A method, device and application for evaluating exercise capacity based on electrocardiosignal

Abstract

The application relates to the field of electrocardiosignal data processing and discloses a motion capacity evaluation method and device based on electrocardiosignal and application, the method comprising the following steps: acquiring electrocardiosignal before and after user motion; calculating a nonlinear dynamics characteristic matrix of the electrocardiosignal before and after user motion; calculating the topological similarity of the electrocardiosignal before and after user motion by using the nonlinear dynamics characteristic matrix; and evaluating the motion capacity of the user according to the size of the topological similarity. The application can identify the nonlinear dynamic item of time-varying electrocardiosignal data, can reflect the essential dynamic characteristics of the electrocardiosignal more, can realize the quantification of motion capacity evaluation, and can more accurately evaluate the motion capacity of the user according to the quantification result.

Description

Technical Field

[0001] This invention relates to the field of electrocardiogram (ECG) signal data processing, and more specifically, to a method, apparatus, and application for assessing exercise capacity based on ECG signals. Background Technology

[0002] Individuals vary in their physical condition and exercise levels, resulting in differences in their adaptability and tolerance to exercise. Assessing motor ability is a research question of great practical significance. The step test, involving alternating jumps on a step with each leg, is a method to assess motor function adaptation. It can be conducted indoors, is suitable for people of different physical conditions, requires no expensive equipment, and can be completed in a short time, making it a reliable method for assessing motor ability. Existing step test methods assess a user's step test ability by measuring parameters before and after the test. However, current step test parameters cannot accurately and objectively characterize a user's motor function level, resulting in inaccurate assessments. Summary of the Invention

[0003] To overcome the shortcomings of inaccurate exercise capacity assessment in existing technologies, this invention provides a method, device, and application for exercise capacity assessment based on electrocardiogram signals.

[0004] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows:

[0005] In a first aspect, the present invention proposes a method for assessing exercise capacity based on electrocardiogram signals, comprising:

[0006] Acquire the user's electrocardiogram (ECG) signals before and after exercise.

[0007] Calculate the nonlinear dynamic characteristic matrix of the user's electrocardiogram signal before and after exercise.

[0008] The topological similarity of the user's electrocardiogram (ECG) signals before and after exercise is calculated using the nonlinear dynamic feature matrix.

[0009] The user's mobility is assessed based on the magnitude of the topological similarity.

[0010] Secondly, the present invention also proposes a motor ability assessment device based on electrocardiogram (ECG) signals, applied in the motor ability assessment method based on ECG signals as described in any embodiment of the first aspect, comprising:

[0011] The acquisition module is used to acquire the user's electrocardiogram (ECG) signals before and after exercise.

[0012] The first calculation module is used to calculate the nonlinear dynamic characteristic matrix of the user's electrocardiogram signals before and after exercise.

[0013] The second calculation module is used to calculate the topological similarity of the user's electrocardiogram signals before and after exercise using the nonlinear dynamic feature matrix.

[0014] The evaluation module is used to evaluate the user's mobility based on the magnitude of the topological similarity.

[0015] Thirdly, the present invention also proposes an application of the exercise capacity assessment method based on electrocardiogram signals as described in any of the technical solutions of the first aspect in the assessment of step test ability, including:

[0016] Acquire the user's electrocardiogram (ECG) signals before and after the step test.

[0017] Calculate the nonlinear dynamic characteristic matrix of the electrocardiogram signal before and after the user performs the step test.

[0018] The topological similarity of the electrocardiogram signals used in the step test was calculated using the aforementioned nonlinear dynamic characteristic matrix.

[0019] The user's ability to conduct step experiments is evaluated based on the magnitude of the topological similarity.

[0020] Compared with the prior art, the beneficial effects of the technical solution of the present invention are:

[0021] (1) By extracting the nonlinear dynamic feature matrix of the electrocardiogram signal before and after the user's exercise, and performing subsequent evaluation and identification processing, this invention can identify the nonlinear dynamic terms of time-varying electrocardiogram signal data, better reflect the essential dynamic characteristics of the electrocardiogram signal, and thus better reflect the level of the body's exercise ability, thereby improving the accuracy of exercise ability assessment.

