[0052] Step S34: Predicting the user behavior pattern of the device heart rate sensor data based on the user behavior pattern data, thereby obtaining user behavior pattern prediction data;

[0053] Step S35: Estimating the user behavior time based on the user behavior pattern prediction data, thereby obtaining user behavior time data.

[0054] The present invention can identify the physiological state and emotional changes of the user by statistics of the user's heart rate sensor data. For example, short heart rate fluctuations may be related to stress, anxiety or physical activity, while long slow heart rate fluctuations may be related to relaxation or quiet state. This provides a reliable data basis for subsequent behavior pattern recognition and ensures the effectiveness of model training. Through the analysis of short and long slow heart rate fluctuation data, the user's temporary use mode and deep use mode can be identified, which can provide users with a more personalized use experience and help users use the device reasonably in different situations. Understanding the user's short-term and long-term behavior patterns helps the device to make intelligent responses according to the user's emotions and physiological state, such as automatically recommending relaxation exercises when the user is under great pressure. Merging the temporary use mode and the deep use mode data can form a panoramic view of the user's behavior pattern, which is convenient for a comprehensive understanding of the user's daily behavior. Through data merging, the potential correlation between user behaviors can be discovered, thereby enhancing the depth and breadth of behavior analysis. Prediction based on user behavior pattern data can identify potential health risks early and provide early warning services, such as reminding users to take rest or relaxation measures when they are under too much pressure. By predicting the user's future behavior patterns, the device's services and functions can be optimized, such as automatically adjusting notification frequency and pushing relevant content. Estimating time based on user behavior pattern prediction data can help users better arrange their daily lives and work and improve time management efficiency. The device can formulate personalized reminders and plans based on the user's behavior time data, such as sending exercise reminders or rest suggestions at the right time to promote user health management.

[0055] Optionally, step S4 is specifically:

[0056] Step S41: dividing the user behavior time data into long-term usage behaviors, thereby obtaining the user's intensive usage prediction time data;

[0057] Step S42: performing intersection time point calculation according to the spinal fatigue adjustment time data and the user depth usage prediction time data, so as to obtain ideal adjustment time point data;

[0058] Step S43: Obtain the equipment vibration parameter group, and set the warning vibration time for the equipment vibration parameter group according to the ideal adjustment time point data, thereby obtaining the equipment warning vibration time data, and transmitting it to the electrical control unit to execute the equipment timed warning vibration task.

[0059] The present invention can deeply understand the user's usage habits and frequency through long-term usage behavior division, and provide a more accurate data basis for subsequent user behavior modeling. Through the intersection calculation of the spinal fatigue adjustment time data and the deep usage prediction time data, the fatigue point of the user's spine can be effectively identified and timely intervention can be carried out. This process helps to improve the user's health level and reduce damage caused by long-term use. The generation of ideal adjustment time point data can guide the device to provide support when the user needs it most, such as issuing adjustment prompts before the user's spine is fatigued, thereby enhancing the auxiliary role of the device. In this way, the self-regulation of intelligent devices is realized, relying on user behavior and physiological feedback to automatically adjust the usage parameters to achieve the best use effect. By setting the early warning vibration time for the device vibration parameter group, a warning can be issued in time when the device is about to reach spinal fatigue, thereby improving the user's health level.

[0060] Optionally, the present specification also provides a system based on intelligent vital sign monitoring and control, which is used to execute the intelligent vital sign monitoring and control method as described above, and the system based on intelligent vital sign monitoring and control includes:

[0061] The device deformation state analysis module is used to obtain device pressure sensor data and device heart rate sensor data, and define the device pressure benchmark according to the device pressure sensor data, so as to obtain the device benchmark pressure data; based on the device benchmark pressure data, the device pressure sensor data is integrated with the device deformation state, so as to obtain the device deformation state data;

[0062] A spinal posture recognition module, used to recognize the spinal posture of the device user based on the device deformation state data, thereby obtaining the spinal posture data of the device user, and to estimate the spinal fatigue adjustment time of the spinal posture data of the device user, thereby obtaining the spinal fatigue adjustment time data;

[0063] A user behavior time estimation module is used to infer user behavior patterns based on device heart rate sensor data, thereby obtaining user behavior pattern data; and to estimate user behavior time based on user behavior pattern data, thereby obtaining user behavior time data;

[0064] The equipment warning vibration time analysis module is used to perform equipment warning vibration time analysis based on the spinal fatigue adjustment time data and the user behavior time data, thereby obtaining the equipment warning vibration time data and transmitting it to the electrical control unit to execute the equipment timed warning vibration task;

[0065] The spinal posture correction module is used to obtain real-time device pressure sensor data, and perform real-time device user spinal posture recognition based on the real-time device pressure sensor data, thereby obtaining real-time device user spinal posture data; perform spinal posture correction strategy analysis on the real-time device user spinal posture data based on spinal fatigue trend data, thereby obtaining the posture correction strategy, and transmit it to the electrical control unit to execute the device torsion spring elastic control task.

[0066] The intelligent vital sign monitoring and control system of the present invention can implement any one of the intelligent vital sign monitoring and control methods of the present invention, and is used to combine the operation and signal transmission medium between various modules to complete the intelligent vital sign monitoring and control method. The internal modules of the system cooperate with each other, thereby improving the accuracy and authenticity of the user's sitting vital sign monitoring.

[0067] Optionally, the present specification also provides a vital sign monitoring and control device, characterized in that it includes a main body of the vital sign monitoring and control device, a power supply unit and an electrical control unit, the main body of the vital sign monitoring and control device includes an ergonomic chair, a vibrator installed on the ergonomic chair, a pressure sensor and a heart rate sensor, the power supply unit is installed inside the main body of the vital sign monitoring and control device, wherein the vibrator, the pressure sensor and the heart rate sensor are all electrically connected to the power supply unit; the electrical control unit is electrically connected to the power supply unit, the electrical control unit is used to charge the main body of the vital sign monitoring and control device and control the main body of the vital sign monitoring and control device, and the electrical control unit is used to execute the intelligent vital sign monitoring and control method as described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0069] Figure 1 It is a schematic diagram of the steps of the intelligent vital sign monitoring and control method of the present invention;

[0070] Figure 2 Detailed step flow diagram of step S1 in the present invention;

[0071] Figure 3 Detailed step flow diagram of step S2 in the present invention;

[0072] 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

[0073] 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.

[0074] 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.

[0075] 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.

