A method and device for assessing the risk of sports injury based on electrocardiogram signals

Abstract

The application discloses a motion injury risk assessment method and device based on an electrocardiosignal, and the method comprises the following steps: segmenting the collected electrocardiosignal according to a preset time window to obtain a plurality of to-be-analyzed segments; then extracting corresponding motion risk features from each to-be-analyzed segment, wherein the motion risk features at least include one of a motion load feature, a recovery ability feature, a stability feature, a motion symmetry feature and a historical baseline offset feature; then calculating a motion injury risk score of each to-be-analyzed segment based on each motion risk feature, and performing nonlinear mapping on the motion injury risk score of each to-be-analyzed segment to obtain a corresponding segment motion injury occurrence probability; and finally fusing the segment motion injury occurrence probabilities of each to-be-analyzed segment to obtain a comprehensive motion injury occurrence probability, so that the motion injury risk assessment can be quickly and accurately performed, the feedback real-time performance is improved, and the use threshold is reduced.

Description

Technical Field

[0001] This invention belongs to the field of physiological signal processing technology, specifically relating to a method and device for assessing sports injury risk based on electrocardiogram signals. Background Technology

[0002] Sports injury risk assessment is of great significance for competitive training, physical fitness testing in adolescents, rehabilitation and reintegration, and public sports safety. Current sports injury risk assessment methods generally rely on subjective questionnaires, coaching experience, video motion analysis, and musculoskeletal ultrasound, but these methods suffer from limitations such as insufficient real-time performance and high barriers to entry.

[0003] Therefore, how to quickly and accurately assess the risk of sports injuries is a technical problem that needs to be solved by those skilled in the art. Summary of the Invention

[0004] The purpose of this invention is to solve the technical problems of insufficient real-time performance and high usage threshold in the existing technology for sports injury risk assessment.

[0005] To achieve the above-mentioned technical objectives, on the one hand, the present invention provides a method for assessing the risk of sports injury based on electrocardiogram signals, the method comprising:

[0006] The collected electrocardiogram signals are segmented according to a preset time window to obtain multiple segments to be analyzed;

[0007] Extract corresponding motion risk features from each of the segments to be analyzed. The motion risk features include at least one of the following: motion load features, recovery ability features, stability features, motion symmetry features, and historical baseline offset features.

[0008] Based on the aforementioned motion risk characteristics, calculate the motion injury risk score of the corresponding segment to be analyzed, and perform nonlinear mapping on the motion injury risk score of each segment to be analyzed to obtain the probability of motion injury occurring in the corresponding segment.

[0009] The probability of occurrence of movement injury corresponding to each segment to be analyzed is fused to obtain the comprehensive probability of occurrence of movement injury.

[0010] Furthermore, the sports injury risk score and the probability of sports injury are calculated using the following formula:

[0011] ;

[0012] ;

[0013] In the formula, For sports injury risk scoring, , , , and All are weights. Characteristics of exercise load, As a characteristic of recovery ability, For stability characteristics, It is a feature of motion symmetry. Historical baseline offset characteristics, For bias terms, This represents the probability of sports injuries.

[0014] Furthermore, the stability characteristics include at least one of rhythm dispersion, proportion of abnormal beats, and respiratory rate fluctuations in adjacent time windows.

[0015] Furthermore, the historical baseline offset feature B is specifically determined by the following formula:

[0016] ;

[0017] In the formula, This represents the current baseline feature vector corresponding to the current time detection window. The baseline feature vector is an individual's historical baseline feature vector. Specifically, the baseline feature vector in the current baseline feature vector and the historical baseline feature vector is at least one of the following: resting heart rate, mean heart rate during exercise, heart rate variability index, RR interval statistics, R wave amplitude statistics, QRS wave morphology statistics, and heart rate recovery index after exercise.

