Rehabilitation training method, rehabilitation training system, electronic equipment and storage medium

Abstract

The invention provides a rehabilitation training method, a rehabilitation training system, electronic equipment and a storage medium, and relates to the technical field of brain-computer interfaces. According to the scheme, the electroencephalogram signals of the target object are collected in the brain-computer interface device, the motion intention of the target object is analyzed from the electroencephalogram signals, and when it is detected and recognized that the electroencephalogram signals of the target object are the motion intention, the control signals are generated; the control signal is sent to the rehabilitation robot through the control interface in the rehabilitation robot, and the rehabilitation robot drives the affected side lower limb assembly to drive the affected limb of the target object to perform active rehabilitation training according to the received control signal, that is, in the rehabilitation training process of the target object, the active movement intention of the target object is fully utilized, and the rehabilitation training effect is improved. Therefore, the rehabilitation training effect is improved, and the problem that the rehabilitation effect and the patient experience are poor due to the fact that the active movement intention of the patient is not fully utilized in the prior art is effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of electroencephalogram signals, and in particular, to a rehabilitation training method, a rehabilitation training system, an electronic device, and a storage medium. Background Art

[0002] A rehabilitation medical robot is a wearable rehabilitation device. Currently, the rehabilitation medical robot can perform physical rehabilitation training on a patient by controlling the movement of the patient's lower limbs. For example, the patient can control the robot controller with the upper limb to manipulate the walking of the lower limbs, or can manipulate the lower limbs by selecting a pre-set program in advance, so as to help the patient complete the recovery training of various motor functions, such as walking training, etc., greatly enhancing the purposefulness and scientific nature of the rehabilitation training process.

[0003] In the prior art, after the traditional single-lower-limb rehabilitation robot mainly completes the rehabilitation training on the healthy lower limb of the patient, the patient needs to manually press the physical button provided on the rehabilitation robot to trigger the affected lower limb component in the single-lower-limb rehabilitation robot to act on the affected lower limb, so as to help the affected lower limb perform mirror learning rehabilitation training according to the gait data of the healthy lower limb, indirectly stimulate the central nervous system of the brain, achieve the purpose of remodeling motor neurons, and accelerate the recovery of motor function.

[0004] However, the rehabilitation training method adopted by the existing single-lower-limb rehabilitation robot does not make full use of the patient's active movement intention, resulting in poor rehabilitation effects and patient experience. Summary of the Invention

[0005] The purpose of the present invention is to provide a rehabilitation training method, a rehabilitation training system, an electronic device, and a storage medium for solving the technical problems existing in the prior art in view of the above deficiencies in the prior art.

[0006] To achieve the above purpose, the technical solutions adopted in the embodiments of the present application are as follows:

[0007] In a first aspect, an embodiment of the present application provides a rehabilitation training method, which is applied to a rehabilitation training system. The rehabilitation training system includes: a brain-computer interface device and a rehabilitation robot. The brain-computer interface device is communicatively connected to the rehabilitation robot through a control interface in the rehabilitation robot. The method includes:

[0008] Collect the electroencephalogram signal of a target object;

[0009] Determine whether the electroencephalogram signal is an electroencephalogram signal indicating motor imagination according to the electroencephalogram signal of the target object and a pre-trained motor imagination detection model;

[0010] If so, generate a control signal and send the control signal to the rehabilitation robot through the control interface on the rehabilitation robot;

[0011] The rehabilitation robot drives the affected lower limb component in the rehabilitation robot to move according to the control signal, so as to perform rehabilitation training on the affected lower limb of the target object bound to the affected lower limb component.

[0012] Optionally, the rehabilitation robot driving the affected lower limb component in the rehabilitation robot to move according to the control signal includes:

[0013] The rehabilitation robot determines whether the rehabilitation training of the healthy lower limb component in the rehabilitation robot is over;

[0014] If so, the rehabilitation robot sends the control signal and the gait data of the healthy lower limb component to the affected lower limb component in the rehabilitation robot, and the affected lower limb component responds to the control signal and moves according to the gait data of the healthy lower limb component.

[0015] Optionally, the affected lower limb component responding to the control signal and moving according to the gait data of the healthy lower limb component includes:

[0016] The affected lower limb component responds to the control signal, reads the movement frequency and movement amplitude in the gait data of the healthy lower limb component, and moves according to the movement frequency and the movement amplitude.

[0017] Optionally, the rehabilitation robot driving the affected lower limb component in the rehabilitation robot to move according to the control signal includes:

[0018] The rehabilitation robot determines whether the rehabilitation training of the healthy lower limb component in the rehabilitation robot is over;

[0019] If so, the rehabilitation robot obtains the movement data of the healthy lower limb collected by the healthy lower limb component, determines the gait data of the affected lower limb component according to the movement data of the healthy lower limb; sends the control signal and the gait data of the affected lower limb component to the affected lower limb component in the rehabilitation robot, and the affected lower limb component responds to the control signal and moves according to the gait data of the affected lower limb component.

[0020] Optionally, the gait data of the affected lower limb component includes one or more of: walking step length, walking step height, walking step frequency, affected ankle joint angle value, affected knee joint angle value, affected hip joint angle value.