[0076] To achieve this, please refer to Figures 1 to 3 The present invention provides a method for intelligent vital sign monitoring and control, the method comprising the following steps:

[0077] Step S1: Obtain device pressure sensor data and device heart rate sensor data, and define a device pressure reference according to the device pressure sensor data, thereby obtaining device reference pressure data; integrate the device deformation state of the device pressure sensor data based on the device reference pressure data, thereby obtaining device deformation state data;

[0078] In this embodiment, data is collected in real time through pressure sensors and heart rate sensors deployed on the device. The pressure sensor should be highly sensitive and able to detect small pressure changes of 0.1 kPa, and the heart rate sensor needs to have photoelectric volumetric pulse wave technology with an accuracy of ±2 bpm. Next, a benchmark is defined based on the acquired pressure data, that is, a period of static data is selected as the benchmark pressure state of the device. For example, 1 minute of pressure data is collected when the user is sitting still, and the average pressure value is calculated as the benchmark data. Using this benchmark data, the deformation state of the device is analyzed, and the deviation between the actual pressure data and the benchmark data is calculated to determine the deformation state of the device. Finally, the deformation state data of the device is obtained for subsequent posture recognition.

[0079] Step S2: recognizing the spinal posture of the device user based on the device deformation state data, thereby obtaining the spinal posture data of the device user, and estimating the spinal fatigue adjustment time of the spinal posture data of the device user, thereby obtaining the spinal fatigue adjustment time data;

[0080] In this embodiment, the user's spinal posture is identified through a set algorithm (such as a machine learning algorithm) based on the obtained device deformation state data. At this time, the algorithm should take into account the natural curvature of the spine and the relationship between the user's sitting posture, and use the data set to train a spinal posture classification model that can classify postures into "good", "average", "bad" and other categories. Afterwards, the identified posture data is analyzed, and the spinal fatigue adjustment time is estimated based on the user's historical data and posture classification results. For example, when it is detected that the user is in a "bad" posture for more than 30 minutes, the user will be prompted to adjust, and the recommended adjustment time is 10 minutes. In this way, spinal fatigue adjustment time data is generated.

[0081] Step S3: inferring the user behavior pattern according to the device heart rate sensor data, thereby obtaining the user behavior pattern data; estimating the user behavior time based on the user behavior pattern data, thereby obtaining the user behavior time data;

[0082] In this embodiment, based on the real-time data obtained by the device's heart rate sensor, a behavior recognition algorithm (such as a hidden Markov model) is used to infer the user's behavior pattern. For example, by analyzing the trend of heart rate changes, it can be determined whether the user is in a "working", "resting" or "exercise" state. At the same time, combined with the user's historical behavior data, the duration of different activities can be accurately identified. For example, if the heart rate continues to fluctuate within a specific range, it indicates that the user is working deeply. By analyzing the behavior pattern, the time of each behavior is further estimated, and the user behavior time data is output, such as 60 minutes of "working time" and 20 minutes of "rest time".

[0083] Step S4: analyzing the equipment warning vibration time according to the spinal fatigue adjustment time data and the user behavior time data, thereby obtaining the equipment warning vibration time data, and transmitting it to the electrical control unit to execute the equipment timing warning vibration task;

[0084] In this embodiment, a dynamic warning model is established based on the spinal fatigue adjustment time data and the user behavior time data to analyze the warning vibration time that is most suitable for the user. For example, if the user has been sitting for 60 consecutive minutes in the "working" state, the spinal fatigue adjustment time will be calculated as 10 minutes, so the warning vibration time will be set to a 5-second vibration warning every 50 minutes. This vibration signal is executed by the electrical control unit to ensure that the user is warned before reaching the fatigue threshold to remind the user to rest.

[0085] Step S5: Acquire real-time device pressure sensor data, and perform real-time device user spinal posture recognition based on the real-time device pressure sensor data, thereby obtaining real-time device user spinal posture data; perform spinal posture correction strategy analysis on the real-time device user spinal posture data based on spinal fatigue trend data, thereby obtaining a posture correction strategy, and transmit it to the electrical control unit to execute the device torsion spring elastic control task.

[0086] In this embodiment, the pressure sensor deployed on the device monitors the pressure of the device after the vibration warning, continuously obtains the real-time data of the device pressure sensor, and uses the aforementioned spinal posture recognition algorithm (user spinal posture recognition model) to analyze the real-time user posture. If it is recognized that the user's spinal posture after the vibration warning is still deviated from the natural spinal posture (sitting upright), the spinal fatigue trend data (historical posture data) will be analyzed to identify the fatigue trend of the user in a specific posture, and the impact of long-term poor posture on spinal health will be evaluated to generate a sitting posture correction strategy. The generated posture correction strategy is converted into a specific instruction format, including adjustment amplitude and execution timing. The instruction is transmitted to the device through the electrical control unit to control the elastic adjustment of the torsion spring, and actively change the height or backrest angle of the chair to help the user restore a good spinal posture. For example, when the user has a bad sitting posture, the chair adjustment height or waist inclination angle is calculated, and the execution command is transmitted through the electrical control unit to control the elasticity of the torsion spring of the device, thereby actively adjusting the position of the chair to help the user restore a good posture.

[0087] Optionally, step S1 specifically includes:

[0088] Step S11: Acquire device pressure sensor data and device heart rate sensor data;

[0089] In this embodiment, built-in pressure sensors and heart rate sensors are used to collect pressure and heart rate data of ergonomic chair users in real time. Pressure sensors are arranged in the seat cushion, backrest and armrests of the chair to accurately obtain the pressure distribution of different parts. The data collection frequency is set to 100 times per second to ensure real-time performance. The heart rate sensor monitors the user's heart rate through photoelectric capacitance pulse wave sensing technology.

[0090] Step S12: performing pressure sensing division according to the device pressure sensing data, thereby obtaining the device torsion spring pressure sensing data and the device interaction pressure sensing data;

[0091] In this embodiment, the collected pressure sensing data is analyzed and first divided into two categories: torsion spring pressure and interaction pressure. Torsion spring pressure refers to the pressure applied to components of the chair, such as the adjustable backrest, while interaction pressure refers to the pressure generated by the interaction between the user and the chair (for example, the pressure change when sitting down and standing up). The pressure signals from different sensor sources are classified according to spatial position. Taking the backrest as an example, if the pressure signal comes from a sensor deployed on the interactive component of the backrest (that is, the pressure generated by direct contact between the user and the chair), it is determined to be interaction pressure. If the pressure signal comes from a sensor deployed on the torsion spring component of the backrest, it is torsion spring pressure.

