ICU-AW patient-oriented multifunctional rehabilitation robot real-time monitoring and intelligent regulation and control system

Abstract

The invention provides a multifunctional rehabilitation robot real-time monitoring and intelligent regulation and control system for ICU-AW patients. Comprising a trial operation data transmission self-inspection module, an initial data acquisition module, a rehabilitation data real-time monitoring module and a rehabilitation training parameter real-time regulation and control module. According to the method, the basic physiological data of the user is collected and analyzed to obtain the personalized rehabilitation characteristic coefficient, so that the training parameters of the robot are initialized, the suitability of the training parameters and the requirements of the patient is ensured, the rehabilitation efficiency is improved, and training injuries are prevented. In addition, the system also performs pilot run self-inspection, so that the data transmission quality is ensured, and the analysis efficiency and accuracy are improved. In addition, the system monitors physiological and training data in rehabilitation training in real time, provides immediate feedback, dynamically adjusts training intensity and rhythm, optimizes the training effect and reduces the training risk.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a multifunctional rehabilitation robot real-time monitoring and intelligent control system for ICU-AW patients. Background Art

[0002] ICU-AW is a common problem that affects functional recovery after intensive care. ICU-AW may lead to long-term muscle atrophy, functional impairment, and reduced quality of life. Early mobilization and rehabilitation can reduce muscle atrophy and joint stiffness caused by long-term bed rest. However, the condition of ICU-AW patients may change rapidly, and continuous monitoring of physiological parameters is required to adjust treatment and rehabilitation plans in a timely manner. Real-time monitoring can ensure that rehabilitation activities are carried out within the user's physiological tolerance range to avoid excessive fatigue or injury.

[0003] The invention patent CN107865753B discloses a rehabilitation robot, including a lower limb robot and a marker arranged at the position of the hip joint of a human lower limb. The lower limb robot includes a hip bone component, a pair of femoral components located below the hip bone component, a hip joint component located between each femoral component and the hip bone component, and a camera. The camera is arranged on the hip joint component and is used to capture a marked image of the marker. As the human lower limb moves, the position of the marked image changes, and the camera outputs a control signal according to the position change of the marked image; the control component responds to the control signal from the camera in real time to control the hip joint component to move to the marked position.

[0004] The invention patent CN114129392B discloses an adaptive redundant drive exoskeleton rehabilitation robot with adjustable end fingertip force, including: a palm-back platform, and a finger linkage mechanism and a control module arranged on the palm-back platform; the finger linkage mechanism is driven by a separate first servo and has multiple joints, each of which is driven by a separate second servo; a pressure sensor is arranged at the fingertip position of the finger linkage mechanism to detect the fingertip force when interacting with an object; the control module receives the fingertip force, adjusts the training action according to the fingertip force and the application time of the fingertip force, and determines the fingertip target position according to the training action; obtains the current fingertip position according to the position reached by the current movement and the joint angle of the fingertip linkage mechanism, obtains the target fingertip force according to the current fingertip position and the fingertip target position, and forms a control instruction to drive the first servo and the second servo to act. It has two training modes, active and passive, and adjusts the fingertip force through force feedback to improve the grip stability.

[0005] Based on the above content, it can be seen that when controlling a rehabilitation robot, the existing technology usually only collects data on individual parts and adopts a single rehabilitation training goal for different users. However, in actual applications, the physiological characteristics and training plans of users are not the same. If only a single rehabilitation training goal is adopted, it may lead to poor rehabilitation training effects and unreasonable use of rehabilitation training robot resources. Summary of the invention

[0006] The present invention provides a multifunctional rehabilitation robot real-time monitoring and intelligent control system for ICU-AW patients.

[0007] In order to solve the above-mentioned invention object, the technical solution provided by the present invention is as follows:

[0008] A multifunctional rehabilitation robot real-time monitoring and intelligent control system for ICU-AW patients, including

[0009] The trial run data transmission self-check module is used to obtain the data transmission quality data of each transmission port during the trial run of the rehabilitation robot, analyze and process to obtain the trial run self-check result, and when the trial run self-check result is qualified, send a formal start permission signal to the control terminal.

[0010] The initial data acquisition module is used to collect basic physiological data uploaded by the data transmission port, analyze and process the user's personalized rehabilitation characteristic coefficient, and perform initialization parameter configuration of the robot rehabilitation training based on the personalized rehabilitation characteristic coefficient.

[0011] The rehabilitation data real-time monitoring module is used to monitor the real-time physiological data of the user during rehabilitation training and the real-time training data of the parts requiring rehabilitation training, analyze and process to obtain the real-time physiological monitoring index and real-time training monitoring index, and upload them to the cloud processor.

[0012] The real-time control module for rehabilitation training parameters is used to receive real-time physiological monitoring indexes and real-time training monitoring indexes through a cloud processor, comprehensively analyze and process to obtain dynamic configuration instructions for rehabilitation training parameters and perform real-time control.

[0013] Optionally, the obtaining of data transmission quality data of each transmission port during the trial operation of the rehabilitation robot and analyzing and processing to obtain the trial operation self-test result specifically includes:

[0014] The data transmission quality data of each transmission port during the trial operation of the rehabilitation robot includes the delay change rate, bandwidth fluctuation rate, RSSI and jitter variance of each transmission port.

[0015] The data transmission quality verification data is extracted from the database, including the delay variation verification rate, bandwidth fluctuation verification rate, RSSI verification value and jitter verification variance. The data transmission quality data of each transmission port is compared and analyzed with the data transmission quality verification data to obtain the data transmission quality evaluation value of each transmission port.

[0016] If the data transmission quality evaluation values ​​of each transmission port are greater than or equal to the data transmission quality threshold, the trial operation self-test result is determined to be qualified, and a formal start permission signal is sent to the control terminal.

[0017] If the data transmission quality evaluation value of a transmission port is less than the data transmission quality threshold, the trial operation self-inspection result of the transmission port is determined to be unqualified, and an early warning message is sent to the management terminal.

