Sports rehabilitation training method, electronic equipment and sports rehabilitation training system

Abstract

The embodiment of the present application provides a sports rehabilitation training method, electronic device and sports rehabilitation training system. The method includes: in the process of using a sports training device to perform rehabilitation training on the limbs of the training object, outputting the movement prompt information corresponding to the first training task of the sports training device in the current time period, so that the training object generates a movement intention according to the movement prompt information to actively follow the movement of the sports training device; obtaining the EEG activity information of multiple positions of the training object's brain in the current time period; according to the EEG activity information, determining the consistency information between the first movement intention of the training object in the current time period and the first training task and the consistency information between the first training task; according to the consistency information, determining the second training task of the sports training device in the next time period. The training effect of sports rehabilitation training can be significantly improved.

Description

Technical Field

[0001] The present application relates to the technical field of sports rehabilitation training, and in particular, to a sports rehabilitation training method, an electronic device and a sports rehabilitation training system. Background Art

[0002] The application of brain-computer interface (BCI) technology in the field of sports rehabilitation training technology mainly involves the following EEG paradigms: pure visual stimulation, steady-state visual evoked potential (SSVEP), and concentration assessment. The core of these paradigms is to control external sports training equipment through different EEG activity patterns.

[0003] However, the BCI-based motor rehabilitation training methods in the prior art have not really considered the relationship between the EEG paradigm and the training task. Therefore, the EEG paradigm they adopt is not suitable for rehabilitation training tasks, resulting in poor training results. Summary of the invention

[0004] In order to at least partially solve the problems existing in the prior art, according to a first aspect of the present application, a sports rehabilitation training method is output, comprising:

[0005] During the process of using the exercise training device to perform rehabilitation training on the limbs of the training subject, outputting exercise prompt information corresponding to the first training task of the exercise training device in the current period, so that the training subject generates exercise intention according to the exercise prompt information to actively follow the exercise training device to move;

[0006] Obtaining brain electrical activity information at multiple locations of the training subject's brain during a current period;

[0007] Determining consistency information between the first movement intention of the training subject in the current period and the first training task according to the EEG activity information;

[0008] determining a second training task of the sports training device in the next period according to the consistency information;

[0009] The consistency information includes: first information indicating that the first movement intention is consistent with the first training task, or second information indicating that the first movement intention is inconsistent with the first training task.

[0010] Exemplarily, determining the second training task of the sports training device in the next period according to the consistency information includes:

[0011] When the consistency information is the first information, determining that the motion difficulty of the second training task is greater than or equal to the difficulty of the first training task; and / or

[0012] When the consistency information is the second information, it is determined that the movement difficulty of the second training task is lower than the difficulty of the first training task.

[0013] Exemplarily, the training task is to drive the left and right limbs of the training subject to perform alternating left and right movements. According to the EEG activity information, the consistency information between the first movement intention of the training subject in the current period and the first training task is determined, including:

[0014] According to the EEG activity information, determine the changing pattern of the training subject's left and right limb movement intentions in the current period;

[0015] According to the changing law and the movement law of the left-right alternating movement, the consistency information between the first movement intention and the first training task is determined.

[0016] Exemplarily, determining the changing pattern of the left and right limb movement intentions of the training subject in the current period based on the EEG activity information includes:

[0017] According to the EEG activity information, fitting the frequency of periodic changes in the EEG activity difference between the left and right sides of the brain of the training subject in the current period;

[0018] According to the changing law and the movement law of the left-right alternating movement, the consistency information between the first movement intention and the first training task is determined, including:

[0019] calculating a frequency difference between the change frequency and a first movement frequency, wherein the first movement frequency is a movement frequency of the left-right alternating movement corresponding to the first training task;

[0020] When the frequency difference is less than or equal to the frequency difference threshold, determining the consistency information as the first information;

[0021] When the frequency difference is greater than the frequency difference threshold, the consistency information is determined to be the second information.

[0022] Exemplarily, the plurality of positions include a plurality of first positions located in the left brain region of the training subject and a plurality of second positions located in the right brain region of the training subject, the plurality of first positions correspond to the plurality of second positions one by one, and according to the EEG activity information, fitting the change frequency of the periodic change of the EEG activity difference between the left and right sides of the brain of the training subject in the current period, including:

[0023] Splitting the EEG activity information of each of the multiple locations into EEG activity information parts of multiple frequency bands;

[0024] According to the EEG activity information portion, calculating the energy difference between the EEG energy of each first position and the corresponding second position in each frequency band in each time window in the current period, and generating an energy difference time series corresponding to each first position;

[0025] The changing frequency is fitted according to a plurality of energy difference time series corresponding to a plurality of first positions.

[0026] Exemplarily, fitting the change frequency according to a plurality of energy difference time series corresponding to a plurality of first positions includes:

[0027] Combine multiple energy difference time series in parallel to obtain an energy difference data set, wherein the sum of elements in each row of the energy difference data set is equal to the product of the number of first positions and the number of frequency segments, and the sum of elements in each column of the energy difference data set is equal to the number of time windows in the current period;

[0028] Performing a correlation analysis on the energy difference data set and a pre-constructed sine and cosine dictionary of a first frequency range to determine the correlation between each frequency component in the first frequency range and the energy difference data set, wherein the first frequency range includes a plurality of frequency segments;

[0029] The change frequency is determined according to a first frequency component within the first frequency range, wherein the correlation between the first frequency component and the energy difference data set is not lower than other frequency components among the frequency components except the first frequency component.

[0030] Exemplarily, outputting the exercise prompt information corresponding to the first training task of the exercise training device in the current period includes:

[0031] Output first movement prompt information and / or second movement prompt information, wherein the first movement prompt information is a movement simulation animation consistent with the first training task, and the second movement prompt information includes prompt information of the limb currently mainly participating in the movement.

[0032] Exemplarily, the method further comprises:

[0033] According to the consistency information, corresponding motion feedback information is output, wherein different consistency information corresponds to different motion feedback information.

[0034] According to another aspect of the present application, a sports rehabilitation training device is also provided, comprising:

[0035] The first output module is used to output the motion prompt information corresponding to the first training task of the motion training device in the current period during the process of performing rehabilitation training on the limbs of the training subject using the motion training device, so that the training subject generates the motion intention according to the motion prompt information to actively follow the motion training device to move;

[0036] A first acquisition module is used to acquire EEG activity information of multiple locations of the brain of the training subject in a current period;

[0037] A first determination module is used to determine consistency information between the first movement intention of the training subject in the current period and the first training task according to the EEG activity information;

[0038] The second determination module is used to determine the second training task of the sports training device in the next time period according to the consistency information; wherein the consistency information includes: first information indicating that the first sports intention is consistent with the first training task, or second information indicating that the first sports intention is inconsistent with the first training task.

[0039] Exemplarily, the second determining module includes:

[0040] A first determination submodule is configured to determine, when the consistency information is the first information, that the movement difficulty of the second training task is greater than or equal to the difficulty of the first training task; and / or

[0041] The second determination submodule is configured to determine, when the consistency information is the second information, that the movement difficulty of the second training task is lower than the difficulty of the first training task.

[0042] Exemplarily, the training task is to drive the left and right limbs of the training subject to perform left-right alternating movements, and the first determination module includes:

[0043] The third determination submodule is used to determine the changing pattern of the training subject's left and right limb movement intentions in the current period according to the EEG activity information;

[0044] The fourth determination submodule is used to determine the consistency information between the first movement intention and the first training task according to the change law and the movement law of the left-right alternating movement.

[0045] Exemplarily, the third determining submodule includes:

[0046] A fitting unit, for fitting the periodic change frequency of the difference in the EEG activities of the left and right sides of the brain of the training subject in the current period according to the EEG activity information;

[0047] The fourth determination submodule includes:

[0048] A calculation unit, configured to calculate a frequency difference between the change frequency and a first movement frequency, wherein the first movement frequency is a movement frequency of the left-right alternating movement corresponding to the first training task;

[0049] A first information determining unit, configured to determine the consistency information as the first information when the frequency difference is less than or equal to a frequency difference threshold;

[0050] The second information determining unit is configured to determine that the consistency information is the second information when the frequency difference is greater than a frequency difference threshold.

