WO2024103467A1

WO2024103467A1 - Exercise state determination method and system applied to lower limb rehabilitation training

Info

Publication number: WO2024103467A1
Application number: PCT/CN2022/138162
Authority: WO
Inventors: 苏栋楠; 罗朝晖; 尚鹏; 曾梓琳; 王通; 吴继鹏; 王俊伟
Original assignee: 深圳先进技术研究院
Priority date: 2022-11-18
Filing date: 2022-12-09
Publication date: 2024-05-23
Also published as: CN115715685A

Abstract

An exercise state determination method and a system applied to lower limb rehabilitation training. The method comprises: acquiring at least one type of initial lower limb exercise data of a rehabilitation user in a lower limb rehabilitation training process, and processing the initial lower limb exercise data to obtain processed lower limb exercise data (S110); extracting features from the lower limb exercise data on the basis of a preset feature extraction model, and determining user load states corresponding to the feature data obtained from feature extraction (S120); and determining an exercise state for the rehabilitation user on the basis of a preset exercise state threshold and the user load states (S130). The technical solution solves the problem of low accuracy in the assessment of exercise states of rehabilitation training in the prior art, improving the accuracy in the determination of exercise states of rehabilitation training.

Description

Method and system for determining motion state for lower limb rehabilitation training

Technical Field

The present invention relates to the field of rehabilitation medical technology, and in particular to a method and system for determining a motion state used in lower limb rehabilitation training.

Background technique

At present, the amount of rehabilitation training conducted in hospitals is mainly determined based on the subjective experience of doctors, but each person is different, which leads to different effects after standardized rehabilitation training for different people. If we rely on the subjective experience of doctors, the final effect of customized lower limb rehabilitation training will be affected due to differences in personal experience and diagnostic ability of doctors. In addition, current rehabilitation assessments are mostly conducted after the training is completed, or only a single physiological signal is used as the criterion for judgment, so the accuracy of the assessment results achieved is low.

Summary of the invention

The present invention provides a motion state determination method and system for lower limb rehabilitation training, so as to solve the problem of low accuracy of motion state evaluation results of rehabilitation training in the prior art and improve the accuracy of operation state determination of rehabilitation training.

In a first aspect, an embodiment of the present invention provides a method for determining a motion state for lower limb rehabilitation training, the method comprising:

Acquire at least one initial lower limb motion data of the rehabilitation user during the lower limb rehabilitation training, perform data processing on each of the initial lower limb motion data, and obtain processed lower limb motion data;

Based on a preset feature extraction model, feature extraction is performed on each of the lower limb motion data, and the user load state corresponding to each feature data after feature extraction is determined;

The exercise state of the rehabilitation user is determined according to a preset exercise state threshold and the load state of each user.

Optionally, the step of obtaining at least one initial lower limb movement data of the rehabilitation user during the lower limb rehabilitation training includes:

Upon receiving a motion data packet sent by the rehabilitation user during the lower limb rehabilitation training, determining whether the motion data packet is encrypted data;

If so, a preset decryption method is used to decrypt the encrypted data packet to obtain the initial lower limb movement data of the rehabilitation user.

Optionally, the initial lower limb motion data includes initial lower limb electromyography data, initial electrocardiogram data and initial heart rate data;

The processing of each of the initial lower limb motion data to obtain processed lower limb motion data includes:

Performing data filtering and data noise reduction processing on the initial lower limb electromyography data and the initial electrocardiogram data of the rehabilitation user to obtain the lower limb electromyography data and the electrocardiogram data of the rehabilitation user;

The initial heart rate data is processed to eliminate abnormal data to obtain the heart rate data of the rehabilitation user.

Optionally, the feature extraction model includes an electrocardiogram feature extraction sub-model;

The method of extracting features from each lower limb motion data based on a preset feature extraction model and determining the user load state corresponding to each feature data after feature extraction includes:

Performing feature extraction on the ECG data based on the ECG feature extraction sub-model to obtain dynamic ECG feature values and heart rate variability of the rehabilitation user;

A first load state of the rehabilitation user is determined based on the dynamic electrocardiogram characteristic value and the heart rate variability.

Optionally, the feature extraction model includes an electromyographic feature extraction sub-model;

Performing feature extraction on the electromyographic data based on the electromyographic feature extraction sub-model to obtain a root mean square feature value of the rehabilitation user;

The second load state of the rehabilitation user is determined based on a preset load state determination model and the root mean square eigenvalue.