[0022] (2) The topological similarity of the user’s electrocardiogram signals before and after exercise is calculated using the nonlinear dynamic feature matrix. Based on the magnitude of the topological similarity, the user’s exercise ability is evaluated, thereby realizing the quantification of exercise ability evaluation. The user’s exercise ability can be evaluated more accurately based on the quantification results.

[0023] (3) The application of the exercise ability assessment method based on electrocardiogram signals proposed in this invention in the step test ability assessment can more accurately assess the user's step test ability, thereby further improving the accuracy of exercise ability assessment. Attached Figure Description

[0024] Figure 1 This is a flowchart illustrating the exercise capacity assessment method based on electrocardiogram signals in Example 1.

[0025] Figure 2 This is a schematic diagram of a 12-lead electrocardiogram of the human body in Example 1.

[0026] Figure 3 This is a flowchart illustrating the application of the ECG-based exercise capacity assessment method in step test ability assessment in Example 2.

[0027] Figure 4 This is a schematic diagram of the exercise ability assessment device based on electrocardiogram signals in Example 3. Detailed Implementation

[0028] The accompanying drawings are for illustrative purposes only and should not be construed as limiting the scope of this patent.

[0029] The technical solution of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0030] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred technical solutions. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred technical solutions are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0031] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0032] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0033] Example 1

[0034] See Figure 1 This embodiment proposes a method for assessing exercise capacity based on electrocardiogram signals, including the following steps:

[0035] S11: Acquire the user's electrocardiogram (ECG) signals before and after exercise.

[0036] S12: Calculate the nonlinear dynamic characteristic matrix of the user's electrocardiogram signals before and after exercise.

[0037] In this embodiment, as Figure 2As shown, this is a schematic diagram of a 12-lead electrocardiogram of the human body in this embodiment. The time span parameters of the electrocardiogram signals before and after exercise are extracted from the schematic diagram of the 12-lead electrocardiogram of the human body. Based on the time span parameters, the nonlinear dynamic feature matrix of the electrocardiogram signals before and after exercise of the user is calculated.

[0038] The time span parameters include: T-wave total time span parameters, T-wave ascending limb time span parameters, and T-wave descending limb time span parameters; the specific steps for extracting the time span parameters of the electrocardiogram signal include:

[0039] Extract the start point, peak, and end point of the T wave in each cardiac cycle of the electrocardiogram signal.

[0040] The start and end points of the T-wave, the start and peak points of the T-wave, and the time span between the peak and end points of the T-wave are calculated and used as the total time span parameter L1, the rising phase time span parameter L2, and the falling phase time span parameter L3 of the T-wave, respectively. Their expressions are as follows:

[0041] L1=abs(x(Ts i )-x(Te i ))

[0042] L2=abs(x(Ts i )-x(Tp i ))

[0043] L3=abs(x(Tp i )-x(Te i ))

[0044] Where L1 represents the T-wave time span parameter, L2 represents the T-wave rising phase time span parameter, and L3 represents the T-wave falling phase time span parameter. x(·) represents the x-coordinate value of the data point in the ECG signal data sequence in a two-dimensional coordinate system, abs(·) represents the absolute value operation, and Ts i Te represents the starting point of the i-th T wave. i Tp represents the end point of the i-th T wave. i This represents the peak of the i-th T-wave.

[0045] In this embodiment, the nonlinear dynamic characteristic matrix of the user's electrocardiogram signal before and after exercise is calculated based on the time span parameter, specifically including:

[0046] Construct a nonlinear dynamic recognition system based on radial basis function neural networks.

[0047] The nonlinear dynamic recognition system inputs the time span parameters before and after the user's exercise into the nonlinear dynamic recognition system for identification, thereby obtaining the nonlinear dynamic feature matrix of the user's electrocardiogram signals before and after exercise.