[0018] Optionally, the basic physiological data uploaded by the data transmission port is collected and analyzed to obtain the personalized rehabilitation characteristic coefficient of the user, specifically including:

[0019] Input the user's part that needs rehabilitation training, and collect the basic physiological data of the part that needs rehabilitation training uploaded by the data transmission port.

[0020] The basic physiological data include reaction time, muscle strength and reflex speed of the part requiring rehabilitation training.

[0021] The basic physiological reference data of the parts requiring rehabilitation training are extracted from the database, including the reference values ​​of reaction time, muscle strength and reflex speed.

[0022] The basic physiological data of the user is compared and analyzed with the basic physiological reference data to obtain the personalized rehabilitation characteristic coefficient of the user, and the personalized rehabilitation characteristic coefficient is used for initialization parameter configuration of robot rehabilitation training.

[0023] Optionally, the performing of the robot rehabilitation training initialization parameter configuration specifically includes:

[0024] The robot rehabilitation training initialization parameters include auxiliary force, speed sensor safety speed range and electromyographic sensor accuracy.

[0025] Based on the user's personalized rehabilitation characteristic coefficient, the robot rehabilitation training initialization parameters corresponding to the real-time training monitoring index pre-stored in the database are mapped and matched to obtain the robot rehabilitation training initialization parameters and configure the robot rehabilitation training initialization parameters.

[0026] The robot rehabilitation training initialization parameters include auxiliary force, speed sensor safety speed range and electromyographic sensor accuracy.

[0027] The assistance intensity is used to determine the training intensity for assisting the user in performing rehabilitation training.

[0028] The speed sensor safety speed range is used to ensure that the user is within a reasonable speed range during rehabilitation training. If the user's real-time speed exceeds the safety speed range, an early warning message is sent to the management terminal.

[0029] The electromyographic sensor accuracy is used to determine the signal sending frequency of the electromyographic sensor.

[0030] Optionally, the real-time physiological data of the user during rehabilitation training and the real-time training data of the part requiring rehabilitation training are monitored, and the real-time physiological monitoring index and the real-time training monitoring index are obtained by analysis and processing, specifically including:

[0031] The real-time physiological data includes the RMS of the sEMG signal, real-time heart rate fluctuation and real-time blood pressure fluctuation.

[0032] The real-time training data of the part requiring rehabilitation training includes the real-time strength, real-time speed and real-time activity amplitude of the part requiring rehabilitation training.

[0033] The real-time physiological monitoring permissible fluctuation indexes are extracted from the database, including the RMS permissible fluctuation value of the sEMG signal, the real-time heart rate fluctuation permissible fluctuation value and the real-time blood pressure fluctuation permissible fluctuation value.

[0034] Based on the personalized rehabilitation characteristic coefficient, the real-time training monitoring indicators corresponding to the interval of the user's personalized rehabilitation characteristic coefficient are extracted from the database, including the real-time indicator intensity, the real-time indicator speed and the real-time indicator activity amplitude.

[0035] Based on the user's real-time physiological data and the real-time physiological monitoring permitted fluctuation index, comprehensive analysis and processing are performed to generate the user's real-time physiological monitoring index.

[0036] Based on the real-time training data of the user's part that needs rehabilitation training and the real-time training monitoring indicators, the real-time training monitoring index of the user is generated through analysis and processing.

[0037] Optionally, the comprehensive analysis and processing to obtain the dynamic configuration instruction of rehabilitation training parameters specifically includes:

[0038] Based on the user's real-time physiological monitoring index, the user's real-time physiological monitoring result is obtained through cloud processor analysis. If the user's real-time physiological monitoring index is greater than 1, the real-time physiological monitoring result is determined to be abnormal, and a request to stop training is sent to the management terminal. If the user's real-time physiological monitoring index is less than or equal to 1, the real-time physiological monitoring result is determined to be normal, and a rehabilitation training parameter dynamic configuration instruction is generated to command the robot to dynamically adjust the rehabilitation training parameters.

[0039] Optionally, the real-time control specifically includes:

[0040] Based on the user's real-time training monitoring index, the robot rehabilitation training dynamic adjustment parameters corresponding to each personalized rehabilitation characteristic coefficient pre-stored in the database are mapped and matched to obtain the robot rehabilitation training dynamic adjustment parameters and dynamically configure the robot rehabilitation training initialization parameters.

[0041] The dynamic adjustment parameters of the robot rehabilitation training include an auxiliary force adjustment value, a speed sensor safety speed range adjustment value, and an electromyographic sensor accuracy adjustment value.

[0042] Optionally, the data transmission quality evaluation value of each transmission port further includes:

[0043] The data transmission quality assessment value of each transmission port with a qualified trial run self-inspection result is statistically analyzed, and a comprehensive data transmission quality assessment value of each transmission port is obtained after mean processing. Based on the comprehensive data transmission quality assessment value, a mapping and matching is performed with the data transmission quality correction factor corresponding to each comprehensive data transmission quality assessment value interval in the database to obtain the data transmission quality correction factor, which is used to correct the damage to data quality caused by data transmission.

[0044] Optionally, the physical performance of each device part of the robot is monitored during the trial operation, including:

[0045] During the trial run, the physical performance data of each device part of the robot is obtained, including the displacement speed of the end effector, the average temperature of the motor device and the response time.

[0046] The physical performance verification data of each device part of the robot are extracted from the database, including the end effector displacement speed verification value, the motor device average verification temperature and the response time verification value.

[0047] The physical performance data of each device part of the robot are compared and analyzed with the physical performance verification data of each device part. The end effector displacement speed, the average temperature of the motor device and the response time of the robot are respectively subtracted from the end effector displacement speed verification value, the average verification temperature of the motor device and the response time verification value, which are recorded as the parameter differences. When the parameter differences are less than or equal to the allowable error range corresponding to the parameters, the physical performance monitoring result of the robot's trial run is judged to be qualified. When a parameter difference is greater than the allowable error range corresponding to the parameters, the physical performance monitoring result of the robot's trial run is judged to be unqualified, and a signal prohibiting formal operation is sent to the management terminal.