[0021] Optionally, determining whether the EEG signal is an EEG signal indicating motor imagery according to the EEG signal of the target object and a pre-trained motor imagery detection model includes:

[0022] Preprocess the EEG signal to obtain a processed EEG signal;

[0023] Extract the features of the processed EEG signal to obtain the feature information of the EEG signal;

[0024] Input the feature information of the EEG signal into the motor imagery detection model to obtain the output result of the motor imagery detection model, and the output result is used to indicate whether the EEG signal is an EEG signal indicating motor imagery.

[0025] Optionally, the motor imagery detection model includes: a support vector machine binary classification model, a decision tree model, and a neural network model.

[0026] Optionally, before inputting the feature information of the EEG signal into a pre-trained motor imagery detection model to determine whether the EEG signal is an EEG signal indicating motor imagery, it further includes:

[0027] Collect a plurality of sample data of the target object, each sample data including: an EEG signal of motor imagery or an EEG signal without motor imagery, and a classification label corresponding to the EEG signal, where the classification label is used to indicate whether the EEG signal is an EEG signal indicating motor imagery;

[0028] Train the motor imagery detection model based on each sample data.

[0029] In a second aspect, an embodiment of the present application further provides a rehabilitation training system, and the rehabilitation training system includes: a brain-computer interface device and a rehabilitation robot, and the brain-computer interface is communicatively connected to the rehabilitation robot through a control interface in the rehabilitation robot; the rehabilitation robot includes: a controller and a contralateral lower limb component;

[0030] The brain-computer interface device is used for:

[0031] Collect the EEG signal of the target object; determine whether the EEG signal is an EEG signal indicating motor imagery according to the EEG signal of the target object and a pre-trained motor imagery detection model; if so, generate a control signal and send the control signal to the rehabilitation robot through the control interface on the rehabilitation robot;

[0032] The controller in the rehabilitation robot is used for:

[0033] Drive the affected - side lower - limb component to move according to the control signal, so as to perform rehabilitation training on the affected - side lower limb of the target object bound to the affected - side lower - limb component.

[0034] Optionally, the rehabilitation robot further includes: a healthy - side lower - limb component;

[0035] The controller in the rehabilitation robot is further configured to:

[0036] Determine whether the rehabilitation training of the healthy - side lower - limb component is completed;

[0037] If so, send the control signal and the gait data of the healthy - side lower - limb component to the affected - side lower - limb component, and the affected - side lower - limb component responds to the control signal and moves according to the gait data of the healthy - side lower - limb component.

[0038] In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor, a storage medium, and a bus. The storage medium stores machine - readable instructions executable by the processor. When the electronic device runs, the processor communicates with the storage medium through the bus, and the processor executes the machine - readable instructions to perform the steps of the method provided in the first aspect.

[0039] In a fourth aspect, an embodiment of the present application further provides a computer - readable storage medium. A computer program is stored on the storage medium, and when the computer program is run by a processor, it performs the steps of the method provided in the first aspect.

[0040] The beneficial effects of the present application are:

[0041] An embodiment of the present application provides a rehabilitation training method, a rehabilitation training system, an electronic device, and a storage medium. It mainly collects the electroencephalogram (EEG) signals of the target object through a brain - computer interface device, and analyzes the movement intention of the target object from the EEG signals. When it is detected and recognized that the EEG signal of the target object is a movement intention, a control signal is generated and sent to the rehabilitation robot through the control interface in the rehabilitation robot. The rehabilitation robot drives the affected - side lower - limb component to drive the affected limb of the target object to perform active rehabilitation training according to the received control signal. That is, during the rehabilitation training of the target object, the active movement intention of the target object is fully utilized, thereby improving the rehabilitation training effect and effectively solving the problem in the prior art that the active movement intention of the patient is not fully utilized, resulting in poor rehabilitation effect and patient experience.

[0042] At the same time, by providing visual feedback to the patient, intelligent closed - loop rehabilitation is realized. After multiple intensive trainings, the purpose of reshaping motor neurons is achieved, accelerating the rehabilitation of motor function, and thus improving the rehabilitation training effect. Description of the Drawings

[0043] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0044] Figure 1 Schematic diagram of the architecture of a rehabilitation training system provided by an embodiment of the present application;

[0045] Figure 2 Schematic diagram of the structure of a brain-computer interface device provided by an embodiment of the present application;

[0046] Figure 3 Schematic diagram of the structure of the electroencephalogram acquisition unit in a brain-computer interface device provided by an embodiment of the present application;

[0047] Figure 4 Schematic diagram of the structure of an electronic device provided by an embodiment of the present application;

[0048] Figure 5 Schematic diagram of the process of another rehabilitation training method provided by an embodiment of the present application;

[0049] Figure 6 Schematic diagram of the process of yet another rehabilitation training method provided by an embodiment of the present application;

[0050] Figure 7 Schematic diagram of the process of another rehabilitation training method provided by an embodiment of the present application;

[0051] Figure 8 Schematic diagram of the process of yet another rehabilitation training method provided by an embodiment of the present application;

[0052] Figure 9 Schematic diagram of the four-layer discrete wavelet decomposition of electroencephalogram signals in a rehabilitation training method provided by an embodiment of the present application;

[0053] Figure 10 Schematic diagram of the process of yet another rehabilitation training method provided by an embodiment of the present application;

[0054] Figure 11 Schematic diagram of the overall process of the rehabilitation training method provided by an embodiment of the present application;

[0055] Figure 12 Schematic diagram of the structure of a rehabilitation training device provided by an embodiment of the present application.

