A method and device for evaluating a multi-modal signal for idiopathic scoliosis rehabilitation

Abstract

The application discloses a kind of idiopathic scoliosis rehabilitation multi-modal signal evaluation method and device.The idiopathic scoliosis rehabilitation multi-modal signal evaluation method includes: obtaining the muscle activation information of the person to be evaluated in the movement cycle;Actual time of reaching action peak in the movement cycle of the person to be evaluated is obtained;The displacement information of the person to be evaluated in the movement cycle is obtained;The movement amplitude information of the person to be evaluated in the movement cycle is obtained;Multi-modal rehabilitation confidence model is obtained;The muscle activation information, actual time of reaching action peak, displacement information and movement amplitude information are input into the multi-modal rehabilitation confidence model, so as to obtain rehabilitation confidence information.The application uses multi-modal information, can more comprehensively evaluate the effect of rehabilitation action;By characteristic parameter representation factor that influences rehabilitation action effect, mapping is established between mathematical model and clinical index, can more comprehensively, scientifically and accurately evaluate rehabilitation action.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a multimodal signal evaluation method and device for idiopathic scoliosis rehabilitation. Background Technology

[0002] Idiopathic scoliosis (IS) is a complex three-dimensional deformity characterized by lateral curvature and vertebral rotation in one or more segments of the spine. It is classified by age into infancy (0–3 years), adolescence (4–9 years), puberty (10–18 years), and adulthood (≥18 years). IS not only affects the patient's physical and mental health, but in severe cases can lead to chest, lower back, and back pain, impaired cardiopulmonary function, and nerve compression. The Cobb angle is the angle formed by the intersection of a vertical line drawn from the upper endplate of the most inclined vertebra at the apex of the spinal curvature and a vertical line drawn from the lower endplate of the vertebra with the opposite inclination. Clinically, it is mainly measured through static X-rays, lacking dynamic assessment methods. When the Cobb angle of an IS patient is less than 45°, conservative treatment and guided exercises under the supervision of a rehabilitation therapist, combined with bracing, are recommended; when the Cobb angle exceeds 45°, surgical intervention should be considered. Postoperatively, patients also need to undergo rehabilitation training to help restore function.

[0003] Current research has explored the etiology, development, and impact of IS, but research on IS patient rehabilitation remains relatively lagging. Clinically, rehabilitation assessment for IS patients mainly relies on the clinical experience of doctors and rehabilitation therapists. Furthermore, most existing studies employ a single modality for assessment, typically measuring IS patient activity through spatial location information or surface electromyography signals. However, a single modality cannot comprehensively and accurately reflect the patient's condition.

[0004] Therefore, it is desirable to have a technical solution to overcome or at least mitigate one of the aforementioned defects of the prior art. Summary of the Invention

[0005] The purpose of this application is to provide a multimodal signal assessment method for rehabilitation of idiopathic scoliosis to overcome or at least mitigate one of the aforementioned deficiencies of the prior art.

[0006] To achieve the above objectives, this application provides a multimodal signal assessment method for rehabilitation of idiopathic scoliosis, the multimodal signal assessment method for rehabilitation of idiopathic scoliosis comprising:

[0007] Obtain information on muscle activation levels of the subject during the exercise cycle;

[0008] Obtain the actual time when the subject of the assessment reaches peak performance within the exercise cycle;

[0009] Obtain displacement information of the person being evaluated during the motion cycle;

[0010] obtaining the movement amplitude information of the subject in the movement cycle;

[0011] obtaining a multi-modal rehabilitation confidence model;

[0012] inputting the muscle activation information, the time of actually reaching the action peak, the displacement information and the movement amplitude information into the multi-modal rehabilitation confidence model, so as to obtain the rehabilitation confidence information.

