WO2018214524A1 - 一种运动训练预警方法及装置 - Google Patents

一种运动训练预警方法及装置 Download PDF

Info

Publication number
WO2018214524A1
WO2018214524A1 PCT/CN2018/072325 CN2018072325W WO2018214524A1 WO 2018214524 A1 WO2018214524 A1 WO 2018214524A1 CN 2018072325 W CN2018072325 W CN 2018072325W WO 2018214524 A1 WO2018214524 A1 WO 2018214524A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
user
fatigue
motion
myoelectric
Prior art date
Application number
PCT/CN2018/072325
Other languages
English (en)
French (fr)
Inventor
包磊
Original Assignee
深圳市未来健身科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市未来健身科技有限公司 filed Critical 深圳市未来健身科技有限公司
Publication of WO2018214524A1 publication Critical patent/WO2018214524A1/zh

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/389—Electromyography [EMG]
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
    • A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
    • A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
    • A63B2230/00—Measuring physiological parameters of the user
    • A63B2230/60—Measuring physiological parameters of the user muscle strain, i.e. measured on the user

Definitions

  • the invention belongs to the technical field of wearable devices, and in particular relates to a sports training early warning method and device.
  • Muscles can cause functional decline when working repeatedly. This phenomenon is muscle fatigue. Athletes may experience muscle fatigue during exercise training. As far as the whole body is concerned, most of the fatigue belongs to fatigue, that is, the fatigue that the human body can perceive. When the muscle fatigue exceeds a certain level, the human body may have muscles. The situation of injury. For athletes' sports training, it is necessary to adjust the exercise training plan as much as possible before the muscle injury occurs, such as stopping the exercise training to avoid muscle damage affecting the training game and affecting the athlete's body.
  • the embodiment of the present invention provides an exercise training early warning method and apparatus to solve the problem that an effective early warning of muscle fatigue cannot be achieved in the prior art.
  • a first aspect of the embodiments of the present invention provides an exercise training early warning method, including:
  • the electromyography data is introduced into the fatigue prediction model to generate a fatigue prediction report, and the fatigue prediction report includes the prediction that the user reaches the muscle fatigue state Time required.
  • a second aspect of the embodiments of the present invention provides an exercise training early warning device, including:
  • a determining module configured to calculate a fatigue index of the user according to the myoelectric data, and determine, according to the fatigue index, whether the user is in a muscle fatigue state;
  • a warning module configured to output a warning signal when the judgment result is that the user is in the muscle fatigue state
  • a prediction module configured to: when the determination result is that the user is not in the muscle fatigue state, import the myoelectric data into a fatigue prediction model, and generate a fatigue prediction report, where the fatigue prediction report includes the user reaching the The time required to predict muscle fatigue status.
  • the embodiment of the present invention has the beneficial effects that after the wearable device collects the user's myoelectric data, it monitors whether the user has muscle fatigue based on the collected myoelectric data, and issues a corresponding fatigue warning, so that Users can know in real time whether they are in a state of muscle fatigue.
  • the user When the user is in a state of non-muscle fatigue, the user will also be fatigue predicted, and a corresponding fatigue prediction report will be generated to inform the user of the time required to reach the muscle fatigue state, and the athlete can be prevented from occurring due to muscle fatigue in a timely and effective manner. In the case of muscle damage, an effective warning of muscle fatigue is achieved.
  • Embodiment 1 is a flowchart of implementing an exercise training early warning method according to Embodiment 1 of the present invention
  • FIG. 2 is a flowchart of implementing an exercise training early warning method according to Embodiment 2 of the present invention
  • Embodiment 3 is a flowchart of implementing an exercise training early warning method according to Embodiment 3 of the present invention.
  • FIG. 5 is a flowchart of a specific implementation of S104 according to Embodiment 5 of the present invention.
  • FIG. 6 is a flowchart of a specific implementation of S104 according to Embodiment 6 of the present invention.
  • FIG. 7 is a structural block diagram of an exercise training early warning apparatus according to Embodiment 7 of the present invention.
  • the wearable device may be a wearable smart fitness garment, or may be a collection of one or more collection modules that are wearable and attachable.
  • the wearable device when the wearable device is a wearable smart fitness garment, it may be a garment or pants made of a flexible fabric, and a plurality of collection modules are embedded on the side of the flexible fabric close to the human skin. Each collection module is fixed at different points of the smart fitness garment so that after the user wears the smart fitness garment, each collection module can be attached to each muscle of the user's body.
  • at least one control module is also embedded, and each of the acquisition modules is separately connected to the control module. In the prior art, generally only one control module is used to implement control of the acquisition module.
  • a wire and a circuit board may be disposed in the wearable device, wherein the circuit board is used to fix various communication buses and the acquisition module.
  • the circuit board and its various solder joints are wrapped with a waterproof glue.
  • the wearable device can be washed by fixing a waterproof trace on the laundry.
  • each acquisition module may include only an acquisition electrode having a somatosensory sensor function, or an integrated circuit having an acquisition function.
  • the above collection electrodes include, but are not limited to, fabric electrodes, rubber electrodes, gel electrodes, and the like.