[0056] Icons: 100 - Rehabilitation training system; 101 - Brain - computer interface device; 102 - Rehabilitation robot; 103 - Controller; 104 - Affected - side lower - limb component; 105 - Unaffected - side lower - limb component; 201 - EEG acquisition unit; 202 - EEG analysis unit. Detailed implementation manners

[0057] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It should be understood that the accompanying drawings in the present application are only for the purposes of illustration and description, and are not used to limit the protection scope of the present application. Additionally, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in the present application illustrate the operations implemented according to some embodiments of the present application. It should be understood that the operations in the flowchart may not be implemented in sequence, and steps without a logical context relationship may be reversed or implemented simultaneously. In addition, those skilled in the art, under the guidance of the content of the present application, may add one or more other operations to the flowchart or remove one or more operations from the flowchart.

[0058] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application usually described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application claimed, but only represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0059] It should be noted that the term "including" will be used in the embodiments of the present application to indicate the existence of the features stated thereafter, but does not exclude the addition of other features.

[0060] First, before elaborating on the technical solutions provided by the present application, a brief description of the structure of the brain - computer interface device provided by the present application will be given.

[0061] Figure 1 It is a schematic diagram of the architecture of a rehabilitation training system provided for an embodiment of the present application; the rehabilitation training system 100 includes: a brain - computer interface device 101 and a rehabilitation robot 102. Among them, the brain - computer interface device 101 is communicatively connected to the rehabilitation robot 102 through a control interface in the rehabilitation robot 102, and the rehabilitation robot 102 includes: a controller 103 and an affected - side lower - limb component 104.

[0062] Among them, the brain-computer interface device 101 is used to collect the electroencephalogram (EEG) signals of the target object, and determine whether the EEG signals are EEG signals indicating motor imagery according to the EEG signals of the target object and a pre-trained motor imagery detection model; if so, generate a control signal and send the control signal to the rehabilitation robot 102 through the control interface on the rehabilitation robot.

[0063] The rehabilitation robot 102 is used to drive the affected lower limb component to move according to the control signal, so as to perform rehabilitation training on the affected lower limb of the target object bound to the affected lower limb component. At the same time, visual feedback is given to the patient to achieve intelligent closed-loop rehabilitation. After multiple intensive trainings, the purpose of reshaping motor neurons is achieved, and the motor function rehabilitation is accelerated, thereby providing the rehabilitation training effect.

[0064] Optionally, the brain-computer interface device 101 can be a processing module integrated on the rehabilitation robot, or the brain-computer interface device 101 and the rehabilitation robot are two separate modules, that is, the brain-computer interface device can communicate with the rehabilitation robot through the control interface on the rehabilitation robot.

[0065] It can be understood that Figure 1 The structure described above is only for illustration, and the rehabilitation training system may further include more or fewer components than those shown Figure 1 or have a different configuration from that shown Figure 1 above. Figure 1 Each component shown above can be implemented by hardware, software, or a combination thereof.

[0066] Optionally, continuing to refer to Figure 1 shown, the rehabilitation robot further includes: a healthy lower limb component 105;

[0067] The controller in the rehabilitation robot is further used to:

[0068] Judge whether the rehabilitation training of the healthy lower limb component 105 is completed;

[0069] If so, send the control signal and the gait data of the healthy lower limb component 105 to the affected lower limb component 104, and the affected lower limb component 104 responds to the control signal and moves according to the gait data of the healthy lower limb component 105. In this way, the affected lower limb component can control the affected lower limb of the target object to perform rehabilitation mirror learning of the healthy side training according to the gait data of the healthy lower limb component, improving the training effect.

[0070] Refer to Figure 2 shown, the brain-computer interface device 101 includes: an EEG acquisition unit 201 and an EEG analysis unit 202, where the EEG acquisition unit 201 is communicatively connected to the EEG analysis unit 202.

[0071] The EEG acquisition unit 201 is used to acquire the EEG signals of the target object, amplify the EEG signals to obtain the amplified EEG signals, and transmit the amplified EEG signals to the EEG analysis unit 202; the EEG analysis unit 202 analyzes and processes the amplified EEG signals to determine whether the target object has performed motor imagery; if so, a control signal is generated and sent to the rehabilitation robot.

[0072] Among them, referring to Figure 3 As shown, the EEG acquisition unit 201 mainly consists of an EEG amplifier, acquisition electrodes, an EEG cap, and a power supply.

[0073] The EEG cap is a fixing device, mainly used to fully contact the acquisition electrodes with the scalp of the target object to acquire EEG signals with good signal quality.

[0074] Exemplarily, for example, the EEG amplifier can be an ADS1299 chip, the acquisition electrodes use 6-channel dry electrodes, and the placement of the electrodes follows the international 10-20 system, and their positions are C3, Cz, C4, FC3, FCz, FC4, that is, mainly near the motor imagery area of the target object's brain, and the EEG sampling frequency is 250Hz.