[0013] Optionally, the multi-modal signal evaluation method for idiopathic scoliosis rehabilitation further comprises:

[0014] obtaining the video stream information transmitted by the three-dimensional motion capture system;

[0015] extracting the spatial position change information of each marker point in the video stream information;

[0016] obtaining the time of actually reaching the action peak, the displacement information and the movement amplitude information of the subject in the movement cycle according to the spatial position change information of each marker point.

[0017] Optionally, the method of obtaining the time of actually reaching the action peak, the displacement information and the movement amplitude information of the subject in the movement cycle according to the spatial position change information of each marker point comprises:

[0018] segmenting the spatial position change information of each marker point, and dividing at least one active segment data and at least one resting segment data around the peak value of the spatial change of each marker point;

[0019] aligning each active segment data in time and space with the vertex of each active segment data as the origin, so as to obtain each aligned data;

[0020] fitting each set of aligned data using a Gaussian function to obtain a Gaussian curve of each set of aligned data;

[0021] obtaining the time of actually reaching the action peak, the displacement information and the movement amplitude information of the subject in the movement cycle according to the Gaussian curve.

[0022] Optionally, the multi-modal signal evaluation method for idiopathic scoliosis rehabilitation further comprises:

[0023] obtaining the electromyographic information of the subject obtained by the electromyographic acquisition system in the movement cycle;

[0024] obtaining the muscle activation information of the subject in the movement cycle according to the electromyographic information.

[0025] Optionally, the multi-modal rehabilitation confidence model is as follows:

[0026] ; wherein,

[0027] is a weight of the muscle activation degree on the action confidence information, is a weight of the symmetry on the rehabilitation confidence coefficient, is a weight of the stability on the action confidence coefficient, is a weight of the range of motion on the rehabilitation confidence coefficient, is the muscle activation degree on the action confidence information, is the symmetry on the rehabilitation confidence coefficient, is the stability on the action confidence coefficient, is the range of motion on the rehabilitation confidence coefficient, is a main force muscle parameter, if the main force muscle is consistent with the muscle required by the rehabilitation action, then = 1, if not consistent, then = 0.

[0028] Optionally, the muscle activation degree on the action confidence information is obtained by the following formula:

[0029] ; wherein,

[0030] is 3, is the muscle activation degree on the action confidence information, is the muscle activation degree.

[0031] Optionally, the symmetry on the rehabilitation confidence coefficient is obtained by the following formula:

[0032] ; wherein,

[0033] is the symmetry on the rehabilitation confidence coefficient, is a motion cycle, is an actual time to reach the action peak.

[0034] Optionally, the stability on the action confidence coefficient is obtained by the following formula:

[0035] ; wherein,

[0036] is a standard deviation of acceleration , wherein the acceleration is a second derivative of displacement information.

[0037] Optionally, the influence information of the movement range on the rehabilitation confidence coefficient is obtained by the following formula:

[0038] ; wherein,

[0039] is the influence information of the movement range on the rehabilitation confidence coefficient, is a constant, and is 1, is the movement amplitude.

[0040] The present application also provides a multi-modal signal evaluation device for idiopathic scoliosis rehabilitation, comprising:

[0041] a muscle activation information acquisition module, configured to acquire muscle activation information of a subject in a movement cycle;

[0042] a time-to-peak acquisition module, configured to acquire a time-to-peak of the subject in the movement cycle;

[0043] a displacement information acquisition module, configured to acquire displacement information of the subject in the movement cycle;

[0044] a movement amplitude information acquisition module, configured to acquire movement amplitude information of the subject in the movement cycle;

[0045] a model acquisition module, configured to acquire a multi-modal rehabilitation confidence model;

[0046] a rehabilitation confidence information acquisition module, configured to input the muscle activation information, the time-to-peak, the displacement information, and the movement amplitude information into the multi-modal rehabilitation confidence model, so as to acquire rehabilitation confidence information.