  • each acquisition module is an integrated circuit having an acquisition function and a wireless transmission function, and the integrated circuit includes the above-mentioned acquisition electrode having a somatosensory sensor function.
  • the EMG signal collected by the acquisition module is transmitted to the remote control module through the wireless network, and the control module is located in the remote terminal device or the remote control box used in conjunction with the acquisition module.
  • FIG. 1 is a flowchart showing an implementation process of an exercise training early warning method according to Embodiment 1 of the present invention, which is described in detail as follows:
  • S101 Control an acquisition module in the wearable device to collect the user's myoelectric data.
  • the required electromyography data refers to the myoelectric data used when performing fatigue monitoring on the user's exercise training. Because the muscles of different sports are mainly different, such as football, the main use of leg muscles, while basketball requires the use of muscles throughout the body, therefore, for different sports, muscle parts that may have muscle fatigue Differently, the myoelectric data required to be collected is also different.
  • the required electromyographic data can be specifically set by the user according to the actual sports item. For example, when the sport is football, the muscle data of the user's leg muscles can be set to the electromyography data used for the collection.
  • the wearable device After the user activates the wearable device, the user needs to select and set the myoelectric data. After receiving the electromyography data and the setting completion command set by the user, the wearable device activates the corresponding acquisition module to start collecting and recording the user's myoelectric data. If the user does not set the EMG data within the preset time after the user activates the wearable device (such as five minutes), the user's last EMG data setting is extended by default, if the wearable device is activated for the first time or the last time If the EMG data is set to data loss, all acquisition modules are activated by default for EMG data acquisition.
  • the technician can perform muscle group division on the muscles of the human body in advance, and provide a human-computer interaction interface for the user to select and set the myoelectric data, and the user only needs to select the exercise.
  • the muscle group that wants to perform muscle fatigue warning during training can set this muscle group as the target of myoelectric data collection.
  • the human muscles are simply divided into leg muscles, chest muscles, back muscles, abdominal muscles, shoulder muscles, and hand muscles. When the user is playing football, the leg muscles can be directly selected. Set as the EMG data acquisition object.
  • the technician in order to facilitate the user's use, can pre-set a plurality of different sports modes, such as a soccer sport mode, a basketball sport mode, a soldier ball sport mode, etc., and for each different The exercise mode sets the corresponding muscle group, and the corresponding muscle group is the electromyography data acquisition object corresponding to the exercise mode. At this time, the user only needs to select the corresponding exercise mode after activating the wearable device. .
  • a soccer sport mode such as a soccer sport mode, a basketball sport mode, a soldier ball sport mode, etc.
  • all collected myoelectric data and corresponding timestamp data are stored together.
  • S102 Processing the myoelectric data to determine whether the user is in a state of muscle fatigue.
  • the muscle fatigue state can be determined by the myoelectric signal linear analysis technique, the myoelectric signal frequency analysis technique, the complex covariance function fatigue estimation method, etc., and the method for determining the muscle fatigue state is not the invention of the present invention. Therefore, it is not limited herein.
  • Non-sensing fatigue the human body can not perceive or perceive weak, and often does not attract people's attention. If it is fatigued for a long time, it will cause damage to the muscles of the human body. For the feeling of fatigue, although the human body can perceive it, for some special people, such as athletes, when exercising, their attention will be highly concentrated on the training itself, even if it occurs and muscle fatigue is felt, often It will be ignored unconsciously until the muscles are damaged and painful.
  • a warning signal of muscle fatigue is output to remind the user to pay attention to rest.
  • the warning prompt may be combined with the prompting module in the wearable device (such as using a voice prompting module to output a voice warning, or using a vibration prompting module to perform a vibration warning), or outputting a warning signal to other devices. Warning notice.
  • the myoelectric data is introduced into the fatigue prediction model to generate a fatigue prediction report, and the fatigue prediction report includes a time required for the user to reach the predicted state of the muscle fatigue state.
  • the muscle fatigue state of the user is predicted based on the collected myoelectric data, and
  • the fatigue prediction report contains the time required for the user to predict muscle fatigue if they continue to exercise. Users can schedule their own exercise training programs based on the predicted time to prevent muscle fatigue and even muscle damage.
  • the average power fatigue MPF and/or the median frequency MF of the myoelectric data are generally used to characterize the degree of muscle fatigue.
  • the MPF and/or MF reach a certain threshold, it is determined that the muscle is fatigued, but When the muscles are in a state of motion, the stability of both MPF and MF is greatly affected. Therefore, the judgment of muscle fatigue in muscle exercise is not suitable for MPF or MF.
  • the cohen frequency-distribution technique has time and frequency shift invariance, the correlation between the median frequency IMDF and the mean frequency IMNF and muscle fatigue is relatively stable even during muscle exercise, so IMDF and IMNF can be used for muscle exercise. Fatigue monitoring.
  • the median frequency IMDF and the average frequency IMNF in the cohen-like time-frequency distribution technique are used to characterize the degree of muscle fatigue.
  • f is the frequency of the myoelectric data
  • S(t, f) is the time-frequency spectrum, which is calculated by the cohen-like time-frequency distribution technique.
  • IMDF and IMNF for curve fitting. It shows its dynamic trend with muscle movement.