[0018] Furthermore, the motion load characteristics Specifically, it is determined using the following formula:

[0019] ;

[0020] In the formula, , and These are the weighting coefficients. Current exercise heart rate, For individual baseline heart rate, To recover from the decrease in heart rate during the recovery phase, The slope of the heart rate rise per unit time.

[0021] Furthermore, the recovery capability characteristic R is specifically determined by the following formula:

[0022] ;

[0023] In the formula, , and These are the weighting coefficients. and As an indicator of heart rate variability, It is the square root of the mean square of the difference between adjacent normal RR intervals during the individual's resting baseline phase. The standard deviation of all normal RR intervals during the individual's resting baseline phase. This is a regression indicator for the R-wave pattern during the recovery phase.

[0024] Furthermore, the motion symmetry feature Specifically, it is determined using the following formula:

[0025] ;

[0026] In the formula, These are the feature statistics corresponding to the motion segment on the left. These are the feature statistics corresponding to the motion segment on the right. To prevent extremely small positive numbers with a denominator of zero, the left and right motion segments are distinguished and determined based on the records during the ECG signal acquisition process. The characteristic statistics include at least one of the following: mean heart rate, peak heart rate, heart rate rise slope, heart rate recovery, heart rate variability index, RR interval statistics, R wave amplitude statistics, and QRS wave morphology statistics.

[0027] Furthermore, the respiratory rate is determined through the following process:

[0028] Respiratory modulation-related features were extracted from each of the segments to be analyzed.

[0029] A respiratory sequence is constructed based on the aforementioned respiratory modulation-related features;

[0030] Based on the respiratory sequence, the main peak frequency is extracted within the target respiratory frequency band;

[0031] The respiratory rate is determined based on the peak frequency.

[0032] Furthermore, after determining the respiratory rate, the method further includes determining the reliability of the respiratory rate using the following formula. :

[0033] ;

[0034] In the formula, , , and These are the weighting coefficients. For R-wave detection quality indicators, As a quality indicator of respiratory sequences, This represents the power spectral density at the main peak frequency. For the target respiratory frequency band, The power spectral density of the respiratory sequence. For frequency integral infinitesimal elements, This serves as a consistency index for results from adjacent time windows.

[0035] On the other hand, the present invention also provides a sports injury risk assessment device based on electrocardiogram signals, the device comprising:

[0036] The segmentation module is used to segment the acquired electrocardiogram signal into multiple segments to be analyzed according to a preset time window;

[0037] The extraction module is used to extract corresponding motion risk features from each of the segments to be analyzed. The motion risk features include at least one of the following: motion load features, recovery ability features, stability features, motion symmetry features, and historical baseline offset features.

[0038] The calculation module is used to calculate the sports injury risk score of the corresponding segment to be analyzed based on each of the sports risk characteristics, and to perform nonlinear mapping on the sports injury risk score of each segment to be analyzed to obtain the probability of sports injury occurrence of the corresponding segment.

[0039] The fusion module is used to fuse the probability of occurrence of motion injury corresponding to each of the segments to be analyzed to obtain the comprehensive probability of occurrence of motion injury.

[0040] This invention provides a method and apparatus for assessing sports injury risk based on electrocardiogram (ECG) signals. Compared with existing technologies, this method first segments the acquired ECG signals into multiple segments to be analyzed according to a preset time window. Then, it extracts corresponding sports risk features from each segment, including at least one of the following: sports load features, recovery ability features, stability features, sports symmetry features, and historical baseline deviation features. Next, it calculates the sports injury risk score for each segment based on the sports risk features, and performs a nonlinear mapping on the sports injury risk scores for each segment to obtain the probability of sports injury occurrence for that segment. Finally, it fuses the probabilities of sports injury occurrence for each segment to obtain a comprehensive probability of sports injury occurrence. This method enables rapid and accurate sports injury risk assessment, improves real-time feedback, and lowers the barrier to entry for users. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 The diagram shown is a flowchart illustrating the sports injury risk assessment method based on electrocardiogram signals provided in the embodiments of this specification.