[0075] Continuing to refer to Figure 3 As shown, the power supply is electrically connected to the EEG amplifier and each acquisition electrode respectively, and is used to supply electrical energy to the EEG amplifier and the acquisition electrodes. Exemplarily, for example, the power supply can be a 6V dry battery.

[0076] Each acquisition electrode is communicatively connected to the EEG amplifier. The EEG signals of the target object can be acquired through each acquisition electrode, and the weak EEG signals acquired are transmitted to the EEG amplifier through wires. The EEG amplifier amplifies the EEG signals to obtain the amplified EEG signals, and then the amplified EEG signals are output to the Figure 2 EEG analysis unit 202 in

[0077] Referring to Figure 4 As shown, it is a schematic structural diagram of an electronic device. The electronic device can be the Figure 1 EEG analysis unit in the brain-computer interface device in Figure 4 or the controller in the rehabilitation robot, a processing device with data analysis function, so as to implement the processing method of the rehabilitation training plan provided by the present application. As

[0078] The processor 401 and the memory 402 are directly or indirectly electrically connected to realize data transmission or interaction. For example, electrical connection can be achieved through one or more communication buses or signal lines.

[0079] Among them, the processor 401 can be an integrated circuit chip with signal processing capabilities. The above-mentioned processor 401 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0080] The memory 402 can be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), an Electric Erasable Programmable Read-Only Memory (EEPROM), etc.

[0081] The memory 402 is used to store programs, and the processor 401 calls the programs stored in the memory 402 to execute the rehabilitation training method provided in the following embodiments.

[0082] The following will illustrate the rehabilitation training method provided in this application and the corresponding beneficial effects through multiple embodiments.

[0083] Figure 5 It is a schematic flowchart of a rehabilitation training method provided in an embodiment of this application. Optionally, the execution subject of this method can be Figure 1 the rehabilitation training system shown in

[0084] It should be understood that in other embodiments, the order of some steps of the rehabilitation training method can be interchanged according to actual needs, or some of the steps can also be omitted or deleted. As Figure 5 shown, this method includes:

[0085] S501. Collect the electroencephalogram signal of the target object.

[0086] Among them, the electroencephalogram signal of the target object is the electroencephalogram signal when the target object performs rehabilitation training.

[0087] S502. Determine whether the electroencephalogram signal is an electroencephalogram signal indicating motor imagery according to the electroencephalogram signal of the target object and the pre-trained motor imagery detection model.

[0088] In an implementable manner, for example, during the rehabilitation training phase of the target object, the target object needs to wear both the rehabilitation robot and the EEG acquisition unit in the brain-computer interface device. The EEG acquisition unit in the brain-computer interface device is used to collect the EEG signals of the target object in real time. Then, the EEG analysis unit in the brain-computer interface device performs preprocessing, segmentation, feature extraction, etc. on the EEG signals of the target object, and inputs the extracted EEG features into the pre-trained motor imagery detection model to detect the real-time EEG signal segments and determine whether the target object has performed motor imagery.

[0089] Optionally, the motor imagery detection model in this solution is trained based on the EEG signals of the patient himself, that is, different detection models are established for the EEG signals of different patients. Therefore, this motor imagery detection model has the characteristics of personalization and can improve the accuracy of the detection results.

[0090] S503. If so, generate a control signal and send the control signal to the rehabilitation robot through the control interface on the rehabilitation robot.

[0091] In this embodiment, for example, if it is detected that the target object has performed motor imagery, the EEG analysis unit in the brain-computer interface device generates a control signal and sends the control signal to the rehabilitation robot through the control interface on the rehabilitation robot to trigger the rehabilitation robot to drive the affected lower limb of the target object for rehabilitation training.

[0092] S504. The rehabilitation robot drives the affected lower limb component in the rehabilitation robot to move according to the control signal to perform rehabilitation training on the affected lower limb of the target object bound to the affected lower limb component.

[0093] In this embodiment, the rehabilitation robot drives the affected lower limb component to move according to the control signal sent by the brain-computer interface device to perform rehabilitation training on the affected lower limb of the target object bound to the affected lower limb component. That is, under the action of the control signal, the rehabilitation robot drives the affected lower limb component to drive the affected limb of the target object for active rehabilitation training, so that it can directly stimulate the sensorimotor cortex of the target object's brain, realize the remodeling and compensation of damaged motor nerves, and establish a closed-loop connection of central-movement-feedback to achieve intelligent closed-loop rehabilitation, and the rehabilitation effect is significantly better than traditional rehabilitation therapies. In this solution, during the rehabilitation training process of the target object, the active movement intention of the target object is fully utilized, thereby improving the rehabilitation training effect.

[0094] In summary, the embodiment of the present application provides a rehabilitation training method. In this solution, mainly, an electroencephalogram (EEG) signal of a target object is collected through a brain-computer interface device, and the movement intention of the target object is analyzed from the EEG signal. When it is detected and recognized that the EEG signal of the target object is a movement intention, a control signal is generated and sent to a rehabilitation robot via a control interface in the rehabilitation robot. According to the received control signal, the rehabilitation robot drives the affected lower limb component to drive the affected limb of the target object to perform active rehabilitation training. That is, during the rehabilitation training of the target object, the active movement intention of the target object is fully utilized, thereby improving the rehabilitation training effect and effectively solving the problem in the prior art that the active movement intention of the patient is not fully utilized, resulting in poor rehabilitation effect and patient experience.