  • any algorithm that fits the IMDF and IMNF change trend graph or the change trend function formula can be used for curve fitting, for example, a common least squares method can be used for curve fitting.
  • an IMDF threshold and an IMNF threshold of fatigue level are first set, that is, when the IMDF and IMNF values reach corresponding thresholds, it is determined that the user's muscles are fatigued.
  • the EMG data is substituted into the formula (1) and formula (2), and the real-time IMDF and IMNF values are obtained, and the combined trend trends of IMDF and IMNF are obtained.
  • change the trend function formula calculate the remaining time T IMDF and T IMNF of the IMDF and IMNF values to reach the set threshold, and calculate the time function formula of the final time required to reach the muscle fatigue prediction T residual according to T IMDF and T IMNF as follows:
  • T residual 0.4 ⁇ T IMDF +0.6T IMNF (3)
  • ⁇ is a weighting coefficient
  • the specific selection is made according to the characteristics of the user's gender, age, disease history, etc.
  • the ⁇ requirement is in the range of ⁇ (1, 1.35).
  • the method further includes:
  • the technicians pre-store a plurality of sports items (such as long-distance running, sprinting, long jump, etc.) and a set of standard actions corresponding to each sports item to the storage module for subsequent comparison.
  • a sports item such as long-distance running, sprinting, long jump, etc.
  • standard actions corresponding to each sports item to the storage module for subsequent comparison.
  • S202 Identify the motion motion of the user according to the electromyography data, and compare the motion motion with the standard motion to obtain motion comparison data.
  • the support vector machine algorithm After acquiring the myoelectric data of the user in S101, identifying the motion motion of the user according to the acquired myoelectric data, in the second embodiment of the present invention, specifically, the support vector machine algorithm, the linear regression analysis algorithm, and the myoelectric data sample may be used.
  • the entropy motion recognition method and the like recognize the user's motion motion.
  • the user's motion action is compared with the read standard action to determine the problem existing in each action of the user, the motion posture error, and the analyzed data is taken as an action. Compare the data for subsequent analysis.
  • the trend analysis of the electromyogram data of a series of actions of the user running is performed, and according to the electromyographic data. Change the trend to perform motion recognition processing, and then compare the obtained motion recognition result with the standard motion to obtain the difference between the actual running motion and the standard motion of the user. For example, when the running is recognized, the user's leg is too much compared with the standard motion. lift.
  • the action guidance data is used to guide the user how to correct the problems in the above sports comparison data, and propose correct exercise suggestions to prevent muscle fatigue or muscle damage.
  • the thigh and the knee should be forced forward
  • the corresponding action guidance data will be output to warn the user that the leg can not be lifted during running, and should be forced forward.
  • the user may be selected to guide the user in the form of voice, and the user may be guided in the form of video.
  • the actual output form should be selected according to the actual situation to meet the actual needs of the user.
  • the user by recognizing the user's motion motion and comparing with the pre-stored standard motion, the user is guided by standard motions, so that the user can correct his or her motion posture in time and avoid the motion posture caused by the wrong motion motion. Muscle fatigue and even muscle damage.
  • the method further includes:
  • S105 Importing the myoelectric data into the exercise evaluation model to generate a motion evaluation report, where the exercise evaluation report includes exercise data, exercise adjustment suggestions, or recommended recipes of the exercise training.
  • the sports assessment report is used to help users understand the specific sports data of the sports training, and provides adjustment suggestions for the users for the lack of sports training, and provides users with a scientific and healthy sports recipe.
  • the user's current exercise training is evaluated based on the collected myoelectric data, and corresponding Sports assessment report.
  • the exercise assessment report includes sports data, sports recommendations and recommended recipes.
  • the exercise data includes the exercise amount of each muscle group in this exercise, the change information of the myoelectric data intensity, and the error action data in this exercise.
  • the user can use the exercise data to understand the specific situation of the exercise training.
  • the exercise recommendations mainly include exercise recommendation data that should be strengthened or should be weakened for the next exercise of the muscle group, exercise guidance data generated for the wrong action data appearing in the exercise, and some exercise skill suggestions.
  • the recommended recipe is a sports recipe recommended for the user for this sports training, providing users with a scientific and healthy sports recipe.
  • the myoelectric data of each muscle group to be measured is analyzed in the stored myoelectric data, and the myoelectric data according to the movement of each muscle group is performed. Intensity, determine the amount of exercise in the exercise training, and compare and analyze each action in the exercise training according to the pre-stored standard action, and record the wrong action data such as the wrong action and the number of errors.
  • the motion suggestion is to analyze the motion data after the motion data is generated, and to obtain the data according to the deficiencies, for example, the motion data shows that the amount of exercise of each muscle group of the user is too large, that is, the user exercise training Excessive, at this time, the sports suggestion will remind the user to reduce the intensity of exercise training.
  • the recommended recipes in the exercise evaluation report need to be generated by synthesizing the user's EMG data, the corresponding time stamp of the EMG data, and personal data.
  • the technician presets a sports diet table, and the corresponding relationship between the user's exercise amount, exercise time, personal data and food type is set in the sports diet recipe table, such as a large amount of exercise and exercise time. For more than an hour, users should add some sugary drinks and some sugary foods. For those who are thin, they should also add some protein-rich foods.