[0043] Figure 2 The diagram shown is a structural schematic of the sports injury risk assessment device based on electrocardiogram signals provided in the embodiments of this specification. Detailed Implementation

[0044] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0045] like Figure 1 The diagram illustrates a flowchart of a motion injury risk assessment method based on electrocardiogram signals provided in an embodiment of this specification. While this specification provides the method operation steps or device structure shown in the following embodiments or figures, based on conventional methods or without creative effort, the method or device may include more or fewer operation steps or module units after partial merging. In steps or structures where there is no logically necessary causal relationship, the execution order of these steps or the module structure of the device is not limited to the execution order or module structure shown in the embodiments or figures of this specification. When the method or module structure is applied in actual devices, servers, or terminal products, it can be executed sequentially or in parallel according to the method or module structure shown in the embodiments or figures (e.g., in a parallel processor or multi-threaded processing environment, or even in a distributed processing or server cluster implementation environment).

[0046] The exercise injury risk assessment method based on electrocardiogram signals provided in the embodiments of this specification can be applied to terminal devices such as client and server devices, such as... Figure 1 As shown, the method specifically includes the following steps:

[0047] Step S101: The acquired electrocardiogram signal is segmented according to a preset time window to obtain multiple segments to be analyzed.

[0048] Specifically, the system collects electrocardiogram (ECG) signals from users in resting or active states. These ECG signals can be short-term detection signals or long-term continuous monitoring signals. The resting state includes supine, sitting, standing, or non-strenuous daily activities; the active state includes walking, running, cycling, strength training, ball sports training, rehabilitation training, or specific movement training. The short-term detection signal can be an ECG recording segment lasting tens of seconds to several minutes, and the long-term continuous monitoring signal can be a continuous ECG recording covering pre-training, during-training, post-training, or daily activity cycles. Preferably, the ECG signals originate from a single-lead ECG acquisition device, a multi-lead ECG acquisition device, or a chest ECG acquisition device. When using a sliding time window for rhythm segmentation in a belt-type ECG device, wearable patch, smart clothing, or integrated motion monitoring terminal, the preferred time window length is 10 seconds, 20 seconds, 30 seconds, 60 seconds, or other preset lengths. The overlap ratio between windows is preferably set to 25%–90% to balance the spectral resolution of respiratory rate estimation and the temporal continuity of motion injury risk assessment. Furthermore, the rhythm segmentation can adaptively select the window length based on resting and motion states. In the resting state, a relatively long analysis window is preferred to improve the stability of respiratory rate frequency domain estimation, while in the motion state, a relatively short analysis window is preferred to improve the response speed to load changes and risk fluctuations.

[0049] Furthermore, to enhance the contextual interpretation capabilities of subsequent motion risk assessments, the data collection phase can simultaneously record motion state labels, left and right limb labels, preset motion procedures, external motion sensor markers, user input markers, motion frequency labels, load level labels, training phase labels, or individual basic information labels. These can serve as auxiliary inputs for subsequent model adaptation and symmetry analysis. Based on the records, it is also possible to distinguish between left-side and right-side motion segments.

[0050] Before segmenting the electrocardiogram (ECG) signal, preprocessing is performed on the ECG signal. This preprocessing includes at least baseline drift removal, power frequency suppression, bandpass filtering, and abnormal segment removal. Preferably, the original ECG signal is... The baseline drift estimate is The baseline-corrected electrocardiogram signal can then be expressed as:

[0051] ;

[0052] Wherein, the baseline drift estimate This can be achieved through moving median filtering, moving average filtering, polynomial fitting, high-pass filtering, or morphological filtering; after baseline correction, ... Power frequency notch filtering is performed to obtain Then perform bandpass filtering to obtain The passband of the bandpass filter is preferably set to 0.5Hz to 40Hz to retain the ECG rhythm, QRS complex, and main frequency components related to respiratory modulation; the power frequency suppression preferably uses a 50Hz or 60Hz notch filter; further, the criteria for abnormal segment removal include, but are not limited to, at least one of the following: saturation distortion, lead dropout, sudden increase in motion artifacts, abnormal R-wave missed detection rate, abnormal distribution of heartbeat interval, sudden change in signal amplitude, and severe QRS morphological distortion; through the above preprocessing and abnormal segment removal, the cascading effect of noise artifacts and signal distortion on subsequent analysis links can be suppressed before feature extraction and risk estimation.