[0092] Step S13: Perform Fourier transform on the device torsion spring pressure sensing data to obtain the device torsion spring pressure spectrum, and perform high-frequency torsion spring pressure statistics based on the device torsion spring pressure spectrum to obtain high-frequency torsion spring pressure data; define the torsion spring pressure benchmark based on the high-frequency torsion spring pressure data to obtain the device torsion spring pressure benchmark data;

[0093] In this embodiment, the fast Fourier transform (FFT) algorithm is used to perform spectrum analysis on the torsion spring pressure sensing data collected by the device. Continuous pressure data within 1 minute is collected and processed by window function to avoid spectrum leakage. After FFT processing, the spectrum diagram obtained is used to identify high-frequency components. The frequency components above a certain threshold (for example, 5Hz) in the spectrum are extracted, and their amplitude and phase are calculated to obtain high-frequency torsion spring pressure data. This data is used to evaluate the dynamic performance of the torsion spring and define the corresponding benchmark (such as 99% data distribution).

[0094] Step S14: performing interactive pressure time series analysis on the interactive pressure sensing data of the device to obtain interactive pressure time series data, and performing long-term interactive pressure statistics on the interactive pressure time series data to obtain long-term interactive pressure data; defining an interactive pressure benchmark according to the long-term interactive pressure data to obtain the interactive pressure benchmark data of the device;

[0095] In this embodiment, the device interaction pressure data is sorted in time series to construct a time series model of interaction pressure. The interaction pressure data within a period of time (e.g., 5 minutes) is statistically analyzed by a sliding window analysis method (e.g., sliding average method). The statistical results show the pressure fluctuations during this period and identify the pattern and trend of pressure changes. Further, based on these data, an interaction pressure benchmark is defined, for example, the interaction pressure benchmark data is obtained by taking the 95% data distribution in a long period as the benchmark.

[0096] Step S15: performing equipment pressure benchmark integration on the equipment torsion spring pressure benchmark data and the equipment interactive pressure benchmark data, thereby obtaining equipment benchmark pressure data;

[0097] In this embodiment, two kinds of pressure reference data are combined to obtain comprehensive data of pressure reference conditions of different parts of the ergonomic chair.

[0098] Step S16: integrating the equipment deformation state of the equipment pressure sensing data based on the equipment baseline pressure data, thereby obtaining equipment deformation state data.

[0099] In this embodiment, the integrated baseline pressure data is combined with the real-time pressure sensor data to determine the deformation state of the device through a comparison algorithm (such as Kalman filtering). Specifically, the real-time pressure sensor data is compared with the baseline data, and if the current pressure data exceeds a certain range (such as 10%) of the baseline value, it is determined that the deformation state occurs.

[0100] Optionally, step S16 is specifically:

[0101] Step S161: Calculating the device pressure offset based on the device pressure sensing data, thereby obtaining the device torsion spring pressure offset and the device interactive pressure offset;

[0102] In this embodiment, the real-time pressure data collected by the pressure sensor is compared with the reference pressure data, and the torsion spring pressure offset (ΔF_t) and the device interactive pressure offset (ΔF_i) of the device are calculated by formula. For example, if the torsion spring pressure reference is P_base and the real-time torsion spring pressure is P_current, the torsion spring pressure offset can be expressed as: ΔF_t=P_current-P_base; if the interactive pressure reference is Q_base and the real-time interactive pressure is Q_current, the device interactive pressure offset can be expressed as ΔF_i=Q_current-Q_base.

[0103] Step S162: performing compression offset statistics on the torsion spring compression data of the device, thereby obtaining the torsion spring compression data of the high-offset device and the torsion spring compression data of the low-offset device;

[0104] In this embodiment, the collected torsion spring compression offset data is statistically analyzed. First, an offset threshold (such as a 5% baseline pressure) is set. Then, the torsion spring compression offset data is divided into two categories: high offset (ΔF_t>5%) and low offset (ΔF_t≤5%) using statistical methods (e.g., standard deviation, mean). The specific data statistics method can use Excel or other data processing software, use the "pivot table" function to generate high offset and low offset torsion spring compression data records, and mark the category of each record in the database for subsequent data analysis.

[0105] Step S163: performing pressure offset statistics on the device interaction pressure offset, thereby obtaining high-offset device interaction pressure data and low-offset device interaction pressure data;

[0106] In this embodiment, the calculated interactive pressure offset (ΔF_i) is also divided into high offset and low offset data. A histogram can be drawn using graphical software (such as MATLAB) to intuitively present the distribution of interactive pressure data. The data of high offset (ΔF_i>5%) and low offset (ΔF_i≤5%) are stored separately to facilitate data association in subsequent steps.

[0107] Step S164: performing compression time-series correlation on the torsion spring compression data of the high-offset device and the interactive compression data of the high-offset device, thereby obtaining the deformation data of the working state; performing compression time-series correlation on the torsion spring compression data of the low-offset device and the interactive compression data of the low-offset device, thereby obtaining the deformation data of the standby state;

[0108] In this embodiment, the high-offset device torsion spring compression data and the high-offset device interactive compression data are time-series correlated to obtain the working state deformation data. The time series analysis technology can be used in combination with the correlation analysis to establish a model. For example, the cross-correlation function (CCF) is used to analyze the synchronous changes in time between the torsion spring and the interactive compression. For low-offset data, a similar method can be used to extract the standby state deformation data. Finally, it is recommended to generate a time series chart of the working state and the standby state to provide an intuitive display of the deformation changes.

[0109] Step S165: Merge the deformation data of the working state and the deformation data of the standby state to obtain the equipment deformation state data.

[0110] In this embodiment, the deformation data of the working state and the deformation data of the standby state are merged to obtain the deformation state data of the device. A data merging tool (such as Python's Pandas library) can be used to match the two sets of data by timestamp and merge them into a comprehensive data set. Conditional formatting can be used to highlight the moment of significant change. For example, if the deformation exceeds a threshold (such as 10%), it is specially marked in the final data set for subsequent analysis. The merged deformation state data is displayed through a data visualization tool (such as Tableau) to facilitate further analysis and decision support.

[0111] Optionally, step S2 specifically includes:

[0112] Step S21: extracting working state deformation features from the equipment deformation state data, thereby obtaining working state deformation data;

[0113] In this embodiment, the principal component analysis method is used to extract the characteristics of the working state, such as average pressure, maximum pressure, pressure fluctuation range, etc., from the deformation state data of the equipment, and finally generate a set of deformation data including the working state of the equipment.