  • the specific time of the user is determined by the corresponding time stamp of the myoelectric data, and the corresponding recommended food is selected according to the sports diet recipe table.
  • the result is a sports recipe that is suitable for the user's exercise.
  • the user's personal data is also read, and the final motion recommendation is generated by combining the user's personal information.
  • the user's muscle training data is collected to evaluate the user's exercise training, and corresponding motion data and motion suggestions are given, so that the user can better understand the effect of the exercise training.
  • the user can make targeted improvements in the next exercise training, and ensure the safety of his muscles while avoiding muscle fatigue or muscle damage.
  • the method includes:
  • the physical fitness information refers to the physical fitness information of the human body such as the endurance level ⁇ and the restoring power level ⁇ of the user.
  • the physical quality information it is necessary to preliminarily evaluate the physical fitness of the human body such as endurance and restoring power of the user, and introduce the rated endurance level ⁇ and the restoring force level ⁇ into the wearable device for storage.
  • the endurance level ⁇ and the restoring force level ⁇ are added to the final T residual calculation formula, and the specific formula is as follows:
  • ⁇ is the average of the sum of the highest endurance level ⁇ max and the highest resilience level ⁇ max , ie:
  • obtaining the physical quality information of the user can not only improve the calculation of T residual , but also can be based on the resilience level ⁇ . And the user's gender age and other information to provide users with rest suggestions, and feedback to the user through the fatigue prediction report.
  • the time T residual required for the final muscle fatigue is corrected by comprehensively considering the user's physical quality information, thereby improving the accuracy of the T residual and providing the user with the user's own convenience. The rest of the situation is recommended.
  • S104 includes:
  • S501 Obtain a sample selection instruction, and select an EMG data sample from the EMG data or the preset EMG data sample library according to the sample selection instruction.
  • the myoelectric data samples are divided into two categories: the first type, the pre-existing myoelectric data samples, and the electromyographic data of the exercise recorded by the user wearing the wearable device in advance, such as the user training in normal exercise. Before, wearing a wearable device, a long-distance running training was carried out, and the collected actual myoelectric data was saved as a sample of the long-distance running muscle data.
  • the second type of real-time EMG data sample refers to the real-time EMG data of the exercise training when the user is in the state of exercise training, such as the user performing running training while wearing the wearable device, and has ran for 5 minutes. At this time, the 5 minute EMG data recorded in this running training is called the real-time EMG data sample.
  • the first type of preset EMG data samples will be pre-stored in the EMG data sample library for recall.
  • the first type of preset EMG data can be selected to be called, so that users can more flexibly arrange their own exercise training, such as fatigue prediction by selecting preset EMG data, for the sprint with greater exercise intensity per unit time.
  • Sprint the user may experience muscle fatigue in a very short period of time, but for long-distance running with less exercise intensity per unit time, the user may not experience muscle fatigue for a long period of time, at this time the user may selectively Carry out long-distance running training for a period of time, while continuing to exercise training while protecting yourself from muscle fatigue.
  • the user when performing muscle fatigue prediction, the user needs to select a corresponding type of myoelectric data sample according to his actual situation, and input a corresponding sample selection instruction.
  • the IMDF and IMNF change trend graph or the change trend function formula are fitted according to the EMG data sample, and the user's IMDF and IMNF are calculated according to the collected EMG data, and the obtained result is obtained.
  • the change trend graph or the change trend function formula calculates the user's IMDF and IMNF, and finally calculates the final predicted time T residual according to formula (3).
  • EMG data samples for the actual needs of different users, two types of EMG data samples are selected, and different EMG data samples are predicted by different scenarios, which greatly improves the accuracy of muscle fatigue prediction.
  • S104 includes:
  • the collected myoelectric data is classified according to the muscle group to which the corresponding muscle belongs.
  • the muscle strength of the leg muscles is much stronger than other muscle groups. Therefore, the muscles of the leg muscles tend to be fatigued for a long time. Shorter than other muscle groups. If all the acquired EMG data is used as the predicted data, even if the muscles of the leg muscles have begun to appear, it may be affected by the muscle data of other muscle groups, resulting in fatigue judgment and fatigue prediction of the leg muscles. Not accurate enough.
  • the electromyography data is classified according to different muscle groups. Fatigue prediction was performed separately for each muscle group.
  • S602 Introduce the electromyography data corresponding to different muscle groups into the fatigue prediction model, and generate a corresponding fatigue prediction report.
  • the user can accurately grasp the fatigue condition of each muscle group in real time, so that the early warning of muscle fatigue becomes more accurate and effective.
  • the user by monitoring whether the user is in muscle fatigue in real time, the user is subjected to fatigue warning, so that the user can detect his or her muscle fatigue state in time.
  • the user's muscle electrical data is used to predict the muscle fatigue of the user, so that the user can effectively warn the user for a period of time before the fatigue occurs, and combine the user's physical quality information and select different EMG data samples.
  • the accuracy of predicting muscle fatigue is greatly guaranteed.
  • the user can also accurately grasp the muscle fatigue of each muscle group and know the early warning of muscle group muscle fatigue.
  • FIG. 7 is a structural block diagram of the exercise training early warning device provided in Embodiment 7 of the present invention. For the convenience of description, only parts related to the embodiment of the present invention are shown.