Optionally, the motion state threshold includes a first load state threshold, a second load state threshold and a heart rate threshold;

The step of determining the exercise state of the rehabilitation user according to a preset exercise state threshold and each user load state includes:

The exercise state of the rehabilitation user is determined according to the first load state threshold, the second load state threshold, the heart rate threshold, the first load state and the second load state.

In a second aspect, an embodiment of the present invention further provides a motion state determination device for lower limb rehabilitation training, the device comprising:

A lower limb motion data acquisition module is used to acquire at least one initial lower limb motion data of a rehabilitation user during the lower limb rehabilitation training, and perform data processing on each of the initial lower limb motion data to obtain processed lower limb motion data;

A user load state determination module, used to extract features from each of the lower limb motion data based on a preset feature extraction model, and determine the user load state corresponding to each feature data after feature extraction;

The motion state determination module is used to determine the motion state of the rehabilitation user according to a preset motion state threshold and the load state of each user.

In a third aspect, an embodiment of the present invention further provides a motion state determination system for lower limb rehabilitation training, the system comprising: a data processing subsystem and a lower limb motion data acquisition subsystem; the lower limb motion data acquisition subsystem comprises an electromyography data acquisition device, an electrocardiogram data acquisition device and a data transmission device; wherein,

The electromyographic data acquisition device is used to collect electromyographic data packets of the rehabilitation user and send the electromyographic data packets to the data transmission device;

The ECG data device is used to collect ECG data packets of the rehabilitation user and send the ECG data packets to the data transmission device;

The data transmission device is used to process the received electromyography data packet and the electrocardiogram data packet, and send the processed motion data packet to the data processing subsystem; the data processing subsystem is used to determine the motion state of the rehabilitation user based on the motion state determination method applied to lower limb rehabilitation training described in any embodiment.

In a third aspect, an embodiment of the present invention further provides an electronic device, including:

at least one processor; and

a memory communicatively connected to the at least one processor; wherein,

The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the motion state determination method for lower limb rehabilitation training described in any embodiment of the present invention.

In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the motion state determination method for lower limb rehabilitation training described in any embodiment of the present invention when executed.

The technical solution provided by the embodiment of the present invention obtains at least one initial lower limb motion data of a rehabilitation user during the lower limb rehabilitation training, performs data processing on each of the initial lower limb motion data, and obtains each processed lower limb motion data; performs feature extraction on each of the lower limb motion data based on a preset feature extraction model, and determines the user load state corresponding to each feature data after feature extraction; and determines the motion state of the rehabilitation user according to a preset motion state threshold and each user load state. The above technical solution obtains a variety of lower limb motion data of a rehabilitation user during the rehabilitation training, processes them to obtain a variety of load states of the rehabilitation user, and then determines the motion state of the rehabilitation user based on different state thresholds, so as to achieve accurate judgment of the motion state of the rehabilitation user during the training process, solves the problem of low accuracy of the motion state evaluation results of the rehabilitation user during rehabilitation training in the prior art, and improves the accuracy of determining the operating state of the rehabilitation training.

It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description.

BRIEF DESCRIPTION OF THE DRAWINGS

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.

FIG1 is a flow chart of a method for determining a motion state for lower limb rehabilitation training provided in accordance with a first embodiment of the present invention;

2 is a schematic diagram of the structure of a motion state determination system for lower limb rehabilitation training provided in accordance with a second embodiment of the present invention;

3 is a schematic diagram of the structure of an electromyographic data acquisition device provided according to a second embodiment of the present invention;

FIG4 is a schematic diagram of the structure of an electrocardiogram data acquisition device provided according to a second embodiment of the present invention;

FIG5 is a schematic diagram of the structure of a data transmission device provided according to Embodiment 3 of the present invention;

6 is a schematic diagram of the structure of a motion state determination device for lower limb rehabilitation training provided in accordance with a fourth embodiment of the present invention;

FIG. 7 is a schematic diagram of the structure of an electronic device that implements the method for determining the motion state applied to lower limb rehabilitation training according to an embodiment of the present invention.

Detailed ways

In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 described embodiments 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 creative work should fall within the scope of protection of the present invention.

It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein.