[0114] Step S22: integrating the pressure distribution of the equipment in working state according to the deformation data in working state, thereby obtaining the pressure distribution data of the equipment in working state, and selecting the pressure center of the equipment in working state for the pressure distribution data in working state, thereby obtaining the pressure center data of the equipment in working state;

[0115] In this embodiment, after obtaining the deformation data of the working state, the data needs to be integrated to form the pressure distribution data of the device under different working states. The statistical characteristics such as the average value and standard deviation of the pressure can be calculated by performing statistical analysis on the data of all pressure sensors. At the same time, the selection of the pressure center of the device can be achieved by identifying the center of gravity of the pressure distribution, and the center of gravity can be calculated by the weighted average method for the pressure distribution data of the device working state. The center of gravity (pressure center) of the pressure distribution can be calculated by weighted averaging the pressure values ​​of each pressure sensor. Assuming the sensor position is (X_i,Y_i) and its pressure value is P_i, the calculation formula of the center of gravity coordinates (X_{cg},Y_{cg}) is: X_{cg}=\frac{\sum_{i=1}^{N}\left(X_{i}\cdotP_{i}\right)}{\sum_{i=1}^{N}P_{i}}; Y_{cg}=\frac{\sum_{i=1}^{N}(Y_i\cdotP_i)}{\sum_{i=1}^{N};

[0116] Assume that there are three pressure sensors, and their position and pressure data are as follows: Sensor 1: position (30,40), pressure value 100N; Sensor 2: position (50,75), pressure value 150N; Sensor 3: position (70,100), pressure value 50N; then

[0117] Total pressure=100+150+50=300N; rox46.67;

[0118] The pressure center position of the device is approximately (46.67, 68.83). In addition, the pressure condition can be further understood by analyzing the left and right pressure difference values ​​of each sensor (for example, the pressure difference between the left and right sensors).

[0119] Step S23: Calculate the left and right pressure difference of the equipment part based on the pressure distribution data of the equipment working state, so as to obtain the left and right pressure difference data of the equipment part;

[0120] In this embodiment, the left and right pressure difference of different parts of the device under working conditions is calculated. The pressure data on the left and right sides of the device can be compared, and the difference can be calculated using absolute value operation. For example, in a certain working state, the pressure on the left side is 100N and the pressure on the right side is 90N, then the left and right pressure difference is |100N-90N|=10N. By averaging the data under multiple working conditions, more stable left and right pressure difference data can be obtained.

[0121] Step S24: recognizing the user's spinal posture according to the device pressure center data in the working state and the left and right pressure difference data of the device parts, thereby obtaining the device user's spinal posture data;

[0122] In this embodiment, after the data of the pressure center of the device in the working state and the left and right pressure difference data are obtained, a machine learning algorithm (such as a support vector machine or a neural network) can be used to identify the user's spinal posture. The model is trained to identify specific posture data, such as a natural sitting posture, a forward leaning posture, or a backward leaning posture. For example, if the model identifies that the user's pressure center offset exceeds a certain threshold, and the left and right pressure difference exceeds a preset standard, it can be determined that the user is in a bad sitting posture. The final output of the process is the user's current spinal posture data, which can feedback that the user's current posture is "leaning forward."

[0123] Step S25: Estimating the spinal fatigue adjustment time based on the device user's spinal posture data, thereby obtaining spinal fatigue adjustment time data.

[0124] In this embodiment, based on the identified spinal posture data and combined with ergonomic principles, the degree of spinal fatigue of the user in the current posture and the time required for adjustment can be estimated. Usually, a regression model based on historical data can be used to predict the fatigue adjustment time. For example, if historical data shows that the user will feel tired after maintaining a forward leaning posture for more than 30 minutes, a judgment can be made based on this and suggestions can be given, such as "it is recommended to adjust the posture within 15 minutes." The output is the spinal fatigue adjustment time data, so as to provide the user with effective posture adjustment suggestions.

[0125] Optionally, step S24 is specifically:

[0126] Step S241: calculating the relative position of the user's body center of gravity in the working state according to the data of the pressure center of the device in the working state, thereby obtaining the relative position data of the user's body center of gravity, and dividing the relative position data of the user's body center of gravity according to the position of the body center of gravity in the working state of the device, thereby obtaining the relative position state data of the upper limb center of gravity and the relative position state data of the lower limb center of gravity;

[0127] In this embodiment, these pressure center data can be used to infer the relative position of the user's body center of gravity. For example, if the pressure on the upper limbs is greater, it indicates that the upper limbs are offset relative to the body when the user operates the device; if the pressure on the lower limbs is less, it indicates that the user's center of gravity may be biased upward. At this time, by calculating the relative position of the user's body center of gravity and the device, the relative position state data of the center of gravity of the upper and lower limbs can be obtained, specifically including data such as the front and back tilt and left and right tilt when sitting.

[0128] Step S242: performing pressure difference clustering calculation based on the left and right pressure difference data of the equipment part, so as to obtain the left and right pressure balanced equipment part status data and the left and right pressure uneven equipment part status data;

[0129] In this embodiment, by analyzing the left and right pressure difference data of the equipment parts, the balanced pressure state of each part can be calculated. For the parts with a smaller pressure difference, it can be considered that the part is in a balanced pressure state on the left and right, while the parts with a larger difference are determined to be in an uneven pressure state on the left and right. Taking the knee as an example, if the pressure on the left knee is 30 units and the right knee is 70 units, the pressure difference is 40 units, indicating that the right knee is unevenly compressed. Therefore, through a clustering algorithm (such as K-means clustering or hierarchical clustering), it is possible to classify and identify which equipment parts are in a balanced pressure state and which are in an uneven state, thereby obtaining the equipment part state data of balanced pressure on the left and right and the equipment part state data of uneven pressure on the left and right.

[0130] Step S243: performing device state intersection operation on the upper limb center of gravity relative position state data and the left and right pressure-balanced device part state data, thereby obtaining the user's spine longitudinal tilt device state data; performing device state intersection operation on the lower limb center of gravity relative position state data and the left and right pressure-balanced device part state data, thereby obtaining the user's spine natural device state data; performing device state intersection operation on the lower limb center of gravity relative position state data and the left and right pressure-uneven device part state data, thereby obtaining the user's spine lateral tilt device state data;

[0131] In this embodiment, the relative position state data of the upper limb center of gravity is combined with the state data of the left and right pressure-balanced device parts to perform an intersection operation. For example, if the state of the user's upper limb center of gravity is "forward or backward", and the device state is "balanced", then the intersection can be expressed as "the device state in the longitudinal tilt posture of the user's spine". Similarly, by combining the data of the relative position of the lower limb center of gravity and the left and right pressure balance, the "device state in the natural posture of the user's spine" can be obtained. If the state of the lower limb center of gravity is "sideways" and the pressure is uneven, the "device state in the lateral tilt posture of the user's spine" is formed. These state data are used for subsequent model training to evaluate the dynamic changes of the user's spine.