[0095] Optionally, referring to Figure 6 as shown, the above step S504 includes:

[0096] S601. The rehabilitation robot determines whether the rehabilitation training of the healthy lower limb component in the rehabilitation robot has ended.

[0097] S602. If so, the rehabilitation robot sends the control signal and the gait data of the healthy lower limb component to the affected lower limb component in the rehabilitation robot, and the affected lower limb component responds to the control signal and moves according to the gait data of the healthy lower limb component.

[0098] In an implementable manner, for example, when performing rehabilitation training on the affected limb of the target object, mainly after the movement is completed on the healthy side, the control signal is sent to the affected lower limb component in real time and drives the affected side to perform mirror learning rehabilitation training.

[0099] Specifically, the rehabilitation robot determines whether the rehabilitation training of the healthy lower limb component has ended. If so, the rehabilitation robot sends the control signal and the gait data of the healthy lower limb component in the rehabilitation robot to the affected lower limb component in the rehabilitation robot to trigger the affected lower limb component to move according to the gait data of the healthy lower limb component. The training result is fed back to the brain through visual nerves to achieve active intelligent closed-loop rehabilitation; multiple reinforced closed-loop trainings are performed to achieve the purpose of reshaping motor neurons and accelerating the recovery of motor function.

[0100] Optionally, the above step S602 includes:

[0101] The affected lower limb component responds to the control signal, reads the movement frequency and movement amplitude in the gait data of the healthy lower limb component, and moves according to the movement frequency and movement amplitude.

[0102] In an achievable manner, for example, after sending a control signal to the affected lower limb component, the affected lower limb component is triggered to read the motion parameters in the gait data of the healthy lower limb component, such as the motion frequency and motion amplitude; then, the affected lower limb component moves according to the motion frequency and motion amplitude, achieving the purpose of rehabilitating the affected lower limb of the target object bound to the affected lower limb component. That is, during the process of the target object undergoing this rehabilitation training, the active motion intention of the target object is fully utilized, thereby improving the rehabilitation training effect.

[0103] Optionally, referring to Figure 7 as shown, the above step S504 includes:

[0104] S701. The rehabilitation robot determines whether the rehabilitation training of the healthy lower limb component in the rehabilitation robot has ended.

[0105] S702. If so, the rehabilitation robot acquires the motion data of the healthy lower limb collected by the healthy lower limb component, and determines the gait data of the affected lower limb component according to the motion data of the healthy lower limb; sends the control signal and the gait data of the affected lower limb component to the affected lower limb component, and the affected lower limb component responds to the control signal and moves according to the gait data of the affected lower limb component.

[0106] In another achievable manner, in order to achieve the user's autonomous gait control, after the healthy side completes the movement, the rehabilitation robot can also acquire the motion data of the healthy lower limb collected by the healthy lower limb component, such as the healthy ankle joint angle value, the healthy knee joint angle value, the healthy hip joint angle value, and the healthy sole pressure value; and calculates the gait data that is more suitable for the affected lower limb component according to the motion data of the healthy lower limb. Then, the control signal and the gait data of the affected lower limb component are sent to the affected lower limb component in the rehabilitation robot, and the affected lower limb component responds to the control signal and moves according to the gait data of the affected lower limb component. That is, a unique gait of the patient can be established through autonomous learning, enabling the affected limb to maintain a gait that conforms to the patient's own characteristics, such as walking speed, step height, step length, and ankle joint motion curve characteristics, etc., and can provide personalized physical rehabilitation training for the patient more comfortably, quickly, and safely.

[0107] Optionally, the gait data of the affected lower limb component includes one or more of the following: walking step length, walking step height, walking step frequency, affected ankle joint angle value, affected knee joint angle value, and affected hip joint angle value.

[0108] Optionally, referring to Figure 8 as shown, the above step S502 includes:

[0109] S801. Preprocess the electroencephalogram signal to obtain the preprocessed electroencephalogram signal.

[0110] Optionally, the preprocessing is mainly to remove the noise introduced during the EEG signal acquisition. The introduced noise mainly includes: electrooculogram (EOG) interference, electromyogram (EMG) interference, power frequency interference, and baseline drift, etc.

[0111] In this solution, a first non-recursive filter with a high-pass cut-off frequency of 5 Hz and a low-pass cut-off frequency of 30 Hz can be used to filter the EEG signal to obtain the EEG signal in the frequency band related to motor imagery; then, a second non-recursive filter with a cut-off frequency of 50 Hz is used to filter the EEG signal in the frequency band related to motor imagery to remove the power frequency interference and obtain the preprocessed EEG signal. In this way, it can be ensured that the preprocessed EEG signal is the EEG signal in the frequency band related to motor imagery and is free from low-frequency noise interference such as EOG, EMG, and power frequency, which is convenient for improving the accuracy of the subsequent EEG signal processing results.

[0112] S802. Extract the features of the processed EEG signal to obtain the feature information of the EEG signal.

