Intelligent orthopedic rehabilitation monitoring method and system

Abstract

The invention relates to the technical field of intelligent medical systems, in particular to an intelligent orthopedic rehabilitation monitoring method and a system thereof.The method comprises the steps that elastic modulus data of target tissue is collected through a surface acoustic wave sensor array, and motion posture and blood oxygen saturation data are synchronously obtained through an accelerometer and a photoelectric volume pulse wave sensor; performing noise filtering, abnormal value detection, multi-source data alignment and feature extraction on the elastic modulus data to obtain feature data, and calculating a joint motion range, a tissue elastic modulus change rate and a blood oxygen fluctuation rate; based on the feature data, the current rehabilitation state is judged, and the current rehabilitation state comprises inflammation, extravasated blood and thrombus risk levels; according to the current rehabilitation state, air bag pressure, an optical flow guiding mode and a voice prompt strategy are adjusted in real time; and when an abnormal index is detected, triggering a grading early warning mechanism, and executing a corresponding intervention measure. Pathology is accurately recognized, and self-adaptive management of the rehabilitation process is completed based on an intelligent algorithm.

Description

Technical Field

[0001] The present invention relates to the technical field of smart medical systems, and in particular to an intelligent orthopedic rehabilitation monitoring method and system thereof. Background Art

[0002] With the aging population and increasing sports injuries, the number of patients suffering from knee joint diseases continues to rise. According to the World Health Organization, approximately 350 million people worldwide suffer from varying degrees of knee joint disease, with the incidence of complications caused by improper postoperative rehabilitation management reaching as high as 28%. In recent years, smart wearable devices have demonstrated great potential in the field of rehabilitation medicine.

[0003] Currently, postoperative knee rehabilitation primarily relies on traditional rehabilitation devices and manual guidance, which suffer from issues such as inadequate monitoring accuracy and delayed feedback. Existing rehabilitation knee braces often utilize a single pressure sensor or inertial measurement unit (IMU) for motion monitoring, failing to assess real-time changes in tissue status (such as edema, congestion, and other pathological features). Clinical studies have shown that approximately 35% of postoperative complications stem from the failure to promptly detect tissue abnormalities during the rehabilitation process. Furthermore, these devices typically rely on external power supplies, limiting their continuous use time and failing to meet the needs of long-term rehabilitation. Furthermore, most commercially available products only monitor motion parameters (such as joint angle and gait) and lack quantitative analysis of tissue biomechanical properties (such as elastic modulus), hindering early identification of inflammation or thrombosis risks. Existing systems often rely on vibration or on-screen prompts, requiring patients to learn the operating logic, leading to poor compliance among the elderly. Continuous monitoring requires daily charging, while the application of piezoelectric energy harvesting technology in this field remains limited to the laboratory stage, with existing solutions exhibiting insufficient energy conversion efficiency.

[0004] In response to the above problems, the present invention proposes an intelligent orthopedic rehabilitation monitoring method and system. Summary of the Invention

[0005] To address the aforementioned technical issues of single detection dimension, inefficient interaction, and high energy dependency, we provide an intelligent orthopedic rehabilitation monitoring method and system. This invention primarily utilizes the deep integration of a surface acoustic wave (SAW) sensor array and a piezoelectric energy harvesting system, combined with multimodal interactive guidance and dynamic pressure regulation mechanisms, to achieve the technical effects of accurate pathology identification, adaptive rehabilitation management, and energy self-sustaining.

[0006] The technical means adopted in the present invention are as follows:

[0007] The intelligent orthopedic rehabilitation monitoring method includes the following steps:

[0008] The elastic modulus data of the target tissue is collected through a surface acoustic wave sensor array, and the motion posture and blood oxygen saturation data are synchronously acquired through an accelerometer and a photoplethysmography sensor;

[0009] Performing noise filtering, outlier detection, multi-source data alignment, and feature extraction on the elastic modulus data to obtain feature data and calculate joint range of motion, tissue elastic modulus change rate, and blood oxygen fluctuation rate;

[0010] Determining the current recovery status based on the characteristic data, the current recovery status including inflammation, congestion, and thrombosis risk levels;

[0011] According to the current recovery status, the airbag pressure, optical flow guidance mode and voice prompt strategy are adjusted in real time;

[0012] When abnormal indicators are detected, the graded warning mechanism is triggered and corresponding intervention measures are implemented.

