Intelligent rehabilitation brace self-adaptive adjusting system and method based on real-time pressure sensing

Abstract

The invention discloses an intelligent rehabilitation brace self-adaptive adjusting system and method based on real-time pressure sensing, and belongs to the technical field of rehabilitation medical instruments. The problems of static structure limitation, monitoring feedback deficiency and low manual adjustment efficiency of an existing method are solved, dynamic pressure adjustment is achieved by collecting pressure data in real time and based on biomechanical model analysis, the response time is made to be shorter than one second, the long-term adaptability is improved by 40%, the pressure adjustment precision error is controlled within 5 kPa, the rehabilitation effect is improved by 25%, and the rehabilitation effect is improved. A doctor can remotely monitor and optimize the scheme through the terminal, and manual intervention is reduced by 60%; the multi-dimensional threshold is calculated by integrating various data sets, pressure data is comprehensively and accurately analyzed, tissue damage is effectively prevented, efficient use of the brace is ensured, comfort is considered, pressure sores are prevented, the rehabilitation effect is remarkably improved, the rehabilitation process is accelerated, and the method has good application prospects.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of rehabilitation medical devices, in particular to an intelligent rehabilitation brace adaptive adjustment system and method based on real-time pressure sensing. BACKGROUND

[0002] The existing rehabilitation brace has three defects: 1. Static structure limitation: The brace is designed statically and cannot adapt to the posture changes during the patient's rehabilitation process (such as improvement of scoliosis angle and recovery of muscle strength), which easily leads to excessive local pressure (risk of pressure sores) or insufficient pressure (affecting rehabilitation); 2. Lack of monitoring and feedback: There is a lack of continuous monitoring of pressure during wearing, and doctors can only adjust regularly, which is lagging and lacks individualization; 3. Low efficiency of manual adjustment: Pressure depends on manual adjustment of straps or shims, which is low in precision and poor in efficiency.

[0003] Although some companies, such as Qingdao Wisdome, have laid out digital orthopedic brace patents, they have not solved the core problem of real-time pressure sensing + dynamic adaptive adjustment, and the intelligence level of the brace is insufficient.

[0004] Therefore, the existing needs are not met, and for this purpose, we propose an intelligent rehabilitation brace adaptive adjustment system and method based on real-time pressure sensing. SUMMARY

[0005] The purpose of the present application is to provide an intelligent rehabilitation brace adaptive adjustment system and method based on real-time pressure sensing, which realizes dynamic pressure regulation by real-time acquisition of pressure data and analysis based on biomechanical model, so that the response time is less than 1 second, the long-term adaptability is improved by 40%, the pressure regulation precision error is controlled within 5kPa, the rehabilitation effect is improved by 25%, and the doctor can remotely monitor and optimize the scheme through the terminal, and the manual intervention is reduced by 60%; by integrating multiple data sets to calculate multi-dimensional threshold values, the pressure data is comprehensively and accurately analyzed, tissue damage is effectively prevented, efficient use of the brace is ensured, comfort is considered, pressure sores are prevented, rehabilitation effect is significantly improved, rehabilitation process is accelerated, and good application prospects are achieved, solving the problems raised in the above background.

[0006] To achieve the above purpose, the present application provides the following technical scheme: An intelligent rehabilitation brace adaptive adjustment system based on real-time pressure sensing, comprising: A pressure monitoring unit configured to integrate a flexible pressure sensor array at the contact part of the brace and the human body for real-time acquisition of pressure data; A data analysis unit configured to construct multi-dimensional threshold values based on historical data and analyze whether the pressure data of the contact part of the brace and the human body exceeds the multi-dimensional threshold value range through a biomechanical model; An adaptive adjustment unit is configured to send a control instruction to the micro air bag through the terminal to adjust the pressure of the corresponding part when the analysis result shows slight pressure abnormalities.

[0007] Further, the data analysis unit comprises: A multi-dimensional threshold setting module is configured to collect historical pressure data continuously collected at a high frequency as a first data set; Collect biomechanical data and kinematic data collected by accelerometers and gyroscopes integrated in the brace and label the information as a second data set; Collect the recorded comfort scores at specific time points or when the patient feels unwell as a third data set; Collect the tissue tolerance curve determined in the clinical trial, such as the pressure-time curve, and the corresponding endothelial temperature data within the corresponding time as a fourth data set; Based on the clinical trial and biomechanics, set the initial multi-dimensional threshold; Based on the initial multi-dimensional threshold, combine the first data set, the second data set, the third data set, and the fourth data set to calculate the multi-dimensional threshold.