[0047] The multi-modal signal evaluation method for idiopathic scoliosis rehabilitation of the present application uses multi-modal information, and can more comprehensively evaluate the effect of rehabilitation actions; by using characteristic parameters to represent factors affecting the effect of rehabilitation actions, and by mapping mathematical models and clinical indexes, the rehabilitation actions can be more comprehensively, scientifically, and accurately evaluated, and the rehabilitation actions can be fed back and guided through the results of the rehabilitation confidence coefficient. BRIEF DESCRIPTION OF DRAWINGS

[0048] Figure 1 is a flowchart of a multi-modal signal evaluation method for idiopathic scoliosis rehabilitation according to an embodiment of the present application.​

[0049] Figure 2 Figure 1 is a structural schematic diagram of an electronic device in an embodiment of the present application.

[0050] Figure 3 Figure 1 is a structural schematic diagram of an electronic device in an embodiment of the present application. Figure 1 Figure 2 is a multi-modal rehabilitation confidence model schematic diagram of a multi-modal signal evaluation method for idiopathic scoliosis rehabilitation shown in Figure 1. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme in the embodiments of the present application will be described in more detail below with reference to the drawings in the embodiments of the present application. In the drawings, the same or similar reference signs represent the same or similar elements or elements with the same or similar functions throughout. The described embodiments are part of the embodiments of the present application, not all of the embodiments. The embodiments described below by reference to the drawings are exemplary and are intended to explain the present application, and cannot be understood as limiting the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application. The embodiments of the present application will be described in detail below with reference to the drawings.

[0052] In the description of the present application, it should be understood that the terms "center", "longitudinal", "transverse", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and therefore cannot be understood as indicating or implying that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the scope of protection of the present application.

[0053] As shown in Figure 1, the multi-modal signal evaluation method for idiopathic scoliosis rehabilitation includes: Figure 1 As shown in Figure 1, the multi-modal signal evaluation method for idiopathic scoliosis rehabilitation includes:

[0054] Step 1: Obtain muscle activation information of the person to be evaluated in a movement cycle;

[0055] Step 2: Obtain the actual time to reach the action peak of the person to be evaluated in the movement cycle;

[0056] Step 3: Obtain displacement information of each marker point of the person to be evaluated in the movement cycle;

[0057] Step 4: Obtain movement amplitude information of the person to be evaluated in the movement cycle;

[0058] Step 5: Obtain a multi-modal rehabilitation confidence model;

[0059] Step 6: inputting the muscle activation information, the time of actually reaching the action peak, the displacement information and the motion amplitude information into the multi-modal rehabilitation confidence model to obtain rehabilitation confidence information.

[0060] The multi-modal signal evaluation method for idiopathic scoliosis rehabilitation of the present application uses multi-modal information to more comprehensively evaluate the effect of rehabilitation actions; factors affecting the effect of rehabilitation actions are represented by characteristic parameters, mapping of mathematical models and clinical indicators is established, rehabilitation actions can be more comprehensively, scientifically and accurately evaluated, and rehabilitation actions are fed back and guided through the results of rehabilitation confidence coefficients.

[0061] In the present embodiment, the multi-modal signal evaluation method for idiopathic scoliosis rehabilitation further comprises:

[0062] Obtaining video stream information transmitted by a three-dimensional motion capture system;

[0063] Extracting spatial position change information of each marker point in the video stream information;

[0064] Obtaining the time of actually reaching the action peak, the displacement information and the motion amplitude information of the to-be-evaluated person in the motion cycle according to the spatial position change information of each marker point.

[0065] In the present embodiment, the obtaining of the time of actually reaching the action peak, the displacement information and the motion amplitude information of the to-be-evaluated person in the motion cycle according to the spatial position change information of each marker point comprises:

[0066] Segmenting the spatial position change information of each marker point, and dividing at least one active segment data and at least one resting segment data around the peak value of the spatial change of each marker point;

[0067] Aligning each active segment data in time and space with the vertex of each active segment data as the origin to obtain each aligned data;

[0068] Fitting each set of aligned data using a Gaussian function to obtain a Gaussian curve of each set of aligned data;

[0069] Obtaining the time of actually reaching the action peak, the displacement information and the motion amplitude information of the to-be-evaluated person in the motion cycle according to the Gaussian curve.