[0051] Exemplarily, the plurality of positions include a plurality of first positions located in the left brain region of the training object and a plurality of second positions located in the right brain region of the training object, the plurality of first positions and the plurality of second positions correspond one to one, and the fitting unit includes:

[0052] A splitting subunit, used for splitting the EEG activity information of each of the multiple locations into EEG activity information parts of multiple frequency bands;

[0053] A calculation and generation subunit, for calculating, based on the EEG activity information portion, the energy difference between the EEG energy of each first position and the corresponding second position in each frequency band in each time window in the current period, and generating an energy difference time series corresponding to each first position;

[0054] The fitting subunit is used to fit the change frequency according to a plurality of energy difference time series corresponding to a plurality of first positions.

[0055] Exemplarily, the fitting subunit is also used to perform the following operations: combining multiple energy difference time series in parallel to obtain an energy difference data set, wherein the sum of elements in each row of the energy difference data set is equal to the product of the number of first positions and the number of frequency segments, and the sum of elements in each column of the energy difference data set is equal to the number of time windows in the current time period; performing correlation analysis on the energy difference data set and a pre-constructed sine and cosine dictionary of a first frequency range to determine the correlation between each frequency component within the first frequency range and the energy difference data set, wherein the first frequency range includes multiple frequency segments; determining the change frequency based on the first frequency component within the first frequency range, wherein the correlation between the first frequency component and the energy difference data set is not lower than other frequency components among the frequency components except the first frequency component.

[0056] Exemplarily, the first output module is also used to output first movement prompt information and / or second movement prompt information, wherein the first movement prompt information is a movement simulation animation consistent with the first training task, and the second movement prompt information includes prompt information of the limb currently mainly involved in the movement.

[0057] Exemplarily, the sports rehabilitation training control device of the embodiment of the present application further includes:

[0058] The second output module is used to output corresponding motion feedback information according to the consistency information, wherein different consistency information corresponds to different motion feedback information.

[0059] According to another aspect of the present application, an electronic device is also output, including a processor and a memory, wherein the memory stores computer program instructions, and the computer program instructions are used to execute the above-mentioned sports rehabilitation training method when the processor is running.

[0060] According to another aspect of the present application, a sports rehabilitation training system is also provided, comprising:

[0061] An EEG acquisition device is used to collect EEG signals from multiple locations of the training subject's brain to obtain EEG activity information;

[0062] A sports training device, used to run according to the training task in each period;

[0063] An output device, used to output the exercise prompt information corresponding to the training task in each period;

[0064] The motor rehabilitation training control device is respectively connected to the EEG acquisition device, the motor training device and the output device, and is used to execute the above-mentioned motor rehabilitation training method.

[0065] According to another aspect of the present application, a storage medium is also outputted, on which program instructions are stored, and the program instructions are used to execute the above-mentioned sports rehabilitation training method when running.

[0066] According to another aspect of the present application, a computer program product is also output, including computer program instructions, which are used to execute the above-mentioned sports rehabilitation training method when running.

[0067] The motor rehabilitation training method of the embodiment of the present application fully considers the importance of the association between the EEG paradigm and the rehabilitation training task. During the training process, the motor prompt information corresponding to the training task is output in time, which can effectively stimulate the training object to actively generate the motor intention related to the training task, enhance the active participation of the training object, and improve the pertinence and efficiency of the motor rehabilitation training. During the training process, according to the EEG activity information of the training object, the consistency information between the motor intention of the training object and the training task of the current period is accurately and timely determined, and then according to the consistency information, the training task of the motor training device in the next period is accurately determined. By matching the motor intention and the training task, the neuroplasticity of the brain can be supported, the repair of damaged neural pathways and the formation of new pathways can be promoted, and the recovery of the motor function of the training object can be promoted. By matching the training task with the motor intention of the training object, the training object can be trained within its ability, reduce the risk of injury, and improve the safety of rehabilitation training. When the motor intention of the training object is effectively identified and responded to, the rehabilitation effect can be improved, and the satisfaction and confidence of the training object in rehabilitation training can be increased, thereby improving the compliance of the training object to the rehabilitation process. On the basis of considering the consistency information between the training object's movement intention and the training task, the training task for the next period is determined according to the consistency information, which can provide the training object with a more personalized rehabilitation plan, ensure that the training content matches the training object's actual ability and rehabilitation goals, and thus significantly improve the efficiency and effect of rehabilitation training. The training task is consistent with the training object's movement intention, which can enhance the training object's active participation awareness, enable the training object to participate more actively in rehabilitation training, and achieve better training results. In general, this motor rehabilitation training method that combines EEG paradigm with motor rehabilitation training tasks can significantly improve the pertinence, safety, compliance and efficiency of motor rehabilitation training, and can also make timely, accurate and personalized adjustments according to the specific situation of the training object, thereby significantly improving the training effect of motor rehabilitation training.

[0068] A series of simplified concepts are introduced in the invention content, which will be further described in detail in the detailed description. The content of this application does not mean to attempt to define the key features and essential technical features of the technical solution claimed for protection, nor does it mean to attempt to determine the scope of protection of the technical solution claimed for protection.

[0069] The advantages and features of the present application are described in detail below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] The following drawings of the present application are used as part of the present application for understanding the present application. The drawings show the implementation methods of the present application and their descriptions, and are used to explain the principles of the present application. In the drawings,

[0071] Figure 1 A schematic flow chart showing a sports rehabilitation training method according to an embodiment of the present application;

[0072] Figure 2 A schematic diagram showing the structure of a sports training device according to an embodiment of the present application is shown;

[0073] Figure 3 A schematic diagram showing the position distribution of electrodes when the EEG acquisition device according to one embodiment of the present application is working;

[0074] Figure 4 A partial schematic diagram showing a picture in a motion simulation animation according to an embodiment of the present application;

[0075] Figure 5 A schematic flow chart showing a sports rehabilitation training method according to another embodiment of the present application;

[0076] Figure 6 A schematic diagram showing a test result of determining the consistency between a first movement intention and a first training task using a sports rehabilitation training method according to an embodiment of the present application;

[0077] Figure 7 A schematic block diagram showing a sports rehabilitation training control device according to an embodiment of the present application;

[0078] Figure 8 A schematic block diagram of an electronic device according to an embodiment of the present application is shown;

[0079] Fig. 9 A schematic block diagram of a sports rehabilitation training system according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0080] In the following description, a large amount of details are provided so that the present application can be thoroughly understood. However, it will be appreciated by those skilled in the art that the following description only exemplarily illustrates the preferred embodiments of the present application, and the present application can be implemented without one or more such details. In addition, in order to avoid confusion with the present application, some technical features well known in the art are not described in detail.

[0081] Brain-computer interface mainly realizes the establishment of communication and control channels between the human or animal brain and external devices. Usually, it is necessary to first collect brain signals through an EEG acquisition device; then pre-process the collected brain signals through an online computer system, extract features and identify them; then, convert the identified brain state or features into instructions that the computer system can understand; finally, transmit the instructions to the external device to achieve control.

[0082] The following is an explanation of several EEG paradigms in the application of BCI technology in the field of sports rehabilitation training technology. Motor Imagery (MI) is an active BCI system that requires the trainee to actively imagine the movement of the limbs to control external devices. For example, in rehabilitation training, the affected limb imagines limb movement, hoping to activate movement-related brain areas and promote neuroplasticity. However, this paradigm focuses on the individual's psychological simulation of movement, but does not represent his or her movement intention. Steady State Visual Evoked Potential (SSVEP) induces EEG signals of the corresponding frequency in the brain by presenting high-frequency flickering visual stimuli to the subjects. By analyzing and identifying these EEG signals, the target of the subject's visual gaze is identified, thereby controlling the corresponding task or external device. Event Related Potential (ERP), an ERP-related paradigm, can identify the brain's response to specific visual or auditory stimuli, and is mainly used to evaluate the attention level and reaction speed of the training subject during the rehabilitation process. A hybrid paradigm that combines motor imagery and steady-state visual evoked potentials can provide richer visual stimulation and instructions, such as imagining grasping movements combined with different flashing frequencies of pictures, to achieve computer control of more instructions.