[0048] The specific expression of the nonlinear dynamic recognition system based on radial basis function neural network is as follows:

[0049]

[0050] in, Let U[t] represent the nonlinear dynamic characteristic matrix output by the nonlinear dynamic identification system at time t, U[t] represent the time span parameter input at time t, and B be the gain parameter of the nonlinear dynamic identification system. Let U[t] be the derivative of U[t] at time t. Let W represent a radial basis function neural network used to identify unknown nonlinear dynamics, where W is the weight of the radial basis function neural network, S is the regression vector of the radial basis function neural network, and T is the computation sampling time.

[0051] Understandable,

[0052]

[0053] Here, vector X(t) represents the state of the system at time t, which is the value of the characteristic time-series curve data points extracted in the above steps. Let f(X(t)) represent the derivative of X(t) at time t, and let f(X(t)) be the evolution of X(t) over time, representing the nonlinear unknown dynamics of the system. The sampled data of the above system trajectory can be represented as {X(0), X(T), ..., X(N-1)T}, where T represents the calculation sampling time and N represents the total step size.

[0054] S13: Calculate the topological similarity of the user's electrocardiogram signals before and after exercise using the nonlinear dynamic feature matrix.

[0055] In this embodiment, the difference matrix between the nonlinear dynamic feature matrix of the user's ECG signal before exercise and the nonlinear dynamic feature matrix of the user's ECG signal after exercise is calculated, and then the average value of all elements in the difference matrix is ​​calculated. The average value is used as the topological similarity of the user's ECG signals before and after exercise.

[0056] S14: Evaluate the user's mobility based on the magnitude of the topological similarity.

[0057] In this embodiment, when the topological similarity is greater than the first threshold, the user's mobility is considered weak.

[0058] When the topological similarity is less than the first threshold and greater than the second threshold, the user's mobility is considered to be moderate.

[0059] When the topological similarity is less than the second threshold and greater than the third threshold, the user's mobility is considered to be good.

[0060] When the topological similarity is less than the third threshold, the user's mobility is considered excellent.

[0061] It is understandable that by extracting the nonlinear dynamic feature matrix of the user's electrocardiogram (ECG) signals before and after exercise, and then performing subsequent evaluation and identification processing, it is possible to identify the nonlinear dynamic terms of time-varying ECG signal data. This better reflects the essential dynamic characteristics of the ECG signals, thereby better reflecting the level of the body's exercise capacity and improving the accuracy of exercise capacity assessment. The topological similarity of the user's ECG signals before and after exercise is calculated using the aforementioned nonlinear dynamic feature matrix. Based on the magnitude of this topological similarity, the user's exercise capacity is assessed, achieving quantification of exercise capacity assessment. The quantification results allow for a more accurate assessment of the user's exercise capacity.

[0062] Example 2

[0063] See Figure 3 This embodiment proposes an application of the exercise capacity assessment method based on electrocardiogram signals as described in Embodiment 1 in the assessment of step test ability, including the following steps:

[0064] S21: Acquire the user's electrocardiogram (ECG) signals before and after the step test.

[0065] S22: Calculate the nonlinear dynamic characteristic matrix of the electrocardiogram signal before and after the user performs the step test.

[0066] In this embodiment, by extracting the time span parameters of the electrocardiogram (ECG) signals before and after the user's step test, the nonlinear dynamic characteristic matrix of the ECG signals before and after the user's step test is calculated based on the time span parameters.

[0067] The time span parameters include: the full time span parameter of the T wave, the time span parameter of the rising T wave, and the time span parameter of the falling T wave; the specific steps for extracting the time span parameters of the ECG signals before and after the step test include:

[0068] Extract the start point, peak, and end point of the T wave in each cardiac cycle of the electrocardiogram signal before and after the step test.