The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

Embodiment 1

FIG1 is a flowchart of a method for determining the motion state of lower limb rehabilitation training provided in the first embodiment of the present invention. This embodiment can be applied to rehabilitation users in rehabilitation training. In practical applications, rehabilitation users can be understood as users who need to perform physical activities that are conducive to recovery or improvement of physical injuries due to physical injuries caused by diseases, accidents, etc. Rehabilitation training refers to the conduct of. Since stroke and other reasons can cause lower limb dysfunction, users with stroke need to perform rehabilitation training on their lower limbs to improve their motor ability and improve their quality of life. During the rehabilitation training process, if the amount of exercise in the lower limb rehabilitation training is insufficient, it is difficult to meet the requirements of the rehabilitation training and it cannot play an effective role. On the contrary, if the amount of exercise in the lower limb rehabilitation training is overloaded, it will cause muscle soreness, which will have a twice the result with half the effort effect, not only undermining the enthusiasm of rehabilitation users for future rehabilitation training, but also forming wrong movement patterns for rehabilitation users, further affecting the rehabilitation users' motor ability.

However, the amount of exercise that rehabilitation users must do during rehabilitation training is mainly determined based on the doctor's subjective experience, and most rehabilitation centers do not monitor rehabilitation users during rehabilitation training. Only nursing staff supervise rehabilitation users to see if they have reached the daily training amount, and finally evaluate the lower limb muscle strength level of rehabilitation users every month or several months during the rehabilitation cycle to determine the rehabilitation status of rehabilitation users. A small number of rehabilitation centers will pay attention to the exercise load status of rehabilitation users during rehabilitation training, but they only detect the electromyographic fatigue status of rehabilitation users and evaluate based on a single judgment standard, resulting in inaccurate evaluation results.

In order to solve the above-mentioned technical problems, the technical solution of this embodiment provides a method for determining the motion state applied to lower limb rehabilitation training. The method specifically obtains a variety of lower limb motion data of the rehabilitation user during the rehabilitation training process, and processes the data to obtain a variety of load states of the rehabilitation user, and then determines the motion state of the rehabilitation user based on different state thresholds, so as to achieve accurate judgment of the motion state of the rehabilitation user during the training process.

The method can be performed by a motion state determination device applied to lower limb rehabilitation training, which can be implemented in the form of hardware and/or software, and can be configured in a data processing subsystem of a motion state determination system applied to lower limb rehabilitation training.

Specifically, as shown in FIG1 , the method includes:

S110. Obtain at least one initial lower limb motion data of a rehabilitation user during lower limb rehabilitation training, perform data processing on each of the initial lower limb motion data, and obtain processed lower limb motion data.

In an embodiment of the present invention, a rehabilitation user can walk on a flatbed cart with the help of a walker to perform rehabilitation training. During this period, the rehabilitation user wears a lower limb motion data acquisition subsystem pre-built in the technical solution of the embodiment of the present invention to collect motion data packets of the rehabilitation user during the lower limb rehabilitation training process, and send the motion data packets to the data processing subsystem of the current motion state determination system, so that the data processing subsystem of the motion state determination system determines the motion state of the rehabilitation user during the lower limb rehabilitation training process based on the motion data packets.

Optionally, the technical solution of this embodiment, when receiving a motion data packet sent by the rehabilitation user during lower limb rehabilitation training, determines whether the motion data packet is encrypted data; if so, uses a preset decryption method to decrypt the encrypted data packet to obtain the initial lower limb motion data of the rehabilitation user.

In practical applications, in order to avoid leaking the health privacy of rehabilitation users during the rehabilitation process during transmission, the lower limb motion data acquisition subsystem encrypts each motion data to form a motion data packet when collecting the various motion data of the rehabilitation users, and then transmits the encrypted motion data packet for data transmission. When the data processing subsystem of the motion state determination system receives the motion data packet, it can determine whether the motion data packet is encrypted data based on the format of the motion data packet. Optionally, if it is determined that the motion data packet is encrypted data, the corresponding decryption key is determined based on the encryption method of the lower limb motion data acquisition subsystem, and the motion data packet is decrypted based on the decryption key to obtain the decrypted initial lower limb motion data. It should be noted that in this embodiment, the encryption method and decryption method of the data are not limited, and the data encryption and data decryption functions can be realized.