[0070] In the embodiment, the three-dimensional motion capture system used by the application is a VICON system, the sampling frequency is 100HZ, the spatial position information change of each marker point is extracted, and the spatial position information change of each part of the experimental object when performing rehabilitation movements is calculated. The data is preprocessed using matlab. First, the data is segmented, and 50 frames of data are taken as the center of the peak value, which is regarded as the active segment data, and the rest is regarded as the resting segment data. Next, the vertex of each segment of data is taken as the origin for time and space alignment, so as to compare the relative position change of each group of data.

[0071] In the embodiment, a Gaussian function is used to fit each group of data to obtain the Gaussian curve of each group of data. As shown in the figure. The expression of the Gaussian function is , wherein, is the amplitude, is the time to reach the peak value, is the standard deviation, is the displacement. The motion amplitude can be obtained from the formula , and the substitution obtains .

[0072] The multi-modal signal evaluation method for the rehabilitation of idiopathic scoliosis in the embodiment further comprises:

[0073] obtaining the electromyographic information of the person to be evaluated obtained by the electromyographic acquisition system in the movement cycle;

[0074] obtaining the muscle activation information of the person to be evaluated in the movement cycle according to the electromyographic information.

[0075] Specifically, the electromyographic signal acquisition system used by the application is Datalink, the sampling frequency is 2000HZ, the sampling range is ±6mv, and the sampling accuracy is 1 , which is used to collect the surface electromyographic signals of the subjects during the experiment. The collected electromyographic signals are preprocessed, and the muscle activation is calculated to express the main muscle force condition. First, the surface electromyographic signals are filtered through a band-pass fourth-order Butterworth filter (20Hz). In the Hill muscle model, is converted into muscle activation signal . Since there is a time delay between muscle contraction and muscle strength, a second-order discrete linear system is used to convert into an intermediate value , which is a recursive filter and can be represented as:

[0076]

[0077] , wherein, represents ; represents the gain coefficient; denotes a recursive coefficient; denotes a time delay. Since there is a difference in muscle activation of each individual during the movement, after normalizing the muscle activation , the main muscle force position in the rehabilitation movement is evaluated.

[0078] Referring to Figure 3 , in the embodiment, the multi-modal rehabilitation confidence model is as follows:

[0079] ; wherein,

[0080] is the weight of the muscle activation degree on the action confidence information, is the weight of the symmetry on the rehabilitation confidence coefficient information, is the weight of the stability on the action confidence coefficient information, is the weight of the range of motion on the rehabilitation confidence coefficient information, is the muscle activation degree on the action confidence information, is the symmetry on the rehabilitation confidence coefficient information, is the stability on the action confidence coefficient information, is the range of motion on the rehabilitation confidence coefficient information, is the main force muscle parameter, if the main force muscle is consistent with the muscle required to be trained in the rehabilitation movement, then =1, if not consistent, then =0.

[0081] In the embodiment, the muscle activation degree on the action confidence information is obtained by the following formula:

[0082] ; wherein,

[0083] is taken as 3, is the muscle activation degree on the action confidence information, is the muscle activation degree.

[0084] Specifically, it is considered that the muscle activation degree has a linear correlation with the muscle force, and the muscle activation degree on the action confidence information is as follows: wherein, is taken as 3.

[0085] According to the muscle activation calculation results of different channels, the maximum value is taken as the main force muscle, and the parameter ​; if the main muscle is consistent with the muscle required by the rehabilitation action, then = 1, and if not, then = 0.