[0053] Step S102: Extract the corresponding motion risk features from each of the segments to be analyzed. The motion risk features include at least one of the following: motion load features, recovery ability features, stability features, motion symmetry features, and historical baseline offset features.

[0054] In this embodiment, the stability feature includes at least one of rhythm dispersion, abnormal beat proportion, and respiratory rate fluctuation in adjacent time windows, used to reflect whether the rhythm is stable within the current time period; the historical baseline offset feature B is specifically determined by the following formula:

[0055] ;

[0056] In the formula, This represents the current baseline feature vector corresponding to the current time detection window. The baseline feature vector is an individual's historical baseline feature vector. Specifically, the baseline feature vector in the current baseline feature vector and the historical baseline feature vector is at least one of the following: resting heart rate, mean heart rate during exercise, heart rate variability index, RR interval statistics, R wave amplitude statistics, QRS wave morphology statistics, and heart rate recovery index after exercise.

[0057] Exercise load feature L is used to describe information such as the current exercise heart rate level, the rate of heart rate rise, and the rate of heart rate fall during the recovery phase. Specifically, it is determined using the following formula:

[0058] ;

[0059] In the formula, , and These are the weighting coefficients. Current exercise heart rate, For individual baseline heart rate, To recover from the decrease in heart rate during the recovery phase, The slope of the heart rate rise per unit time.

[0060] The recovery capability characteristic R is used to reflect the autonomic nervous system's recovery capability and the ability to revert to its waveform after exercise. The recovery capability characteristic R is specifically determined by the following formula:

[0061] ;

[0062] In the formula, , and These are the weighting coefficients. and As an indicator of heart rate variability, It is the square root of the mean square of the difference between adjacent normal RR intervals during the individual's resting baseline phase. The standard deviation of all normal RR intervals during the individual's resting baseline phase. This is a regression indicator for the R-wave pattern during the recovery phase.

[0063] The motion symmetry feature Specifically, it is determined using the following formula:

[0064] ;

[0065] In the formula, These are the feature statistics corresponding to the motion segment on the left. These are the feature statistics corresponding to the motion segment on the right. To prevent extremely small positive numbers with a denominator of zero.

[0066] This invention can more comprehensively characterize the risk of sports injury than simply using heart rate or a single fatigue indicator.

[0067] Step S103: Calculate the sports injury risk score of the corresponding segment to be analyzed based on each of the sports risk characteristics, and perform nonlinear mapping on the sports injury risk score of each segment to be analyzed to obtain the probability of sports injury occurring in the corresponding segment.

[0068] In this embodiment, the sports injury risk score and the probability of sports injury occurrence are specifically calculated using the following formula:

[0069] ;

[0070] ;

[0071] In the formula, For sports injury risk scoring, , , , and All are weights. Characteristics of exercise load, As a characteristic of recovery ability, For stability characteristics, It is a feature of motion symmetry. Historical baseline offset characteristics, For bias terms, The probability of sports injury is given by, where, The value range is from 0 to 1.

[0072] Step S104: The probability of occurrence of motion injury corresponding to each segment to be analyzed is fused to obtain the comprehensive probability of occurrence of motion injury.

[0073] Specifically, after determining the probability of motion damage occurrence for each segment to be analyzed, a fusion weight can be determined for each segment based on at least one of the following: time sequence, signal quality, motion phase label, and segment risk stability. For example, a higher signal quality will have a higher fusion weight. This application does not impose specific restrictions on the method of determining the fusion weight. Then, the probabilities of motion damage occurrence for multiple segments are weighted and fused based on the fusion weight to obtain the comprehensive probability of motion damage occurrence.