[0008] Further, in the data analysis unit, based on the initial multi-dimensional threshold, combine the first data set, the second data set, and the third data set to calculate the multi-dimensional threshold, comprising: For the first data set, take the statistical extreme value of the data of each sensor in each activity state, and take the minimum value with the general safety threshold to obtain the safety threshold; For the second data set, according to the clinical orthopedic target, calculate the minimum pressure value required to be maintained on the contact surface of the brace and the human body contact part through the biomechanical model, and combine the lower limit of the pressure in the second data set to achieve this effect to obtain the efficiency threshold; For the third data set, take the first data set as the feature and the comfort score in the third data set as the label, and predict the pressure interval of comfort through the logistic regression algorithm as the comfort threshold; For the fourth data set, according to the tissue tolerance curve and skin temperature data, set the upper limit of the pressure-time integral for each sensor as the time integral threshold.

[0009] Further, the data analysis unit further comprises: A model construction module is configured to construct a biomechanical model composed of a spine finite element model and an ankle motion model based on patient image data, input historical pressure data into the biomechanical model, calculate the stress of the spine or ankle in different activity states according to the input data, and analyze whether the pressure exceeds the safety threshold, whether it is lower than the efficiency threshold, whether it exceeds the comfort threshold, and whether it approaches or exceeds the time integral threshold. a model verification module configured to compare the prediction results of the biomechanical model with historical clinical results to verify the accuracy and reliability of the biomechanical model; if there is a large deviation between the prediction results of the biomechanical model and the historical clinical results, further adjust the model parameters; until the prediction results of the model are consistent with the historical clinical results, and put into use.

[0010] Further, the data analysis unit further comprises: a model application module configured to input the patient pressure data collected by the pressure monitoring unit in real time after preprocessing into the biomechanical model that has passed the training for prediction, and output the prediction results; a model updating module configured to update and optimize the biomechanical model according to the adjustment effect and patient feedback; and periodically recalibrate and verify the biomechanical model to ensure its long-term stability and reliability.

[0011] Further, the adaptive adjustment unit comprises: an adjustment instruction generation module configured to generate corresponding control instructions according to the analysis results of the biomechanical model, and send the control instructions to the micro air bag through the terminal; a monitoring and feedback module configured to monitor the pressure change in real time during the air bag adjustment process to ensure that the adjustment effect meets the expectation; if the pressure still does not reach the threshold range, continue to adjust until the pressure reaches the safe, effective and comfortable range.

[0012] Further, the pressure monitoring unit comprises: a closed-loop monitoring module configured to collect pressure data again after the completion of air bag adjustment, and compare with the multi-dimensional threshold to verify the adjustment effect; if the pressure still exceeds the threshold range, continue to adjust, and record the process and results of each adjustment.

[0013] Further, the pressure monitoring unit further comprises: a preprocessing module configured to clean the collected pressure data to remove outliers and noise; and normalize the data to convert the pressure data to a unified dimension range; a feature extraction module configured to extract key features of the pressure data, including the mean, variance and extreme value of the pressure, and extract the time variation characteristics of the pressure data, including the rising rate and falling rate of the pressure, as input parameters of the biomechanical model.

[0014] Further, it further comprises: a data transmission unit configured to transmit the pressure data in real time to the control terminal through Bluetooth or WiFi by the flexible pressure sensor array integrated in the brace, and the terminal includes but is not limited to a mobile phone or a dedicated controller. A data storage unit is configured to store the collected pressure data in real time in the storage device of the terminal, and the data storage format includes a timestamp, a pressure value and sensor position information, so that medical personnel can view the real-time pressure data and historical pressure change trend of the patient at any time through the terminal device.