  • the exercise training early warning device includes:
  • the acquisition module 71 is configured to collect the myoelectric data of the user.
  • the determining module 72 is configured to process the myoelectric data to determine whether the user is in a state of muscle fatigue.
  • the warning module 73 is configured to output a warning signal when the judgment result is that the user is in a muscle fatigue state.
  • the prediction module 74 is configured to: when the determination result is that the user is not in a muscle fatigue state, import the myoelectric data into the fatigue prediction model to generate a fatigue prediction report, where the fatigue prediction report includes a time required for the user to reach a predicted state of muscle fatigue.
  • the exercise training early warning device further includes:
  • the identification module is configured to identify the current sport item and read the standard action corresponding to the sport item.
  • the comparison module is configured to identify the user's motion motion based on the myoelectric data, and compare the motion motion with the standard motion to obtain motion comparison data.
  • a guidance module for outputting action guidance data based on the action comparison data.
  • the exercise training early warning device further includes:
  • the exercise evaluation module is used for introducing the electromyography data into the exercise evaluation model to generate a motion evaluation report, and the exercise evaluation report includes exercise data, exercise adjustment suggestions or recommended recipes of the exercise training.
  • the prediction module 74 includes:
  • a data acquisition sub-module for obtaining physical fitness information of the user is a data acquisition sub-module for obtaining physical fitness information of the user.
  • the first prediction sub-module is configured to introduce personal data and myoelectric data into the fatigue prediction model to generate a fatigue prediction report.
  • the prediction module 74 includes:
  • the instruction acquisition sub-module is configured to acquire a sample selection instruction, and select a myoelectric data sample from the myoelectric data or the preset electromyographic data sample library according to the sample selection instruction.
  • the second prediction sub-module is configured to introduce the myoelectric data and the myoelectric data sample into the fatigue prediction model to generate a fatigue prediction report.
  • each functional unit and module in the above system may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit, and the integrated unit may be hardware.