[0069] The start and end points of the T-wave, the start and peak points of the T-wave, and the time span between the peak and end points of the T-wave are calculated and used as the total time span parameter L1, the rising phase time span parameter L2, and the falling phase time span parameter L3 of the T-wave, respectively. Their expressions are as follows:

[0070] L1=abs(x(Ts i )-x(Te i ))

[0071] L2=abs(x(Ts i )-x(Tp i ))

[0072] L3=abs(x(Tp i )-x(Te i ))

[0073] Where L1 represents the T-wave time span parameter, L2 represents the T-wave rising phase time span parameter, and L3 represents the T-wave falling phase time span parameter. x(·) represents the x-coordinate value of the data point in the ECG signal data sequence in a two-dimensional coordinate system, abs(·) represents the absolute value operation, and Ts i Te represents the starting point of the i-th T wave. i Tp represents the end point of the i-th T wave. i This represents the peak of the i-th T-wave.

[0074] In this embodiment, the nonlinear dynamic characteristic matrix of the electrocardiogram signal before and after the user's step test is calculated based on the time span parameter, specifically including:

[0075] Construct a nonlinear dynamic recognition system based on radial basis function neural networks.

[0076] The time span parameters before and after the user's step test are input into the nonlinear dynamic recognition system for identification, thereby obtaining the nonlinear dynamic feature matrix of the user's electrocardiogram signals before and after the step test.

[0077] The specific expression of the nonlinear dynamic recognition system based on radial basis function neural network is as follows:

[0078]

[0079] in, Let U[t] represent the nonlinear dynamic characteristic matrix output by the nonlinear dynamic identification system at time t, U[t] represent the time span parameter input at time t, and B be the gain parameter of the nonlinear dynamic identification system. Let U[t] be the derivative of U[t] at time t. Let W represent a radial basis function neural network used to identify unknown nonlinear dynamics, where W is the weight of the radial basis function neural network, S is the regression vector of the radial basis function neural network, and T is the computation sampling time.

[0080] S23: Calculate the topological similarity of the electrocardiogram signals used in the step test using the nonlinear dynamic characteristic matrix.

[0081] In this embodiment, the difference matrix between the nonlinear dynamic feature matrix of the ECG signal before the user's step test and the nonlinear dynamic feature matrix of the ECG signal after the user's step test is calculated. Then, the average value of all elements in the difference matrix is ​​calculated, and the average value is used as the topological similarity of the ECG signals before and after the user's step test.

[0082] S24: Evaluate the user's ability to conduct step experiments based on the magnitude of the topological similarity.

[0083] In this embodiment, electrocardiogram signals were collected 3 minutes and 15 minutes after the step test, and the topological similarity ε1 between 3 minutes after the step test and before the step test and the topological similarity ε2 between 15 minutes after the step test and before the step test were calculated, respectively.

[0084] In the specific implementation process, by comparing the nonlinear differences in ECG signals 3 minutes before and after the step test, the smaller the topological similarity ε1, the faster the exercise recovery and the stronger the exercise capacity after the step test; the larger the topological similarity ε1, the slower the exercise recovery and the weaker the exercise capacity after the step test. Experiments show that when ε1 > 0.5, the system indicates a weaker step test ability.

[0085] By comparing the nonlinear differences in ECG signals 15 minutes before and after the step test, a smaller topological similarity ε2 indicates faster exercise recovery and stronger exercise capacity after the step test, while a larger ε2 indicates slower exercise recovery and weaker exercise capacity. Numerical experiments show that when ε2 > 0.2, the system indicates weaker step test ability.

[0086] Through comprehensive comparative experiments, it can be concluded that if ε1 > 0.5 and ε2 < 0.2, the user's step test capability is moderate. If 0.1 < ε1 < 0.5 and 0.05 < ε2 < 0.2, the user's step test capability is good. If ε1 < 0.1 and ε2 < 0.05, the user's step test capability is excellent.