[0015] The intelligent rehabilitation brace adaptive adjustment method based on real-time pressure sensing includes the following steps: One FlexiForce A201 sensor is arranged every 5 cm on the convex or concave side of the brace to form a flexible pressure sensor array; A 10 mL micro air bag is embedded at the corresponding position, and an air pump and an electromagnetic valve are connected; After the patient wears the brace, the flexible pressure sensor array collects pressure data in real time, and the pressure data is transmitted to the biomechanical model for analysis to determine whether the pressure data exceeds or is lower than the multidimensional threshold; The analysis result is displayed on the terminal, if the analysis result shows that the pressure of a certain area on the convex side exceeds the multidimensional threshold, the air bag is controlled to deflate; If the analysis result shows that the pressure of a certain point on the concave side is lower than the multidimensional threshold, the air bag is controlled to inflate; The adjusted pressure data is continuously monitored, and the adjustment effect is fed back through the terminal to optimize the adjustment strategy and biomechanical model parameters.

[0016] Compared with the prior art, the present application has the following advantages: 1. In the present application, the pressure data of the patient is collected in real time, analyzed based on the biomechanical model, and the pressure output is dynamically adjusted, so that the response time of the adjustment is less than 1 second, the posture change in the rehabilitation process is adapted, and the long-term adaptability is improved by 40%; based on the biomechanical model and clinical feedback, the pressure adjustment accuracy error is less than or equal to 5kPa, and the rehabilitation effect is improved by 25%; based on the terminal visual display, the doctor can remotely monitor and optimize the scheme, and the manual intervention is reduced by 60%; the pressure sensor can support multiple types of braces such as the spine and ankle joint, the model is continuously iterated with clinical data, and has good application prospect.

[0017] 2. In the present application, the precise multidimensional threshold is calculated by integrating multiple data sets, which can comprehensively and accurately analyze whether the pressure data of the contact part between the brace and the human body exceeds the safety, efficiency, comfort and time integral multidimensional threshold range; combined with the appropriate adjustment method, it can effectively prevent tissue damage and ensure that the brace is always in an efficient use state to provide effective support or orthosis for the patient; at the same time, the comfort of the patient is taken into account to prevent blood circulation and pressure sores caused by long-term moderate pressure, thereby significantly improving the rehabilitation effect and accelerating the rehabilitation process of the patient. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 Flow chart of the intelligent rehabilitation brace adaptive adjustment method based on real-time pressure sensing of the present application; Figure 2 Flow chart of the multi-dimensional threshold setting of the present application; Figure 3 System composition diagram of the intelligent rehabilitation brace adaptive adjustment system based on real-time pressure sensing of the present application; Figure 4 Scoliosis brace sensor arrangement schematic of the present application.

[0019] In the figure: 1, brace; 2, flexible pressure sensor array. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0021] To solve the technical problems in the prior art that the static structure has limitations, cannot adapt to the posture changes in the rehabilitation process of the patient, is prone to cause excessive or insufficient local pressure, lacks monitoring feedback mechanism, and the doctor can only adjust regularly, which is lagging and lacks individualization, and the pressure relies on manual adjustment of the bandage or gasket, which has low precision and poor efficiency, please refer to Figure 1 Figure 4 The technical solutions provided by the present embodiment are as follows: The intelligent rehabilitation brace adaptive adjustment system based on real-time pressure sensing comprises: A pressure monitoring unit is configured at the contact part of the brace 1 and the human body, such as the convex or concave side of the scoliosis brace 1 or the medial or lateral side of the ankle brace 1, and integrates a flexible pressure sensor array 2, such as a thin film sensor, which has an accuracy of ±1kPa and a sampling frequency of ≥50Hz, for real-time acquisition of pressure data; the pressure monitoring unit comprises: A closed-loop monitoring module is configured to collect pressure data again after the completion of air bag adjustment, compare the data with multi-dimensional thresholds, and verify the adjustment effect; if the pressure still exceeds the threshold range, the adjustment is continued, and the process and results of each adjustment are recorded, including the pressure values before and after adjustment, adjustment time, adjustment amplitude, etc.; so that subsequent analysis of the recorded data can continuously optimize the adjustment strategy and improve the accuracy and efficiency of the adjustment.

[0022] ​The preprocessing module is configured to clean the collected pressure data, remove outliers and noise; for example: identify and eliminate data points outside the normal range through statistical methods; normalize the data, convert the pressure data to a unified dimension range, and facilitate subsequent analysis and processing.

[0023] The feature extraction module is configured to extract key features of the pressure data, including mean, variance and extreme value of the pressure, and extract time-varying features of the pressure data, including the rising rate and falling rate of the pressure, as input parameters of the biomechanical model, which helps the model analyze the dynamic changes of the pressure.