[0083] In the prior art, some BCI-based motor rehabilitation training methods use EEG paradigms of pure visual motion stimulation such as Newton's rings. However, this paradigm can only solve the problem of triggering commands through visual brain-computer interfaces, and has little relevance to motor rehabilitation training. Some BCI-based motor rehabilitation training methods use the EEG paradigm of steady-state motion visual evoked potentials. However, the actual brain response area of ​​this scheme is located in the primary visual cortex of the occipital region, and the induced EEG components are only related to the visual changes of the motion image, and have nothing to do with whether the training subject understands and follows the motor movements of the rehabilitation training task. Moreover, since the primary visual cortex does not reflect high-level cognitive information, the training subject only needs to keep watching to trigger the operation of the rehabilitation equipment, which cannot reflect its active movement intention. Some BCI-based motor rehabilitation training methods mainly use the EEG paradigm of concentration assessment, but this paradigm can only distinguish whether the training subject is in a focused task state, and its focused task state may have nothing to do with the rehabilitation training task. For example, the training subject will still get a high concentration score when concentrating on thinking about other problems. Therefore, these programs do not really consider the relationship between EEG paradigms and rehabilitation training tasks, and these EEG paradigms are not suitable for rehabilitation training tasks, and these training methods often have little effect.

[0084] In order to at least partially solve the above-mentioned technical problems, according to one aspect of the present application, a kind of motor rehabilitation training method is provided. The motor rehabilitation training method of the embodiment of the present application first considers the importance of the association between the EEG paradigm and the rehabilitation training task, and further studies the EEG paradigm closely associated with the rehabilitation training task. Considering that the purpose of motor rehabilitation training is usually to help the training object gradually recover or improve active movement ability (rather than mechanical passive movement). Therefore, the motor rehabilitation training method of the embodiment of the present application, in the training process, timely outputs the motion prompt information corresponding to the training task, so as to help stimulate the training object to actively generate the movement intention related to the training task. And according to the EEG activity information of the training object, accurately determine the consistency information between the movement intention of the training object and the training task of the current period, and according to the consistency information, accurately determine the training task of the sports training device in the next period. This motor rehabilitation training method combining the EEG paradigm with the motor rehabilitation training task can significantly improve the pertinence, safety, compliance and efficiency of motor rehabilitation training, and can also be timely, accurately and individually adjusted according to the specific situation of the training object, so as to significantly improve the training effect of motor rehabilitation training.

[0085] Figure 1 FIG. 1 is a schematic flow chart of a sports rehabilitation training method 100 according to an embodiment of the present application. Figure 1 As shown, the method 100 includes the following steps.

[0086] Step S110, during the process of using the exercise training device to perform rehabilitation training on the limbs of the training subject, output the exercise prompt information corresponding to the first training task of the exercise training device in the current period, so that the training subject generates exercise intention according to the exercise prompt information to actively follow the exercise training device.

[0087] The exercise training device in the embodiment of the present application can be any suitable limb exercise training device, including but not limited to an upper limb exercise training device, a lower limb exercise training device, and an upper and lower limb exercise training device. Figure 2The exercise training device shown in the figure is an active and passive training device for upper and lower limbs, which can rotate the upper limb rocker arm or lower limb pedal under the control of the control system. It can assist training subjects with movement disorders to train their neuroplasticity and limb movement ability. For example, in the process of using the exercise training device to train the upper limbs, if the training subject's hand grasping ability is weak, the forearm can be placed in the forearm support, and when the upper limb turntable rotates, the left and right arms can passively complete circular motion under the support of the support. In this process, the left and right arms of the training subject are in a state of periodic left-right alternating motion. If the training subject's hand has a certain grasping ability, the rocker arm handle can be directly grasped, and during the rotation of the turntable, the rocker arm drives the arm to passively complete circular motion. That is, a repetitive passive motion similar to "left arm movement half circle - right arm movement half circle - left arm movement half circle" is completed. It can be understood that for normal people who actively complete this type of exercise, they need to control the left and right limbs to exert force alternately to make the turntable rotate continuously. In this case, it periodically pays attention to the movement of each side of the limb.

[0088] In an embodiment of the present application, during the rehabilitation training process, the motion prompt information corresponding to the current training task is also output in real time, so that the training subject generates movement intentions according to the motion prompt information to actively follow the movement of the motion training device. The motion prompt information can have any suitable form, including but not limited to audio, text, image, video, animation, etc. For example, the motion training device is provided with an output device, or the motion training device is connected to an output device. The output device can be a voice output device (such as a speaker, a built-in speaker), or a display device. For example, Figure 2 The sports training device shown in the figure includes an LCD screen and may also include a built-in speaker. During the training process of the training subject using the sports training device, the LCD screen can synchronously display the sports picture corresponding to the current training task. In one example, Figure 4 As shown, the motion picture can be a simulated animation of the current training task, which can be a simulated animation of the movement that the limbs of the training subject are currently participating in from the perspective of the training subject. Voice prompt information of the training task can also be given through the built-in speaker. For example, real-time prompts are given for the limb parts that need to be exerted (such as emitting a "left"-"right"-"left" movement rhythm prompt sound). Sports skills can also be prompted, such as how to exert force, the direction of force, etc. In this way, through the stimulation of the current training task at multiple sensory levels such as vision and hearing, the training subject can pay attention to the limb parts that should be paid attention to in real time and accurately, accurately understand the parts that need to be activated at the moment, stimulate the training subject to generate movement intentions corresponding to the training task, help activate and repair motor nerves, and prompt the training subject to actively follow the movement of the sports training device to improve the effect of rehabilitation training.

[0089] Step S120, obtaining EEG activity information of multiple locations of the training subject's brain in the current time period.

[0090] In an embodiment of the present application, during the training process, any suitable EEG acquisition device can be used to collect EEG signals at multiple locations of the brain of the training object at a certain acquisition frequency. The acquisition frequency can be set according to actual needs, such as 240Hz. The position of the EEG electrode can be set according to actual needs, and can be specifically determined according to the relationship between the training site and the EEG of the current training task. For example, the position of the electrode may include the precentral gyrus area, the bilateral superior temporal lobe area, the sensorimotor cortex, and the supplementary motor area located in the frontal lobe of the training object's brain. In one example, the electrode position can be set according to the International Clinical Neuroelectrophysiology League EEG electrode placement standard. In an example where the training task is upper and lower limb movement, the electrode position can be set to include C3, C4, T3, T4, F3, F4, F7, and F8 in the EEG 10-20 international standard lead system.

[0091] like Figure 3 As shown, the EEG signals of the 8 electrode positions in the figure can be collected during the training process. For example, P1 can correspond to F3 in the EEG 10-20 international standard lead system, P2 corresponds to C3 in the lead system, P3 corresponds to F7 in the lead system, P4 corresponds to T3 in the lead system, P5 corresponds to C4 in the lead system, P6 corresponds to F4 in the lead system, P7 corresponds to T4 in the lead system, and P8 corresponds to F8 in the lead system.

[0092] In the embodiment of the present application, the unit time length represented by the current time period can be set according to actual needs, such as 1 minute, 2 minutes, 5 minutes, 10 minutes, etc. Taking the unit time length as 2 minutes as an example, the EEG activity information of the current time period can be the EEG signal collected by the EEG collection device in the last 2 minutes.

[0093] Step S130, determining consistency information between the first movement intention of the training subject in the current period and the first training task according to the EEG activity information.

[0094] In an embodiment of the present application, the first movement intention is specifically the movement intention of the training subject determined by the EEG activity information (such as EEG signals) of the current time period. Movement intention refers to the internal psychological state of an individual before performing or preparing to perform a certain movement, which involves planning and decision-making for the upcoming movement. In this step, firstly, a variety of suitable methods can be used to decode the EEG signal to obtain a decoding result that can characterize the movement intention of the training subject. Then, the consistency information between the first movement intention and the first training task can be further determined based on the decoding result and the characteristics of the current training task.

[0095] Exemplarily, the process of decoding EEG signals may include: analyzing the EEG signals collected in the current period; extracting key features related to motor intentions based on the analysis results, such as activation patterns of different brain regions, changes in sensorimotor rhythms, energy values ​​of EEG signals, etc.; and then using a variety of suitable methods to determine the motor intentions of the training subject based on the characteristic values ​​of these key features. For example, the motor intentions of the training subject may be determined based on predefined rules, formulas, or logic. Alternatively, a machine learning method may be used to determine the motor intentions of the training subject (such as using a convolutional neural network to train a model to identify and classify different motor intentions). Specifically, in this step, the category of the motor intention may be qualitatively determined, or the intensity of the motor intention or the law of change over time may be quantitatively determined.