Optionally, the initial lower limb motion data obtained in this embodiment include but are not limited to the initial lower limb electromyography data, initial electrocardiogram data and initial heart rate data of the rehabilitation user. Since there may be data noise and abnormal data in the data acquisition process, it is necessary to perform data processing on the above-mentioned initial lower limb motion data before determining the motion state based on the above-mentioned initial lower limb motion data. Optionally, in this embodiment, the method of performing data processing on each of the initial lower limb motion data to obtain the processed lower limb motion data may include: performing data filtering and data noise reduction processing on the initial lower limb electromyography data and the initial electrocardiogram data of the rehabilitation user to obtain the lower limb electromyography data and electrocardiogram data of the rehabilitation user; performing abnormal data elimination processing on the initial heart rate data to obtain the heart rate data of the rehabilitation user.

In practical applications, since the ECG data and the EMG data are non-stationary data signals, the processing of the above-mentioned initial EMG data and the initial ECG data can be performed by using a digital filter for data filtering processing, and by using a wavelet transform noise reduction method for data noise reduction processing to obtain processed EMG data and ECG data. Optionally, the efficiency transformation noise reduction method used in this embodiment includes Haar wavelet windowing noise reduction. Exemplarily, the scaling function includes:

in,

represents the Haar wavelet scaling function; x represents the windowed time domain range.

Optionally, since the heart rate data is a smooth data signal, there is no need to filter or reduce the noise for the initial heart rate data. However, since the rehabilitation user is in motion, the obtained heart rate data may contain abnormal heart rate data caused by motion. Therefore, it is necessary to eliminate the abnormal data from the initial heart rate data, and use the heart rate data obtained after elimination to determine the exercise state of the rehabilitation user.

S120, performing feature extraction on each of the lower limb motion data based on a preset feature extraction model, and determining the user load state corresponding to each feature data after feature extraction.

In the embodiment of the present invention, since the lower limb motion data includes different motion data, the feature extraction model needs to include different sub-models to realize feature extraction of different motion data respectively, and then determine the corresponding motion state based on the extracted motion features.

Optionally, the feature extraction model in the present embodiment includes an ECG feature extraction sub-model; accordingly, the method in the present embodiment for performing feature extraction on each of the lower limb motion data based on a preset feature extraction model, and determining the user load state corresponding to each feature data after feature extraction may include: performing feature extraction on the ECG data based on the ECG feature extraction sub-model to obtain dynamic ECG feature values and heart rate variability of the rehabilitation user; and determining the first load state of the rehabilitation user based on the dynamic ECG feature values and the heart rate variability.

In practical applications, since the QRS complex of the ECG data contains the main ECG information of the ECG data, the ECG data is feature extracted to obtain the QRS complex of the ECG data. Specifically, an ECG feature extraction submodel is obtained, and the ECG data is input into the ECG feature extraction submodel to obtain the feature extraction result output by the model. The specific extraction result may include the dynamic ECG feature value and heart rate variability of the rehabilitation user.

In this embodiment, the second load state of the rehabilitation user can be determined based on a traditional algorithm, or based on a pre-trained neural network model. This embodiment does not limit the determination method. In practical applications, the entropy value corresponding to the rehabilitation user can be determined by substituting the dynamic electrocardiogram characteristic value and the heart rate variability into the entropy value algorithm, and the first fatigue state of the patient can be determined based on the entropy value. In this embodiment, the first fatigue state includes an unloaded state, a normal load state, and a high load state. It should be noted that the range of entropy values is mostly between 0.4 and 0.8, where the larger the entropy value, the stronger the vagus nerve regulation. Optionally, when the entropy value is below 0.6, it means that the rehabilitation user is in an unloaded state; when the entropy value is between 0.6 and 0.7, it means that the rehabilitation user is in a normal load state; when the entropy value is above 0.7, it means that the rehabilitation user is in a high load state.

Optionally, the feature extraction model in this embodiment includes an electromyographic feature extraction sub-model; accordingly, the method in this embodiment for performing feature extraction on each of the lower limb motion data based on a preset feature extraction model, and determining the user load state corresponding to each feature data after feature extraction may include: performing feature extraction on the electromyographic data based on the electromyographic feature extraction sub-model to obtain the root mean square eigenvalue of the rehabilitation user; determining the second load state of the rehabilitation user based on the preset load state determination model and the root mean square eigenvalue.

In practical applications, the processed electromyographic data is input into the electromyographic feature extraction sub-model to obtain the electromyographic feature value output by the model, that is, the root mean square feature value of the rehabilitation user. Further, a preset load state determination model is obtained. Specifically, the root mean square feature value obtained above is input into the acquired load state determination model to obtain the second load state output by the model. Optionally, the second load state includes 5 load states from low to high, specifically including a relief state, a pressurized state, an intermediate transition state, a load state, and a deep load state.