[0024] The data analysis unit is configured to construct multi-dimensional threshold based on historical data, and analyze whether the pressure data of the contact part between the brace 1 and the human body exceeds the multi-dimensional threshold range through a biomechanical model, such as a spine finite element or ankle joint motion model; the data analysis unit includes: The multi-dimensional threshold setting module is configured to collect historical pressure data collected at a high frequency of ≥50Hz as a first data set; for example: sitting, walking, running and sleeping; use a digital filter, such as a low-pass filter, to smooth the historical pressure data and eliminate abnormal spikes caused by interference; align the cleaned historical pressure data with the activity state label, and prepare for subsequent classification analysis by activity mode.

[0025] Collect the biomechanical data and kinematic data collected by the accelerometer and gyroscope integrated in the brace 1, and label the information as a second data set; it includes posture data: angle and curvature of the limb, such as Cobb angle estimation of the spine and inversion or eversion angle of the ankle joint; activity state recognition: different activity modes such as sitting, walking, running and going up and down stairs; electromyographic signal data: attach EMG sensors to key muscle groups to monitor muscle fatigue, which can cause posture deformation and abnormal pressure, thus serving as a leading indicator for early warning.

[0026] Collect the comfort score recorded at a specific time point or when the patient feels uncomfortable, such as 1-10 points, as a third data set; collect the tissue tolerance curve determined in the clinical trial, such as the pressure-time curve, and the corresponding time endothelial temperature data, as a fourth data set.

[0027] Based on clinical trials and biomechanics, set initial multi-dimensional threshold values; for example: a safety threshold of 200kPa and an efficiency threshold of 30kPa; based on the initial multi-dimensional threshold values, combine the first data set, the second data set, the third data set and the fourth data set to calculate the multi-dimensional threshold values, including: For the first data set, the statistical extreme value of the data of each sensor in each active state is taken, such as taking the 99.5% quantile of all data points, and then taking the minimum value with the general safety threshold to obtain the safety threshold; ensure that even if extreme action occurs, the pressure will not exceed this value.

[0028] For the second data set, according to the clinical orthopedic target, such as a 150kPa orthopedic force, the minimum pressure value required to be maintained on the contact surface of the contact part of the brace 1 and the human body is calculated through the biomechanical model, combined with the lower limit of the pressure in the second data set to achieve this effect, to obtain the efficiency threshold; ensure that the brace 1 is in high-efficiency use at any time, thereby providing effective support or orthopedic for the patient at all times.

[0029] For the third data set, the first data set is taken as a feature, and the comfort score in the third data set is taken as a label, and the pressure interval of the comfort degree is predicted through a logistic regression algorithm as a comfort threshold.

[0030] For the fourth data set, according to the tissue tolerance curve and skin temperature data, set the upper limit of the pressure-time integral for each sensor as the time integral threshold; for example: set the risk value as 80kPa pressure lasting more than 2 hours: 7200 seconds, then I_max=80*7200=576000kPa·s; also can be fine-tuned according to the local skin temperature data, if the temperature of a certain place is detected to rise continuously, then reduce the I_max value of this area.

[0031] The model construction module is configured to construct a biomechanical model composed of a spine finite element model and an ankle joint motion model based on patient image data, input historical pressure data into the biomechanical model, and calculate the stress of the spine or ankle joint in different active states according to the input data, analyze whether the pressure exceeds the safety threshold, whether it is lower than the efficiency threshold, whether it exceeds the comfort threshold, and whether it approaches or exceeds the time integral threshold.

[0032] The model verification module is configured to compare the prediction results of the biomechanical model with the historical clinical results to verify the accuracy and reliability of the biomechanical model; if the prediction results of the biomechanical model deviate greatly from the historical clinical results, further adjust the model parameters; until the prediction results of the model are consistent with the historical clinical results, ensure that the biomechanical model can accurately reflect the actual biomechanical behavior, and put into use.

[0033] The model application module is configured to input the patient pressure data collected by the pressure monitoring unit in real time after preprocessing into the biomechanical model that has passed the training for prediction, and output the prediction results; if the pressure data exceeds the safety threshold and the comfort threshold, and the pressure-time integral value approaches the dangerous value, the terminal is sent a corresponding alarm signal, and the adaptive adjustment unit is notified to adjust; if the pressure data is lower than the efficiency threshold, the terminal is sent a signal prompting insufficient efficiency, and the adaptive adjustment unit is notified to adjust.