[0074] In this embodiment of the application, the respiratory rate is determined through the following process:

[0075] Respiratory modulation-related features were extracted from each of the segments to be analyzed.

[0076] A respiratory sequence is constructed based on the aforementioned respiratory modulation-related features;

[0077] Based on the respiratory sequence, the main peak frequency is extracted within the target respiratory frequency band;

[0078] The respiratory rate is determined based on the peak frequency.

[0079] Specifically, the respiratory modulation-related features include at least one or more of the following: R-peak amplitude modulation features, QRS area modulation features, and RR interval swing features. R-wave detection is performed on the preprocessed electrocardiogram signal to obtain the first... R peak time and the corresponding R peak amplitude And respiratory modulation-related features are extracted based on the position of the R peak; among which, the R peak amplitude modulation feature sequence is defined as:

[0080] ;

[0081] QRS area modulation features are achieved by pre-setting windows before and after the R peak. The integral of the absolute value of the ECG signal is obtained by the following condition:

[0082] ;

[0083] The characteristic sequence of RR interval swings satisfies:

[0084] ;

[0085] Furthermore, at least one of the above feature sequences is normalized to reduce the impact of differences in dimensions and individuals. The normalized features satisfy the following:

[0086] ;

[0087] in, and These are the mean and standard deviation of the corresponding feature sequences, respectively; then, the normalized discrete cardiac rate feature sequences are resampled into continuous time series using linear interpolation, spline interpolation, or local polynomial interpolation. And construct the ECG-derived respiratory sequence using a weighted fusion method:

[0088] ;

[0089] in, And satisfy:

[0090] ;

[0091] The weights can be preset fixed values, or they can be adaptively updated based on the local stationarity of each feature sequence within the current time window, the significance of the main peak of the spectrum, the noise level, or the consistency with historical outputs, so that the final ECG-derived respiratory sequence has both stability and adaptability.

[0092] The ECG was used to derive the respiratory sequence within a sliding time window. Power spectral density was obtained by performing power spectral analysis. and in the target respiratory band Internal selection of main peak frequency:

[0093] ;

[0094] Further, the respiratory rate was estimated as follows:

[0095] ;

[0096] in, The unit is breaths per minute. In resting-state applications, the target respiratory frequency band is preferably set to... In motion-based applications, the target respiratory frequency band is preferably set to... This is to accommodate the higher respiratory rate range during exercise. In another embodiment, peak detection can also be performed on the ECG-derived respiratory sequence, and the time interval between adjacent respiratory peaks can be used as a basis for analysis. Calculate the time-domain respiratory rate, satisfying:

[0097] ;

[0098] Furthermore, this invention can perform weighted fusion or optimal output of the frequency domain and time domain results based on their consistency, stability, or respective reliability. To suppress the adverse effects of motion artifacts, missed R-waves, and short-term abnormal fluctuations on respiratory rate estimation,

[0099] The reliability of the respiratory rate is determined using the following formula. :

[0100] ;

[0101] In the formula, , , and These are the weighting coefficients. For R-wave detection quality indicators, As a quality indicator of respiratory sequences, This represents the power spectral density at the main peak frequency. For the target respiratory frequency band, The power spectral density of the respiratory sequence. For frequency integral infinitesimal elements, This serves as a consistency index for results from adjacent time windows.

[0102] The reliability of the respiratory rate estimation results is determined by comprehensively considering the quality of R-wave detection, the quality of the ECG-derived respiratory sequence, the significance of the main peak of the spectrum, and the consistency of results from adjacent time windows. For sports injury risk assessment results, the reliability of the risk assessment is obtained by comprehensively considering the input ECG segment quality score, feature integrity score, model output variance, and consistency of results in adjacent time windows. ,in:

[0103] ;

[0104] in, To input the quality score of the electrocardiogram segment, Score the feature completeness. Output the variance for the model. To ensure consistency in risk output between adjacent time windows. For weighting coefficients; when When the risk level is below a preset threshold, the risk level of the corresponding time window is marked as low confidence, and prompts such as retesting, reducing interference, or combining with other information for verification are preferred.