  • Formal implementation can also be implemented in the form of software functional units.
  • the specific names of the respective functional units and modules are only for the purpose of facilitating mutual differentiation, and are not intended to limit the scope of protection of the present application.
  • the disclosed apparatus and method may be implemented in other manners.
  • the system embodiment described above is merely illustrative.
  • the division of the module or unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be used. Combinations can be integrated into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in electrical, mechanical or other form.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
  • the medium includes a plurality of instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor to perform all or part of the steps of the methods described in various embodiments of the embodiments of the present invention.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Medical Informatics (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Engineering & Computer Science (AREA)
  • Physical Education & Sports Medicine (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Physics & Mathematics (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

一种运动训练预警方法，包括：控制可穿戴装置中的采集模块采集用户的肌电数据；对肌电数据进行处理判断用户是否处于肌肉疲劳状态；当判断结果为用户处于肌肉疲劳状态时，输出警告信号；当判断结果为用户未处于肌肉疲劳状态时，将肌电数据导入疲劳预测模型，生成疲劳预测报告，疲劳预测报告中包括用户达到肌肉疲劳状态的预测所需时间。还包括运动训练预警装置。

Description

一种运动训练预警方法及装置 技术领域
本发明属于可穿戴设备技术领域，尤其涉及一种运动训练预警方法及装置。
背景技术
肌肉在反复工作的情况下会导致做功能力下降，这种现象就是肌肉疲劳。运动员在运动训练过程中可能会出现肌肉疲劳的现象，就人体整体而言，绝大多数疲劳属于有感疲劳，即人体可以感知到的疲劳，当肌肉疲劳超过一定程度时，人体就可能出现肌肉损伤的情况。对运动员的运动训练而言，需要尽可能地在肌肉损伤情况发生之前，调整好运动训练计划，如停止运动训练，以避免肌肉损伤对训练比赛以及对运动员身体造成影响。
现有技术中，为了避免运动员出现肌肉损伤，一般采取的方法有两种：1、由专业教练根据自己的经验，对运动员肌肉的疲劳状态进行检测评估，当发现运动员肌肉疲劳时，停止运动员的运动训练以防止出现肌肉损伤。2、利用专业的疲劳检测仪器对运动员进行肌肉疲劳检测，当检测出运动员出现运动疲劳时，停止运动员的运动训练以防止出现肌肉损伤。
实际情况中，一般当上述两种情况能检测到运动员肌肉疲劳时，运动员已经发生了轻度的肌肉损伤，即现有技术只能在已经发生肌肉损伤的时候才停止运动训练，无法做到对肌肉疲劳的有效预警，保证运动员的安全。
发明内容
有鉴于此，本发明实施例提供了一种运动训练预警方法及装置，以解决现有技术中无法做到对肌肉疲劳的有效预警的问题。
本发明实施例的第一方面提供了一种运动训练预警方法，包括：
控制可穿戴装置中的采集模块采集用户的肌电数据；
根据所述肌电数据计算所述用户的疲劳指数，并基于所述疲劳指数判定所述用户是否处于肌肉疲劳状态；
当判断结果为所述用户处于所述肌肉疲劳状态时，输出警告信号；
当判断结果为所述用户未处于所述肌肉疲劳状态时，将所述肌电数据导入疲劳预测模型，生成疲劳预测报告，所述疲劳预测报告中包括所述用户达到所述肌肉疲劳状态的预测所需时间。
本发明实施例的第二方面提供了一种运动训练预警装置，包括：
采集模块，用于采集用户的肌电数据；
判断模块，用于根据所述肌电数据计算所述用户的疲劳指数，并基于所述疲劳指数判定所述用户是否处于肌肉疲劳状态；
警告模块，用于当判断结果为所述用户处于所述肌肉疲劳状态时，输出警告信号；
预测模块，用于当判断结果为所述用户未处于所述肌肉疲劳状态时，将所述肌电数据导入疲劳预测模型，生成疲劳预测报告，所述疲劳预测报告中包括所述用户达到所述肌肉疲劳状态的预测所需时间。
本发明实施例与现有技术相比存在的有益效果是：可穿戴装置采集了用户的肌电数据后，基于采集到的肌电数据监控用户是否出现肌肉疲劳，并发出相应的疲劳警告，使得用户能实时知道自己是否处于肌肉疲劳状态。在用户处于非肌肉疲劳状态下时，还会对用户进行疲劳预测，并生成相应的疲劳预测报告，告知用户达到肌肉疲劳状态的预测所需时间，能够及时有效地避免运动员出现因肌肉疲劳导致的肌肉损伤的情况，实现对肌肉疲劳状态的有效预警。
附图说明