[0132] Step S244: constructing a user spine posture recognition model based on the user spine longitudinal tilt device state data, the user spine natural device state data, and the user spine lateral tilt device state data;

[0133] In this embodiment, a spinal posture recognition model is constructed based on the device state data collected when the user's spine is in longitudinal, natural and lateral postures. A machine learning algorithm (such as a support vector machine or a deep learning model) is used to train and verify the collected data. At the same time, a large number of spinal state data of users in different postures can be collected, including spinal longitudinal, natural and lateral data. Then, a machine learning algorithm (such as a support vector machine, a random forest or a deep learning model) can be used to train these data to establish a model that can predict the user's spinal posture. The model input is the device pressure state data, and the output is the spinal posture category (such as normal, forward leaning, backward leaning, etc.). In order to enhance the accuracy of the model, data enhancement technology will be used, such as adding posture samples of different users to ensure that the model can adapt to different physical characteristics and posture changes. Ultimately, the model will be able to effectively identify the user's spinal posture and provide data support for personalized health feedback.

[0134] Step S245: performing device user spine posture recognition on the working state deformation data through the user spine posture recognition model, thereby obtaining device user spine posture data.

[0135] In this embodiment, the user spine posture recognition model is used to perform real-time recognition of the deformation data of the working state. By inputting the newly collected pressure and center of gravity data into the model, the device can quickly recognize the current spine posture data. For example, when the user performs a specific activity on the device (such as sitting or standing), their posture will be analyzed in real time, and feedback will be given such as "normal spine posture" or "bad spine posture". At the same time, improvement suggestions can be provided based on the recognition results, such as adjusting the sitting posture or performing specific exercises to help users improve their spinal health.

[0136] Optionally, step S25 is specifically:

[0137] Step S251: integrating the time series distribution of the user's spinal posture according to the device user's spinal posture data, thereby obtaining the user's spinal posture time series data;

[0138] In this embodiment, a signal processing algorithm (such as a sliding window method) is used to organize and integrate the device user's spinal posture data, extract the user's spinal posture information in different time periods, and form spinal posture time series data.

[0139] Step S252: performing lateral spinal posture time statistics and longitudinal spinal posture time statistics on the user's spinal posture time series data, thereby obtaining lateral spinal posture time data and longitudinal spinal posture time data, and merging the lateral spinal posture time data and longitudinal spinal posture time data by time period, thereby obtaining bad spinal posture time data;

[0140] In this embodiment, for the obtained spinal posture time series data, the lateral inclination and longitudinal inclination data are summarized separately to calculate the total duration of each posture. Then, the spinal posture is classified according to the body center of gravity angle (such as ±10 degrees is normal, and exceeding this range is a bad posture), and the time occupied by each posture is counted. Next, the time data of the lateral inclination and longitudinal inclination are merged to identify the duration of the bad spinal posture, and finally form the time data of the bad spinal posture. It should be specifically explained that the body center of gravity angle includes the lateral inclination angle (the degree of inclination of the body center of gravity in the left and right direction) of the body's center of gravity on the horizontal plane, and the longitudinal inclination angle of the body's center of gravity in the front and back direction. Then the lateral inclination and longitudinal inclination angles are monitored and classified separately. For example, when the lateral inclination and longitudinal inclination angles are both within the range of ±10 degrees, it is regarded as a normal posture; if any angle exceeds ±10 degrees, it is regarded as a bad posture. When counting the time occupied by each posture, the time of the lateral inclination and longitudinal inclination can be recorded separately, and their results can be merged at the end to identify the overall duration of the bad posture.

[0141] Step S253: calculating the time proportion of the user's bad spinal posture on the user's spinal posture time series data according to the bad spinal posture time data, thereby obtaining the user's bad spinal posture time proportion data;

[0142] In this embodiment, based on the bad spinal posture time data, the proportion of bad postures in the user's overall posture monitoring time is calculated. The proportion of bad spinal postures in the user's entire monitoring period can be obtained through the formula "user bad posture time proportion = bad posture time / total monitoring time". This data helps to evaluate the user's posture health level.

[0143] Step S254: performing spinal fatigue trend analysis based on the user's bad spinal posture time proportion data, thereby obtaining spinal fatigue trend data;

[0144] In this embodiment, based on the obtained data on the proportion of time of bad spinal posture of the user, a statistical analysis method (such as time series analysis or moving average method) is used to perform trend analysis on the data. The change of the proportion of bad posture over time can be displayed by a graph to identify the rising or falling trend of spinal fatigue. For example, if the proportion of bad posture continues to increase over a period of time, it indicates that the user's spinal fatigue is getting worse. A fatigue threshold can also be set. If the proportion exceeds 40%, fatigue is indicated. The fatigue trend data for the next few hours is predicted by a time series analysis algorithm (such as an ARIMA model).

[0145] Step S255: obtaining the spinal fatigue degree rule through the expert experience database, and performing spinal fatigue time threshold statistics according to the spinal fatigue degree rule, thereby obtaining spinal fatigue time threshold data;

[0146] In this embodiment, an expert experience database is compiled by cooperating with orthopedic experts or consulting relevant materials. Spinal fatigue degree rules including spinal fatigue degree definition rules and spinal repair rules are obtained through the expert experience database. In the spinal fatigue degree rules, experts define multiple fatigue degree thresholds (such as mild, moderate, and severe) based on clinical experience, and each level corresponds to a different time threshold (such as mild is more than 30% of bad posture, and the duration is ≤30 minutes; moderate is more than 40% of bad posture, and the duration is ≤60 minutes; severe is more than 50% of bad posture, and the duration is >60 minutes). Then, according to these thresholds and the clinical experience of experts, the corresponding rest time threshold is defined for each fatigue level. For example, if mild fatigue occurs, you should rest for 10 minutes; if moderate fatigue occurs, you should rest for 20 minutes; if severe fatigue occurs, you should rest for 30 minutes. For example, mild fatigue corresponds to a bad posture that accounts for more than 30% for 1 hour, and you need to rest for 10 minutes to relieve the spinal impact caused by mild fatigue.

[0147] Step S256: Estimate the spinal fatigue adjustment time of the spinal fatigue trend data according to the spinal fatigue time threshold data, thereby obtaining the spinal fatigue adjustment time data.

[0148] In this embodiment, the obtained spinal fatigue time threshold data is used to evaluate the spinal fatigue trend. First, the spinal fatigue trend is compared with the time threshold defined by experts. For example, when the user's bad posture lasts longer than the threshold of mild fatigue (such as 30 minutes), it will be marked as mild fatigue, and the required rest time (such as 10 minutes) will be calculated. Then, if the trend of the spinal fatigue prediction continues and reaches the moderate or severe fatigue threshold, the rest recommendation will be adjusted accordingly, and the required adjustment time will be estimated to avoid further spinal injury. Ultimately, the generated spinal fatigue adjustment time data will be used to optimize the user's work or activity plan to ensure their spinal health.