[0096] In the embodiment of the present application, the consistency information between the first movement intention and the first training task includes: first information indicating that the first movement intention is consistent with the first training task, or second information indicating that the first movement intention is inconsistent with the first training task. That is, when it is determined that the first movement intention is consistent with the first training task, the consistency information is the first information; when it is determined that the first movement intention is inconsistent with the first training task, the consistency information is the second information.

[0097] In some special examples, the second information can also be subdivided, for example, the second information can be subdivided according to the degree of inconsistency between the first movement intention and the first training task. For example, the second information is subdivided into third information, fourth information, and fifth information. The third information indicates that the degree of inconsistency between the first movement intention and the first training task is highly inconsistent; the fourth information indicates that the degree of inconsistency between the first movement intention and the first training task is moderately inconsistent; and the fifth information indicates that the degree of inconsistency between the first movement intention and the first training task is lowly inconsistent.

[0098] Specifically, a variety of suitable methods can be used to determine whether the first movement intention is consistent with the first training task. Specifically, it is to evaluate whether the movement information of the movement that may be triggered in the subjective movement consciousness of the training subject is consistent with the movement information of the movement corresponding to the current training task. The movement information may include movement categories, movement laws (such as the movement frequency of periodic movements), etc. For example, it can be determined whether the first movement intention is consistent with the first training task based on whether the change law of the first movement intention and the movement law of the movement corresponding to the first training task are consistent.

[0099] Step S140, determining the second training task of the exercise training device in the next period according to the consistency information, wherein the consistency information includes: first information indicating that the first exercise intention is consistent with the first training task, or second information indicating that the first exercise intention is inconsistent with the first training task.

[0100] It can be understood that, to a certain extent, the consistency between the training subject's movement intention and the current training task can represent the matching degree between the current training task and the training subject. Therefore, the training task for the next period can be determined based on the consistency information between the training subject's movement intention and the current training task, so that the training tasks for each period can match the actual situation of the training subject.

[0101] Exemplarily, when the first motion intention is consistent with the first training task, it can be determined that the second training task is the same as the first training task, or it can be determined that the difficulty of the second training task is higher than that of the first training task. For example, the motion speed or the motion frequency of the training subject can be increased by one gear by increasing the operating power of the motion training device. Exemplarily, when the first motion intention is inconsistent with the first training task, it can be determined that the difficulty of the second training task is lower than that of the first training task. For example, by reducing the operating power of the motion training device, the motion speed or the motion frequency is reduced by one or more gears. In the above-mentioned example of subdividing the second information, different gears can be reduced for different second information. Exemplarily, before adjusting the gear, a prompt message that the motion gear is about to be adjusted can be output.

[0102] In the embodiment of the present application, after determining the second training task for the next period, the exercise training device can be controlled according to the control logic corresponding to the second training task, for example, reducing, maintaining or increasing the operating power, maintaining or changing the exercise mode, etc. In this way, the training task of the training subject in each period can be matched with his or her actual situation.

[0103] The motor rehabilitation training method of the embodiment of the present application fully considers the importance of the association between the EEG paradigm and the rehabilitation training task. During the training process, the timely output of the motion prompt information corresponding to the training task can effectively stimulate the training object to actively generate the motor intention related to the training task, enhance the active participation of the training object, and improve the pertinence and efficiency of the motor rehabilitation training. During the training process, according to the EEG activity information of the training object, the consistency information between the training object's motor intention and the training task of the current period is accurately and timely determined, and then according to the consistency information, the training task of the sports training device in the next period is accurately determined. By matching the motor intention and the training task, the neuroplasticity of the brain can be supported, the repair of damaged neural pathways and the formation of new pathways can be promoted, and the recovery of the motor function of the training object can be promoted. By matching the training task with the motor intention of the training object, the training object can be prevented from training beyond its ability, reducing the risk of injury and improving the safety of rehabilitation training. When the motor intention of the training object is effectively identified and responded to, the rehabilitation effect can be improved, the satisfaction and confidence of the training object in rehabilitation training can be increased, thereby improving the compliance of the training object to the rehabilitation process. On the basis of considering the consistency information between the training object's movement intention and the training task, the training task for the next period is determined according to the consistency information, which can provide the training object with a more personalized rehabilitation plan, ensure that the training content matches the training object's actual ability and rehabilitation goals, and thus significantly improve the efficiency and effect of rehabilitation training. The training task is consistent with the training object's movement intention, which can enhance the training object's active participation awareness, enable the training object to participate more actively in rehabilitation training, and achieve better training results. In general, this motor rehabilitation training method that combines EEG paradigm with motor rehabilitation training tasks can significantly improve the pertinence, safety, compliance and efficiency of motor rehabilitation training, and can also make timely, accurate and personalized adjustments according to the specific situation of the training object, thereby significantly improving the training effect of motor rehabilitation training.

[0104] Exemplarily, step S140 determines the second training task of the sports training device in the next time period according to the consistency information, including step S141 and / or step S142.

[0105] Step S141: when the consistency information is the first information, determining that the exercise difficulty of the second training task is greater than or equal to the difficulty of the first training task.

[0106] It can be understood that when the training subject's movement intention is consistent with the current training task, it often means that the training subject is capable of and actively follows the rehabilitation training movements under the current training task. In this case, the training difficulty can be gradually increased until the training difficulty that matches the training subject is reached. Figure 2At a certain moment when the exercise training device shown in the figure performs upper limb training on a training subject, the speed of the upper limb rotating disk is, for example, 1 revolution per second. If the EEG signal within 5 minutes determines that the training subject's exercise intention is consistent with the current training task, the speed of the upper limb rotating disk can be increased to 2 revolutions per second within the next 5 minutes. In this way, the difficulty of the training task can be gradually increased until the difficulty is consistent with the training subject's exercise intention. Figure 1 The maximum rotation speed is the same as the training object, which means that the training can be carried out stably according to the training task that best matches the training object.

[0107] In this way, their abilities can be improved through positive feedback, and can be used to evaluate their neurological rehabilitation, making it easier to formulate more reasonable rehabilitation training plans and improve rehabilitation effects.

[0108] Step S142: when the consistency information is the second information, determining that the exercise difficulty of the second training task is lower than the difficulty of the first training task.

[0109] It is understandable that when the training subject's exercise intention is inconsistent with the current training task, it means to a certain extent that the training subject is less motivated to follow the rehabilitation training under the current training task and may not be able to keep up with the current training task. In this case, the difficulty of training can be gradually reduced. For example, when using Figure 2 At a certain moment when the sports training device shown in the figure is performing upper limb training on the training object, the rotation speed of the upper limb turntable is, for example, 3 turns / second. If the EEG signals within 5 minutes determine that the training object's movement intention is inconsistent with the current training task, the rotation speed of the upper limb turntable can be reduced to 2 turns / second within the next 5 minutes.

[0110] In this way, the adaptability, safety, and effectiveness of rehabilitation training can be improved, while reducing the stress and frustration of the training subjects, thereby promoting a more effective rehabilitation process.

[0111] For example, the training task is to drive the left and right limbs of the training subject to perform alternating left and right movements. Figure 2 The upper limb training device shown in the figure drives the left arm and right arm of the training object to perform alternating circular motions, or the lower limb training drives the left leg and right leg of the training object to perform alternating circular motions. In this case, the training prompt information can make the training object pay attention to the left limb and the right limb alternately.

[0112] It can be understood that, since the motor cortex of the brain has cross-control over body movement, the left cerebral hemisphere controls the sensation and movement of the right side of the face and limbs, while the right cerebral hemisphere controls the sensation and movement of the left side of the face and limbs. Therefore, when the training subject focuses on the movement of one side of the limbs, the active area of ​​the brain is mainly concentrated in the opposite cerebral hemisphere. For example, when the training subject focuses on the movement of the left leg, the EEG activity of the right side of the brain is more active. Therefore, the consistency information between the first movement intention and the first training task of the training subject in the current period can be determined by analyzing the EEG activity information of different brain areas of the training subject during the left-right alternating movement under the stimulation of the training prompt information synchronized with the left-right alternating movement.

[0113] Step S130 determines the consistency information between the first movement intention of the training subject in the current period and the first training task according to the EEG activity information, including step S131 and step S132.

[0114] Step S131, determining the changing pattern of the training subject's left and right limb movement intentions in the current time period based on the EEG activity information.

[0115] Step S132, determining consistency information between the first movement intention and the first training task according to the change law and the movement law of the left-right alternating movement.