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅 仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1是本发明实施例一提供的运动训练预警方法的实现流程图；
图2是本发明实施例二提供的运动训练预警方法的实现流程图；
图3是本发明实施例三提供的运动训练预警方法的实现流程图；
图4是本发明实施例四提供的S104的具体实现流程图；
图5是本发明实施例五提供的S104的具体实现流程图；
图6是本发明实施例六提供的S104的具体实现流程图；
图7是本发明实施例七提供的运动训练预警装置的结构框图。
具体实施方式
以下描述中，为了说明而不是为了限定，提出了诸如特定系统结构、技术之类的具体细节，以便透彻理解本发明实施例。然而，本领域的技术人员应当清楚，在没有这些具体细节的其它实施例中也可以实现本发明。在其它情况中，省略对众所周知的系统、装置、电路以及方法的详细说明，以免不必要的细节妨碍本发明的描述。
首先，对本发明实施例中提及的可穿戴装置进行解释说明。在本发明实施例中，可穿戴装置可以是可穿戴式的智能健身衣，也可以是可穿戴、可贴附式的一个或多个采集模块的集合。
其中，当可穿戴装置为可穿戴式的智能健身衣时，其可以是由柔性面料制成的衣服或裤子，且在柔性面料贴近人体皮肤的一侧镶嵌有多个采集模块。每个采集模块固定于智能健身衣的不同位置点，以使得用户穿上该智能健身衣之后，各个采集模块能够贴附于用户身体的各块肌肉。在可穿戴装置中，还镶嵌有至少一个控制模块，每个采集模块分别与该控制模块通信相连。现有技术中，一般仅采用一个控制模块，来实现对采集模块的控制。
在具体实现中，示例性地，可穿戴装置中还可以安置有电线及电路板，其 中，电路板用于固定各类通讯总线以及采集模块。此外，电路板及其各个焊接处都包裹有防水胶，作为一种具体的实现方式，通过在衣物上固定防水的走线，使得该可穿戴装置能够被洗涤。
特别地，当采集模块与控制模块通信相连时，每个采集模块中可以仅包含具有体感传感器功能的采集电极，也可以包含具有采集功能的集成电路。上述采集电极包括但不限于织物电极、橡胶电极以及凝胶电极等。
当可穿戴装置为可穿戴、可贴附式的一个或多个采集模块的集合时，用户可将各个采集模块灵活地固定于用户所指定的身体位置点，使得各个采集模块能够分别贴附于用户身体的指定肌肉。此时，每个采集模块为具有采集功能以及具有无线传输功能的集成电路，且该集成电路中包含上述具有体感传感器功能的采集电极。采集模块所采集到的肌电信号通过无线网络传输至远程的控制模块，该控制模块位于与采集模块配套使用的远程终端设备或远程控制盒子中。
为了说明本发明的技术方案，下面通过具体实施例来进行说明。
图1示出了本发明实施例一提供的运动训练预警方法的实现流程，详述如下：
S101，控制可穿戴装置中的采集模块采集用户的肌电数据。
其中，所需采集的肌电数据是指，对用户运动训练进行疲劳监测时所使用到的肌电数据。由于不同运动项目所主要运动到的肌肉不尽相同，如足球运动主要使用腿部肌肉，而篮球运动则需要使用到全身的肌肉，因此，针对不同的运动项目，可能出现肌肉疲劳的肌肉部位也不同，导致所需采集的肌电数据也不尽相同，本发明实施例中，所需采集的肌电数据具体可由用户根据实际运动项目进行设定。例如：当运动项目为足球运动时，可将用户腿部肌肉的肌电数据设定为所需采集使用的肌电数据。
本发明实施例中，用户在激活可穿戴装置后，需要对肌电数据进行选择设定。可穿戴装置在接收到用户设定的肌电数据及设定完成指令后，激活相应的采集模块，开始对用户的肌电数据进行采集记录。若用户在激活可穿戴装置后 的预设时间内(如五分钟)，没有设定肌电数据，默认延用用户上一次的肌电数据设定，若为首次激活可穿戴装置或上一次的肌电数据设定数据丢失，则默认激活全部的采集模块进行肌电数据采集。
作为本发明的一个具体实施例，技术人员可以预先对人体的肌肉进行肌肉群划分，并通过提供人机交互界面，供至用户进行肌电数据的选择设定，此时用户只需选择好运动训练时想要进行肌肉疲劳预警的肌肉群，即可设定该肌肉群作为肌电数据采集对象。例如：预先将人体肌肉简单划分为腿部肌群、胸部肌群、背部肌群、腹部肌群、肩部肌群及手部肌群，用户进行足球运动时，可直接选择将腿部肌群设定为肌电数据采集对象。
作为本发明的另一个具体实施例，为了方便用户的使用，技术人员可预先设定好多种不同的运动模式，如足球运动模式、篮球运动模式、兵兵球运动模式等，并为每种不同的运动模式设定好对应的肌肉群，该对应的肌肉群即为该运动模式对应的肌电数据采集对象，此时，用户只需在激活可穿戴装置后，选定相应的运动模式即可。
本发明实施例中，为了方便后续肌肉疲劳监测、预测时的调用，所有采集到的肌电数据及其对应的时间戳数据，都会被一同存储。
S102，对肌电数据进行处理判断用户是否处于肌肉疲劳状态。
本发明实施例中，可以通过肌电信号线性分析技术、肌电信号频率分析技术、复协方差函数疲劳估计法等对肌肉疲劳状态进行判定，肌肉疲劳状态的判定方法并非本发明的发明点，因此在此不作限定。
S103，当判断结果为用户处于肌肉疲劳状态时，输出警告信号。
由于肌肉疲劳可分为有感疲劳及无感疲劳。对于无感疲劳，人体无法感知或者感知较弱，经常不会引起人们的注意，而长时间处于肌肉疲劳的话，则会人体的肌肉造成损伤。对于有感疲劳，虽然人体可以感知到，但对于一些特殊的人群，如运动员而言，在进行运动训练时，其注意力会高度集中在训练本身上，即使发生且感知到了肌肉疲劳，也经常会被无意识地忽略掉，直至肌肉发 生损伤疼痛时才会注意。
为了为用户提供肌肉疲劳预警，防止用户出现肌肉损伤，本发明实施例中，当S102中判断出用户处于肌肉疲劳状态时，输出肌肉疲劳的警告信号，提醒用户注意休息。
本发明实施例中，既可以结合可穿戴装置中的提示模块进行警告提示，(如使用语音提示模块输出语音警告，或者使用震动提示模块进行震动警告)，也可以将警告信号输出至其他设备进行警告提示。
S104，当判断结果为用户未处于肌肉疲劳状态时，将肌电数据导入疲劳预测模型，生成疲劳预测报告，疲劳预测报告中包括用户达到肌肉疲劳状态的预测所需时间。