[0149] Optionally, step S3 specifically includes:

[0150] Step S31: performing heart rate fluctuation statistics on the device heart rate sensor data, thereby obtaining the user's short heart rate fluctuation data and the user's long heart rate fluctuation data;

[0151] In this embodiment, the heart rate sensor of the ergonomic chair continuously monitors the user's heart rate and records the changes in heart rate. Through data analysis, the user's heart rate fluctuations are divided into two categories: short (such as heart rate fluctuations multiple times in a short period of time, with an amplitude greater than 10bpm) and long slow (such as heart rate changes slowly within 5 minutes, with a change amplitude less than 5bpm). For example, when the user is using the chair, the heart rate rises rapidly due to making a phone call in a short period of time, which will be recorded as a short fluctuation; and the heart rate gradually drops after sitting for a long time, which is recorded as a long slow fluctuation.

[0152] Step S32: identifying the user's temporary use mode according to the user's short heart rate fluctuation data, thereby obtaining the user's temporary use mode data; identifying the user's deep use mode according to the user's long and slow heart rate fluctuation data, thereby obtaining the user's deep use mode data;

[0153] In this embodiment, a machine learning algorithm (such as K-means clustering) is used to identify the user's temporary usage mode for short heart rate fluctuation data. For example, in a high-intensity working state, short fluctuations frequently occur and are marked as "concentrated work". For long and slow heart rate fluctuations, by analyzing the long-term stable heart rate, it is inferred that the user is in a deep relaxation state, such as an afternoon rest. If the user's heart rate remains stable and gradually decreases to 60bpm during a long period of sitting, this mode will be marked as "deep use".

[0154] Step S33: merging the user temporary usage pattern data and the user deep usage pattern data to obtain user behavior pattern data;

[0155] In this embodiment, temporary usage pattern data and deep usage pattern data are combined to generate user behavior pattern data. A weighted algorithm is used to consider the frequency and duration of different patterns. For example, if a user experiences 3 short fluctuations and 2 long slow fluctuations in a day, a comprehensive behavior pattern such as "work concentration and short rest" will be obtained and recorded as the user's main behavior pattern.

[0156] Step S34: Predicting the user behavior pattern of the device heart rate sensor data based on the user behavior pattern data, thereby obtaining user behavior pattern prediction data;

[0157] In this embodiment, based on the user behavior pattern data, a prediction algorithm (such as time series analysis or regression model) is applied to analyze the device heart rate sensor data to predict the user's future behavior pattern. For example, if the user exhibits short heart rate fluctuations many times during work, it can be predicted that his future usage pattern will be high-intensity activities or short breaks. The generated user behavior pattern prediction data can provide real-time feedback to the device to optimize the user experience.

[0158] Step S35: Estimating the user behavior time based on the user behavior pattern prediction data, thereby obtaining user behavior time data.

[0159] In this embodiment, the user behavior time is estimated using statistical methods (such as regression analysis) based on the user behavior pattern prediction data. For example, if the model prediction shows that the user's heart rate fluctuates frequently and lasts for 30 minutes while working, it can be inferred that the user's behavior time is 30 minutes. On this basis, combined with the device's usage history data, the user's average behavior time in different time periods is calculated, thereby obtaining more accurate user behavior time data.

[0160] Optionally, step S4 is specifically:

[0161] Step S41: dividing the user behavior time data into long-term usage behaviors, thereby obtaining the user's intensive usage prediction time data;

[0162] In this embodiment, a machine learning algorithm is used to analyze the user's behavior time data to identify the user's deep usage pattern in a specific time period, such as a long period of usage from 1pm to 2pm. By dividing these time periods, the user's fatigue state after continuous use of the device can be determined, and the next time point of deep usage can be predicted.

[0163] Step S42: performing intersection time point calculation according to the spinal fatigue adjustment time data and the user depth usage prediction time data, so as to obtain ideal adjustment time point data;

[0164] In this embodiment, the spinal fatigue adjustment time data (such as the user's bad spinal posture, the duration of the bad spinal posture exceeds 20 minutes, the bad spinal posture trend shows that the posture will exceed 10 minutes, it is mild fatigue, and you should rest for 10 minutes) and the obtained deep use prediction time data (such as the user has used it for 20 minutes, and the predicted usage time is greater than 45 minutes) are intersected. Through the intersection operation, the two sets of data are combined to identify an ideal adjustment time point. For example, when the user reaches 30 minutes of use, the user is reminded to take a break and is advised to rest for 10 minutes. This process ensures that the user can adjust the posture in time during long-term use, thereby reducing the risk of spinal fatigue and improving the comfort of use.

[0165] Step S43: Obtain the equipment vibration parameter group, and set the warning vibration time for the equipment vibration parameter group according to the ideal adjustment time point data, thereby obtaining the equipment warning vibration time data, and transmitting it to the electrical control unit to execute the equipment timed warning vibration task.

[0166] In this embodiment, the vibration parameters of the device, such as vibration frequency and amplitude, are collected by the vibrator included in the device, and the device vibration warning is set at the ideal adjustment time point. When the time reaches the preset point, the device emits a warning vibration to remind the user to take a rest. In specific implementation, the warning vibration can be designed to be a gradual increase mode to ensure that the user can notice it in time. All data is transmitted through the electrical control unit to ensure that the device can perform the warning task on time.

[0167] Optionally, the present specification also provides a system based on intelligent vital sign monitoring and control, which is used to execute the intelligent vital sign monitoring and control method as described above, and the system based on intelligent vital sign monitoring and control includes:

[0168] The device deformation state analysis module is used to obtain device pressure sensor data and device heart rate sensor data, and define the device pressure benchmark according to the device pressure sensor data, so as to obtain the device benchmark pressure data; based on the device benchmark pressure data, the device pressure sensor data is integrated with the device deformation state, so as to obtain the device deformation state data;

[0169] A spinal posture recognition module, used to recognize the spinal posture of the device user based on the device deformation state data, thereby obtaining the spinal posture data of the device user, and to estimate the spinal fatigue adjustment time of the spinal posture data of the device user, thereby obtaining the spinal fatigue adjustment time data;

[0170] A user behavior time estimation module is used to infer user behavior patterns based on device heart rate sensor data, thereby obtaining user behavior pattern data; and to estimate user behavior time based on user behavior pattern data, thereby obtaining user behavior time data;

[0171] The equipment warning vibration time analysis module is used to perform equipment warning vibration time analysis based on the spinal fatigue adjustment time data and the user behavior time data, thereby obtaining the equipment warning vibration time data and transmitting it to the electrical control unit to execute the equipment timed warning vibration task;

[0172] The spinal posture correction module is used to obtain real-time device pressure sensor data, and perform real-time device user spinal posture recognition based on the real-time device pressure sensor data, thereby obtaining real-time device user spinal posture data; perform spinal posture correction strategy analysis on the real-time device user spinal posture data based on spinal fatigue trend data, thereby obtaining the posture correction strategy, and transmit it to the electrical control unit to execute the device torsion spring elastic control task.