[0116] Exemplarily, the changing rules of the left and right limb movement intentions may specifically include at least one of the following: the changing rules of the training subject's attention to the left limb movement over time, the changing rules of the training subject's attention to the right limb movement over time, and the changing rules of the difference between the training subject's attention to the left limb movement and the right limb movement over time. Exemplarily, the changing rules may include the frequency, period, amplitude, etc. of the periodic change.

[0117] A variety of suitable methods can be used to process the EEG activity information of the current period to determine the changing pattern of the training subject's intention to move the left and right limbs in the current period. For example, the EEG signals collected by the electrodes located in the right brain area can be analyzed for time changes, and the changing pattern of the training subject's attention to the movement of the left limb over time can be obtained as the changing pattern of the intention to move the left and right limbs. For another example, the difference between the EEG signals of the electrodes located in the right brain area and the contralateral electrodes at the same time can be analyzed for time changes, and the changing pattern of the difference in the training subject's attention to the movement of the left and right limbs over time can be obtained as the changing pattern of the intention to move the left and right limbs.

[0118] It can be understood that when the training subject actively participates in the current movement and is able to follow the current movement, the change law of its attention to limb movement is usually highly consistent with the movement law of the actual passive movement; on the contrary, if the training subject does not actively participate in the current movement or is unable to follow the current movement, the consistency between the change law of its attention to limb movement and the movement law of the actual passive movement is low. Therefore, the determined change law can be compared with the movement law of the left-right alternating movement corresponding to the current training task. If the comparison result of the two meets the consistency requirement, it can be determined that the movement intention of the current period is consistent with the training task of the current period. Otherwise, it can be determined that the movement intention of the current period is inconsistent with the training task of the current period.

[0119] In this scheme, combined with the changes in the training subjects' attention to limb parts during the left-right alternating movement, the consistency problem of movement intention and training task is creatively transformed into judging the consistency between the changing rules of the training subjects' left-right limb movement intentions in the current period and the movement rules of the left-right alternating movement corresponding to the current training task. This can quickly and accurately determine the consistency information between the first movement intention and the first training task, which in turn helps to timely and accurately adjust the training tasks and improve the safety and rehabilitation effect of rehabilitation training.

[0120] Exemplarily, step S131 determines the changing pattern of the training subject's left and right limb movement intentions in the current time period based on the EEG activity information, including: step S1311, fitting the frequency of change of the periodic change of the EEG activity difference between the left and right sides of the training subject's brain in the current time period based on the EEG activity information.

[0121] In this step, a variety of suitable methods can be used to fit the frequency of change of the difference in EEG activity between the left and right sides of the brain of the training object in the current period. In one example, the linear or nonlinear change law of the difference in EEG signals between the electrodes corresponding to the left and right brain regions of the training object in the current period can be used to extract its periodic characteristics, and then the frequency of change of EEG activity can be fitted based on the extracted periodic characteristics using a mathematical model (such as Fourier transform, autoregressive model, etc.). In another example, the EEG signals of the contralateral electrodes of the left and right brains of the training object can be analyzed, and the energy difference between the contralateral electrodes of the left and right brains of the training object in the unit time window can be calculated to obtain an energy deviation time series, and the energy deviation time series can be subjected to a canonical correlation analysis with the sine and cosine dictionary H to obtain the frequency component with the largest correlation as the fitting change frequency; in another example, the machine learning method can also be used to fit the frequency of change of the difference in EEG activity between the left and right sides of the brain of the training object in the current period.

[0122] In an embodiment of the present application, step S132 determines the consistency information between the first movement intention and the first training task according to the change law and the movement law of the left-right alternating movement, and may include the following steps: step S1321, calculating the frequency difference between the change frequency and the first movement frequency, wherein the first movement frequency is the movement frequency of the left-right alternating movement corresponding to the first training task; step S1322, when the frequency difference is less than or equal to the frequency difference threshold, determining that the consistency information is the first information; step S1323, when the frequency difference is greater than the frequency difference threshold, determining that the consistency information is the second information.

[0123] In an embodiment of the present application, the frequency difference threshold can be set according to actual needs. For example, it can be determined according to the size of the movement frequency of the left and right alternating movement corresponding to the current training task. The frequency difference threshold can be less than or equal to 30% of the current movement frequency. For example, if the current movement frequency is 2Hz, the frequency difference threshold can be 0.5Hz. For example, when the frequency difference between the fitted change frequency and the first movement frequency is 1Hz, it can be determined that the first movement intention is inconsistent with the first training task, and the movement frequency in the training task of the next period can be reduced by one level.

[0124] In the above scheme, the frequency of the periodic change of the difference in the EEG activity between the left and right sides of the brain of the training subject in the current period is accurately fitted based on the EEG activity information of the current period, and then the consistency information between the first movement intention and the first training task is determined based on the difference between the fitted change frequency and the movement frequency of the left and right alternating movements in the current training task. This scheme can improve the accuracy and efficiency of identifying the consistency between the movement intention and the current training task, enhance the personalization and real-time nature of the training, and thus further improve the rehabilitation training effect.

[0125] Exemplarily, the plurality of positions include a plurality of first positions located in the left brain region of the training subject and a plurality of second positions located in the right brain region of the training subject, and the plurality of first positions and the plurality of second positions correspond to each other one by one. For example, the first positions and the corresponding second positions are symmetrical about the center line of the brain. Exemplarily, with reference to Figure 3 , at least part of the electrode positions of the EEG acquisition device can be located in the bilateral superior temporal lobe area of ​​the training subject, which may include 4 first positions (P1, P2, P3, P4) located in the left superior temporal lobe of the training subject and 4 second positions (P5, P6, P7, P8) located in the right superior temporal lobe of the training subject. Among them, the electrode at the P1 position corresponds to the electrode at the P6 position, and the two electrodes form an electrode pair. Similarly, the electrode at the P2 position corresponds to the electrode at the P5 position, the electrode at the P3 position corresponds to the electrode at the P8 position, and the electrode at the P4 position corresponds to the electrode at the P7 position. The electrodes at these 8 positions form 4 electrode pairs.

[0126] It can be understood that during the training process, the training subjects pay attention to the left and right limbs in turn according to the action prompts in the training task, which will produce differences in the contralateral spatial attention components in the EEG signals of the bilateral superior temporal lobes. Therefore, for each electrode pair, the difference characteristics of the spatial attention components can be extracted and their change frequency can be fitted.

[0127] Step S1311 fits the frequency of periodic changes in the difference in EEG activities between the left and right sides of the brain of the training subject in the current period according to the EEG activity information, including the following steps S1311.1 to S1311.3.

[0128] Step S1311.1, splitting the EEG activity information of each of the multiple locations into EEG activity information parts of multiple frequency bands.

[0129] The number of frequency bands can be set according to actual needs, for example, 2, 3, 4, 5, etc. In one example, each EEG signal can be decomposed into components using a bandpass filter group of 1-4 Hz, 4-7 Hz, 8-12 Hz, and 13-20 Hz, that is, each EEG signal collected by each electrode can be decomposed into EEG signal components of 4 frequency bands.

[0130] Step S1311.2, based on the EEG activity information, calculate the energy difference between the EEG energy of each first position and the corresponding second position in each frequency band in each time window in the current time period, and generate an energy difference time series corresponding to each first position.

[0131] In an embodiment of the present application, the time length of the time window is less than the time length of the current time period. It can be specifically set according to the acquisition frequency of the EEG acquisition device and the computing power of the processor. The time length of the current time period is, for example, 5 minutes, and the time length of the time window is, for example, 0.5 seconds. The sliding time window method can be used to count the changes in EEG activity. The sliding step size can be set according to actual needs. Specifically, a 0.5-second time window can be used to slide on the EEG signal component curve of each frequency channel of each electrode position within 5 minutes, and the EEG energy in the window is calculated each time it slides (specifically, it can be the power of the EEG signal component within 0.5 seconds). Then, the difference in EEG energy in each frequency segment of each electrode pair (contralateral electrodes of the left and right brain) in each time window can be calculated. For example, it can be calculated Figure 3The difference between the 1-4Hz EEG energy of the electrode at the P1 position in the first time window and the 1-4Hz EEG energy of the electrode at the P6 position in the first time window, continue sliding the time window, and calculate the difference between the 1-4Hz EEG energy of the two electrodes in the next time window, and so on, the difference between the 1-4Hz EEG energy of the electrode at the P1 position and the electrode at the P6 position in each time window in the current period can be obtained. These differences can constitute a channel (1-4Hz) part of the energy difference time series corresponding to the electrode position P1. Similarly, the other three channels (4-7Hz, 8-12Hz, 13-20Hz) of the energy difference time series corresponding to the electrode position P1 can be obtained. That is, the energy difference time series Y1 corresponding to the electrode position P1 is obtained. And the energy difference time series Y2 corresponding to the electrode position P2, the energy difference time series Y3 corresponding to the electrode position P3 and the energy difference time series Y4 corresponding to the electrode position P4 can be calculated.