[0048] Optionally, the analysis and processing to obtain the user's personalized rehabilitation characteristic coefficient specifically includes:

[0049]

[0050] Among them, ε is the user's personalized rehabilitation characteristic coefficient, TZ is the reaction time, po is the muscle strength, v is the reflex speed, TZ 0 is the reference value of reaction time, po 0 is the reference value of muscle strength, v 0 is the reflection speed reference value, is the reaction time weight factor, is the muscle strength weighting factor, is the reflection speed weight factor, δ is the data transmission quality correction factor, Mish function is the activation function, Mish(x)=x*tanh[softplus(x)].

[0051] The above technical solution provided by the present invention has at least the following beneficial effects compared with the prior art:

[0052] In the above scheme, the basic physiological data of the user is collected, the personalized rehabilitation characteristic coefficient of the user is obtained through analysis and processing, and the initial configuration of the robot rehabilitation training initialization parameters is performed based on the personalized rehabilitation characteristic coefficient, thereby ensuring that the robot's rehabilitation training parameters are highly adaptable to the user's rehabilitation needs, improving the efficiency of rehabilitation training, and avoiding injuries caused by rehabilitation training parameters exceeding the applicable range of the user.

[0053] By conducting trial run tests on the rehabilitation robot, we obtained data transmission quality data of each transmission port to ensure that the data transmission quality in the subsequent formal operation is at a high level. The higher quality data also improves the efficiency of the analysis process and the accuracy of the analysis results when performing analysis.

[0054] By monitoring the user's real-time physiological data during rehabilitation training and the real-time training data of the parts that require rehabilitation training, and providing instant feedback, the intensity and rhythm of rehabilitation training can be adjusted in real time, thereby improving the efficiency and effectiveness of rehabilitation training and reducing the probability of danger during rehabilitation training. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0056] Figure 1 The present invention is a multifunctional rehabilitation robot real-time monitoring and intelligent control system for ICU-AW patients DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] Unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, words such as "one", "one" or "the" do not indicate a quantitative limitation, but indicate the existence of at least one. Words such as "include" or "comprise" mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Words such as "connect" or "connected" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect.

[0059] like Figure 1 As shown, the embodiment of the present invention provides a multifunctional rehabilitation robot real-time monitoring and intelligent control system for ICU-AW patients, including:

[0060] The trial run data transmission self-check module is used to obtain the data transmission quality data of each transmission port during the trial run of the rehabilitation robot, analyze and process to obtain the trial run self-check result, and when the trial run self-check result is qualified, send a formal start permission signal to the control terminal.

[0061] The step of obtaining the data transmission quality data of each transmission port during the trial operation of the rehabilitation robot and analyzing and processing to obtain the trial operation self-test result specifically includes:

[0062] The data transmission quality data of each transmission port during the trial operation of the rehabilitation robot includes the delay change rate, bandwidth fluctuation rate, RSSI and jitter variance of each transmission port.

[0063] The delay variation rate, also known as network jitter, refers to the difference in packet arrival times, that is, the rate of change of packet transmission delay. The delay variation rate can be used to evaluate the quality and stability of the network. A high delay variation rate may cause unstable packet arrival times and affect the performance of real-time applications.

[0064] Bandwidth fluctuation rate refers to the degree of change in network bandwidth over a period of time, that is, the fluctuation of network transmission rate.

[0065] RSSI (Received Signal Strength Indicator) is a quantitative indicator of the received signal strength indicator, which represents the measure of the received wireless signal strength. RSSI is used to evaluate the coverage and quality of wireless signals. A low RSSI value may mean a weak signal or a long distance from the access point.

[0066] Jitter variance is a statistic that describes the variation in the delay time of data packet transmission. It is the statistical variance of jitter. Jitter variance can be used to analyze the stability of network transmission. The smaller the variance, the more stable the network transmission. By reducing jitter variance, the performance of network applications can be improved, especially those with high real-time requirements.

[0067] Use network diagnostic tools to capture and analyze network data packets. By sending a series of data packets and recording the sending and receiving time of each data packet, the difference in data packet arrival time is calculated to obtain the delay change rate.

[0068] Use statistical software to calculate the delay variation rate and jitter variance.

[0069] Use the bandwidth test tool to continuously measure the bandwidth within a set time and calculate the rate of change of the bandwidth at each moment compared to the previous moment, that is, the bandwidth fluctuation rate.

[0070] The data transmission quality verification data is extracted from the database, including the delay variation verification rate, bandwidth fluctuation verification rate, RSSI verification value and jitter verification variance. The data transmission quality data of each transmission port is compared and analyzed with the data transmission quality verification data to obtain the data transmission quality evaluation value of each transmission port.

[0071] The obtaining of the data transmission quality evaluation value of each transmission port specifically includes:

[0072]

[0073] Among them, SJ i is the data transmission quality evaluation value of the i-th transmission port, SY i is the delay variation rate of the i-th transmission port, BD i is the bandwidth fluctuation rate of the i-th transmission port, RSSI i is the RSSI of the ith transmission port, D i is the jitter variance of the i-th transmission port, SY 0 is the delay variation check rate, BD 0 is the bandwidth fluctuation check rate, RSSI 0 is the RSSI check value, D0 is the jitter check variance, i is the transmission port number, i = 1, 2, 3, ..., n, n is the total number of transmission ports, softplus function is a built-in function in Python, softplus(x) = lg(1+e x ).