[0105] In some embodiments, to simultaneously consider both rapid response to acute state changes and stable trends in long-term continuous monitoring, the respiratory rate estimation results and sports injury risk assessment results can be fused across multiple time scales, with the fused output Y satisfying:

[0106] ;

[0107] in, , and Output results for short time windows, medium time windows, and long time windows, respectively. And satisfy:

[0108] ;

[0109] By using the multi-timescale fusion, the smoothness and stability of the output under long-term continuous monitoring conditions can be improved while maintaining sensitivity to short-term acute risk changes.

[0110] Based on the above-described method for assessing sports injury risk using electrocardiogram (ECG) signals, one or more embodiments of this specification also provide a platform or terminal for assessing sports injury risk using ECG signals. This platform or terminal may include devices, software, modules, plug-ins, servers, clients, etc., using the methods described in the embodiments of this specification, combined with necessary hardware implementation devices. Based on the same innovative concept, the systems in one or more embodiments provided in this specification are as described in the following embodiments. Since the implementation schemes and methods for solving the system problem are similar, the specific system implementation in the embodiments of this specification can refer to the implementation of the aforementioned methods. Repeated descriptions will not be repeated. The terms "unit" or "module" used below can refer to a combination of software and / or hardware that achieves a predetermined function. Although the systems described in the following embodiments are preferably implemented in software, hardware implementations, and a combination of software and hardware, are also possible and contemplated.

[0111] Specifically, Figure 2 This is a schematic diagram of the module structure of an embodiment of the sports injury risk assessment device based on electrocardiogram signals provided in this specification, as shown below. Figure 2 As shown, the sports injury risk assessment device based on electrocardiogram signals provided in this specification includes:

[0112] The segmentation module 201 is used to segment the acquired electrocardiogram signal into multiple segments to be analyzed according to a preset time window.

[0113] Extraction module 202 is used to extract corresponding motion risk features from each of the segments to be analyzed. The motion risk features include at least one of the following: motion load features, recovery ability features, stability features, motion symmetry features, and historical baseline offset features.

[0114] The calculation module 203 is used to calculate the sports injury risk score of the corresponding segment to be analyzed based on each of the sports risk characteristics, and to perform nonlinear mapping on the sports injury risk score of each segment to be analyzed to obtain the probability of sports injury occurring in the corresponding segment.

[0115] The fusion module 204 is used to fuse the probability of occurrence of motion injury of each segment to be analyzed to obtain the comprehensive probability of occurrence of motion injury.

[0116] It should be noted that the system described above may include other implementation methods based on the description of the corresponding method embodiments. The specific implementation methods can be referred to the description of the corresponding method embodiments above, and will not be elaborated here.

[0117] This application also provides an electronic device, including:

[0118] processor;

[0119] Memory used to store the processor's executable instructions;

[0120] The processor is configured to perform the methods provided in the embodiments described above.

[0121] The electronic device provided in this application stores executable instructions of a processor in a memory. When the processor executes the executable instructions, it can segment the acquired electrocardiogram signal into multiple segments to be analyzed according to a preset time window. Then, it extracts corresponding motion risk features from each segment to be analyzed. The motion risk features include at least one of the following: motion load features, recovery ability features, stability features, motion symmetry features, and historical baseline offset features. Next, it calculates the motion injury risk score of the corresponding segment based on each motion risk feature, and performs a nonlinear mapping on the motion injury risk score of each segment to obtain the probability of motion injury occurrence of the corresponding segment. Finally, it fuses the probability of motion injury occurrence of each segment to obtain a comprehensive probability of motion injury occurrence. This allows for rapid and accurate assessment of motion injury risk, improves real-time feedback, and lowers the barrier to entry.