[0132] Step S1311.3, fitting the change frequency according to multiple energy difference time series corresponding to multiple first positions.

[0133] In the embodiments of the present application, a variety of suitable analysis methods can be used to perform statistical analysis on these energy difference time series, and the change frequency can be fitted according to the analysis results.

[0134] In one example, step S1311.3 fits the change frequency according to multiple energy difference time series corresponding to multiple first positions, and may include the following steps: step S1311.3a, combining multiple energy difference time series in parallel to obtain an energy difference data set, wherein the sum of elements in each row of the energy difference data set is equal to the product of the number of first positions and the number of frequency segments, and the sum of elements in each column of the energy difference data set is equal to the number of time windows in the current time period; step S1311.3b, performing correlation analysis on the energy difference data set and a pre-constructed sine and cosine dictionary of a first frequency range to determine the correlation between each frequency component in the first frequency range and the energy difference data set, wherein the first frequency range includes multiple frequency segments; step S1311.3c, determining the change frequency according to the first frequency component in the first frequency range, wherein the correlation between the first frequency component and the energy difference data set is not lower than other frequency components among the frequency components except the first frequency component.

[0135] For example, the energy difference time series Y1 corresponding to the electrode position P1, the energy difference time series Y2 corresponding to the electrode position P2, the energy difference time series Y3 corresponding to the electrode position P3, and the energy difference time series Y4 corresponding to the electrode position P4 can be combined in parallel into a multivariate data set as an energy difference data set. Each row of the energy difference data set corresponds to a time window, and the elements of each row include the difference in EEG energy of different frequency bands of the four electrode pairs in the corresponding time window; each column corresponds to an electrode pair or a first position, and the elements of each column include the difference in EEG energy of the corresponding electrode pair in a certain frequency band in different time windows. The first frequency range is, for example, 1 to 20 Hz. The energy difference data set can be subjected to a canonical correlation analysis with the sine-cosine dictionary H of 1 to 20 Hz to find the frequency component with the largest proportion, which is used as the frequency of change in which the difference in EEG activity between the left and right sides of the brain of the training object in the current period changes periodically.

[0136] In another example, Fourier transform can be performed on each energy difference time series to convert it from the time domain to the frequency domain. The common frequency component of the difference in brain electrical activity between the left and right sides of each electrode pair is extracted based on the Fourier transform result.

[0137] The above scheme can quickly and accurately fit the frequency of periodic changes in the difference in EEG activity between the left and right sides of the brain of the training subject in the current period. The EEG features are more effective and more widely applicable to the population, and the periodic characteristics of the prominent features are more conducive to EEG decoding and classification. This EEG decoding algorithm only focuses on the consistency of attention switching frequency and motor task frequency, avoids complex training processes, and has strong adaptability. In addition, this EEG decoding scheme has a small amount of calculation, can save computing resources and has higher calculation accuracy, which improves the real-time and accuracy of training task adjustment, and further improves the rehabilitation training effect.

[0138] Exemplarily, step S110 outputs the motion prompt information corresponding to the first training task of the sports training device in the current time period, including: step S111, outputting the first motion prompt information and / or the second motion prompt information, wherein the first motion prompt information is a motion simulation animation consistent with the first training task, and the second motion prompt information includes prompt information of the limb currently mainly involved in the motion.

[0139] For example, the sports training device is connected to or provided with a display screen, which can control the display screen to display in real time a first-person perspective action picture (sports simulation animation) consistent with the training content. And prompt information of limb movements that need attention can be given in real time. Figure 2 and Figure 4 , in the training object using Figure 2During the training of the upper limb trainer in the sports training device shown in the figure, the display screen can display a simulated dynamic picture of a hand-cranked generator. For example, when performing lower limb training, a motion simulation animation of a pedal generator can be displayed. During training, the limbs that currently need to be paid attention to (the limbs that mainly participate in the movement) can be displayed in real time in a highlighted manner in the picture. For example, the limb area that needs attention is highlighted or flashed, so that the user can more intuitively understand the limb that should be paid attention to at present, thereby accurately and efficiently stimulating the user to actively follow the rhythmic movement of the sports training device. This visual motion paradigm is more friendly, reduces visual discomfort, and the display picture is more in line with the sports scene, so that the training subject can focus on the training task and improve the training efficiency.

[0140] Exemplarily, the sports rehabilitation training method of the embodiment of the present application further includes: step S150, outputting corresponding sports feedback information according to the consistency information, wherein different consistency information corresponds to different sports feedback information.

[0141] In the embodiment of the present application, during rehabilitation training, the training subject can also be promptly prompted whether the current movement attention meets the training requirements. Figure 4 As shown in the figure, when the training subject's exercise intention is consistent with the training task, the container element just above the center of the screen can show that power is being poured in to encourage the training subject to continue to maintain the state and actively increase the speed in the next training task. When the exercise intention is inconsistent with the training task, the container element may not give feedback on the power being poured in. Alternatively, a prompt message such as "Failed to charge successfully, keep trying" can be popped up on the screen to prompt the training subject to adjust the state and concentrate on training.

[0142] This approach not only makes training more interactive and interesting by providing immediate visual feedback, but also helps improve training effectiveness and enhance the self-awareness and participation of the trainees.

[0143] Combine the following Figure 5 The specific implementation process of the sports rehabilitation training method of another embodiment of the present application is described. For example, the upper and lower limb active and passive training devices can be used to train the training object. Taking upper limb training as an example, during the training process, the upper limb training device drives the left arm and right arm of the training object to perform circular motions alternately. The training object can wear a computer power collection device, and the 8 electrodes in the computer power collection device can be respectively Figure 3The electrode position diagram shown in is set. During the training process, the rehabilitation training control device can control the LCD screen connected to the active and passive training devices to display the action picture of the first perspective consistent with the training content. For example, the display screen can display the simulated dynamic picture of the hand-cranked generator, and can display the limbs that currently need attention in real time in a highlighted manner. In this way, the training subject can be effectively reminded to alternately pay attention to the left and right arms according to the movement rhythm of the current training task, and generate movement intentions. In addition, during the training process, the 8 electrodes in the computer electricity acquisition device continuously collect the EEG signals of the training subject's brain.

[0144] The rehabilitation training control device can obtain EEG signals and perform EEG decoding to evaluate whether the frequency of the periodic changes in the EEG activity difference between the left and right sides of the training subject's brain is consistent with the frequency of the left and right alternating movements corresponding to the current training task, and obtain consistency information. The running rhythm of the active and passive training device can be controlled according to the consistency information, and the display screen can be controlled to display the corresponding visual feedback information.

[0145] Exemplarily, for each EEG signal collected by each electrode, a bandpass filter group of 1-4Hz, 4-7Hz, 8-12Hz, and 13-20Hz can be used to decompose the EEG signal into components. And a time window of 0.5 seconds can be used to slide and calculate the energy of each channel for each group of EEG components, and the energy difference between the electrodes on the opposite sides of the left and right brains can be calculated to obtain energy deviation time series Y1, Y2, Y3, and Y4, each of which contains 4 channels. Then, Y1, Y2, Y3, and Y4 can be connected in parallel, and canonical correlation analysis can be performed with the sine and cosine dictionary H of 1 to 20Hz to find the frequency component with the largest proportion, which is used as the frequency F of the periodic change of the difference in EEG activity between the left and right sides of the brain of the training object. If the absolute value of the difference between F and the current training movement frequency X is less than or equal to 0.5Hz, it can be considered that the training object is concentrating on the current training task, and it can be determined that the training object's movement intention is consistent with the current training task. Therefore, the movement frequency of the alternating movement of the upper limbs can be increased in the training task of the next period. On the contrary, if the absolute value of the difference between F and X is greater than 0.5 Hz, it can be determined that the training subject's movement intention is inconsistent with the current training task, and the movement frequency of the upper limb alternating movement can be reduced in the next training task.