[0113] In this embodiment, for example, discrete wavelet transform can be used to extract the features of the processed EEG signal. The obtained feature information of the EEG signal includes: the energies E(μ) and E(β) in the μ frequency band (8 - 13 Hz) and the β frequency band (14 - 28 Hz), and the effective mean value Aa.

[0114] Specifically, perform Mallat wavelet decomposition on the discretized signal X(n) as shown in the following formula (1):

[0115]

[0116] where L is the decomposition level, cAL is the low-frequency approximation component, and cDk are the high-frequency detail components at different scales. If the sampling frequency of the signal X(n) is fs, then the frequency ranges of cAL, cDL, cDL-1, …… cD1 are [0, fs / 2 L+1 , [fs / 2 L+1 , fs / 2 L , [fs / 2 L , fs / 2 L-1 , …… [fs / 2 2 , fs / 2].

[0117] As Figure 9 shown is the four-layer discrete wavelet decomposition Mallat of the EEG signal.

[0118] Since the sampling frequency is 250 Hz, according to the Nyquist sampling theorem, the frequency range of X(n) is 0 - 125 Hz. At the same time, in this solution, the μ band (8 - 13 Hz) and β band (14 - 28 Hz) related to motor imagery are selected as the main frequency bands for analysis. After 4 - layer discrete wavelet decomposition, the frequency bands are mainly located in D4 and D3. Then, D4 and D3 are used to reconstruct the EEG signal to obtain the reconstructed EEG signal. After that, feature extraction is performed on the reconstructed EEG signal. The extracted feature information includes: the energies E(μ) and E(β) of the μ band (8 - 13 Hz) and β band (14 - 28 Hz), and the effective mean Aa.

[0119] Among them, the calculation formulas for the energies E(μ), E(β) and the effective mean Aa are as follows:

[0120]

[0121]

[0122]

[0123] S803. Input the feature information of the EEG signal into the motor imagery detection model to obtain the output result of the motor imagery detection model.

[0124] Among them, the output result is used to indicate whether the EEG signal is an EEG signal indicating motor imagery.

[0125] In this embodiment, for example, the above - extracted feature information can be input into the motor imagery detection model to obtain whether the EEG signal is an EEG signal indicating motor imagery. If so, it can be determined that the EEG signal of the target object is an EEG signal with a motor intention; if not, it can be determined that the EEG signal of the target object is an EEG signal without a motor intention.

[0126] Optionally, the motor imagery detection model includes: a support vector machine (SVM) binary classification model. In this embodiment, the binary classification model used is the SVM binary classification model.

[0127] Among them, the core idea of SVM is to find an optimal decision hyperplane to maximize the distance between the two types of samples closest to the plane on both sides of the plane in the training set, that is, different classification models are established for the EEG signals of different patients. Therefore, this model has the characteristic of being personalized.

[0128] How to train the motor imagery detection model will be specifically explained through the following embodiments.

[0129] Optionally, as shown in Figure 10 Before the above - mentioned step S502, it further includes:

[0130] S1001. Collect multiple sample data of the target object.

[0131] Among them, each sample data includes: electroencephalogram (EEG) signals of motor imagery or EEG signals without motor imagery, and a classification label corresponding to the EEG signal, where the classification label is used to indicate whether the EEG signal is an EEG signal indicating motor imagery.

[0132] S1002. Train a motor imagery detection model based on each sample data.

[0133] It should be noted that during the training of the motor imagery detection model, the target object does not need to wear a rehabilitation robot, but only wears the EEG acquisition unit in the brain-computer interface device.

[0134] In this embodiment, for example, the target object sits in front of the screen and completes the motor imagery task according to the prompt. At the same time, the EEG acquisition unit collects the EEG signals of the target object when performing the motor imagery task multiple times, that is, multiple sample data are obtained; then, the EEG signals are preprocessed and segmented, etc., and the segmented EEG signals are marked according to the motor imagery task time, denoted as motor imagery and no motor imagery, that is, the classification labels corresponding to each sample data are obtained; then, the features related to motor imagery are extracted, and the feature information of each sample data and the label of each sample data are combined into a data set. The data set is divided into training set data and test set data according to 7:3. The initial SVM model for motor imagery binary classification is iteratively trained using the training set data, and the model after each round of training is verified using the test set data until the error rate of the finally trained model is less than the preset error, then the training is ended, and the SVM model for motor imagery binary classification obtained from the last training is used as the motor imagery detection model.

[0135] Optionally, as Figure 11 shown, it is a schematic diagram of the overall process of the rehabilitation training method provided by the embodiment of the present application; as Figure 11 shown, the method includes:

[0136] S1101. The brain-computer interface device collects the EEG signals of the target object.

[0137] S1102. The brain-computer interface device preprocesses the EEG signals to obtain the preprocessed EEG signals.

[0138] S1103. The brain-computer interface device extracts the features of the preprocessed EEG signals to obtain the feature information of the EEG signals.

[0139] S1104. The brain-computer interface device inputs the feature information of the EEG signals into the motor imagery detection model to obtain the output result of the motor imagery detection model.

[0140] S1105. If the output result is used to indicate that the EEG signal is an EEG signal indicating motor imagery, the brain-computer interface device generates a control signal.

[0141] S1106. Send the control signal to the rehabilitation robot through the control interface on the rehabilitation robot.