[0034] The model updating module is configured to update and optimize the biomechanical model according to the adjustment effect and patient feedback; if it is found that the model is inaccurate in some cases, the model parameters need to be adjusted or the model structure needs to be improved; and the biomechanical model is periodically recalibrated and verified to ensure its long-term stability and reliability; to better adapt to the individual differences and rehabilitation process of patients and provide the best rehabilitation support for patients.

[0035] The adaptive adjustment unit is configured to send control instructions to the micro air bag through the terminal to adjust the pressure of the corresponding part when the analysis result shows slight pressure abnormalities; for example, if a certain area is > 200kPa or < 30kPa, the air bag is controlled to inflate or deflate; the adaptive adjustment unit includes: The adjustment instruction generation module is configured to generate corresponding control instructions according to the analysis results of the biomechanical model, and send control instructions to the micro air bag through the terminal; for example, when the pressure of a certain part exceeds the safety threshold, the air bag of the part is controlled to deflate quickly to reduce the pressure; when the pressure is lower than the efficiency threshold, the air bag is controlled to inflate to increase the support force.

[0036] The monitoring and feedback module is configured to monitor the pressure changes in real time during the air bag adjustment process to ensure that the adjustment effect meets the expectations; if the pressure is still not within the threshold range, the adjustment continues until the pressure is within the safe, effective and comfortable range.

[0037] The above-mentioned beneficial effects: by integrating multiple data sets to calculate accurate multi-dimensional thresholds, the pressure data of the contact part of the brace 1 and the human body can be comprehensively and accurately analyzed to determine whether it exceeds the safety, efficiency, comfort and time integral multi-dimensional threshold range; combined with appropriate adjustment methods, tissue damage can be effectively prevented, and the brace 1 can always be in an efficient use state to provide effective support or orthopedic for patients; at the same time, the comfort of patients is taken into account to prevent problems such as poor blood circulation and pressure sores caused by long-term moderate pressure, thereby significantly improving the rehabilitation effect and accelerating the rehabilitation process of patients.

[0038] The data transmission unit is configured as a flexible pressure sensor array 2 integrated in the support 1 to transmit pressure data to the control terminal in real time via Bluetooth or WiFi. The terminal includes, but is not limited to, a mobile phone or a dedicated controller.

[0039] The data storage unit is configured to store the collected pressure data in real time in the terminal's storage device. The data storage format includes timestamps, pressure values, and sensor location information. Medical staff can view the patient's real-time pressure data and historical pressure change trends at any time through the terminal device, providing support for clinical decision-making.

[0040] The adaptive adjustment method for intelligent rehabilitation braces based on real-time pressure sensing includes the following steps: In one embodiment, let's take "scoliosis brace 1" as an example: One FlexiForceA201 sensor is arranged every 5cm on the convex or concave side of the support 1, for a total of 12 sensors, forming a flexible pressure sensor array 2; Embed a 10mL micro-airbag in the corresponding position and connect an air pump to a solenoid valve. The air pump flow rate is 10mL or s. After the patient wears brace 1, pressure data is collected in real time at a sampling frequency of 50Hz by flexible pressure sensor array 2, and the pressure data is transmitted to the biomechanical model for analysis to determine whether the pressure data exceeds or falls below the multi-dimensional threshold. If the analysis results are displayed on the terminal, and the analysis results show that the pressure in a certain area on the convex side is 220 kPa, which exceeds the multi-dimensional threshold of 200 kPa, then the airbag is controlled to pump air to 180 kPa. If the analysis results show that the pressure at a certain point on the concave side is 40 kPa, which is lower than the multidimensional threshold of 50 kPa, then control the airbag to inflate to 60 kPa. Continue to monitor the adjusted pressure data. The patient returned for a follow-up visit 2 weeks later. The scoliosis had improved from 30° to 25°. The doctor input "the support on the convex side can be reduced and the support on the concave side needs to be strengthened" through the terminal and optimized the model parameters. The subsequent adjustment accuracy improved by 15% and the fit increased from 80% to 92%.