[0146] The motor rehabilitation training method in the above scheme has a friendly visual experience and a high execution success rate. In addition, a new brain-computer interaction paradigm in which EEG features are highly correlated with rehabilitation movement status is used to evaluate the consistency between the training subject's motor intention and rehabilitation training movements. This can ensure that the training subject's motor intention is always consistent with the training task during the overall rehabilitation training, and can effectively assist training subjects with movement disorders to train their neural plasticity and limb movement ability, thereby significantly improving the rehabilitation training effect.

[0147] In addition, if Figure 6 As shown, the embodiment of the present application also tests and verifies the EEG decoding method used in the above-mentioned sports rehabilitation training method. Specifically, training tests were conducted on 12 volunteers who participated in the experiment. All volunteers had normal vision / corrected vision and normal limb function. The volunteers participated in the test according to the above process. Each test lasted for 10 minutes. EEG decoding was performed every 5 seconds, and a consistency comparison between the movement intention and the actual training task of the equipment was performed. The experiment requires that the volunteers must actively participate in the training throughout the 10 minutes, so the movement state is always regarded as active intention. Therefore, the movement intention of all volunteers should be consistent with the training task. Specifically, the frequency difference between the change frequency obtained by EEG decoding and the movement frequency of the training task should be less than the frequency difference threshold, otherwise it is regarded as an error. The accuracy of the EEG decoding results of each volunteer within 10 minutes is counted. For example, for volunteer A, 120 tests, if the frequency difference between the change frequency obtained by EEG decoding and the movement frequency of the training task is less than the frequency difference threshold each time, the accuracy can be determined to be 100%. As Figure 6 As shown, the average accuracy of the EEG decoding results for the 12 volunteers was 91%. Therefore, the accuracy of the above-mentioned sports rehabilitation training method of the embodiment of the present application is verified to a certain extent.

[0148] According to another aspect of the present application, a sports rehabilitation training control device is also provided. Figure 7 FIG. 1 is a schematic block diagram of a sports rehabilitation training control device 700 according to an embodiment of the present application. Figure 7 As shown, the exercise rehabilitation training control device 700 includes:

[0149] The first output module 710 is used to output the motion prompt information corresponding to the first training task of the motion training device in the current period during the process of performing rehabilitation training on the limbs of the training subject using the motion training device, so that the training subject generates the motion intention according to the motion prompt information to actively follow the motion training device to move;

[0150] A first acquisition module 720 is used to acquire EEG activity information of multiple locations of the brain of the training subject in a current period;

[0151] A first determination module 730 is used to determine consistency information between the first movement intention of the training subject in the current period and the first training task according to the EEG activity information;

[0152] The second determination module 740 is used to determine the second training task of the sports training device in the next time period according to the consistency information; wherein the consistency information includes: first information indicating that the first sports intention is consistent with the first training task, or second information indicating that the first sports intention is inconsistent with the first training task.

[0153] Exemplarily, the second determining module 740 includes:

[0154] A first determination submodule is configured to determine, when the consistency information is the first information, that the movement difficulty of the second training task is greater than or equal to the difficulty of the first training task; and / or

[0155] The second determination submodule is configured to determine, when the consistency information is the second information, that the movement difficulty of the second training task is lower than the difficulty of the first training task.

[0156] Exemplarily, the training task is to drive the left and right limbs of the training subject to perform left-right alternating movements. The first determination module 730 includes:

[0157] The third determination submodule is used to determine the changing pattern of the training subject's left and right limb movement intentions in the current period according to the EEG activity information;

[0158] The fourth determination submodule is used to determine the consistency information between the first movement intention and the first training task according to the change law and the movement law of the left-right alternating movement.

[0159] Exemplarily, the third determining submodule includes:

[0160] A fitting unit, for fitting the periodic change frequency of the difference in the EEG activities of the left and right sides of the brain of the training subject in the current period according to the EEG activity information;

[0161] The fourth determination submodule includes:

[0162] A calculation unit, configured to calculate a frequency difference between the change frequency and a first movement frequency, wherein the first movement frequency is a movement frequency of the left-right alternating movement corresponding to the first training task;

[0163] A first information determining unit, configured to determine the consistency information as the first information when the frequency difference is less than or equal to a frequency difference threshold;

[0164] The second information determining unit is configured to determine that the consistency information is the second information when the frequency difference is greater than a frequency difference threshold.

[0165] Exemplarily, the plurality of positions include a plurality of first positions located in the left brain region of the training object and a plurality of second positions located in the right brain region of the training object, the plurality of first positions and the plurality of second positions correspond one to one, and the fitting unit includes:

[0166] A splitting subunit, used for splitting the EEG activity information of each of the multiple locations into EEG activity information parts of multiple frequency bands;

[0167] A calculation and generation subunit, for calculating, based on the EEG activity information portion, the energy difference between the EEG energy of each first position and the corresponding second position in each frequency band in each time window in the current period, and generating an energy difference time series corresponding to each first position;

[0168] The fitting subunit is used to fit the change frequency according to a plurality of energy difference time series corresponding to a plurality of first positions.

[0169] Exemplarily, the fitting subunit is also used to perform the following operations: combining multiple energy difference time series in parallel to obtain an energy difference data set, wherein the sum of elements in each row of the energy difference data set is equal to the product of the number of first positions and the number of frequency segments, and the sum of elements in each column of the energy difference data set is equal to the number of time windows in the current time period; performing correlation analysis on the energy difference data set and a pre-constructed sine and cosine dictionary of a first frequency range to determine the correlation between each frequency component within the first frequency range and the energy difference data set, wherein the first frequency range includes multiple frequency segments; determining the change frequency based on the first frequency component within the first frequency range, wherein the correlation between the first frequency component and the energy difference data set is not lower than other frequency components among the frequency components except the first frequency component.

[0170] Exemplarily, the first output module 710 is also used to output first movement prompt information and / or second movement prompt information, wherein the first movement prompt information is a movement simulation animation consistent with the first training task, and the second movement prompt information includes prompt information of the limb currently mainly involved in the movement.

[0171] Exemplarily, the exercise rehabilitation training control device 700 of the embodiment of the present application further includes:

[0172] The second output module is used to output corresponding motion feedback information according to the consistency information, wherein different consistency information corresponds to different motion feedback information.

[0173] According to another aspect of the present application, an electronic device is also provided. Figure 8 FIG. 1 is a schematic block diagram of an electronic device according to an embodiment of the present application. Figure 8As shown, the electronic device 800 includes: a memory 810 and a processor 820. The memory 810 stores computer program instructions, and the computer program instructions are used to execute the above-mentioned sports rehabilitation training method 100 when the processor 820 is running.

[0174] According to another aspect of the present application, a sports rehabilitation training system is also provided. Fig. 9 FIG. 1 is a schematic block diagram of a sports rehabilitation training system according to an embodiment of the present application. Fig. 9 As shown, the motor rehabilitation training system 900 includes: an EEG acquisition device 910, which is used to acquire EEG signals at multiple locations of the brain of the training object to obtain EEG activity information; a motor training device 920, which is used to run according to the training tasks of each time period; an output device 930, which is used to output the movement prompt information corresponding to the training tasks of each time period; and a motor rehabilitation training control device 940, which is respectively connected to the EEG acquisition device 910, the motor training device 920 and the output device 930, and is used to execute the above-mentioned motor rehabilitation training method 100.

[0175] Optionally, the motion prompt information may include text, icons, images, animations, videos and other information, and the output device 930 may include a display device. Alternatively, the motion prompt information may also include voice prompt information, and the output device 930 may include a voice output transposition.

[0176] Exemplarily, the EEG acquisition device 910 may include an 8-channel wireless EEG amplifier, which may have a variety of suitable forms, such as head-mounted. For example, the head-mounted EEG acquisition device 910 may send the collected EEG signals to the motor rehabilitation training control device 940 via the Bluetooth protocol.