[0142] S1107. The rehabilitation robot determines whether the rehabilitation training of the healthy lower limb component in the rehabilitation robot is completed. If so, execute step S1108.

[0143] S1108. The rehabilitation robot sends the control signal and the gait data of the healthy lower limb component to the affected lower limb component. The affected lower limb component responds to the control signal and performs movements according to the gait data of the healthy lower limb component.

[0144] Optionally, the specific implementation steps and beneficial effects of this rehabilitation training method have been described in detail in the previous specific embodiments, and will not be repeated here.

[0145] The following describes the rehabilitation training device and the like used to execute this application. For its specific implementation process and technical effects, refer to the above, and will not be repeated below.

[0146] Figure 12 It is a schematic structural diagram of a rehabilitation training device provided by an embodiment of this application; it is applied to a rehabilitation training system, and the rehabilitation training system includes: a brain-computer interface device and a rehabilitation robot. The brain-computer interface device is communicatively connected to the rehabilitation robot through the control interface in the rehabilitation robot, as Figure 12 shown, the device includes:

[0147] An acquisition module 1201, configured to acquire the EEG signal of the target object;

[0148] A determination module 1202, configured to determine whether the EEG signal is an EEG signal indicating motor imagery according to the EEG signal of the target object and a pre-trained motor imagery detection model;

[0149] A generation module 1203, configured to generate a control signal if so;

[0150] A sending module 1204, configured to send the control signal to the rehabilitation robot through the control interface on the rehabilitation robot;

[0151] A driving module 1205, configured to drive the affected lower limb component in the rehabilitation robot to move according to the control signal, so as to perform rehabilitation training on the affected lower limb of the target object bound to the affected lower limb component.

[0152] Optionally, the driving module 1205 is configured to:

[0153] The rehabilitation robot determines whether the rehabilitation training of the healthy lower limb component in the rehabilitation robot has ended;

[0154] If so, the rehabilitation robot sends the control signal and the gait data of the healthy lower limb component to the affected lower limb component in the rehabilitation robot, and the affected lower limb component responds to the control signal and moves according to the gait data of the healthy lower limb component.

[0155] Optionally, the driving module 1205 is used for:

[0156] The affected lower limb component responds to the control signal, reads the movement frequency and movement amplitude in the gait data of the healthy lower limb component, and moves according to the movement frequency and movement amplitude.

[0157] Optionally, the driving module is further used for:

[0158] The rehabilitation robot determines whether the rehabilitation training of the healthy lower limb component in the rehabilitation robot has ended;

[0159] If so, the rehabilitation robot obtains the movement data of the healthy lower limb collected by the healthy lower limb component, and determines the gait data of the affected lower limb component according to the movement data of the healthy lower limb; sends the control signal and the gait data of the affected lower limb component to the affected lower limb component in the rehabilitation robot, and the affected lower limb component responds to the control signal and moves according to the gait data of the affected lower limb component.

[0160] Optionally, the gait data of the affected lower limb component includes one or more of: walking step length, walking step height, walking step frequency, affected ankle joint angle value, affected knee joint angle value, affected hip joint angle value.

[0161] Optionally, the determination module 1202 is used for:

[0162] Preprocess the electroencephalogram signal to obtain the processed electroencephalogram signal;

[0163] Extract the features of the processed electroencephalogram signal to obtain the feature information of the electroencephalogram signal;

[0164] Input the feature information of the electroencephalogram signal into the motor imagery detection model to obtain the output result of the motor imagery detection model, and the output result is used to indicate whether the electroencephalogram signal is an electroencephalogram signal indicating motor imagery.

[0165] Optionally, the motor imagery detection model includes: a support vector machine binary classification model, a decision tree model, and a neural network model.

[0166] Optionally, the acquisition module 1201 is further configured to acquire a plurality of sample data of the target object, where each sample data includes: electroencephalogram signals with motor imagery or without motor imagery, and a classification label corresponding to the electroencephalogram signal, where the classification label is used to indicate whether the electroencephalogram signal is an electroencephalogram signal indicating motor imagery;

[0167] The apparatus further includes:

[0168] A training module, configured to train a motor imagery detection model based on each sample data.

[0169] The above-mentioned apparatus is used to execute the method provided in the foregoing embodiment, and its implementation principle and technical effects are similar, and will not be elaborated here.

[0170] The above modules may be one or more integrated circuits configured to implement the above methods. For example: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), etc. Again, when the above certain module is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processors that can call program code. Again, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0171] Optionally, the present invention further provides a program product, such as a computer-readable storage medium, including a program that is used to execute the above method embodiment when executed by a processor.

[0172] In several embodiments provided by the present invention, it should be understood that the disclosed apparatus and method can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, and the indirect coupling or communication connection of the device or unit may be in electrical, mechanical or other forms.

[0173] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0174] In addition, each functional unit in various embodiments of the present invention may be integrated into a processing unit, may exist separately as individual physical units, or two or more units may be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0175] The above integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above software functional unit stored in a storage medium includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (English: processor) to execute some steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: USB flash drives, mobile hard disks, read-only memories (English: Read-Only Memory, abbreviated as: ROM), random access memories (English: Random Access Memory, abbreviated as: RAM), magnetic disks, or optical disks and other various media that can store program codes.

