CN-122006109-A - Method, apparatus and storage medium for adjusting muscular electric signal for dynamic load distribution

CN122006109ACN 122006109 ACN122006109 ACN 122006109ACN-122006109-A

Abstract

The application provides a method, equipment and a storage medium for adjusting muscular electric signals for dynamic load distribution, wherein the method comprises the following steps of obtaining individual physiological parameters of a target object; the method comprises the steps of determining neuromuscular activation target parameters corresponding to a target training mode, generating initial load distribution signals based on the individual physiological parameters, collecting myoelectric signals of a target object in real time, extracting real-time myoelectric signal characteristic values, comparing the real-time myoelectric signal characteristic values with the neuromuscular activation target parameters, and generating first dynamic adjustment signals when the first training mode is executed and the real-time myoelectric signal characteristic values deviate from the target parameters by more than a first preset threshold value. The training scheme is in accordance with individual characteristics of a trainer at the beginning stage, solves the problems of single training mode and lack of cooperative control, ensures the training effect and simultaneously avoids overload so as to realize the balance of the training effect and the safety.

Inventors

HONG XUBIN
HONG ZICHENG
WU GANGCHUAN

Assignees

深圳爱倍力健康科技有限公司

Dates

Publication Date: 20260512
Application Date: 20260309

Claims (10)

1. A method for adjusting electrical muscle signals for dynamic load distribution, comprising: Acquiring an individualized physiological parameter of a target object, wherein the individualized physiological parameter at least comprises a training period, a relative maximum force value based on weight and an electromyographic signal baseline characteristic value; determining neuromuscular activation target parameters corresponding to the target training modes; generating an initial load distribution signal based on the individual physiological parameters, wherein the initial load distribution signal is used for indicating the time distribution ratio between a first type training mode and a second type training mode, the first type training mode is a training mode taking the neuromuscular activation target parameter as a control target, and the second type training mode is a training mode taking an external load parameter as the control target; Collecting electromyographic signals of a target object in real time, and extracting characteristic values of the real-time electromyographic signals; Comparing the real-time electromyographic signal characteristic value with the neuromuscular activation target parameter, and generating a first dynamic adjustment signal when the first training mode is executed and the real-time electromyographic signal characteristic value deviates from the target parameter by more than a first preset threshold.
2. The method of claim 1, wherein generating an initial load distribution signal based on the personalized physiological parameter comprises: When the training period is below a period threshold, the weight-based relative maximum effort value is below an effort threshold, and the electromyographic signal baseline characteristic value is below a baseline threshold, the proportion of time allocated to the first type of training mode is higher than the proportion of time allocated to the second type of training mode.
3. The method of claim 1, wherein the first type of training pattern comprises at least a first sub-pattern and a second sub-pattern, wherein the neuromuscular activation target parameter corresponding to the first sub-pattern is a first target parameter set comprising a first amplitude threshold range and a first frequency threshold range, wherein the neuromuscular activation target parameter corresponding to the second sub-pattern is a second target parameter set comprising a second amplitude threshold range and a second frequency threshold range, and wherein a lower limit of the first frequency threshold range is higher than a lower limit of the second frequency threshold range.
4. The method of claim 3, wherein the real-time electromyographic signal characteristic values comprise a real-time root mean square amplitude value and a real-time median frequency value, and wherein comparing the real-time electromyographic signal characteristic values to the neuromuscular activation target parameters comprises: Determining, while executing the first sub-mode, whether the real-time median frequency value is below a lower limit of the first frequency threshold range; while executing the second sub-mode, determining whether the real-time median frequency value is below a lower limit of the second frequency threshold range.
5. The method of claim 4, wherein the first dynamic adjustment signal is specifically configured to trigger a switch from the first sub-mode to the second sub-mode when the real-time median frequency value is detected to be continuously below the lower limit of the first frequency threshold range for more than a first duration during execution of the first sub-mode, and to trigger a switch from the first type of training mode to the second type of training mode when the second sub-mode is executed for more than a second duration and the real-time median frequency value is detected to be not yet reached to the lower limit of the first frequency threshold range.
6. The method of claim 5, wherein the first dynamic adjustment signal is further for: And triggering to increase the time distribution proportion of the second training mode when the real-time root mean square amplitude value is detected to be lower than the lower limit of the amplitude threshold range corresponding to the current sub-mode and exceeds the amplitude deviation threshold value during the execution of the first sub-mode or the second sub-mode.
7. The method of claim 6, further comprising, after said comparing the real-time electromyographic signal characteristic value to a neuromuscular activation target parameter: Monitoring the descending rate of the real-time median frequency value in a preset time window; When the descending speed exceeds the frequency descending threshold, judging that the target object enters a fatigue state, and generating a second dynamic adjustment signal, wherein the second dynamic adjustment signal is used for updating the initial load distribution signal, and the updating of the initial load distribution signal comprises at least one of increasing the time distribution proportion of the second training mode, reducing the neuromuscular activation target parameter threshold of each sub-mode in the first training mode, triggering suspension training and outputting a rest prompt.
8. A muscular-electrical-signal-conditioning device for dynamic distribution of load, characterized by comprising: the acquisition module is used for acquiring the personalized physiological parameters of the target object, wherein the personalized physiological parameters at least comprise training years and electromyographic signal baseline characteristic values; The determining module is used for determining neuromuscular activation target parameters corresponding to the target training modes; The system comprises a generation module, a control module and a control module, wherein the generation module is used for generating an initial load distribution signal based on the individuation physiological parameter, wherein the initial load distribution signal is used for indicating the time distribution ratio between a first type training mode and a second type training mode; The extraction module is used for collecting the electromyographic signals of the target object in real time and extracting the characteristic values of the real-time electromyographic signals; And the comparison module is used for comparing the real-time electromyographic signal characteristic value with the neuromuscular activation target parameter, and generating a first dynamic adjustment signal when the first training mode is executed and the real-time electromyographic signal characteristic value deviates from the target parameter by more than a first preset threshold value.
9. An electronic device, comprising: a memory and a processing module; the memory is used for storing a computer program; The processing module is configured to execute the computer program and implement the steps of the method for adjusting muscular electric signals for dynamic load distribution according to any one of claims 1 to 7 when the computer program is executed.
10. A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program; The computer program, when executed by one or more processing modules, causes the one or more processing modules to perform the steps of the method for adjusting muscular-electrical signals for dynamic load distribution as recited in any one of claims 1 to 7.