[0087] It is understandable that by extracting the nonlinear dynamic feature matrix of the electrocardiogram (ECG) signals before and after the step test, and performing subsequent evaluation and identification processing, it is possible to identify the nonlinear dynamic terms of time-varying ECG signal data. This better reflects the essential dynamic characteristics of the ECG signals before and after the step test, thus better reflecting the level of the body's exercise capacity and improving the accuracy of exercise capacity assessment. The topological similarity of the ECG signals before and after the step test is calculated using the aforementioned nonlinear dynamic feature matrix. Based on the magnitude of the topological similarity, the user's ability to perform the step test is assessed, achieving a quantification of the step test ability assessment. The quantification results allow for a more accurate assessment of the user's exercise capacity.

[0088] Example 3

[0089] See Figure 4 This embodiment provides a motor ability assessment device based on electrocardiogram (ECG) signals, applied to the motor ability assessment method based on ECG signals as described in Embodiment 1, comprising:

[0090] The acquisition module 100 is used to acquire the user's electrocardiogram (ECG) signals before and after exercise.

[0091] The first calculation module 200 is used to calculate the nonlinear dynamic characteristic matrix of the electrocardiogram signals before and after the user's exercise.

[0092] The second calculation module 300 is used to calculate the topological similarity of the user's electrocardiogram signals before and after exercise using the nonlinear dynamic feature matrix.

[0093] The evaluation module 400 is used to evaluate the user's mobility based on the magnitude of the topological similarity.

[0094] In this embodiment, the system further includes an extraction module, which is used to extract the time span parameters of the user's electrocardiogram (ECG) signals before and after exercise. The first calculation module 200 calculates the nonlinear dynamic feature matrix of the user's ECG signals before and after exercise based on the time span parameters.

[0095] In this embodiment, the time span parameters include: the T-wave full time span parameter, the T-wave rising branch time span parameter, and the T-wave falling branch time span parameter.

[0096] The specific steps for extracting the time span parameter of the electrocardiogram signal include:

[0097] Extract the start point, peak, and end point of the T wave in each cardiac cycle of the electrocardiogram signal.

[0098] The start and end points of the T-wave, the start and peak points of the T-wave, and the time span between the peak and end points of the T-wave are calculated and used as the total time span parameter L1, the rising phase time span parameter L2, and the falling phase time span parameter L3 of the T-wave, respectively. Their expressions are as follows:

[0099] L1=abs(x(Ts i )-x(Te i ))

[0100] L2=abs(x(Ts i )-x(Tp i ))

[0101] L3=abs(x(Tp i )-x(Tei ))

[0102] Where L1 represents the T-wave time span parameter, L2 represents the T-wave rising phase time span parameter, and L3 represents the T-wave falling phase time span parameter. x(·) represents the x-coordinate value of the data point in the ECG signal data sequence in a two-dimensional coordinate system, abs(·) represents the absolute value operation, and Ts i Te represents the starting point of the i-th T wave. i Tp represents the end point of the i-th T wave. i This represents the peak of the i-th T-wave.

[0103] In this embodiment, the device further includes a nonlinear dynamic recognition system based on a radial basis function neural network.

[0104] The nonlinear dynamic recognition system inputs the time span parameters before and after the user's exercise into the nonlinear dynamic recognition system for identification, thereby obtaining the nonlinear dynamic feature matrix of the user's electrocardiogram signals before and after exercise.

[0105] The specific expression of the nonlinear dynamic recognition system based on radial basis function neural network is as follows:

[0106]

[0107] in, Let U[t] represent the nonlinear dynamic characteristic matrix output by the nonlinear dynamic identification system at time t, U[t] represent the time span parameter input at time t, and B be the gain parameter of the nonlinear dynamic identification system. Let U[t] be the derivative of U[t] at time t. Let W represent a radial basis function neural network used to identify unknown nonlinear dynamics, where W is the weight of the radial basis function neural network, S is the regression vector of the radial basis function neural network, and T is the computation sampling time.