Claims

1. A rehabilitation training method, characterized in that, Applied to a rehabilitation training system, the rehabilitation training system includes: a brain-computer interface device and a rehabilitation robot. The brain-computer interface device is communicatively connected to the rehabilitation robot through a control interface in the rehabilitation robot. The method includes: Collecting the electroencephalogram (EEG) signals of a target object; Determining whether the EEG signals are EEG signals indicating motor imagery according to the EEG signals of the target object and a pre-trained motor imagery detection model; If so, generating a control signal and sending the control signal to the rehabilitation robot through the control interface on the rehabilitation robot; The rehabilitation robot drives the affected lower limb component in the rehabilitation robot to move according to the control signal, so as to perform rehabilitation training on the affected lower limb of the target object bound to the affected lower limb component.

2. The method according to claim 1, wherein The rehabilitation robot drives the affected lower limb component in the rehabilitation robot to move according to the control signal, including: The rehabilitation robot determines whether the rehabilitation training of the healthy lower limb component in the rehabilitation robot has ended; If so, the rehabilitation robot sends the control signal and the gait data of the healthy lower limb component to the affected lower limb component in the rehabilitation robot, and the affected lower limb component responds to the control signal and moves according to the gait data of the healthy lower limb component.

3. The method according to claim 2, wherein The affected lower limb component responds to the control signal and moves according to the gait data of the healthy lower limb component, including: The affected lower limb component responds to the control signal, reads the movement frequency and movement amplitude in the gait data of the healthy lower limb component, and moves according to the movement frequency and the movement amplitude.

4. The method according to claim 1, wherein The rehabilitation robot drives the affected lower limb component in the rehabilitation robot to move according to the control signal, including: The rehabilitation robot determines whether the rehabilitation training of the healthy lower limb component in the rehabilitation robot has ended; If so, the rehabilitation robot obtains the movement data of the healthy lower limb collected by the healthy lower limb component, and determines the gait data of the affected lower limb component according to the movement data of the healthy lower limb; sends the control signal and the gait data of the affected lower limb component to the affected lower limb component in the rehabilitation robot, and the affected lower limb component responds to the control signal and moves according to the gait data of the affected lower limb component.

5. The method according to claim 4, wherein The gait data of the affected lower limb component includes one or more of: walking step length, walking step height, walking step frequency, affected ankle joint angle value, affected knee joint angle value, affected hip joint angle value.

6. The method according to claim 1, wherein Determining whether the EEG signals are EEG signals indicating motor imagery according to the EEG signals of the target object and a pre-trained motor imagery detection model, including: Preprocessing the EEG signals to obtain processed EEG signals; Extracting the features of the processed EEG signals to obtain the feature information of the EEG signals; Input the characteristic information of the electroencephalogram (EEG) signal into the motor imagery detection model to obtain the output result of the motor imagery detection model, where the output result is used to indicate whether the EEG signal is an EEG signal indicating motor imagery.

7. The method according to claim 6, characterized in that, The motor imagery detection model includes: a support vector machine binary classification model, a decision tree model, and a neural network model.

8. The method according to claim 1, characterized in that, Before inputting the characteristic information of the EEG signal into a pre-trained motor imagery detection model to determine whether the EEG signal is an EEG signal indicating motor imagery, it further includes: Collect multiple sample data of the target object, each sample data including: an EEG signal of motor imagery or an EEG signal without motor imagery, and a classification label corresponding to the EEG signal, where the classification label is used to indicate whether the EEG signal is an EEG signal indicating motor imagery; Train the motor imagery detection model based on each sample data.

9. A rehabilitation training system, characterized in that, The rehabilitation training system includes: a brain-computer interface device and a rehabilitation robot, and the brain-computer interface is communicatively connected to the rehabilitation robot through a control interface in the rehabilitation robot; the rehabilitation robot includes: a controller and a affected lower limb component; The brain-computer interface device is used for: Collect the EEG signal of the target object; determine whether the EEG signal is an EEG signal indicating motor imagery according to the EEG signal of the target object and a pre-trained motor imagery detection model; if so, generate a control signal and send the control signal to the rehabilitation robot through the control interface on the rehabilitation robot; The controller in the rehabilitation robot is used for: Drive the affected lower limb component to move according to the control signal to perform rehabilitation training on the affected lower limb of the target object bound to the affected lower limb component.

10. The system according to claim 9, wherein, The rehabilitation robot further includes: a healthy lower limb component; The controller in the rehabilitation robot is further used for: Judge whether the rehabilitation training of the healthy lower limb component is completed; If so, send the control signal and the gait data of the healthy lower limb component to the affected lower limb component, and the affected lower limb component responds to the control signal and moves according to the gait data of the healthy lower limb component.

11. An electronic device, characterized in that, It includes: A processor, a storage medium, and a bus. The storage medium stores machine-readable instructions executable by the processor. When the electronic device runs, the processor communicates with the storage medium through the bus, and the processor executes the machine-readable instructions to execute the steps of the method according to any one of claims 1-8.

12. A computer-readable storage medium, characterized in that, A computer program is stored on the storage medium, and when the computer program is run by the processor, it executes the method according to any one of claims 1-8.

Images