[0041] The beneficial effects achieved by the above are as follows: By collecting patients' pressure data in real time and analyzing it based on a biomechanical model, the pressure output can be dynamically adjusted; thereby achieving a response time of less than 1 second, adapting to changes in posture during rehabilitation, and improving long-term adaptability by 40%; based on the biomechanical model and clinical feedback, the pressure adjustment accuracy error is ≤5kPa, improving rehabilitation effect by 25%; based on terminal visualization, doctors can remotely monitor and optimize the plan, reducing manual intervention by 60%; the pressure sensor can support multiple types of braces such as the spine and ankle joints1, and the model is continuously iterated with clinical data, showing good application prospects.

[0042] Working principle: Real-time pressure data is collected by the flexible pressure sensor array 2, four data sets are collected and integrated, and safety threshold, efficiency threshold, comfort threshold and time integral threshold are calculated for each data set to form a multi-dimensional threshold; through biomechanical model analysis, whether the real-time pressure data exceeds the multi-dimensional threshold is analyzed, if the pressure data exceeds or is lower than the multi-dimensional threshold, the adaptive adjustment unit sends control instructions to the micro air bag through the terminal to quickly adjust the pressure of the corresponding part, and ensures that the patient is always in a safe, effective and comfortable treatment state during the rehabilitation process, while preventing problems such as poor blood circulation and pressure sores caused by long-term moderate pressure.

[0043] It should be noted that, in this document, the terms such as first and second are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between such entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or inherent to such a process, method, article or device.

[0044] Although embodiments of the present application have been shown and described, it will be understood by those having ordinary skill in the art that various changes, modifications, alternatives and variations can be made thereto without departing from the principles and spirit of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. An intelligent rehabilitation orthosis adaptive adjustment system based on real-time pressure sensing, characterized in that, The application relates to a self-adaptive pressure regulating system for orthosis, comprising: a pressure monitoring unit configured to integrate a flexible pressure sensor array (2) at the contact part between the orthosis (1) and the human body, for real-time acquisition of pressure data; a data analysis unit configured to construct a multi-dimensional threshold based on historical data, and analyze whether the pressure data of the contact part between the orthosis (1) and the human body exceeds the multi-dimensional threshold range through a biomechanical model; an adaptive adjustment unit configured to send a control instruction to a micro air bag through a terminal when the analysis result shows slight pressure abnormality, so as to adjust the pressure of the corresponding part.

2. The real-time pressure-sensor-based smart rehabilitation orthosis adaptive adjustment system according to claim 1, characterized in that, The data analysis unit comprises: a multi-dimensional threshold setting module configured to collect historical pressure data acquired at a high frequency as a first data set; collect biomechanical data and kinematic data collected by accelerometers and gyroscopes integrated in the orthosis (1), and perform information labeling on the data, as a second data set; collect comfort scores recorded at specific time points or when the patient feels uncomfortable, as a third data set; collect the tissue tolerance curve determined in the clinical test, such as the pressure-time curve, and the corresponding endothelial temperature data within the time, as a fourth data set; set an initial multi-dimensional threshold based on the clinical test and the biomechanics; calculate the multi-dimensional threshold based on the initial multi-dimensional threshold, combined with the first data set, the second data set, the third data set and the fourth data set.

3. The real-time pressure-sensor-based smart rehabilitation orthosis adaptive adjustment system according to claim 2, characterized in that, In the data analysis unit, based on the initial multi-dimensional threshold, combined with the first data set, the second data set and the third data set, the multi-dimensional threshold is calculated, comprising: for the first data set, taking the statistical extreme value of each sensor in each activity state, and taking the minimum value with the general safety threshold to obtain the safety threshold; for the second data set, according to the clinical orthopedic target, the minimum pressure value required to be maintained on the contact surface of the contact part between the orthosis (1) and the human body is calculated through a biomechanical model, and the lower limit of the pressure in the second data set to achieve this effect is combined to obtain the efficiency threshold; for the third data set, the first data set is taken as a feature, and the comfort score in the third data set is taken as a label, and the pressure interval of the comfort degree is predicted through a logistic regression algorithm, as a comfort threshold; for the fourth data set, according to the tissue tolerance curve and the skin temperature data, the upper limit of the pressure-time integral of each sensor is set as the time integral threshold.