[0074] It should be noted that there is a certain correlation between the parameters of delay variation rate, bandwidth fluctuation rate, RSSI and jitter variance. The delay variation rate is a manifestation of jitter, while the jitter variance is a statistic that describes jitter variation. Both are indicators for measuring the stability of network transmission. A large delay variation rate means a large jitter variance, and vice versa. Bandwidth fluctuations may lead to an increase in the delay variation rate. If the network bandwidth is unstable, the data packet may encounter delays during transmission, resulting in an increase in the delay variation rate. RSSI is an indicator for measuring the strength of the received signal in a wireless network. Weak signal strength (low RSSI value) may cause bandwidth fluctuations in the wireless network, because weak signals may cause a decrease in data transmission rate or even retransmission. A low RSSI value may indicate poor wireless signal quality, which may increase the delay of data packet transmission, thereby increasing the delay variation rate. Jitter variance can be affected by bandwidth fluctuations. If the network bandwidth fluctuates greatly, the fluctuation of the data packet arrival time may also increase, resulting in an increase in jitter variance. In summary, they jointly reflect the quality and stability of the network. A change in one parameter may affect other parameters and thus affect the performance of the entire network.

[0075] If the data transmission quality evaluation values ​​of each transmission port are greater than or equal to the data transmission quality threshold, the trial operation self-test result is determined to be qualified, and a formal start permission signal is sent to the control terminal.

[0076] If the data transmission quality assessment value of a transmission port is less than the data transmission quality threshold, the trial operation self-test result is determined to be unqualified, and a warning message is sent to the management terminal.

[0077] The data transmission quality threshold is processed as follows: in a specific embodiment, the data transmission quality threshold is set directly in the database during the development of the multifunctional rehabilitation robot real-time monitoring and intelligent control system for ICU-AW patients involved in the embodiment of the present invention. There are many methods for setting the data transmission quality threshold, such as obtaining it through statistical analysis, including counting the data transmission quality values ​​under historical high-quality transmission states (for example, when the delay change rate is less than 10ms), and averaging the data transmission quality values ​​obtained multiple times to obtain the data transmission quality threshold.

[0078] The data transmission quality evaluation value of each transmission port also includes:

[0079] The data transmission quality assessment value of each transmission port with a qualified trial run self-inspection result is statistically analyzed, and a comprehensive data transmission quality assessment value of each transmission port is obtained after mean processing. Based on the comprehensive data transmission quality assessment value, a mapping and matching is performed with the data transmission quality correction factor corresponding to each comprehensive data transmission quality assessment value interval in the database to obtain the data transmission quality correction factor, which is used to correct the damage to data quality caused by data transmission.

[0080] It also includes physical performance monitoring of various parts of the robot during the trial run, including:

[0081] During the trial run, the physical performance data of each device part of the robot is obtained, including the displacement speed of the end effector, the average temperature of the motor device and the response time.

[0082] The end effector displacement velocity refers to the speed of the robot's end effector (such as a manipulator, tool, etc.) during movement, usually measured in terms of the distance moved per unit time (such as meters per second).

[0083] The average temperature of the motor unit refers to the average temperature of the motor caused by the heat generated during operation, which is usually monitored by a temperature sensor. The motor temperature can reflect the operating status and load conditions of the motor. Excessive temperature may be a sign of overload or failure.

[0084] Response time refers to the time it takes for a system to start executing a command after receiving it, also known as system latency or reaction time. In situations where fast response is required, such as automated control or emergency shutdown, short response time is crucial. Response time is an important indicator for evaluating system performance, especially in applications with high real-time requirements.

[0085] The physical performance verification data of each device part of the robot are extracted from the database, including the end effector displacement speed verification value, the motor device average verification temperature and the response time verification value.

[0086] The physical performance data of each device part of the robot are compared and analyzed with the physical performance verification data of each device part. The end effector displacement speed, the average temperature of the motor device and the response time of the robot are respectively subtracted from the end effector displacement speed verification value, the average verification temperature of the motor device and the response time verification value, which are recorded as the parameter differences. When the parameter differences are less than or equal to the allowable error range corresponding to the parameters, the physical performance monitoring result of the robot's trial run is judged to be qualified. When a parameter difference is greater than the allowable error range corresponding to the parameters, the physical performance monitoring result of the robot's trial run is judged to be unqualified, and a signal prohibiting formal operation is sent to the management terminal.

[0087] The allowable error range corresponding to each parameter is processed as follows: in a specific embodiment, the allowable error range corresponding to each parameter is directly set in the database during the development of the multifunctional rehabilitation robot real-time monitoring and intelligent control system for ICU-AW patients involved in the embodiment of the present invention. There are many methods for setting the allowable error range corresponding to each parameter, such as through statistical analysis, including counting the difference between each parameter under historical high physical performance conditions (for example, when the response time is less than 10ms), and averaging the difference between each parameter obtained multiple times to obtain the allowable error range corresponding to each parameter.

[0088] The initial data acquisition module is used to collect the basic physiological data uploaded by the data transmission port, analyze and process the user's personalized rehabilitation characteristic coefficient, and perform initial configuration of the robot rehabilitation training initialization parameters based on the personalized rehabilitation characteristic coefficient.

[0089] The data collection and transmission port collects and uploads basic physiological data of the part requiring rehabilitation training, and analyzes and processes to obtain the user's personalized rehabilitation characteristic coefficient, specifically including:

[0090] The basic physiological data of the part requiring rehabilitation training include reaction time, muscle strength and reflex speed of the part requiring rehabilitation training.

[0091] The basic physiological reference data of the part requiring rehabilitation training are extracted from the database, including the reaction time reference value, muscle strength reference value and reflex speed reference value of the part requiring rehabilitation training.

[0092] The basic physiological reference data, including the reaction time reference value, muscle strength reference value and reflex speed reference value of the part requiring rehabilitation training, are obtained by collecting information from multiple databases and importing them into the built-in big data model (such as the MEGNet model) of the system for analysis and processing when the multifunctional rehabilitation robot real-time monitoring and intelligent control system for ICU-AW patients involved in the embodiment of the present invention is built.

[0093] Reaction time, also known as electromyographic reaction time, refers to the time required from stimulation of a muscle to the time the muscle produces a noticeable contraction. This process involves signal transmission at the neuromuscular junction and activation of muscle fibers. Muscle reaction time is an important indicator for evaluating nervous system function and muscle health.