[0013] Furthermore, the surface acoustic wave sensor array acquires tissue elastic modulus data at a sampling frequency of 120 Hz, and synchronously acquires motion posture and blood oxygen saturation data through an accelerometer and a photoplethysmography sensor, and sets the following judgment thresholds:

[0014] Normal reference value: 14.2±1.5kPa;

[0015] Criteria for determining inflammatory edema: decrease in tissue elastic modulus > 15%;

[0016] Criteria for determining congestive swelling: tissue elastic modulus decreases by <5% and blood oxygen saturation decreases by >3%.

[0017] Furthermore, the noise filtering, outlier detection, multi-source data alignment and feature extraction specifically include:

[0018] A 0.1-40Hz bandpass filter was used to remove ambient noise;

[0019] Identify abnormal waveforms based on the mean ± 3σ principle;

[0020] Multi-sensor data synchronization through timestamp interpolation;

[0021] Extract the characteristics of joint range of motion, tissue elasticity change trends and blood oxygen dynamic changes.

[0022] Furthermore, judging the current recovery status based on the characteristic data includes:

[0023] Acute phase monitoring: monitoring of swelling and basal range of motion;

[0024] Functional phase monitoring: assessing gait reconstruction and myoelectric activation levels;

[0025] Monitoring during the intensive phase: Analyze muscle balance and step training performance.

[0026] Furthermore, the real-time adjustment of the airbag pressure, optical flow guidance mode and voice prompt strategy includes:

[0027] Airbag pressure control: Based on the joint angle θ, swelling degree S and pain index P, the airbag pressure value is calculated according to Pi = f(θ, S, P), with a control cycle of 200ms;

[0028] Optical flow guidance adjustment: initial optical flow speed is 1.2 seconds / cycle, which is adaptively adjusted according to the patient's reaction time;

[0029] Voice interaction optimization: Based on the voiceprint features collected by the bone conduction microphone, the prompt frequency and content are adjusted in real time.

[0030] Furthermore, the hierarchical warning mechanism includes:

[0031] Green warning: If the target is not met on a single day, the system will automatically optimize the training plan;

[0032] Yellow warning: If abnormalities occur for two consecutive days, a review request will be sent to the community workstation;

[0033] Red alert: If the daytime leg circumference increases by >3cm and the nighttime blood oxygen fluctuation is <1%, the patient is considered at risk of thrombosis and the following actions are performed:

[0034] Automatically switches to 20mmHg continuous pressure mode;

[0035] Send emergency alerts to family members and hospitals;

[0036] Make an appointment for a vascular ultrasound at the nearest hospital.

[0037] Furthermore, the method also includes an adaptive adjustment operation during the rehabilitation stage:

[0038] Stage advancement conditions: achieving stage goals for 5 consecutive days without adverse reactions;

[0039] Stage decline conditions: failure to achieve the target for three consecutive days or abnormal indicators appear;

[0040] Transition Training Pack Insertion: When the descent condition is triggered, insert 5 simplified movement trainings for 2 days.

[0041] The present invention also includes an intelligent orthopedic rehabilitation monitoring system for implementing the above-mentioned intelligent orthopedic rehabilitation monitoring method, comprising:

[0042] Biosignal sensing and energy self-sufficiency module, including a surface acoustic wave sensor array and a piezoelectric energy harvesting system;

[0043] Multimodal interaction module, including bone conduction voice system and optical flow guidance system;

[0044] A dynamic pressure control module, including an array of several regional independent airbags;

[0045] A dynamic adjustment module for the rehabilitation process, used to adjust the training program based on multi-dimensional indicators;

[0046] The three-level early warning network module enables collaborative intervention of patients' health among hospitals, communities and families.

[0047] Furthermore, the surface acoustic wave sensor array adopts an 8×8 matrix layout, a unit size of 2mm×2mm, and a sampling frequency of 120Hz.