[0086] In the embodiment, the influence information of the symmetry on the rehabilitation confidence coefficient is obtained by the following formula:

[0087] ; wherein,

[0088] is the influence information of the symmetry on the rehabilitation confidence coefficient, is the motion cycle, is the actual time of reaching the action peak, and e is a natural constant.

[0089] Specifically, the symmetry is related to the in the Gaussian function and the motion cycle , and the closer and are, the better the symmetry is. Assuming that the difference between and reaches , the symmetry is considered to be extremely low. In combination with the Gaussian fitting function, the above influence information of the symmetry on the rehabilitation confidence coefficient is obtained.

[0090] In the embodiment, the influence information of the stability on the action confidence coefficient is obtained by the following formula:

[0091] ; wherein,

[0092] is the standard deviation of the acceleration , wherein the acceleration is the second derivative of the displacement information.

[0093] In the embodiment, the stability is related to the standard deviation of the acceleration , and the smaller is, the better the stability is. Assuming that the experimental object reaches the optimal condition when the standard deviation reaches 0.02 in the motion, the above influence information of the stability on the action confidence coefficient is obtained.

[0094] In the embodiment, the influence information of the motion range on the rehabilitation confidence coefficient is obtained by the following formula:

[0095] = ; wherein,

[0096] is the influence information of the motion range on the rehabilitation confidence coefficient, is a constant, and is taken as 1, The amplitude of motion.

[0097] In this embodiment, the motion amplitude () is obtained by using a Gaussian fitting equation. )for Substituting into the equation yields... Regarding the impact of range of motion on rehabilitation confidence coefficient, referencing the maximum muscle contraction MVC, we propose the maximum range of motion. Furthermore, parameters are proposed. for and The ratio, ranging from [0, 1], is expressed as a linear function. Impact on the confidence coefficient of rehabilitation = , It is a constant, and is set to 1.

[0098] In this embodiment, by extracting the spatial position information and muscle information features of the subject during rehabilitation movements, the changes in these features are combined with the rehabilitation movements themselves to obtain a multimodal assessment strategy. This strategy is then used to calculate the rehabilitation confidence coefficient to assess the subject's rehabilitation exercise score.

[0099] This application also provides a multimodal signal assessment device for idiopathic scoliosis rehabilitation. The device includes a muscle activation information acquisition module, an actual peak time acquisition module, a displacement information acquisition module, a motion amplitude information acquisition module, a model acquisition module, and a rehabilitation confidence information acquisition module.

[0100] The muscle activation information acquisition module is used to acquire muscle activation information of the person being evaluated during the exercise cycle;

[0101] The actual time to reach peak motion is used to obtain the actual time when the subject of the assessment reaches peak motion within the motion cycle;

[0102] The displacement information acquisition module is used to acquire the displacement information of each marker point of the person being evaluated during the motion cycle;

[0103] The motion amplitude information acquisition module is used to acquire the motion amplitude information of the person being evaluated during the motion cycle;

[0104] The model acquisition module is used to acquire multimodal rehabilitation confidence models;

[0105] The rehabilitation confidence information acquisition module is used to input the muscle activation information, the actual time to reach the peak of the movement, displacement information, and movement amplitude information into the multimodal rehabilitation confidence model to obtain rehabilitation confidence information.

[0106] It should be noted that the foregoing explanation of the method embodiment is also applicable to the device of the present embodiment, which will not be repeated here.

[0107] The present application also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor implements the method for evaluating a multi-modal signal for idiopathic scoliosis rehabilitation as above when executing the computer program.

[0108] The present application also provides a computer readable storage medium, which stores a computer program, wherein the computer program is executed by a processor to implement the method for evaluating a multi-modal signal for idiopathic scoliosis rehabilitation as above.

[0109] Figure 2 is an exemplary structural diagram of an electronic device capable of implementing the method for evaluating a multi-modal signal for idiopathic scoliosis rehabilitation according to an embodiment of the present application.