[0094] Muscle strength is the amount of force a muscle can produce in a single maximal effort. It reflects the ability of a muscle to contract and is an important indicator of muscle health and function. Muscle strength can be measured through isotonic muscle strength testing, which supports daily activities such as walking, standing, and lifting objects.

[0095] Reflex speed, also known as reaction time or reaction speed, refers to how quickly a muscle or reflex arc responds to a stimulus. It usually involves how quickly the nervous system processes the stimulus and how quickly the muscle contracts. Reflex speed is measured through a muscle stretch reflex test, and it can reflect the function of the nervous system.

[0096] The basic physiological data of the user's part requiring rehabilitation training is compared and analyzed with the basic physiological reference data to obtain the user's personalized rehabilitation characteristic coefficient, and the personalized rehabilitation characteristic coefficient is used for initial configuration of the robot rehabilitation training initialization parameters.

[0097] The analysis and processing to obtain the user's personalized rehabilitation characteristic coefficient specifically includes:

[0098]

[0099] Among them, ε is the user's personalized rehabilitation characteristic coefficient, TZ is the reaction time, po is the muscle strength, v is the reflex speed, TZ 0 is the reference value of reaction time, po 0 is the reference value of muscle strength, v 0 is the reflection speed reference value, is the reaction time weight factor, is the muscle strength weighting factor, is the reflection velocity weight factor, δ i is the data transmission quality correction factor of the i-th transmission port, i is the transmission port number, i=1,2,3,...,n, n is the total number of transmission ports, Mish function is the activation function, Mish(x)=x*tanh[softplus(x)].

[0100] It should be noted that the reaction time weight factor, muscle strength weight factor and reflex speed weight factor all have a value range between 0 and 1 and satisfy The reaction time weight factor is an influence factor corresponding to the personalized rehabilitation characteristic coefficient preset in the database, and indicates a numerical value of the influence degree of the reaction time on the personalized rehabilitation characteristic coefficient. The muscle strength weight factor is an influence factor corresponding to the personalized rehabilitation characteristic coefficient preset in the database, and indicates a numerical value of the influence degree of the muscle strength on the personalized rehabilitation characteristic coefficient. The reflex speed weight factor is an influence factor corresponding to the personalized rehabilitation characteristic coefficient preset in the database, and indicates a numerical value of the influence degree of the reflex speed on the personalized rehabilitation characteristic coefficient. When used, the reaction time weight factor, muscle strength weight factor and reflex speed weight factor can be directly obtained from the database, and the corresponding relationship is a preset mapping relationship. For example, the reaction time, muscle strength and reflex speed respectively form a mapping set with the reaction time weight factor, muscle strength weight factor and reflex speed weight factor. The reaction time, muscle strength and reflex speed involved in the embodiment of the present invention are input into the mapping set for mapping and matching to obtain the reaction time weight factor, muscle strength weight factor and reflex speed weight factor involved in the embodiment of the present invention. The mapping relationship is one-to-one corresponding. For example, the reaction time is input into the mapping set, and the reaction time weight factor, muscle strength weight factor and reflex speed weight factor are obtained through matching of the preset mapping relationship.

[0101] It should also be noted that the three parameters of reaction time, muscle strength and reflex speed are directly related to each other. Short reaction time usually means fast nervous system transmission and muscle activation, which may lead to faster reflex speed. However, reaction time is part of the psychological and neural processing process, while reflex speed is more of a physiological muscle activation process. The size of muscle strength does not directly determine reflex speed, but stronger muscles may be faster in generating force because they can be activated more effectively by the nervous system. People with more fast-twitch muscle fibers (such as white muscle fibers) may have stronger muscle strength and faster reflex speed. In general, all three are important components of athletic ability and physical performance. They influence each other and jointly determine the performance of an individual in a specific activity. Training can improve these parameters, thereby improving overall athletic performance.

[0102] The initial configuration of the initialization parameters for the robot rehabilitation training specifically includes:

[0103] The robot rehabilitation training initialization parameters include auxiliary force, speed sensor safety speed range and electromyographic sensor accuracy.

[0104] Based on the user's personalized rehabilitation characteristic coefficient, the auxiliary force, speed sensor safety speed range and electromyographic sensor accuracy corresponding to each personalized rehabilitation characteristic coefficient pre-stored in the database are mapped and matched to obtain the robot rehabilitation training initialization parameters and configure the robot rehabilitation training initialization parameters.

[0105] The robot rehabilitation training initialization parameters include auxiliary force, speed sensor safety speed range and electromyographic sensor accuracy.

[0106] The assistance intensity is used to determine the training intensity for assisting the user in performing rehabilitation training.

[0107] The speed sensor safety speed range is used to ensure that the user is within a reasonable speed range during rehabilitation training. If the real-time speed of the part of the user that requires rehabilitation training exceeds the safety speed range, an early warning message is sent to the management terminal.

[0108] The electromyographic sensor accuracy is used to determine the signal sending frequency of the electromyographic sensor.

[0109] The rehabilitation data real-time monitoring module is used to monitor the real-time physiological data of the user during rehabilitation training and the real-time training data of the parts requiring rehabilitation training, analyze and process to obtain the real-time physiological monitoring index and real-time training monitoring index, and upload them to the cloud processor.

[0110] The monitoring of the real-time physiological data of the user during rehabilitation training and the real-time training data of the part requiring rehabilitation training, and the analysis and processing to obtain the real-time physiological monitoring index and the real-time training monitoring index of the part requiring rehabilitation training specifically include:

[0111] The real-time physiological data includes the RMS of the sEMG signal, real-time heart rate fluctuation and real-time blood pressure fluctuation.

[0112] The RMS (root mean square) of the sEMG signal refers to the square root of the average value of the square of the voltage of the surface electromyography signal within a certain period of time. It is a common indicator for measuring the intensity of myoelectric activity, which can reflect the level of muscle contraction and is obtained through a surface electromyography device. The RMS value can be used to quantify the activity of the muscle, that is, the intensity of muscle contraction. In rehabilitation training, RMS can be used to monitor and control exercise intensity to ensure the correct training effect.