In this embodiment, the load state determination model can also be obtained by training based on a neural network. The neural network may include an input layer, two pooling layers, corresponding to 27 neurons, and an output layer, corresponding to 5 neurons. Specifically, the above neural network is trained using the 8-fold angle verification method to obtain a trained compliance state determination model. Of course, the network structure of the above neural network is only an exemplary introduction scheme of this embodiment, and is not intended to limit the technical solution of this embodiment. This embodiment may also use other network structures to form a neural network, without limitation.

Regarding heart rate data, the normal heart rate of the human body is 60-100 beats per minute. For stroke users, if the heart rate reaches above 130, they are in a state of load exercise and should take appropriate rest.

It should be noted that, in this embodiment, the effect of obtaining electrocardiogram data and heart rate data in addition to electromyography data is that the electromyography data can reflect from the muscle surface whether the rehabilitation patient is in a state of exercise saturation, and the electrocardiogram data and heart rate data can further reflect whether the current state of the rehabilitation user is exercise saturated based on the body data. The two situations are combined to comprehensively determine the exercise state of the rehabilitation user, so as to improve the accuracy of determining the exercise state of the rehabilitation user during the rehabilitation training process.

S130, determining the exercise state of the rehabilitation user according to a preset exercise state threshold and the load state of each user.

In an embodiment of the present invention, the motion state threshold may be jointly designated by multiple doctors in a rehabilitation center. Of course, for greater accuracy, a neural network may be trained based on data from historical rehabilitation users, and the motion state threshold may be obtained based on the trained model.

In this embodiment, the corresponding motion state thresholds are determined based on the multiple load states determined by the lower limb motion data. Specifically, the motion state thresholds include a first load state threshold, a second load state threshold and a heart rate threshold.

In actual applications, when the HRV entropy value of the rehabilitation user during rehabilitation training is below 0.6, the heart rate is below 120 beats/minute, and the electromyographic fatigue state is below the intermediate transition state, it means that the rehabilitation user is currently in an unsaturated state of exercise, and training suggestions for continuing exercise can be given at this time; optionally, when the HRV entropy value of the rehabilitation user during rehabilitation training is 0.7, the heart rate is below 120 beats/minute, the electromyographic fatigue state is below the intermediate transition state, or the heart rate is above 120 beats/minute but not exceeding When the HRV entropy value of the rehabilitation user is over 130 times/minute, the heart rate exceeds 130 times/minute, or the electromyography fatigue state is in the intermediate transition state, or the electromyography fatigue state is in the load state, the HRV entropy value is below 0.6, and the heart rate is below 120 times/minute, it means that the rehabilitation user is currently in a critical state, and training suggestions such as rest or reducing the amplitude and speed of movement can be given; optionally, when the HRV entropy value of the rehabilitation user during the rehabilitation training is 0.8 or the heart rate exceeds 130 times/minute, or the electromyography fatigue state is in the deep load state, it means that the rehabilitation user is in the state of exercise supersaturation, and training suggestions such as immediate rest can be given.

Embodiment 2

FIG2 is a schematic diagram of the structure of a motion state determination system for lower limb rehabilitation training provided by Embodiment 2 of the present invention. As shown in FIG2, the system includes: a data processing subsystem 210 and a lower limb motion data acquisition subsystem 220; the lower limb motion data acquisition subsystem 220 includes an electromyography data acquisition device 2201, an electrocardiogram data acquisition device 2202, and a data transmission device 2203; wherein,

The electromyographic data acquisition device 2201 is used to collect electromyographic data packets of the rehabilitation user and send the electromyographic data packets to the data transmission device 2203;

The ECG data device is used to collect ECG data packets of the rehabilitation user and send the ECG data packets to the data transmission device 2203;

The data transmission device 2203 is used to process the received electromyography data packet and the electrocardiogram data packet, and send the processed motion data packet to the data processing subsystem 210; the data processing subsystem 210 is used to determine the motion state of the rehabilitation user based on the motion state determination method applied to lower limb rehabilitation training described in any embodiment.

In the embodiment of the present invention, the myoelectric data acquisition device 2201 may be a wireless acquisition device. Optionally, the wireless data acquisition device may include a power module, a signal amplification circuit, a signal filtering circuit, a root mean square value extraction module, a micro control unit, a Bluetooth module, and an electromyographic acquisition electrode.