[0048] Furthermore, the piezoelectric energy harvesting system comprises:

[0049] Piezoelectric fibers made of polyvinylidene fluoride are placed at the knee brace hinge;

[0050] Energy conversion efficiency 12.5mW / flexion and extension movement;

[0051] The power consumption is distributed as follows: surface acoustic wave sensor array 3.2mW / h, micro air pump 5.5mW / h, computing chip 2.8mW / h.

[0052] Compared with the prior art, the present invention has the following advantages:

[0053] 1. This invention integrates SAW ultrasonic tissue elasticity detection, motion posture sensing, and blood oxygen monitoring to construct a multi-dimensional rehabilitation assessment system that comprehensively reflects the physiological state and motor function of the knee joint. Combined with dynamic pressure regulation and optical flow guidance, it achieves a closed-loop management system for "tissue state-motion posture-rehabilitation training," significantly improving the scientific and targeted nature of rehabilitation programs.

[0054] 2. This invention utilizes an interactive method that combines bone conduction voice prompts with visual optical flow guidance, reducing operational complexity through multi-sensory collaborative feedback. The system automatically adjusts guidance strategies based on the patient's real-time performance, providing personalized guidance for users at different stages of rehabilitation and cognitive levels, significantly improving compliance and accuracy in rehabilitation training.

[0055] 3. This invention's innovative piezoelectric energy harvesting and intelligent power management system utilizes human motion to generate power, enabling long-term, continuous operation of the monitoring device. This system transcends the limitations of traditional rehabilitation equipment that rely on external power sources, enabling truly uninterrupted rehabilitation monitoring and is particularly well-suited for home rehabilitation applications.

[0056] 4. This invention establishes a three-level intelligent early warning mechanism based on multi-parameter fusion, which automatically triggers appropriate intervention measures based on risk levels. From automatic system adjustments to community medical intervention and then to emergency hospital treatment, it forms a complete "monitoring-early warning-intervention" closed-loop management chain, effectively reducing the risk of complications during the recovery process.

[0057] Based on the above reasons, the present invention can be widely promoted in fields such as smart medical systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0059] Figure 1 This is a flow chart of an intelligent orthopedic rehabilitation monitoring method of the present invention. DETAILED DESCRIPTION

[0060] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only 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 ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0061] like Figure 1 As shown, the present invention provides an intelligent orthopedic rehabilitation monitoring method, the specific steps are:

[0062] S1. Collect elastic modulus data of target tissue through surface acoustic wave sensor array, and synchronously acquire motion posture and blood oxygen saturation data through accelerometer and photoplethysmography sensor.

[0063] Specifically, the surface acoustic wave sensor array acquires tissue elastic modulus data at a sampling frequency of 120 Hz, and synchronously acquires motion posture and blood oxygen saturation data through an accelerometer and photoplethysmography sensor. The following judgment thresholds are set:

[0064] Normal reference value: 14.2±1.5kPa.

[0065] Criteria for determining inflammatory edema: a decrease in tissue elastic modulus >15%.

[0066] Criteria for determining congestive swelling: tissue elastic modulus decreases by <5% and blood oxygen saturation decreases by >3%.

[0067] S2. Perform noise filtering, outlier detection, multi-source data alignment, and feature extraction on the elastic modulus data to obtain feature data and calculate joint range of motion, tissue elastic modulus change rate, and blood oxygen fluctuation rate.

[0068] The specific steps of noise filtering, outlier detection, multi-source data alignment and feature extraction are:

[0069] A 0.1-40 Hz bandpass filter was used to remove ambient noise.

[0070] Abnormal waveforms are identified based on the mean ± 3σ principle.

[0071] Multi-sensor data synchronization is achieved through timestamp interpolation.

[0072] Extract the characteristics of joint range of motion, tissue elasticity change trends and blood oxygen dynamic changes.

[0073] S3. Based on the characteristic data, determine the current recovery status, which includes the risk levels of inflammation, congestion, and thrombosis.

[0074] The current recovery status is determined as follows:

[0075] Acute phase monitoring: monitoring of swelling and basal range of motion;

[0076] Functional phase monitoring: assessing gait reconstruction and myoelectric activation levels;

[0077] Monitoring during the intensive phase: Analyze muscle balance and step training performance.