[0113] Real-time heart rate fluctuation refers to the instantaneous change of heart rate, which is affected by many factors, including the activity of the autonomic nervous system, physical activity level, emotional state, blood pressure changes, etc. Heart rate fluctuation can reflect the heart's adaptability and regulatory ability to physiological needs.

[0114] Real-time blood pressure fluctuation refers to the instantaneous change of blood pressure, which is the difference between the blood pressure at a certain moment and the blood pressure at the previous moment. It is measured by a sphygmomanometer. For example, if the systolic blood pressure at a certain moment is 96 and the systolic blood pressure at the next moment is 90, the real-time blood pressure fluctuation is 6. It is affected by the regulation of the autonomic nervous system, physical activity, emotions, breathing and other factors. Blood pressure fluctuation is an important mechanism to maintain organ perfusion and regulate the body's response to different physiological needs.

[0115] The real-time training data of the part requiring rehabilitation training includes the real-time strength, real-time speed and real-time activity amplitude of the part requiring rehabilitation training, which are obtained through integrated sensors.

[0116] The real-time physiological monitoring permissible fluctuation indexes are extracted from the database, including the RMS permissible fluctuation value of the sEMG signal, the real-time heart rate fluctuation permissible fluctuation value and the real-time blood pressure fluctuation permissible fluctuation value.

[0117] Based on the personalized rehabilitation characteristic coefficient, the real-time training monitoring indicators of the part requiring rehabilitation training corresponding to the interval of the user's personalized rehabilitation characteristic coefficient are extracted from the database, including the real-time indicator strength, real-time indicator speed and real-time indicator activity amplitude of the part requiring rehabilitation training.

[0118] Based on the user's real-time physiological data and the real-time physiological monitoring permitted fluctuation index, the user's real-time physiological monitoring index is generated through comprehensive analysis and processing, including:

[0119]

[0120] Wherein, sl is the user's real-time physiological monitoring index, RMS(sEMG) is the RMS of the sEMG signal, r is the real-time heart rate fluctuation, xy is the real-time blood pressure fluctuation, ΔRMS(sEMG) is the RMS allowable fluctuation value of the sEMG signal, Δr is the real-time heart rate fluctuation allowable fluctuation value, Δxy is the real-time blood pressure fluctuation allowable fluctuation value, ω 1 is the sEMG weighting factor, ω 2 is the real-time heart rate fluctuation weight factor, ω 3 is the real-time blood pressure fluctuation weight factor.

[0121] It should be noted that the sEMG weight factor, the real-time heart rate fluctuation weight factor, and the real-time blood pressure fluctuation weight factor all have a value range between 0 and 1 and satisfy ω 1 +ω 2 +ω 3=1, the sEMG weight factor is an influence factor corresponding to the real-time physiological monitoring index preset in the database, indicating a numerical value of the influence degree of sEMG on the real-time physiological monitoring index, the real-time heart rate fluctuation weight factor is an influence factor corresponding to the real-time physiological monitoring index preset in the database, indicating a numerical value of the influence degree of real-time heart rate fluctuation on the real-time physiological monitoring index, and the real-time blood pressure fluctuation weight factor is an influence factor corresponding to the real-time physiological monitoring index preset in the database, indicating a numerical value of the influence degree of real-time blood pressure fluctuation on the real-time physiological monitoring index. When used, the sEMG weight factor, the real-time heart rate fluctuation weight factor and the real-time blood pressure fluctuation weight factor can be directly obtained from the database, and the corresponding relationship is a preset mapping relationship. For example, the RMS of the sEMG signal, the real-time heart rate fluctuation and the real-time blood pressure fluctuation respectively form a mapping set with the sEMG weight factor, the real-time heart rate fluctuation weight factor and the real-time blood pressure fluctuation weight factor, and the RMS of the sEMG signal, the real-time heart rate fluctuation and the real-time blood pressure fluctuation involved in the embodiment of the present invention are input into the mapping set for mapping and matching to obtain the weight factors of the RMS of the sEMG signal, the real-time heart rate fluctuation and the real-time blood pressure fluctuation involved in the embodiment of the present invention, wherein the mapping relationship is one-to-one corresponding.

[0122] It should also be noted that there is a certain correlation between the RMS of the sEMG signal, the real-time heart rate fluctuation, and the real-time blood pressure fluctuation. When muscle activity increases (the RMS value of the sEMG signal increases), the body's demand for energy increases, which usually causes the heart rate to increase to meet the oxygen and nutrient supply of the muscles. Therefore, there is a positive correlation between the RMS value of the sEMG signal and the heart rate, that is, when muscle activity increases, the heart rate will also increase accordingly. When muscle activity increases, in order to maintain muscle contraction, blood vessels may contract to increase blood pressure to ensure that sufficient blood flows to the active muscles. Therefore, there may also be a positive correlation between the RMS value of the sEMG signal and blood pressure fluctuations, especially during intense or continuous exercise. Heart rate and blood pressure are closely related because changes in heart rate directly affect the heart's ability to pump blood, thereby affecting blood pressure. An increase in heart rate usually leads to an increase in blood pressure, especially when the heart's stroke volume remains unchanged or increases. In general, the correlation between the three parameters of the RMS of the sEMG signal, real-time heart rate fluctuations, and real-time blood pressure fluctuations is reflected in the fact that they are all responses of the body to changes in physiological needs (such as exercise). Increased muscle activity typically causes an increase in heart rate and fluctuations in blood pressure to meet the muscles' demand for oxygen and nutrients.

[0123] Based on the real-time training data and real-time training monitoring indicators of the user's part requiring rehabilitation training, the real-time training monitoring index of the user is generated through analysis and processing, specifically including:

[0124]

[0125] Among them, xl is the user's real-time training monitoring index, ld is the real-time strength of the part that needs rehabilitation training, sd is the real-time speed of the part that needs rehabilitation training, fd is the real-time activity range of the part that needs rehabilitation training, and ld 0 is the real-time indicator strength, sd 0 is the real-time indicator speed, fd 0 It is the activity amplitude of real-time indicators.