[0122] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0123] The methods or apparatus described in the embodiments provided in this specification can implement business logic through a computer program and record it on a storage medium. The storage medium can be read and executed by a computer to achieve the effects of the solutions described in the embodiments of this specification, such as:

[0124] The collected electrocardiogram signals are segmented according to a preset time window to obtain multiple segments to be analyzed;

[0125] Extract corresponding motion risk features from each of the segments to be analyzed. The motion risk features include at least one of the following: motion load features, recovery ability features, stability features, motion symmetry features, and historical baseline offset features.

[0126] Based on the aforementioned motion risk characteristics, calculate the motion injury risk score of the corresponding segment to be analyzed, and perform nonlinear mapping on the motion injury risk score of each segment to be analyzed to obtain the probability of motion injury occurring in the corresponding segment.

[0127] The probability of occurrence of movement injury corresponding to each segment to be analyzed is fused to obtain the comprehensive probability of occurrence of movement injury.

[0128] The storage medium can include physical devices for storing information, typically digitizing the information and then storing it using electrical, magnetic, or optical methods. The storage medium can include: devices that store information using electrical energy, such as various types of memory, like RAM and ROM; devices that store information using magnetic energy, such as hard disks, floppy disks, magnetic tapes, magnetic core memory, bubble memory, and USB flash drives; and devices that store information using optical methods, such as CDs or DVDs. Of course, there are other readable storage media, such as quantum memories and graphene memories.

[0129] The embodiments in this specification are not limited to conforming to industry communication standards, standard computer resource data update and data storage rules, or the situations described in one or more embodiments of this specification. Slightly modified implementations based on certain industry standards or custom methods or embodiments can also achieve the same, equivalent, or similar, or predictable, implementation effects as described above. Embodiments that utilize these modified or modified methods for data acquisition, storage, judgment, and processing still fall within the scope of optional implementations of the embodiments in this specification.

[0130] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, ASICs, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0131] The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or plug-ins may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0132] These computer program instructions can also be loaded onto a computer or other programmable resource data updating device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable device for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0133] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, system embodiments are basically similar to method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. In the description of this specification, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this specification. 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 can 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 and the features of different embodiments or examples.

[0134] Those skilled in the art will recognize that the embodiments described herein are intended to help the reader understand the principles of the invention, and should be understood that the scope of protection of the invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific modifications and combinations based on the technical teachings disclosed in this invention without departing from the spirit of the invention, and these modifications and combinations are still within the scope of protection of this invention.

Claims

1. A method for assessing the risk of sports injury based on electrocardiogram signals, characterized in that, The collected electrocardiogram signals are segmented according to a preset time window to obtain multiple segments to be analyzed; Extract corresponding motion risk features from each of the segments to be analyzed. The motion risk features include at least one of the following: motion load features, recovery ability features, stability features, motion symmetry features, and historical baseline offset features. Based on the aforementioned motion risk characteristics, calculate the motion injury risk score of the corresponding segment to be analyzed, and perform nonlinear mapping on the motion injury risk score of each segment to be analyzed to obtain the probability of motion injury occurring in the corresponding segment. The probability of occurrence of movement injury corresponding to each segment to be analyzed is fused to obtain the comprehensive probability of occurrence of movement injury.

2. The method for assessing sports injury risk based on electrocardiogram signals as described in claim 1, characterized in that, The sports injury risk score and the probability of sports injury occurrence are calculated using the following formula: ； ； In the formula, For sports injury risk scoring, , , , and All are weights. As a characteristic of exercise load, As a characteristic of recovery ability, For stability characteristics, It is a feature of motion symmetry. Historical baseline offset characteristics, For bias terms, This represents the probability of sports injuries.

3. The method for assessing sports injury risk based on electrocardiogram signals as described in claim 2, characterized in that, The stability characteristics include at least one of rhythm dispersion, proportion of abnormal beats, and respiratory rate fluctuations in adjacent time windows.