[0078] S4. Adjust the airbag pressure, optical flow guidance mode, and voice prompt strategy in real time according to the current recovery status.

[0079] Specifically, step S4 includes:

[0080] Airbag pressure control: Based on the joint angle θ, swelling degree S and pain index P, the airbag pressure value is calculated according to Pi = f(θ, S, P), with a control cycle of 200ms;

[0081] Optical flow guidance adjustment: initial optical flow speed is 1.2 seconds / cycle, which is adaptively adjusted according to the patient's reaction time;

[0082] Voice interaction optimization: Based on the voiceprint features collected by the bone conduction microphone, the prompt frequency and content are adjusted in real time.

[0083] S5. When abnormal indicators are detected, the graded warning mechanism is triggered and corresponding intervention measures are implemented.

[0084] The specific hierarchical early warning mechanism is as follows:

[0085] Green warning: If the target is not met on a single day, the system will automatically optimize the training plan.

[0086] Yellow alert: When abnormalities occur for two consecutive days, a review request will be sent to the community workstation.

[0087] Red alert: If the daytime leg circumference increases by >3cm and the nighttime blood oxygen fluctuation is <1%, the patient is considered at risk of thrombosis and the following actions are performed:

[0088] Automatically switches to 20mmHg continuous pressure mode.

[0089] Send emergency alerts to family members and hospitals.

[0090] Make an appointment for a vascular ultrasound at the nearest hospital.

[0091] S6. Adaptive adjustment operation during the rehabilitation phase:

[0092] Stage advancement conditions: achieving stage goals for 5 consecutive days without adverse reactions.

[0093] Conditions for stage decline: failure to achieve the target for three consecutive days or abnormal indicators appear.

[0094] Transition Training Pack Insertion: When the descent condition is triggered, insert 5 simplified movement trainings for 2 days.

[0095] The present invention also includes an intelligent orthopedic rehabilitation monitoring system for implementing the above-mentioned intelligent orthopedic rehabilitation monitoring method, comprising:

[0096] Biosignal sensing and energy self-sufficiency module, including a surface acoustic wave sensor array and a piezoelectric energy harvesting system.

[0097] Specifically, the biosignal sensing and energy self-sufficiency module utilizes an 8×8 matrix layout of 64 surface acoustic wave (SAW) sensor arrays, each measuring 2mm×2mm, placed between the inner and outer fabric layers of the knee brace. The sensors measure tissue elastic modulus at a sampling frequency of 120Hz, with a normal reference value of 14.2±1.5kPa. A decrease in elastic modulus exceeding 15% (i.e., less than 12.07kPa) is considered inflammatory edema; a decrease in modulus less than 5% accompanied by a decrease in blood oxygen saturation exceeding 3% is considered congestive edema. To ensure continuous system operation, PVDF piezoelectric fibers are positioned at the knee brace hinges, covering the entire range of joint motion from 0° to 120°. Each full flexion and extension movement generates 12.5mW of electrical energy, of which 3.2mW / h is supplied to the SAW sensor array, 5.5mW / h to the micro-air pump, and 2.8mW / h to the computational control chip. The system forms a detection-energy supply closed loop, where SAW sensor data is used to adjust the energy distribution strategy, and the piezoelectric system provides continuous power to the sensing module.

[0098] Multimodal interaction module, including bone conduction voice system and optical flow guidance system.

[0099] The workflow of the bone conduction voice system is as follows:

[0100] The speaker is positioned close to the upper edge of the patella, with a frequency response range of 200Hz-8kHz. The dual-microphone design supports a 180-degree pickup range. A pain soundprint recognition algorithm based on spectral energy distribution characteristics analyzes the patient's "ah" sound and converts it into a VAS score (0-10). A VAS score greater than 4 triggers automatic adjustment of training intensity.

[0101] The workflow of the optical flow guidance system is:

[0102] It includes 120 full-color RGB lights with a brightness of 600 nits and a viewing angle of up to 120°. The guidance mode and color coding are set to flow blue to indicate the correct movement trajectory, flash red to indicate incorrect posture warnings (the frequency is proportional to the degree of error), and pulse green to indicate that the target is reached. The optical flow speed can be adaptively adjusted according to the patient's reaction time, with an initial value of 1.2 seconds per cycle.