[0110] As shown in Figure 2 , the electronic device comprises an input device 501, an input interface 502, a central processor 503, a memory 504, an output interface 505, and an output device 506. The input interface 502, the central processor 503, the memory 504, and the output interface 505 are connected to each other through a bus 507, and the input device 501 and the output device 506 are connected to the bus 507 through the input interface 502 and the output interface 505, respectively, and further connected to other components of the electronic device. Specifically, the input device 504 receives input information from the outside and transmits the input information to the central processor 503 through the input interface 502; the central processor 503 processes the input information based on the computer executable instructions stored in the memory 504 to generate output information, temporarily or permanently stores the output information in the memory 504, and then transmits the output information to the output device 506 through the output interface 505; the output device 506 outputs the output information to the outside of the electronic device for use by the user.

[0111] That is, the electronic device shown in Figure 2 may also be implemented to comprise a memory storing computer executable instructions; and one or more processors that, when executing the computer executable instructions, can implement the method for evaluating a multi-modal signal for idiopathic scoliosis rehabilitation described in conjunction with Figure 1 .

[0112] In one embodiment, Figure 2The electronic device shown can be implemented to include: a memory 504 configured to store executable program codes; and one or more processors 503 configured to execute the executable program codes stored in the memory 504 to perform the multi-modal signal evaluation method for idiopathic scoliosis rehabilitation in the above-described embodiments.

[0113] In one typical arrangement, the computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0114] The memory can include non-persistent memory and / or volatile memory, such as a random access memory (RAM) including a cache area for the temporary storage of data. A

[0115] Computer-readable media includes permanent and non-permanent, movable and non-movable media that can be implemented by any method or technology for storing information. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0116] Those skilled in the art will appreciate that embodiments of the present application can be provided as methods, systems or computer program products. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) containing computer usable program code.

[0117] In addition, it is clear that the word "comprising" does not exclude other units or steps. The plurality of units, modules or devices stated in the device claim can also be implemented by one unit or a total device by means of software or hardware.

[0118] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other processing devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other processing devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0119] Those skilled in the art will understand that embodiments of the present application can be provided as a method, a system or a computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer readable program code.

[0120] Furthermore, the term "comprising" does not exclude other elements or steps. Multiple elements, means or devices specified in a claim can also be provided by one element, means or device. The provision "by means of" does not exclude multiple means or devices, and that a plurality of elements, means or devices are presented by one element, means or device.

[0121] Although the present application has been disclosed in connection with the preferred embodiments thereof, it should be understood that other modifications, substitutions, and alternatives can become apparent to those skilled in the art and can be made without departing from the spirit and scope of the application in its broadest form.

[0122] Finally, it should be noted that the above-mentioned embodiments are merely intended for describing and illustrating, not limiting, the technical solutions of the present application. Even though the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still make modifications or equivalent replacements to the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of evaluating a multi-modal signal for rehabilitation of idiopathic scoliosis, the method comprising: The method for evaluating the rehabilitation of idiopathic scoliosis based on multi-modal signals comprises: obtaining muscle activation information of the subject in a movement cycle; obtaining the time of actual reaching the action peak of the subject in the movement cycle; obtaining displacement information of each marker point of the subject in the movement cycle; obtaining movement amplitude information of the subject in the movement cycle; obtaining a multi-modal rehabilitation confidence model; inputting the muscle activation information, the time of actual reaching the action peak, the displacement information and the movement amplitude information into the multi-modal rehabilitation confidence model to obtain rehabilitation confidence information; The method for evaluating the rehabilitation of idiopathic scoliosis based on multi-modal signals further comprises: obtaining video stream information transmitted by a three-dimensional motion capture system; extracting spatial position change information of each marker point in the video stream information; obtaining the time of actual reaching the action peak, the displacement information and the movement amplitude information of the subject in the movement cycle according to the spatial position change information of each marker point; The method for obtaining the time of actual reaching the action peak, the displacement information and the movement amplitude information of the subject in the movement cycle according to the spatial position change information of each marker point comprises: segmenting the spatial position change information of each marker point respectively, and dividing at least one active segment data and at least one resting segment data around the peak value of the spatial change of each marker point; aligning each active segment data in time and space with the vertex of each active segment data as the origin to obtain aligned data; fitting each set of aligned data using a Gaussian function to obtain a Gaussian curve of each set of aligned data; obtaining the time of actual reaching the action peak, the displacement information and the movement amplitude information of the subject in the movement cycle according to the Gaussian curve respectively; The multi-modal rehabilitation confidence model is as follows: ; wherein, a weight for the information of the influence of muscle activation on the action confidence, a weight for the information of the influence of symmetry on the rehabilitation confidence coefficient, a weight for the information of the influence of stability on the action confidence coefficient, a weight for the information of the influence of the range of motion on the rehabilitation confidence coefficient, the information of the influence of muscle activation on the action confidence, the information of the influence of symmetry on the rehabilitation confidence coefficient, the information of the influence of stability on the action confidence coefficient, the information of the influence of the range of motion on the rehabilitation confidence coefficient, is a main force muscle parameter, if the main force muscle is consistent with the muscle required to be trained by the rehabilitation action, = 1, if not consistent, = 0.