4. The method for assessing sports injury risk based on electrocardiogram signals as described in claim 2, characterized in that, The historical baseline offset feature B is specifically determined by the following formula: ； In the formula, This represents the current baseline feature vector corresponding to the current time detection window. The baseline feature vector is an individual's historical baseline feature vector. Specifically, the baseline feature vector in the current baseline feature vector and the historical baseline feature vector is at least one of the following: resting heart rate, mean heart rate during exercise, heart rate variability index, RR interval statistics, R wave amplitude statistics, QRS wave morphology statistics, and heart rate recovery index after exercise.

5. The method for assessing sports injury risk based on electrocardiogram signals as described in claim 2, characterized in that, The characteristics of the exercise load Specifically, it is determined using the following formula: ； In the formula, , and These are the weighting coefficients. Current exercise heart rate, For individual baseline heart rate, To recover from the decrease in heart rate during the recovery phase, The slope of the heart rate rise per unit time.

6. The method for assessing sports injury risk based on electrocardiogram signals as described in claim 2, characterized in that, The recovery capability characteristic R is specifically determined by the following formula: ； In the formula, , and These are the weighting coefficients. and As an indicator of heart rate variability, It is the square root of the mean square of the difference between adjacent normal RR intervals during the individual's resting baseline phase. The standard deviation of all normal RR intervals during the individual's resting baseline phase. This is a regression indicator for the R-wave pattern during the recovery phase.

7. The method for assessing sports injury risk based on electrocardiogram signals as described in claim 2, characterized in that, The motion symmetry feature Specifically, it is determined using the following formula: ； In the formula, These are the feature statistics corresponding to the motion segment on the left. These are the feature statistics corresponding to the motion segment on the right. To prevent extremely small positive numbers with a denominator of zero, the left and right motion segments are distinguished and determined based on the records during the ECG signal acquisition process. The characteristic statistics include at least one of the following: mean heart rate, peak heart rate, heart rate rise slope, heart rate recovery, heart rate variability index, RR interval statistics, R wave amplitude statistics, and QRS wave morphology statistics.

8. The method for assessing sports injury risk based on electrocardiogram signals as described in claim 3, characterized in that, The respiratory rate is determined through the following process: Respiratory modulation-related features were extracted from each of the segments to be analyzed. A respiratory sequence is constructed based on the aforementioned respiratory modulation-related features; Based on the respiratory sequence, the main peak frequency is extracted within the target respiratory frequency band; The respiratory rate is determined based on the peak frequency.

9. The method for assessing sports injury risk based on electrocardiogram signals as described in claim 8, characterized in that, After determining the respiratory rate, the method further includes determining the reliability of the respiratory rate using the following formula. : ； In the formula, , , and These are the weighting coefficients. For R-wave detection quality indicators, As a quality indicator of respiratory sequences, This represents the power spectral density at the main peak frequency. Target respiratory frequency band, The power spectral density of the respiratory sequence. For frequency integral infinitesimal elements, This serves as a consistency index for results from adjacent time windows.

10. A sports injury risk assessment device based on electrocardiogram signals, characterized in that, The device includes: The segmentation module is used to segment the acquired electrocardiogram signal into multiple segments to be analyzed according to a preset time window; The extraction module is used to extract corresponding motion risk features from each of the segments to be analyzed. The motion risk features include at least one of the following: motion load features, recovery ability features, stability features, motion symmetry features, and historical baseline offset features. The calculation module is used to calculate the sports injury risk score of the corresponding segment to be analyzed based on each of the sports risk characteristics, and to perform nonlinear mapping on the sports injury risk score of each segment to be analyzed to obtain the probability of sports injury occurrence of the corresponding segment. The fusion module is used to fuse the probability of occurrence of motion injury corresponding to each of the segments to be analyzed to obtain the comprehensive probability of occurrence of motion injury.

Images