In actual application, see Figure 3. The power module includes a 3.3V voltage regulator circuit and a lithium battery charging and discharging circuit. Specifically, it is used to power each module in the acquisition device. The amplifier in the signal amplification circuit uses the AD620 chip, which has the characteristics of high precision and low power consumption. Specifically, a three-op-amp differential amplifier circuit is used to amplify the microvolt-level surface electromyographic signal by 1000 times. The cutoff frequency of the low-pass filter designed in the signal filtering circuit is 530Hz, and the operational amplifier used is AD8062AR. Specifically, the effective frequency of the electromyographic signal is about 10-500Hz, so this part of the circuit is to filter out clutter to obtain high-quality electromyographic signals. The AD536A chip is used in the root mean square value extraction module. Specifically, the input of this module is the amplified surface electromyographic signal, and the output is the root mean square value, so as to extract the amplified surface electromyographic signal. The STM32 series chip is used as the control chip in the microcontroller unit (MCU) module. Specifically, the control acquisition and extraction of the electromyographic signal is uploaded to the data terminal module via Bluetooth. The Bluetooth module can use the Bluetooth 5.0 communication protocol with a baud rate of 115200. Specifically, the data is uploaded to the data terminal module in a transparent manner. Optionally, Bluetooth can be in slave mode. The electromyographic acquisition electrodes can use dry electrodes, and each electromyographic module requires a pair of dry electrodes. Optionally, the electrode pairs are worn on the rectus femoris, sartorius, vastus medialis and vastus lateralis of the patient's left and right legs (a total of four pairs) to accurately collect the electromyographic signals of the rehabilitation user.

In the embodiment of the present invention, the ECG data acquisition device 2202 can collect the heart rate changes and dynamic ECG of the rehabilitation user during the rehabilitation training process. Optionally, the ECG data acquisition device 2202 can be a wireless acquisition device. The ECG data acquisition device 2202 can include a power module, a preamplifier circuit, a filter circuit, a heart rate detection module, an MCU module, a Bluetooth module, and an ECG acquisition electrode.

In practical applications, see Figure 4. The power module includes a 3.3V voltage regulator circuit and a lithium battery charging and discharging circuit, which are used to provide power for each module in the ECG data acquisition device 2202. The preamplifier circuit uses the AD620 chip, which has the characteristics of high precision and low power consumption. Specifically, a three-op-amp differential amplifier circuit is used to amplify the microvolt ECG signal by 1000 times. The second-order Chebyshev low-pass filter designed in the filter circuit has a cut-off frequency of 110Hz. It is used to collect the effective frequency of 0.05-100HZ of dynamic ECG. The heart rate detection module uses the PTP321 heart rate dedicated detection chip to read the heart rate, where the effective heart rate range is 50-200 times/minute. The MCU module also uses the STM32 series chip as the control chip, and specifically uploads the collected dynamic ECG and heart rate to the data terminal module via Bluetooth. The Bluetooth module can use the Bluetooth 5.0 communication protocol with a baud rate of 115200. Specifically, the data is uploaded to the data terminal module in a transparent transmission manner, and optionally, Bluetooth can be in slave mode. The electrocardiogram collection electrodes can be made of Ag ion gel electrodes and attached to V1-V2 in the form of chest leads to accurately collect the electrocardiogram data of the rehabilitation user.

In an embodiment of the present invention, the data transmission device 2203 includes a power module, an MCU module, a Bluetooth module and a WIFI module. In practical applications, see Figure 5, the power module includes a 3.3V voltage stabilizing circuit, a lithium battery charging and discharging circuit and a 5V voltage step-down circuit, which are used to provide power for the data transmission device 2203. The MCU module uses an STM32 chip for programming control to control Bluetooth data transmission and reception and WIFI module data upload. The Bluetooth module can use the Bluetooth 5.0 communication protocol with a baud rate of 115200 to upload data to the data terminal module in a transparent transmission manner. Optionally, Bluetooth is in host mode. The WIFI module can use ESP-32 07S to ensure stable signal connection during data transmission.

The technical solution of the embodiment of the present invention integrates and encrypts the data collected by the electromyography data acquisition device 2201 and the electrocardiography data acquisition device 2202 and sends them to the data processing subsystem 210. After decrypting the received data, the data processing subsystem 210 evaluates the exercise load status through relevant algorithm analysis and gives corresponding suggestions, so as to achieve the difference between each user.