[0103] The dynamic pressure control module includes an array of several independent airbags.

[0104] Specifically, the dynamic pressure control module consists of 6 independent airbags, namely the front, back, medial upper / lower, and lateral upper / lower airbags. The pressure parameters under different training conditions are set as 30mmHg for the airbag above the patella and 20mmHg for the inner and outer sides during extension training; 10mmHg for the popliteal fossa and 25mmHg for the inner and outer sides during flexion training; and a pressure cycle of 5-25mmHg at a frequency of 5Hz during nighttime lymphatic drainage. The resistance levels are divided into L1 (15mmHg, walking on flat ground, at the end of the acute phase), L2 (20mmHg, walking on a gentle slope, at the beginning of the functional phase), L3 (25mmHg, 5cm steps, in the middle of the functional phase), L4 (30mmHg, 10cm steps, at the end of the functional phase), and L5 (35mmHg, 15cm steps, at the beginning of the strengthening phase). The pressure control algorithm calculates the pressure value of each airbag Pi = f(θ, S, P) based on the joint angle θ, swelling degree S, and pain index P, with an iteration cycle of 200ms / time.

[0105] The rehabilitation process dynamic adjustment module is used to adjust the training plan based on multidimensional indicators.

[0106] Specifically, the rehabilitation phase is divided into an acute phase (0-2 weeks, the core goal is to control swelling and basic range of motion, and the quantitative indicators are leg circumference difference <2cm, flexion >80°), a functional phase (2-4 weeks, the core goal is gait reconstruction and muscle strength activation, and the quantitative indicators are GEI>0.6, myoelectric activation>40%), and an intensive phase (4-24 weeks, the core goal is muscle balance and functional recovery, and the quantitative indicators are MBI2.0-2.5, step <15cm). The process adjustment algorithm is set to an ascending phase when the stage goal is achieved for 5 consecutive days without adverse reactions; a descending phase when the stage goal is not achieved for 3 consecutive days or abnormal indicators appear, and 5 simplified movements (lasting 2 days) are inserted as a transition training package.

[0107] The three-level early warning network module enables collaborative intervention of patients' health among hospitals, communities and families.

[0108] Specifically, the warning classification standard is green (mild) warning, which is triggered when the standard is not met or there is a slight abnormality on a single day, and the system prompts the patient to make self-adjustments; yellow (moderate) warning is triggered when there is an abnormality for 2 consecutive days or a sudden increase in pain, and the community station will conduct a review; red (severe) warning is triggered when thrombosis risk or serious abnormality is detected, and the hospital will intervene immediately. The thrombosis risk is determined by a dual-indicator joint determination method of an increase in leg circumference of >3cm during the day and a fluctuation in blood oxygen of <1% at night. The emergency response process is for the knee brace to automatically switch to "first aid mode" (continuous 20mmHg pressure), push an alarm to the patient's family (voice + optical flow red flash), send a drug preparation notification to the cooperating pharmacy within 5 kilometers, and automatically make an appointment for a vascular ultrasound examination at the nearest hospital.

[0109] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0110] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0111] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent orthopedic rehabilitation monitoring method, characterized in that: The following steps are involved: The elastic modulus data of the target tissue is collected through a surface acoustic wave sensor array, and the motion posture and blood oxygen saturation data are synchronously acquired through an accelerometer and a photoplethysmography sensor; Performing noise filtering, outlier detection, multi-source data alignment, and feature extraction on the elastic modulus data to obtain feature data and calculate joint range of motion, tissue elastic modulus change rate, and blood oxygen fluctuation rate; Determining the current recovery status based on the characteristic data, the current recovery status including inflammation, congestion, and thrombosis risk levels; According to the current recovery status, the airbag pressure, optical flow guidance mode and voice prompt strategy are adjusted in real time; When abnormal indicators are detected, the graded warning mechanism is triggered and corresponding intervention measures are implemented.