[0173] The intelligent vital sign monitoring and control system of the present invention can implement any one of the intelligent vital sign monitoring and control methods of the present invention, and is used to combine the operation and signal transmission medium between various modules to complete the intelligent vital sign monitoring and control method. The internal modules of the system cooperate with each other, thereby improving the accuracy and authenticity of the user's sitting vital sign monitoring.

[0174] Optionally, the present specification also provides a vital sign monitoring and control device, characterized in that it includes a main body of the vital sign monitoring and control device, a power supply unit and an electrical control unit, the main body of the vital sign monitoring and control device includes an ergonomic chair, a vibrator installed on the ergonomic chair, a pressure sensor and a heart rate sensor, the power supply unit is installed inside the main body of the vital sign monitoring and control device, wherein the vibrator, the pressure sensor and the heart rate sensor are all electrically connected to the power supply unit; the electrical control unit is electrically connected to the power supply unit, the electrical control unit is used to charge the main body of the vital sign monitoring and control device and control the main body of the vital sign monitoring and control device, and the electrical control unit is used to execute the intelligent vital sign monitoring and control method as described above.

[0175] 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.

[0176] 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 method for intelligent vital sign monitoring and control, characterized in that: The following steps are involved: Step S1: obtaining device pressure sensor data and device heart rate sensor data, and defining a device pressure reference according to the device pressure sensor data, thereby obtaining device reference pressure data; Integrate the equipment deformation state of the equipment pressure sensing data based on the equipment baseline pressure data, so as to obtain the equipment deformation state data; Step S2: recognizing the spinal posture of the device user based on the device deformation state data, thereby obtaining the spinal posture data of the device user, and estimating the spinal fatigue adjustment time of the spinal posture data of the device user, thereby obtaining the spinal fatigue adjustment time data; Step S3: inferring the user behavior pattern according to the device heart rate sensor data, thereby obtaining the user behavior pattern data; estimating the user behavior time based on the user behavior pattern data, thereby obtaining the user behavior time data; Step S4: analyzing the equipment warning vibration time according to the spinal fatigue adjustment time data and the user behavior time data, thereby obtaining the equipment warning vibration time data, and transmitting it to the electrical control unit to execute the equipment timing warning vibration task; Step S5: acquiring real-time device pressure sensing data, and performing real-time device user spinal posture recognition based on the real-time device pressure sensing data, thereby obtaining real-time device user spinal posture data; The spinal posture correction strategy is analyzed on the real-time device user's spinal posture data according to the spinal fatigue trend data to obtain the posture correction strategy, which is then transmitted to the electrical control unit to execute the device torsion spring elastic control task.

2. The intelligent vital sign monitoring and control method according to claim 1 is characterized in that: Step S1 is specifically as follows: Step S11: Acquire device pressure sensor data and device heart rate sensor data; Step S12: performing pressure sensing division according to the device pressure sensing data, thereby obtaining the device torsion spring pressure sensing data and the device interaction pressure sensing data; Step S13: Perform Fourier transform on the device torsion spring pressure sensing data to obtain the device torsion spring pressure spectrum, and perform high-frequency torsion spring pressure statistics based on the device torsion spring pressure spectrum to obtain high-frequency torsion spring pressure data; define the torsion spring pressure benchmark based on the high-frequency torsion spring pressure data to obtain the device torsion spring pressure benchmark data; Step S14: performing interactive pressure time series analysis on the interactive pressure sensing data of the device to obtain interactive pressure time series data, and performing long-term interactive pressure statistics on the interactive pressure time series data to obtain long-term interactive pressure data; Define the interactive pressure benchmark based on the long-term interactive pressure data, so as to obtain the interactive pressure benchmark data of the equipment; Step S15: performing equipment pressure benchmark integration on the equipment torsion spring pressure benchmark data and the equipment interactive pressure benchmark data, thereby obtaining equipment benchmark pressure data; Step S16: integrating the equipment deformation state of the equipment pressure sensing data based on the equipment baseline pressure data, thereby obtaining equipment deformation state data.

3. The intelligent vital sign monitoring and control method according to claim 2 is characterized in that: Step S16 is specifically as follows: Step S161: Calculating the device pressure offset based on the device pressure sensing data, thereby obtaining the device torsion spring pressure offset and the device interactive pressure offset; Step S162: performing compression offset statistics on the torsion spring compression data of the device, thereby obtaining the torsion spring compression data of the high-offset device and the torsion spring compression data of the low-offset device; Step S163: performing pressure offset statistics on the device interaction pressure offset, thereby obtaining high-offset device interaction pressure data and low-offset device interaction pressure data; Step S164: performing compression time-series correlation on the compression data of the torsion spring of the high-offset device and the interactive compression data of the high-offset device, so as to obtain deformation data of the working state; Perform compression time-series correlation on the torsion spring compression data of the low-offset device and the interactive compression data of the low-offset device, so as to obtain the standby state deformation data; Step S165: Merge the deformation data of the working state and the deformation data of the standby state to obtain the equipment deformation state data.

4. The intelligent vital sign monitoring and control method according to claim 1 is characterized in that: Step S2 is specifically as follows: Step S21: extracting working state deformation features from the equipment deformation state data, thereby obtaining working state deformation data; Step S22: integrating the pressure distribution of the equipment in working state according to the deformation data in working state, thereby obtaining the pressure distribution data of the equipment in working state, and selecting the pressure center of the equipment in working state for the pressure distribution data in working state, thereby obtaining the pressure center data of the equipment in working state; Step S23: Calculating the left and right pressure difference of the equipment part based on the pressure distribution data of the equipment working state, thereby obtaining the left and right pressure difference data of the equipment part; Step S24: recognizing the user's spinal posture according to the device pressure center data in the working state and the left and right pressure difference data of the device parts, thereby obtaining the device user's spinal posture data; Step S25: Estimating the spinal fatigue adjustment time based on the device user's spinal posture data, thereby obtaining spinal fatigue adjustment time data.