[0126] It should be noted that there is a certain correlation between the parameters of real-time force, real-time speed and real-time range of motion. In some dynamic movements, higher forces are usually accompanied by faster speeds. The range of motion refers to the range in which a joint or body part can move. The magnitude of the force may affect the range of motion, especially when the limit of the muscle or joint is reached. If the force is too great, the range of motion may be limited because the muscle may not be able to effectively contract over a larger range. In some cases, a proper increase in force can help increase the range of motion, such as stretching exercises in rehabilitation training. Speed ​​and range of motion are usually positively correlated, that is, at a certain force, increasing speed usually means increasing the range of motion.

[0127] The real-time control module for rehabilitation training parameters is used to receive real-time physiological monitoring indexes and real-time training monitoring indexes through a cloud processor, comprehensively analyze and process to obtain dynamic configuration instructions for rehabilitation training parameters and perform real-time control.

[0128] The comprehensive analysis and processing to obtain the dynamic configuration instruction of the rehabilitation training parameters specifically includes:

[0129] Based on the user's real-time physiological monitoring index, the user's real-time physiological monitoring result is obtained through cloud processor analysis. If the user's real-time physiological monitoring index is greater than 1, the real-time physiological monitoring result is judged to be abnormal, and a request to stop training is sent to the management terminal. If the user's real-time physiological monitoring index is less than 1, the real-time physiological monitoring result is judged to be normal, and a rehabilitation training parameter dynamic configuration instruction is generated to command the robot to dynamically adjust the rehabilitation training parameters.

[0130] The real-time control specifically includes:

[0131] Based on the user's real-time training monitoring index, the robot rehabilitation training dynamic adjustment parameters corresponding to the real-time training monitoring index pre-stored in the database are mapped and matched to obtain the robot rehabilitation training dynamic adjustment parameters and dynamically configure the robot rehabilitation training initialization parameters.

[0132] The dynamic adjustment parameters of the robot rehabilitation training include an auxiliary force adjustment value, a speed sensor safety speed range adjustment value, and an electromyographic sensor accuracy adjustment value.

[0133] It should be noted that the terms "up", "down", "left", "right", "front", "back", etc. used in the present invention are only used to indicate relative position relationships. When the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0134] There are a few points to note:

[0135] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention, and other structures may refer to the general design.

[0136] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of the layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0137] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0138] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A multifunctional rehabilitation robot real-time monitoring and intelligent control system for ICU-AW patients, characterized in that: include: The trial operation data transmission self-check module is used to obtain the data transmission quality data of each transmission port during the trial operation of the rehabilitation robot, analyze and process the trial operation self-check result, and send a formal start permission signal to the control terminal when the trial operation self-check result is qualified; The initial data acquisition module is used to collect basic physiological data uploaded by the data transmission port, analyze and process the user's personalized rehabilitation characteristic coefficient, and perform initialization parameter configuration of the robot rehabilitation training based on the personalized rehabilitation characteristic coefficient; The rehabilitation data real-time monitoring module is used to monitor the real-time physiological data of the user during rehabilitation training and the real-time training data of the parts that need rehabilitation training, analyze and process to obtain the real-time physiological monitoring index and real-time training monitoring index, and upload them to the cloud processor; The real-time control module for rehabilitation training parameters is used to receive real-time physiological monitoring indexes and real-time training monitoring indexes through a cloud processor, comprehensively analyze and process to obtain dynamic configuration instructions for rehabilitation training parameters and perform real-time control.

2. According to claim 1, the multifunctional rehabilitation robot real-time monitoring and intelligent control system for ICU-AW patients is characterized in that: The step of obtaining the data transmission quality data of each transmission port during the trial operation of the rehabilitation robot and analyzing and processing to obtain the trial operation self-test result specifically includes: The data transmission quality data of each transmission port during the trial operation of the rehabilitation robot includes the delay change rate, bandwidth fluctuation rate, RSSI and jitter variance of each transmission port; Extract data transmission quality verification data from the database, including delay variation verification rate, bandwidth fluctuation verification rate, RSSI verification value and jitter verification variance, compare and analyze the data transmission quality data of each transmission port with the data transmission quality verification data, and obtain the data transmission quality evaluation value of each transmission port; If the data transmission quality evaluation values ​​of each transmission port are greater than or equal to the data transmission quality threshold, the trial operation self-test result is determined to be qualified, and a formal start permission signal is sent to the control terminal; If the data transmission quality evaluation value of a transmission port is less than the data transmission quality threshold, the trial operation self-inspection result of the transmission port is determined to be unqualified, and an early warning message is sent to the management terminal.

3. The multifunctional rehabilitation robot real-time monitoring and intelligent control system for ICU-AW patients according to claim 1 is characterized in that: The collecting of basic physiological data uploaded by the data transmission port and analyzing and processing to obtain the user's personalized rehabilitation characteristic coefficient specifically includes: Input the user's part that needs rehabilitation training, and collect the basic physiological data of the part that needs rehabilitation training uploaded by the data transmission port; The basic physiological data include reaction time, muscle strength and reflex speed of the part requiring rehabilitation training; Extract basic physiological reference data of the parts that need rehabilitation training from the database, including reaction time reference value, muscle strength reference value and reflex speed reference value; The basic physiological data of the user is compared and analyzed with the basic physiological reference data to obtain the personalized rehabilitation characteristic coefficient of the user, and the personalized rehabilitation characteristic coefficient is used for initialization parameter configuration of robot rehabilitation training.