[0177] For example, in combination Figure 2, the motion training device 920 and the output device 930 can be integrated into a rehabilitation training device. Of course, the motion training device 920, the output device 930 and the motion rehabilitation training control device 940 can also be integrated into a rehabilitation training device. For example, the EEG acquisition device 910 can be connected to the rehabilitation training device that integrates the motion training device 920, the output device 930 and the motion rehabilitation training control device 940. When the training subject wears the EEG acquisition device 910 and both arms are placed in the forearm support brace and ensure that the preparation is complete, the training subject or the rehabilitation trainer can set the initial training task (for example, set the training mode to the upper limb isokinetic passive training mode, set the training difficulty to primary) by interacting with the training task setting interface displayed on the LCD screen, and can click the "Start Training" button on the LCD screen. When it is recognized that the button is pressed, the motor rehabilitation training control device 940 controls the upper limb turntable to start rotating at a uniform speed corresponding to the primary training (for example, 0.5 laps / second or 0.5Hz), and controls the LCD screen to display the upper limb movement picture synchronized with the current movement. When the left arm needs to exert force to move (the training subject needs to pay attention to the movement of the left arm), the left hand area in the picture can be highlighted and activated; when the right arm needs to exert force (the training subject needs to pay attention to the movement of the right arm), the right hand area in the picture can be highlighted and activated. During the exercise, the EEG acquisition device 910 collects EEG signals from multiple locations of the training subject's brain in real time and sends them to the sports rehabilitation training control device 940. The sports rehabilitation training control device 940 can use the above-mentioned sports rehabilitation training method 100 to determine the rotation speed of the upper limb turntable in the training task of the next time period based on the EEG signals obtained in each time period (such as 5 minutes).

[0178] According to another aspect of the present application, a storage medium is also provided. Program instructions are stored on the storage medium, and the program instructions are used to execute the above-mentioned sports rehabilitation training method 100 when running. The storage medium may include, for example, an erasable programmable read-only memory (EPROM), a portable read-only memory (CD-ROM), a USB memory, or any combination of the above storage media. The storage medium may be any combination of one or more computer-readable storage media.

[0179] According to another aspect of the present application, a computer program product is also provided, including computer program instructions, which are used to execute the above-mentioned sports rehabilitation training method 100 when running.

[0180] A person skilled in the art can understand the specific implementation schemes and beneficial effects of the above-mentioned sports rehabilitation training device, sports rehabilitation training system, electronic device, storage medium and computer program product by reading the above-mentioned description of the sports rehabilitation training method. For the sake of brevity, they will not be elaborated here.

[0181] Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above example embodiments are merely exemplary and are not intended to limit the scope of the present application to this. Those of ordinary skill in the art may make various changes and modifications therein without departing from the scope and spirit of the present application. All these changes and modifications are intended to be included within the scope of the present application as required by the appended claims.

[0182] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0183] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.

[0184] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0185] Similarly, it should be understood that in order to streamline the present application and help understand one or more of the various inventive aspects, in the description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, the method of the present application should not be interpreted as reflecting the following intention: the claimed application requires more features than the features clearly stated in each claim. More specifically, as reflected in the corresponding claims, the inventive point is that the corresponding technical problem can be solved with features less than all the features of a single disclosed embodiment. Therefore, the claims following the specific embodiment are hereby explicitly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the present application.

[0186] It will be understood by those skilled in the art that, except for mutually exclusive features, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this specification may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0187] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present application and form different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

[0188] The various component embodiments of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some modules in the system according to an embodiment of the present application. The application can also be implemented as a device program (e.g., computer program and computer program product) for executing a part or all of the methods described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0189] It should be noted that the above embodiments illustrate the present application rather than limit the present application, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets should not be constructed as a limitation to the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of multiple such elements. The present application may be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim that lists several devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names.

[0190] The above is only a specific implementation or description of a specific implementation of the present application, and the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. The protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A sports rehabilitation training method, characterized in that: include: During the process of using the exercise training device to perform rehabilitation training on the limbs of the training subject, outputting exercise prompt information corresponding to the first training task of the exercise training device in the current period, so that the training subject generates exercise intention according to the exercise prompt information to actively follow the exercise training device to exercise; Acquiring brain electrical activity information at multiple locations of the training subject's brain in a current time period; Determining consistency information between the first movement intention of the training subject in the current period and the first training task according to the EEG activity information; Determining a second training task of the sports training device in a next period of time according to the consistency information; The consistency information includes: first information indicating that the first movement intention is consistent with the first training task, or second information indicating that the first movement intention is inconsistent with the first training task.

2. The exercise rehabilitation training method according to claim 1, characterized in that: Determining the second training task of the sports training device in the next period according to the consistency information includes: In a case where the consistency information is the first information, determining that the exercise difficulty of the second training task is greater than or equal to the difficulty of the first training task; and / or When the consistency information is the second information, it is determined that the movement difficulty of the second training task is lower than the difficulty of the first training task.

3. The exercise rehabilitation training method according to claim 1, characterized in that: The first training task is a task of driving the left limb and the right limb of the training subject to perform left-right alternating movements, and determining, based on the EEG activity information, consistency information between the first movement intention of the training subject in the current period and the first training task includes: Determining the changing pattern of the left and right limb movement intentions of the training subject in the current time period according to the EEG activity information; According to the change rule and the movement rule of the left-right alternating movement, consistency information between the first movement intention and the first training task is determined.

4. The exercise rehabilitation training method according to claim 3, characterized in that: Determining the changing pattern of the left and right limb movement intentions of the training subject in the current period according to the EEG activity information includes: According to the EEG activity information, fitting the frequency of the periodic change of the EEG activity difference between the left and right sides of the brain of the training subject in the current period; The determining, according to the change rule and the movement rule of the left-right alternating movement, the consistency information between the first movement intention and the first training task includes: calculating a frequency difference between the change frequency and a first movement frequency, wherein the first movement frequency is a movement frequency of the left-right alternating movement corresponding to the first training task; When the frequency difference is less than or equal to a frequency difference threshold, determining that the consistency information is the first information; When the frequency difference is greater than the frequency difference threshold, the consistency information is determined to be the second information.

5. The exercise rehabilitation training method according to claim 4, characterized in that: The multiple positions include: multiple first positions located in the left brain area of ​​the training object and multiple second positions located in the right brain area of ​​the training object, the multiple first positions correspond to the multiple second positions one by one, and the fitting of the change frequency of the periodic change of the difference in brain electrical activities between the left and right sides of the brain of the training object in the current period according to the brain electrical activity information includes: Splitting the EEG activity information of each of the multiple locations into EEG activity information parts of multiple frequency bands; According to the EEG activity information part, calculating the energy difference between the EEG energy of each first position and the corresponding second position in each frequency band in each time window in the current period, and generating an energy difference time series corresponding to each first position; The change frequency is fitted according to a plurality of energy difference time series corresponding to the plurality of first positions.

6. The exercise rehabilitation training method according to claim 5, characterized in that: The step of fitting the change frequency according to a plurality of energy difference time series corresponding to the plurality of first positions comprises: Combining the multiple energy difference time series in parallel to obtain an energy difference data set, wherein the sum of elements in each row of the energy difference data set is equal to the product of the number of the first positions and the number of the frequency segments, and the sum of elements in each column of the energy difference data set is equal to the number of time windows in the current time period; Performing a correlation analysis on the energy difference dataset and a pre-constructed sine-cosine dictionary of a first frequency range to determine the correlation between each frequency component in the first frequency range and the energy difference dataset, wherein the first frequency range includes the plurality of frequency segments; The change frequency is determined according to a first frequency component within the first frequency range, wherein the correlation between the first frequency component and the energy difference data set is not lower than other frequency components among the various frequency components except the first frequency component.

7. The sports rehabilitation training method according to any one of claims 1 to 6, characterized in that: The outputting of the exercise prompt information corresponding to the first training task of the exercise training device in the current period includes: Output first movement prompt information and / or second movement prompt information, wherein the first movement prompt information is a movement simulation animation consistent with the first training task, and the second movement prompt information includes prompt information of a limb currently mainly involved in the movement.

8. The sports rehabilitation training method according to any one of claims 1 to 6, characterized in that: The method further comprises: According to the consistency information, corresponding motion feedback information is output, wherein different consistency information corresponds to different motion feedback information.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores computer program instructions, and the computer program instructions are used by the processor to execute the sports rehabilitation training method according to any one of claims 1 to 8 when the processor is running.

10. A sports rehabilitation training system, characterized in that: include: An EEG acquisition device is used to collect EEG signals from multiple locations of the training subject's brain to obtain EEG activity information; A sports training device, used to run according to the training task in each period; An output device, used to output the exercise prompt information corresponding to the training task in each period; A motor rehabilitation training control device is respectively connected to the EEG acquisition device, the motor training device and the output device, and is used to execute the motor rehabilitation training method as described in any one of claims 1 to 8.

Images