5. The intelligent vital sign monitoring and control method according to claim 4 is characterized in that: Step S24 is specifically as follows: Step S241: calculating the relative position of the user's body center of gravity in the working state according to the data of the pressure center of the device in the working state, thereby obtaining the relative position data of the user's body center of gravity, and dividing the relative position data of the user's body center of gravity according to the position of the body center of gravity in the working state of the device, thereby obtaining the relative position state data of the upper limb center of gravity and the relative position state data of the lower limb center of gravity; Step S242: performing pressure difference clustering calculation based on the left and right pressure difference data of the equipment part, so as to obtain the left and right pressure balanced equipment part status data and the left and right pressure uneven equipment part status data; Step S243: performing device state intersection operation on the upper limb center of gravity relative position state data and the left and right pressure-balanced device part state data, thereby obtaining the user's spine longitudinal tilt device state data; performing device state intersection operation on the lower limb center of gravity relative position state data and the left and right pressure-balanced device part state data, thereby obtaining the user's spine natural device state data; performing device state intersection operation on the lower limb center of gravity relative position state data and the left and right pressure-uneven device part state data, thereby obtaining the user's spine lateral tilt device state data; Step S244: constructing a user spine posture recognition model based on the user spine longitudinal tilt device state data, the user spine natural device state data, and the user spine lateral tilt device state data; Step S245: performing device user spine posture recognition on the working state deformation data through the user spine posture recognition model, thereby obtaining device user spine posture data.

6. The intelligent vital sign monitoring and control method according to claim 4 is characterized in that: Step S25 is specifically as follows: Step S251: integrating the time series distribution of the user's spinal posture according to the device user's spinal posture data, thereby obtaining the user's spinal posture time series data; Step S252: performing lateral spinal posture time statistics and longitudinal spinal posture time statistics on the user's spinal posture time series data, thereby obtaining lateral spinal posture time data and longitudinal spinal posture time data, and merging the lateral spinal posture time data and longitudinal spinal posture time data by time period, thereby obtaining bad spinal posture time data; Step S253: calculating the time proportion of the user's bad spinal posture on the user's spinal posture time series data according to the bad spinal posture time data, thereby obtaining the user's bad spinal posture time proportion data; Step S254: performing spinal fatigue trend analysis based on the user's bad spinal posture time proportion data, thereby obtaining spinal fatigue trend data; Step S255: obtaining the spinal fatigue degree rule through the expert experience database, and performing spinal fatigue time threshold statistics according to the spinal fatigue degree rule, thereby obtaining spinal fatigue time threshold data; Step S256: Estimate the spinal fatigue adjustment time of the spinal fatigue trend data according to the spinal fatigue time threshold data, thereby obtaining the spinal fatigue adjustment time data.

7. The intelligent vital sign monitoring and control method according to claim 1 is characterized in that: Step S3 is specifically as follows: Step S31: performing heart rate fluctuation statistics on the device heart rate sensor data, thereby obtaining the user's short heart rate fluctuation data and the user's long heart rate fluctuation data; Step S32: identifying the temporary use mode of the user according to the short heart rate fluctuation data of the user, thereby obtaining the temporary use mode data of the user; Identify the user's in-depth usage pattern based on the user's long-term heart rate fluctuation data, thereby obtaining the user's in-depth usage pattern data; Step S33: merging the user temporary usage pattern data and the user deep usage pattern data to obtain user behavior pattern data; Step S34: Predicting the user behavior pattern of the device heart rate sensor data based on the user behavior pattern data, thereby obtaining user behavior pattern prediction data; Step S35: Estimating the user behavior time based on the user behavior pattern prediction data, thereby obtaining user behavior time data.

8. The intelligent vital sign monitoring and control method according to claim 1 is characterized in that: Step S4 is specifically as follows: Step S41: dividing the user behavior time data into long-term usage behaviors, thereby obtaining the user's intensive usage prediction time data; Step S42: performing intersection time point calculation according to the spinal fatigue adjustment time data and the user depth usage prediction time data, so as to obtain ideal adjustment time point data; Step S43: Obtain the equipment vibration parameter group, and set the warning vibration time for the equipment vibration parameter group according to the ideal adjustment time point data, thereby obtaining the equipment warning vibration time data, and transmitting it to the electrical control unit to execute the equipment timed warning vibration task.

9. A system based on intelligent vital signs monitoring and control, characterized in that: Used to execute the intelligent vital sign monitoring control method according to claim 1, the intelligent vital sign monitoring control system comprises: The device deformation state analysis module is used to obtain device pressure sensor data and device heart rate sensor data, and define the device pressure benchmark according to the device pressure sensor data, so as to obtain the device benchmark pressure data; based on the device benchmark pressure data, the device pressure sensor data is integrated with the device deformation state, so as to obtain the device deformation state data; A spinal posture recognition module, used to recognize the spinal posture of the device user based on the device deformation state data, thereby obtaining the spinal posture data of the device user, and to estimate the spinal fatigue adjustment time of the spinal posture data of the device user, thereby obtaining the spinal fatigue adjustment time data; A user behavior time estimation module is used to infer user behavior patterns based on device heart rate sensor data, thereby obtaining user behavior pattern data; and to estimate user behavior time based on user behavior pattern data, thereby obtaining user behavior time data; The equipment warning vibration time analysis module is used to perform equipment warning vibration time analysis based on the spinal fatigue adjustment time data and the user behavior time data, thereby obtaining the equipment warning vibration time data and transmitting it to the electrical control unit to execute the equipment timed warning vibration task; The spinal posture correction module is used to obtain real-time device pressure sensor data, and perform real-time device user spinal posture recognition based on the real-time device pressure sensor data, thereby obtaining real-time device user spinal posture data; perform spinal posture correction strategy analysis on the real-time device user spinal posture data based on spinal fatigue trend data, thereby obtaining the posture correction strategy, and transmit it to the electrical control unit to execute the device torsion spring elastic control task.

10. A vital sign monitoring and control device, characterized in that: It includes a main body of a vital sign monitoring and control device, a power supply unit and an electrical control unit. The main body of the vital sign monitoring and control device includes an ergonomic chair, a vibrator installed on the ergonomic chair, a pressure sensor and a heart rate sensor. The power supply unit is installed inside the main body of the vital sign monitoring and control device, wherein the vibrator, the pressure sensor and the heart rate sensor are all electrically connected to the power supply unit; the electrical control unit is electrically connected to the power supply unit, the electrical control unit is used to charge the main body of the vital sign monitoring and control device and control the main body of the vital sign monitoring and control device, and the electrical control unit is used to execute the intelligent vital sign monitoring and control method as described in any one of claims 1-8.

Images