The best exercise effect can be achieved, and at the same time, the user will not be required to continue training when the user exceeds the upper limit of the user's exercise load, which is conducive to reducing the user's resistance to rehabilitation training.

The motion state determination system for lower limb rehabilitation training provided by the embodiment of the present invention can execute the motion state determination method for lower limb rehabilitation training provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

Embodiment 3

FIG6 is a schematic diagram of the structure of a motion state determination device for lower limb rehabilitation training provided by Embodiment 3 of the present invention. As shown in FIG6 , the device includes:

The lower limb motion data acquisition module 310 is used to acquire at least one initial lower limb motion data of the rehabilitation user during the lower limb rehabilitation training, and perform data processing on each of the initial lower limb motion data to obtain processed lower limb motion data;

A user load state determination module 320 is used to extract features from each of the lower limb motion data based on a preset feature extraction model, and determine the user load state corresponding to each feature data after feature extraction;

The motion state determination module 330 is used to determine the motion state of the rehabilitation user according to a preset motion state threshold and the load state of each user.

Based on the above embodiments, optionally, the device further includes:

A data status determination module, used for determining whether the motion data packet is encrypted data when receiving the motion data packet sent by the rehabilitation user during the lower limb rehabilitation training;

The initial lower limb motion data acquisition module is used to, if yes, use a preset decryption method to decrypt the encrypted data packet to obtain the initial lower limb motion data of the rehabilitation user.

Based on the above embodiments, optionally, the initial lower limb motion data includes initial lower limb electromyography data, initial electrocardiogram data and initial heart rate data;

The lower limb motion data acquisition module 310 includes:

A lower limb electromyography data and electrocardiogram data acquisition unit, used for performing data filtering and data noise reduction processing on the initial lower limb electromyography data and the initial electrocardiogram data of the rehabilitation user to obtain the lower limb electromyography data and the electrocardiogram data of the rehabilitation user;

The heart rate data acquisition unit is used to perform abnormal data elimination processing on the initial heart rate data to obtain the heart rate data of the rehabilitation user.

Based on the above embodiments, the feature extraction model includes an electrocardiogram feature extraction sub-model;

Optionally, the user load state determination module 320 includes:

A first feature extraction unit, configured to extract features from the ECG data based on the ECG feature extraction sub-model, to obtain dynamic ECG feature values and heart rate variability of the rehabilitation user;

The first load state determining unit is used to determine the first load state of the rehabilitation user based on the dynamic electrocardiogram characteristic value and the heart rate variability.

Based on the above embodiments, the feature extraction model includes an electromyographic feature extraction sub-model;

Optionally, the user load state determination module 320 includes:

A second feature extraction unit, configured to perform feature extraction on the electromyographic data based on the electromyographic feature extraction sub-model to obtain a root mean square feature value of the rehabilitation user;

The second load state determination unit is used to determine the second load state of the rehabilitation user based on a preset load state determination model and the root mean square eigenvalue.

Based on the above embodiments, the exercise state threshold includes a first load state threshold, a second load state threshold and a heart rate threshold;

Optionally, the motion state determination module 330 includes:

An exercise state determination unit is used to determine the exercise state of the rehabilitation user based on the first load state threshold, the second load state threshold, the heart rate threshold, the first load state and the second load state.

The motion state determination device for lower limb rehabilitation training provided by the embodiment of the present invention can execute the motion state determination method for lower limb rehabilitation training provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

Embodiment 4

FIG7 shows a block diagram of an electronic device 10 that can be used to implement an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and/or required herein.

As shown in FIG7 , the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, ROM 12 and RAM 13 are connected to each other through a bus 14. An input/output (I/O) interface 15 is also connected to the bus 14.

A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the motion state determination method applied to lower limb rehabilitation training.

In some embodiments, the motion state determination method applied to lower limb rehabilitation training can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and/or installed on the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the motion state determination method applied to lower limb rehabilitation training described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the motion state determination method applied to lower limb rehabilitation training in any other appropriate manner (for example, by means of firmware).

Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and/or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions/operations specified in the flow chart and/or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

A method for determining a motion state applied to lower limb rehabilitation training, characterized by comprising:

Acquire at least one initial lower limb motion data of the rehabilitation user during the lower limb rehabilitation training, perform data processing on each of the initial lower limb motion data, and obtain processed lower limb motion data;

Based on a preset feature extraction model, feature extraction is performed on each of the lower limb motion data, and the user load state corresponding to each feature data after feature extraction is determined;

The exercise state of the rehabilitation user is determined according to a preset exercise state threshold and the load state of each user.
The method according to claim 1, characterized in that the step of obtaining at least one initial lower limb motion data of a rehabilitation user during lower limb rehabilitation training comprises:

Upon receiving a motion data packet sent by the rehabilitation user during the lower limb rehabilitation training, determining whether the motion data packet is encrypted data;

If so, a preset decryption method is used to decrypt the encrypted data packet to obtain the initial lower limb movement data of the rehabilitation user.
The method according to claim 1, characterized in that the initial lower limb motion data includes initial lower limb electromyography data, initial electrocardiogram data and initial heart rate data;

The processing of each of the initial lower limb motion data to obtain processed lower limb motion data includes:

Performing data filtering and data noise reduction processing on the initial lower limb electromyography data and the initial electrocardiogram data of the rehabilitation user to obtain the lower limb electromyography data and the electrocardiogram data of the rehabilitation user;

The initial heart rate data is processed to eliminate abnormal data to obtain the heart rate data of the rehabilitation user.
The method according to claim 3, characterized in that the feature extraction model includes an electrocardiogram feature extraction sub-model;

The method of extracting features from each lower limb motion data based on a preset feature extraction model and determining the user load state corresponding to each feature data after feature extraction includes:

Performing feature extraction on the ECG data based on the ECG feature extraction sub-model to obtain dynamic ECG feature values and heart rate variability of the rehabilitation user;

A first load state of the rehabilitation user is determined based on the dynamic electrocardiogram characteristic value and the heart rate variability.
The method according to claim 3, characterized in that the feature extraction model includes an electromyographic feature extraction sub-model;

The method of extracting features from each lower limb motion data based on a preset feature extraction model and determining the user load state corresponding to each feature data after feature extraction includes:

Performing feature extraction on the electromyographic data based on the electromyographic feature extraction sub-model to obtain a root mean square feature value of the rehabilitation user;

A second load state of the rehabilitation user is determined based on a preset load state determination model and the root mean square eigenvalue.
The method according to claim 1, characterized in that the motion state threshold comprises a first load state threshold, a second load state threshold and a heart rate threshold;

The step of determining the exercise state of the rehabilitation user according to a preset exercise state threshold and each user load state includes:

The exercise state of the rehabilitation user is determined according to the first load state threshold, the second load state threshold, the heart rate threshold, the first load state and the second load state.
A motion state determination device for lower limb rehabilitation training, characterized by comprising:

A lower limb motion data acquisition module is used to acquire at least one initial lower limb motion data of a rehabilitation user during the lower limb rehabilitation training, and perform data processing on each of the initial lower limb motion data to obtain processed lower limb motion data;

A user load state determination module, used to extract features from each of the lower limb motion data based on a preset feature extraction model, and determine the user load state corresponding to each feature data after feature extraction;

The motion state determination module is used to determine the motion state of the rehabilitation user according to a preset motion state threshold and the load state of each user.
An electronic device, characterized in that the electronic device comprises:

at least one processor; and

a memory communicatively connected to the at least one processor; wherein,

The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the motion state determination method for lower limb rehabilitation training described in any one of claims 1-6.
A computer-readable storage medium, characterized in that the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the motion state determination method for lower limb rehabilitation training described in any one of claims 1-6 when executed.
A motion state determination system for lower limb rehabilitation training, characterized in that it comprises: a data processing subsystem and a lower limb motion data acquisition subsystem; the lower limb motion data acquisition subsystem comprises an electromyography data acquisition device, an electrocardiogram data acquisition device and a data transmission device; wherein,

The electromyographic data acquisition device is used to collect electromyographic data packets of the rehabilitation user and send the electromyographic data packets to the data transmission device;

The ECG data device is used to collect ECG data packets of the rehabilitation user and send the ECG data packets to the data transmission device;

The data transmission device is used to process the received electromyography data packet and the electrocardiogram data packet, and send the processed motion data packet to the data processing subsystem; the data processing subsystem is used to determine the motion state of the rehabilitation user based on the motion state determination method applied to lower limb rehabilitation training as described in any one of claims 1-6.