2. The method of idiopathic scoliosis rehabilitation of multi-modal signal evaluation as claimed in claim 1, wherein, The method for evaluating the rehabilitation of idiopathic scoliosis based on multi-modal signals further comprises: obtaining electromyography information of the subject obtained by an electromyography acquisition system in the movement cycle; obtaining muscle activation information of the subject in the movement cycle according to the electromyography information.

3. The method of idiopathic scoliosis rehabilitation of multi-modal signal evaluation of claim 2, wherein, The influence information of the muscle activation on the action confidence is obtained by the following formula: ; wherein, take 3, muscle activation degree to action confidence degree influence information, muscle activation degree.

4. The method of idiopathic scoliosis rehabilitation of multi-modal signal evaluation of claim 3, wherein, The influence information of the symmetry on the rehabilitation confidence coefficient is obtained by the following formula: ; wherein, for the influence of symmetry on the rehabilitation confidence coefficient, for the movement cycle, is the time of actual arrival at the action peak, e is the natural constant.

5. The method of idiopathic scoliosis rehabilitation of multi-modal signal evaluation of claim 4, wherein, The influence information of the stability on the action confidence coefficient is obtained by the following formula: ; wherein, is the standard deviation of the acceleration , where acceleration is the second derivative of the displacement information.

6. The method of idiopathic scoliosis rehabilitation of multi-modal signal evaluation of claim 5, wherein, The influence information of the movement range on the rehabilitation confidence coefficient is obtained by the following formula: = 0.5 ; wherein, for the influence of the range of motion on the coefficient of confidence of the rehabilitation, is a constant, taken as 1, is the amplitude of the motion.

7. A multi-modal signal evaluation device for idiopathic scoliosis rehabilitation, characterized by, The device for evaluating the rehabilitation of idiopathic scoliosis based on multi-modal signals is used for executing the method according to any one of claims 1-6, and the device comprises: a muscle activation information obtaining module, which is used for obtaining muscle activation information of the subject in a movement cycle; a time of actual reaching the action peak obtaining module, which is used for obtaining the time of actual reaching the action peak of the subject in the movement cycle; a displacement information obtaining module, which is used for obtaining displacement information of each marker point of the subject in the movement cycle; The motion amplitude information acquisition module is configured to acquire motion amplitude information of the to-be-evaluated person in a motion cycle. The model acquisition module is configured to acquire a multi-modal rehabilitation confidence model. The rehabilitation confidence information acquisition module is configured to input the muscle activation information, the actual time to reach the motion peak value, the displacement information and the motion amplitude information into the multi-modal rehabilitation confidence model, so as to acquire rehabilitation confidence information.

Images