4. The multifunctional rehabilitation robot real-time monitoring and intelligent control system for ICU-AW patients according to claim 1 is characterized in that: The configuration of the initialization parameters for the robot rehabilitation training specifically includes: Based on the user's personalized rehabilitation characteristic coefficients, the robot rehabilitation training initialization parameters corresponding to the personalized rehabilitation characteristic coefficients pre-stored in the database are mapped and matched to obtain the robot rehabilitation training initialization parameters and configure the robot rehabilitation training initialization parameters; The robot rehabilitation training initialization parameters include auxiliary force, speed sensor safety speed range and electromyography sensor accuracy; The assistance strength is used to determine the training strength for assisting the user in performing rehabilitation training; The speed sensor safety speed range is used to ensure that the user is within a reasonable speed range during rehabilitation training. If the user's real-time speed exceeds the safety speed range, an early warning message is sent to the management terminal; The electromyographic sensor accuracy is used to determine the signal sending frequency of the electromyographic sensor.

5. The multifunctional rehabilitation robot real-time monitoring and intelligent control system for ICU-AW patients according to claim 1 is characterized in that: The monitoring of the real-time physiological data of the user during rehabilitation training and the real-time training data of the part requiring rehabilitation training, and the analysis and processing to obtain the real-time physiological monitoring index and the real-time training monitoring index specifically include: The real-time physiological data includes the RMS of the sEMG signal, real-time heart rate fluctuation and real-time blood pressure fluctuation; The real-time training data of the part requiring rehabilitation training includes the real-time strength, real-time speed and real-time activity amplitude of the part requiring rehabilitation training; Extracting real-time physiological monitoring permissible fluctuation indicators from the database, including the RMS permissible fluctuation value of the sEMG signal, the real-time heart rate fluctuation permissible fluctuation value, and the real-time blood pressure fluctuation permissible fluctuation value; Based on the personalized rehabilitation characteristic coefficient, the real-time training monitoring indicators corresponding to the interval of the user's personalized rehabilitation characteristic coefficient are extracted from the database, including the real-time indicator intensity, the real-time indicator speed and the real-time indicator activity amplitude; Based on the user's real-time physiological data and the real-time physiological monitoring permission fluctuation index, comprehensive analysis and processing are performed to generate the user's real-time physiological monitoring index; Based on the real-time training data of the user's part that needs rehabilitation training and the real-time training monitoring indicators, the real-time training monitoring index of the user is generated through analysis and processing.

6. The multifunctional rehabilitation robot real-time monitoring and intelligent control system for ICU-AW patients according to claim 1 is characterized in that: The comprehensive analysis and processing to obtain the dynamic configuration instruction of the rehabilitation training parameters specifically includes: Based on the user's real-time physiological monitoring index, the user's real-time physiological monitoring result is obtained through cloud processor analysis. If the user's real-time physiological monitoring index is greater than 1, the real-time physiological monitoring result is determined to be abnormal, and a request to stop training is sent to the management terminal. If the user's real-time physiological monitoring index is less than or equal to 1, the real-time physiological monitoring result is determined to be normal, and a rehabilitation training parameter dynamic configuration instruction is generated to command the robot to dynamically adjust the rehabilitation training parameters.

7. The multifunctional rehabilitation robot real-time monitoring and intelligent control system for ICU-AW patients according to claim 1 is characterized in that: The real-time control specifically includes: Based on the user's real-time training monitoring index, the robot rehabilitation training dynamic adjustment parameters corresponding to the real-time training monitoring index pre-stored in the database are mapped and matched to obtain the robot rehabilitation training dynamic adjustment parameters and dynamically configure the robot rehabilitation training initialization parameters; The dynamic adjustment parameters of the robot rehabilitation training include an auxiliary force adjustment value, a speed sensor safety speed range adjustment value, and an electromyographic sensor accuracy adjustment value.

8. The multifunctional rehabilitation robot real-time monitoring and intelligent control system for ICU-AW patients according to claim 2 is characterized in that: The data transmission quality evaluation value of each transmission port also includes: The data transmission quality assessment value of each transmission port with a qualified trial run self-inspection result is statistically analyzed, and a comprehensive data transmission quality assessment value of each transmission port is obtained after mean processing. Based on the comprehensive data transmission quality assessment value, a mapping and matching is performed with the data transmission quality correction factor corresponding to each comprehensive data transmission quality assessment value interval in the database to obtain the data transmission quality correction factor, which is used to correct the damage to data quality caused by data transmission.

9. The multifunctional rehabilitation robot real-time monitoring and intelligent control system for ICU-AW patients according to claim 2 is characterized in that: It also includes physical performance monitoring of various parts of the robot during the trial run, including: During the test run, obtain the physical performance data of each device part of the robot, including the displacement speed of the end effector, the average temperature of the motor device and the response time; Extract physical performance verification data of various device parts of the robot from the database, including the end effector displacement speed verification value, the motor device average verification temperature and the response time verification value; The physical performance data of each device part of the robot are compared and analyzed with the physical performance verification data of each device part. The end effector displacement speed, the average temperature of the motor device and the response time of the robot are respectively subtracted from the end effector displacement speed verification value, the average verification temperature of the motor device and the response time verification value, which are recorded as the parameter differences. When the parameter differences are less than or equal to the allowable error range corresponding to the parameters, the physical performance monitoring result of the robot's trial run is judged to be qualified. When a parameter difference is greater than the allowable error range corresponding to the parameters, the physical performance monitoring result of the robot's trial run is judged to be unqualified, and a signal prohibiting formal operation is sent to the management terminal.

10. The multifunctional rehabilitation robot real-time monitoring and intelligent control system for ICU-AW patients according to claim 3 is characterized in that: The analysis and processing to obtain the user's personalized rehabilitation characteristic coefficient specifically includes: Among them, ε is the user's personalized rehabilitation characteristic coefficient, TZ is reaction time, po is muscle strength, v is reflex speed, TZ0 is the reference value of reaction time, po0 is the reference value of muscle strength, v0 is the reference value of reflex speed, is the reaction time weight factor, is the muscle strength weighting factor, is the reflection speed weight factor, δ is the data transmission quality correction factor, Mish function is the activation function, Mish(x)=x*tanh[softplus(x)].

Images