[0108] In this embodiment, the difference matrix between the nonlinear dynamic feature matrix of the user's ECG signal before exercise and the nonlinear dynamic feature matrix of the user's ECG signal after exercise is calculated, and the average value of all elements in the difference matrix is ​​calculated. The average value is used as the topological similarity of the user's ECG signals before and after exercise.

[0109] When the topological similarity is greater than the first threshold, the user's mobility is considered weak.

[0110] When the topological similarity is less than the first threshold and greater than the second threshold, the user's mobility is considered to be moderate.

[0111] When the topological similarity is less than the second threshold and greater than the third threshold, the user's mobility is considered to be good.

[0112] When the topological similarity is less than the third threshold, the user's mobility is considered excellent.

[0113] It is understandable that by extracting the nonlinear dynamic feature matrix of the user's electrocardiogram (ECG) signals before and after exercise, and then performing subsequent evaluation and identification processing, it is possible to identify the nonlinear dynamic terms of time-varying ECG signal data. This better reflects the essential dynamic characteristics of the ECG signals, thereby better reflecting the level of the body's exercise capacity and improving the accuracy of exercise capacity assessment. The topological similarity of the user's ECG signals before and after exercise is calculated using the aforementioned nonlinear dynamic feature matrix. Based on the magnitude of this topological similarity, the user's exercise capacity is assessed, achieving quantification of exercise capacity assessment. The quantification results allow for a more accurate assessment of the user's exercise capacity.

[0114] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0115] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0116] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0117] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (FPGAs), field-programmable gate arrays (FPGAs), etc.

[0118] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium. When executed, the program includes one or a combination of the steps of the method embodiments.

[0119] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the implementation of the present invention. Those skilled in the art can make other variations or modifications based on the above description. It is neither necessary nor possible to exhaustively describe all embodiments here. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. A method for assessing exercise capacity based on electrocardiogram (ECG) signals, characterized in that, include: Acquire the user's electrocardiogram (ECG) signals before and after exercise; Extracting time span parameters of the user's electrocardiogram (ECG) signals before and after exercise: The time span parameters include the T-wave full time span parameter, the T-wave rising branch time span parameter, and the T-wave falling branch time span parameter; Extract the start point, peak, and end point of the T wave in each cardiac cycle of the electrocardiogram signal; Calculate the start and end points of the T-wave, the start and peak points of the T-wave, and the time span between the peak and end points of the T-wave, and use these as the full time span parameters of the T-wave. L 1. Time span parameters of the rising limb of the T wave L 2. T-wave descending limb time span parameter L 3, its expression is as follows: in, Represents the parameters of the T-wave over its entire time span. Indicates the time span parameter of the rising branch of the T wave, This represents the time span parameter of the descending branch of the T-wave. This represents the x-coordinate value of a data point in a two-dimensional coordinate system within an electrocardiogram (ECG) signal data sequence. This indicates the absolute value operation. Indicates the first i The starting point of a T wave, Indicates the first i The end point of a T wave, Indicates the first i The peak of a T-wave Based on the time span parameter, calculate the nonlinear dynamic characteristic matrix of the user's electrocardiogram signal before and after exercise; Construct a nonlinear dynamic recognition system based on radial basis function neural networks; The time span parameters before and after the user's exercise are input into the nonlinear dynamic recognition system for recognition, and the nonlinear dynamic feature matrix of the user's electrocardiogram signal before and after exercise is obtained. The specific expression of the nonlinear dynamic recognition system based on radial basis function neural network is as follows: in, express t The nonlinear dynamic characteristic matrix output by the time-invariant dynamic identification system. express t The time span parameter input at any time, B For the gain parameters of the nonlinear dynamic identification system, express t time The derivative of This represents a radial basis function neural network used to identify unknown nonlinear dynamics. The weights of the radial basis function neural network are... For the regression vector of the radial basis function neural network, To calculate the sampling time; Calculate the difference matrix between the nonlinear dynamic characteristic matrix of the user's ECG signal before exercise and the nonlinear dynamic characteristic matrix of the user's ECG signal after exercise; Calculate the average value of all elements in the difference matrix, and use the average value as the topological similarity of the user's electrocardiogram signals before and after exercise; The user's mobility is assessed based on the magnitude of the topological similarity.