2. The intelligent orthopedic rehabilitation monitoring method according to claim 1, characterized in that: The surface acoustic wave sensor array acquires tissue elastic modulus data at a sampling frequency of 120 Hz, and synchronously acquires motion posture and blood oxygen saturation data through an accelerometer and a photoplethysmography sensor. The following judgment thresholds are set: Normal reference value: 14.2±1.5kPa; Criteria for determining inflammatory edema: decrease in tissue elastic modulus > 15%; Criteria for determining congestive swelling: tissue elastic modulus decreases by <5% and blood oxygen saturation decreases by >3%.

3. The intelligent orthopedic rehabilitation monitoring method according to claim 1, characterized in that: The noise filtering, outlier detection, multi-source data alignment and feature extraction specifically include: A 0.1-40Hz bandpass filter was used to remove ambient noise; Identify abnormal waveforms based on the mean ± 3σ principle; Multi-sensor data synchronization through timestamp interpolation; Extract the characteristics of joint range of motion, tissue elasticity change trends and blood oxygen dynamic changes.

4. The intelligent orthopedic rehabilitation monitoring method according to claim 1, characterized in that: The determining of the current recovery status based on the characteristic data includes: Acute phase monitoring: monitoring of swelling and basal range of motion; Functional phase monitoring: assessing gait reconstruction and myoelectric activation levels; Monitoring during the intensive phase: Analyze muscle balance and step training performance.

5. The intelligent orthopedic rehabilitation monitoring method according to claim 1, characterized in that: The real-time adjustment of the airbag pressure, optical flow guidance mode and voice prompt strategy includes: Airbag pressure control: According to the joint angle θ, swelling degree S and pain index P, press P i =f(θ,S,P) calculates the pressure value of each airbag, and the control cycle is 200ms; Optical flow guidance adjustment: initial optical flow speed is 1.2 seconds / cycle, which is adaptively adjusted according to the patient's reaction time; Voice interaction optimization: Based on the voiceprint features collected by the bone conduction microphone, the prompt frequency and content are adjusted in real time.

6. The intelligent orthopedic rehabilitation monitoring method according to claim 1, characterized in that: The hierarchical early warning mechanism includes: Green warning: If the target is not met on a single day, the system will automatically optimize the training plan; Yellow warning: If abnormalities occur for two consecutive days, a review request will be sent to the community workstation; Red alert: If the daytime leg circumference increases by >3cm and the nighttime blood oxygen fluctuation is <1%, the patient is considered at risk of thrombosis and the following actions are performed: Automatically switches to 20mmHg continuous pressure mode; Send emergency alerts to family members and hospitals; Make an appointment for a vascular ultrasound at the nearest hospital.

7. The intelligent orthopedic rehabilitation monitoring method according to claim 1, characterized in that: The method further includes adaptive adjustment operations during the rehabilitation phase: Stage advancement conditions: achieving stage goals for 5 consecutive days without adverse reactions; Stage decline conditions: failure to achieve the target for three consecutive days or abnormal indicators appear; Transition Training Pack Insertion: When the descent condition is triggered, insert 5 simplified movement trainings for 2 days.

8. An intelligent orthopedic rehabilitation monitoring system, used to implement the intelligent orthopedic rehabilitation monitoring method according to any one of claims 1 to 7, characterized in that: include: Biosignal sensing and energy self-sufficiency module, including a surface acoustic wave sensor array and a piezoelectric energy harvesting system; Multimodal interaction module, including bone conduction voice system and optical flow guidance system; A dynamic pressure control module, including an array of several regional independent airbags; A dynamic adjustment module for the rehabilitation process, used to adjust the training program based on multi-dimensional indicators; The three-level early warning network module enables collaborative intervention of patients' health among hospitals, communities and families.

9. The intelligent orthopedic rehabilitation monitoring system according to claim 8, characterized in that: The surface acoustic wave sensor array adopts an 8×8 matrix layout, a unit size of 2mm×2mm, and a sampling frequency of 120Hz.

10. The intelligent orthopedic rehabilitation monitoring system according to claim 8, characterized in that: The piezoelectric energy harvesting system comprises: Piezoelectric fibers made of polyvinylidene fluoride are placed at the knee brace hinge; Energy conversion efficiency 12.5mW / flexion and extension movement; The power consumption is distributed as follows: surface acoustic wave sensor array 3.2mW / h, micro air pump 5.5mW / h, computing chip 2.8mW / h.

Images