Description

Method, apparatus and storage medium for adjusting muscular electric signal for dynamic load distribution Technical Field The invention relates to the technical field of bioelectric signal processing and rehabilitation training, in particular to a method, equipment and a storage medium for adjusting muscle electric signals for dynamic load distribution. Background The surface electromyographic signals (surface Electromyography, sEMG) are bioelectric signals generated during muscle contraction, and can be collected noninvasively by placing electrodes on the surface of the skin, so that the activation degree and the functional state of the muscle can be reflected in real time. As sEMG signals have the advantages of noninvasive, real-time, objective and the like, the sEMG signals are widely applied to the fields of clinical rehabilitation evaluation, sports science, man-machine interaction and the like. In the field of neuromuscular rehabilitation training, how to dynamically adjust the training load according to individual differences and real-time states of patients is a core problem of concern to those skilled in the art. In the prior art, a muscle electrical stimulation system generally adopts an electrical stimulation mode with fixed parameters, for example, the existing method for identifying multiple actions based on a single myoelectric sensor realizes action identification through threshold judgment, but only can identify limited action types, and training load cannot be dynamically adjusted according to muscle states. Or the electrical stimulation parameters are adaptively adjusted according to the muscle contraction signals, but the adjustment strategy is mainly based on simple threshold comparison of the signal amplitude, and the dynamic allocation of the training mode level is lacked. Therefore, how to perform initial load distribution according to the individual physiological parameters and to dynamically adjust the cooperative control method among multiple training modes according to real-time electromyographic signal feedback so as to realize the optimal balance of training effect and safety is a technical problem to be solved. Disclosure of Invention In view of the above, the embodiments of the present application provide a method, an apparatus, and a storage medium for dynamically distributing a muscular signal, which reasonably distributes a time ratio between a first training mode targeting neuromuscular activation and a second training mode targeting external load parameters according to individual physiological parameters (training years, myoelectric baseline characteristics, etc.) of a trainer, and dynamically adjusts the training mode distribution according to real-time myoelectric signal feedback during training, and intelligently switches from a high-demand activation mode to a low-demand load mode when the muscle activation capability is reduced, thereby avoiding excessive muscle fatigue while ensuring the training effect, and achieving an optimal balance of the training effect and safety. In a first aspect, an embodiment of the present application provides a method for adjusting an electrical muscle signal for dynamic load distribution, including: acquiring an individualized physiological parameter of a target object, wherein the individualized physiological parameter at least comprises a training age and an electromyographic signal baseline characteristic value; determining neuromuscular activation target parameters corresponding to the target training modes; generating an initial load distribution signal based on the individual physiological parameters, wherein the initial load distribution signal is used for indicating the time distribution ratio between a first type training mode and a second type training mode, the first type training mode is a training mode taking the neuromuscular activation target parameter as a control target, and the second type training mode is a training mode taking an external load parameter as the control target; Collecting electromyographic signals of a target object in real time, and extracting characteristic values of the real-time electromyographic signals; Comparing the real-time electromyographic signal characteristic value with the neuromuscular activation target parameter, and generating a first dynamic adjustment signal when the first training mode is executed and the real-time electromyographic signal characteristic value deviates from the target parameter by more than a first preset threshold. In an embodiment, the generating an initial load distribution signal based on the personalized physiological parameter comprises: When the training period is below a period threshold, the weight-based relative maximum effort value is below an effort threshold, and the electromyographic signal baseline characteristic value is below a baseline threshold, the proportion of time allocated to the first type of training mode is higher than the proportion of