2. The method for assessing exercise capacity based on electrocardiogram signals according to claim 1, characterized in that, The user's mobility is evaluated based on the magnitude of the topological similarity, specifically including: When the topological similarity is greater than the first threshold, the user's mobility is considered weak. When the topological similarity is less than the first threshold and greater than the second threshold, the user's mobility is considered to be moderate. When the topological similarity is less than the second threshold and greater than the third threshold, the user's mobility is considered to be good. When the topological similarity is less than the third threshold, the user's mobility is considered excellent.

3. A device for assessing exercise capacity based on electrocardiogram (ECG) signals, applied to the exercise capacity assessment method based on ECG signals as described in any one of claims 1 to 2, characterized in that, include: The acquisition module is used to acquire the user's electrocardiogram (ECG) signals before and after exercise. The extraction module is used to extract the time span parameters of the user's electrocardiogram (ECG) signals before and after exercise. The time span parameters include: the T-wave full time span parameter, the T-wave rising branch time span parameter, and the T-wave falling branch time span parameter; The specific steps for extracting the time span parameter of the electrocardiogram signal include: Extract the start point, peak, and end point of the T wave in each cardiac cycle of the electrocardiogram signal; Calculate the start and end points of the T-wave, the start and peak points of the T-wave, and the time span between the peak and end points of the T-wave, and use these as the full time span parameters of the T-wave. L 1. Time span parameters of the rising limb of the T wave L 2. T-wave descending limb time span parameter L 3, its expression is as follows: in, Represents the parameters of the T-wave over its entire time span. Indicates the time span parameter of the rising branch of the T wave, This represents the time span parameter of the descending branch of the T-wave. This represents the x-coordinate value of a data point in a two-dimensional coordinate system within an electrocardiogram (ECG) signal data sequence. This indicates the absolute value operation. Indicates the first i The starting point of a T wave, Indicates the first i The end point of a T wave, Indicates the first i The peak of a T-wave; The first calculation module is used to calculate the nonlinear dynamic feature matrix of the user's electrocardiogram signal before and after exercise based on the time span parameter, including: inputting the time span parameter before and after the user's exercise into a nonlinear dynamic recognition system based on a radial basis function neural network for recognition, and obtaining the nonlinear dynamic feature matrix of the user's electrocardiogram signal before and after exercise. The specific expression of the nonlinear dynamic recognition system based on radial basis function neural network is as follows: in, express t The nonlinear dynamic characteristic matrix output by the time-invariant dynamic identification system. express t The time span parameter input at any time, B For the gain parameters of the nonlinear dynamic identification system, express t time The derivative of This represents a radial basis function neural network used to identify unknown nonlinear dynamics. The weights of the radial basis function neural network are... For the regression vector of the radial basis function neural network, To calculate the sampling time; The second calculation module is used to calculate the difference matrix between the nonlinear dynamic feature matrix of the user's ECG signal before exercise and the nonlinear dynamic feature matrix of the user's ECG signal after exercise, calculate the average value of all elements in the difference matrix, and use the average value as the topological similarity of the user's ECG signals before and after exercise. The evaluation module is used to evaluate the user's mobility based on the magnitude of the topological similarity.

4. The application of the exercise capacity assessment method based on electrocardiogram signals as described in any one of claims 1 to 2 in the assessment of step test ability, characterized in that, include: Acquire electrocardiogram (ECG) signals of the user before and after the step test; Calculate the nonlinear dynamic characteristic matrix of the electrocardiogram signal before and after the user performs the step test; The topological similarity of the electrocardiogram signals used in the step test was calculated using the aforementioned nonlinear dynamic feature matrix. The user's ability to conduct step experiments is evaluated based on the magnitude of the topological similarity.

Images