4. The real-time pressure-sensor-based smart rehabilitation orthosis adaptive adjustment system according to claim 3, characterized in that, The data analysis unit further comprises: a model construction module configured to construct a biomechanical model composed of a spine finite element model and an ankle motion model based on patient image data, input historical pressure data into the biomechanical model, calculate the stress condition of the spine or ankle in different activity states according to the input data, and analyze whether the pressure exceeds the safety threshold, whether the pressure is lower than the efficiency threshold, whether the pressure exceeds the comfort threshold and whether the pressure approaches or exceeds the time integral threshold; a model verification module configured to compare the prediction result of the biomechanical model with the historical clinical result, verify the accuracy and reliability of the biomechanical model, further adjust the model parameters if the prediction result of the biomechanical model deviates greatly from the historical clinical result, and until the prediction result of the model is consistent with the historical clinical result and is put into use.

5. The real-time pressure-sensor-based smart rehabilitation orthosis adaptive adjustment system according to claim 4, characterized in that, The data analysis unit further comprises: The model application module is configured to input the patient pressure data collected by the pressure monitoring unit in real time after preprocessing into the biomechanical model that has passed the training for prediction, and output the prediction results; The model updating module is configured to update and optimize the biomechanical model according to the adjustment effect and patient feedback; and periodically recalibrate and verify the biomechanical model to ensure its long-term stability and reliability.

6. The real-time pressure-sensor-based smart rehabilitation orthosis adaptive adjustment system according to claim 5, characterized in that, The adaptive adjustment unit comprises: The adjustment instruction generation module is configured to generate corresponding control instructions according to the analysis results of the biomechanical model, and send the control instructions to the micro air bag through the terminal; The monitoring and feedback module is configured to monitor the pressure change in real time during the air bag adjustment process to ensure that the adjustment effect meets the expectation; if the pressure still does not reach the threshold range, continue to adjust until the pressure reaches a safe, effective and comfortable range.

7. The real-time pressure-sensor-based smart rehabilitation orthosis adaptive adjustment system according to claim 6, characterized in that, The pressure monitoring unit comprises: The closed-loop monitoring module is configured to collect pressure data again after the air bag adjustment is completed, and compare it with the multi-dimensional threshold to verify the adjustment effect; if the pressure still exceeds the threshold range, continue to adjust and record the process and results of each adjustment.

8. The real-time pressure-sensor-based smart rehabilitation orthosis adaptive adjustment system according to claim 7, characterized in that, The pressure monitoring unit further comprises: The preprocessing module is configured to clean the collected pressure data and remove outliers and noise; normalize the data to convert the pressure data into a unified dimension range; The feature extraction module is configured to extract the key features of the pressure data, including the mean, variance and extreme value of the pressure, and the time-varying features of the pressure data, including the rising rate and falling rate of the pressure, as input parameters of the biomechanical model.

9. The real-time pressure-sensor-based smart rehabilitation orthosis adaptive adjustment system according to claim 1, wherein, Further comprising: The data transmission unit is configured to transmit the pressure data in real time from the flexible pressure sensor array (2) integrated in the brace (1) to the control terminal through Bluetooth or WiFi, and the terminal includes but is not limited to a mobile phone or a dedicated controller; The data storage unit is configured to store the collected pressure data in real time in the storage device of the terminal, and the data storage format includes timestamp, pressure value and sensor position information, and medical personnel can check the real-time pressure data and historical pressure change trend of the patient at any time through the terminal device.

10. The adaptive adjustment method of the intelligent rehabilitation brace based on real-time pressure sensing, applied to the adaptive adjustment system of the intelligent rehabilitation brace based on real-time pressure sensing according to any one of claims 1-9, characterized in that, The steps comprise: One FlexiForce A201 sensor is arranged every 5 cm on the convex or concave side of the brace (1) to form a flexible pressure sensor array (2); A 10 mL micro air bag is embedded at the corresponding position and connected with an air pump and an electromagnetic valve; After the patient wears the brace (1), the flexible pressure sensor array (2) collects pressure data in real time and transmits the pressure data to the biomechanical model for analysis to determine whether the pressure data exceeds or is lower than the multi-dimensional threshold; If the analysis result shows that the pressure of a certain area on the convex side exceeds the multi-dimensional threshold, the air bag is controlled to deflate; If the analysis result shows that the pressure of a certain point on the concave side is lower than the multi-dimensional threshold, the air bag is controlled to inflate; Continue to monitor the pressure data after adjustment, and feed back the adjustment effect through the terminal to optimize the adjustment strategy and biomechanical model parameters.

Images