仅仅只是在用户出现疲劳时进行预警，有时并不能很好地防止用户出现肌肉损伤。例如：当运动员在训练比赛过程中出现了肌肉疲劳时，虽然可以对运动员发出肌肉疲劳警告，但此时运动员出于体育精神，往往会坚持完后续的比赛，此时虽然对运动员进行了肌肉疲劳预警，但并不能防止其出现后续的肌肉损伤，因此仅仅只是在用户出现疲劳时进行预警，并不能做到真正有效的预警，防止肌肉损伤。基于上述情况，本发明实施例中，当S102中判断出用户未处于肌肉疲劳状态，即未出现肌肉疲劳时，会基于采集到的肌电数据，对用户的肌肉疲劳状态进行预测，并得出疲劳预测报告，报告中包含了用户如果继续运动，可能出现肌肉疲劳的预测所需时间。用户可以根据该预测所需时间来安排自己的运动训练计划，防止出现肌肉疲劳甚至肌肉损伤。
现有技术中，一般采用肌电数据的平均功率疲劳MPF和/或中位频率MF来表征肌肉疲劳程度，当MPF和/或MF达到一定的阈值时，便可认定肌肉产生了疲劳，但在肌肉处于运动状态的情况下时，MPF和MF的稳定性均会受到极大的影响，因此，对肌肉运动中的肌肉疲劳的判断，并不适宜采用MPF或MF作为判断依据。
由于cohen类频分布技术具有时间和频率移不变性，即使是在肌肉运动时， 其中值频率IMDF和平均频率IMNF与肌肉疲劳的关联关系也是相对稳定的，因此IMDF及IMNF可以用于肌肉运动时的疲劳监测。在本发明实施例中，为了增强对肌肉运动时的疲劳判定的准确性，采用同时使用cohen类时频分布技术中的中值频率IMDF和平均频率IMNF来表征肌肉疲劳程度。
其中IMDF及IMNF的计算公式如下：
Figure PCTCN2018072325-appb-000001
Figure PCTCN2018072325-appb-000002
其中，f是肌电数据的频率，S(t，f)是时频频谱，由cohen类时频分布技术计算得出。
本发明实施例中，为了实现对肌肉疲劳的预测，在利用采集到的肌电数据，计算得出所需的各个时刻的IMDF和IMNF之后，还需要利用IMDF和IMNF进行曲线拟合，以得出其随着肌肉运动的动态变化趋势。本发明实施例中，凡是拟合得出IMDF和IMNF变化趋势图或变化趋势函数公式的算法皆可用于进行曲线拟合，如可采用常见的最小二乘法进行曲线拟合。
本发明实施例中，首先要设定一个疲劳程度的IMDF阈值及IMNF阈值，即当IMDF和IMNF值达到相应阈值时，判断用户肌肉出现了疲劳。在采集到用户的肌电数据数据之后，将肌电数据代入至公式(1)和公式(2)中，得出实时的IMDF和IMNF值，再将结合得出的IMDF和IMNF的变化趋势图或变化趋势函数公式，计算IMDF和IMNF值要达到设定的阈值的剩余时间T IMDF及T IMNF，根据T IMDF及T IMNF来计算最终的达到肌肉疲劳的预测所需时间T residual的时间函数公式如下：
T residual＝0.4β T IMDF+0.6T IMNF   (3)
其中β是一个加权系数，根据用户的性别、年龄、疾病史等特征进行具体选择，在实际测试结果中，当取值范围β∈(1，1.35)时，所得到的T residual最接近 实际的达到肌肉疲劳的所需时间，因此本发明实施例中，β要求取值范围为β∈(1，1.35)。
作为本发明的一个优选实施例二，如图2所示，在S101之后，该方法还包括：
S201，识别当前的运动项目，并读取运动项目对应的标准动作。
实际情况中，除了长时间或高强度的运动训练可能导致肌肉疲劳，不正确的运动姿势也可能导致肌肉疲劳，严重的甚至可能导致瘫痪。为了帮助用户预警肌肉疲劳，防止肌肉损伤，在本发明实施例二中，会对用户的运动动作进行指导，帮助用户纠正自己的错误运动姿势。
在本发明实施例二中，技术人员会预先存储好多个运动项目(如长跑、短跑、跳远等)以及每个运动项目对应的一套标准动作至存储模块，以便后续对比时的调用。作为本发明实施例二的一种具体实现方式，用户在使用本发明实施例二的动作指导功能之前，需要手动选择自己所需的运动项目，可穿戴装置根据用户选择的运动项目读取相对应的标准动作，用于后续动作对比。
S202，根据肌电数据识别用户的运动动作，并将运动动作与标准动作进行对比，得到动作对比数据。
在S101获取到用户的肌电数据后，根据获取到的肌电数据识别用户的运动动作，在本发明实施例二中具体地，可以基于支持向量机算法、线性回归分析算法以及肌电数据样本熵动作识别方法等对用户的运动动作进行识别。
在识别出用户的运动动作之后，将用户的运动动作与读取到的标准动作进行对比分析，确定用户每个动作中存在的问题，运动姿势的错误，并将分析得出的数据做为动作对比数据供后续分析。
例如：用户在跑步时，会进行蹬腿、抬腿、摆腿及落地一系列动作，在S202中，会对用户跑步中的一系列动作的肌电数据进行变化趋势分析，并根据肌电数据的变化趋势进行动作识别处理，再将得到的动作识别结果与标准动作进行比较，得出用户实际跑步动作与标准动作的差异，如识别出跑步过程中，相对 标准动作而言，用户腿部过于上抬。
S203，根据动作对比数据输出动作指导数据。
其中，动作指导数据用于指导用户如何纠正上述的运动对比数据中出现的问题，并提出正确的运动建议，以防出现肌肉疲劳或肌肉损伤。例如：跑步标准动作中，大腿和膝应当是用力前摆，而实际S202中，识别出用户在跑步过程中，相对标准动作而言出现了腿部上抬动作，这可能会引起膝关节受伤，针对该情况，会输出相应的动作指导数据，警告用户跑步时腿部不能上抬，应当用力前摆。
本发明实施例二，既可以选择以语音的形式指导用户，也可以以视频的形式指导用户，实际的输出形式应当结合实际情况进行选定，以最大化的满足用户实际需求为准。
在本发明实施例二中，通过识别用户的运动动作并与预存的标准动作进行对比，对用户进行标准动作指导，使得用户能及时纠正自己的运动姿势，避免因错误的运动动作运动姿势导致的肌肉疲劳甚至肌肉损伤。
作为本发明的另一个优选实施例三，如图3所示，在S101之后，该方法还包括：
S105，将肌电数据导入运动评估模型，生成运动评估报告，运动评估报告中包括本次运动训练的运动数据、运动调整建议或推荐食谱。运动评估报告用以帮助用户了解本次运动训练的具体运动数据情况，并针对本次运动训练的不足为用户提供调整建议，同时为用户提供一个科学健康的运动食谱。
为了帮助用户更好的了解自己运动训练的情况，科学安排自己的运动训练，本发明实施例三中，会基于采集到的肌电数据，对用户本次运动训练的进行评估，并给出相应的运动评估报告。
其中，运动评估报告包括运动数据、运动建议及推荐食谱三大部分。
运动数据包括如本次运动中各个肌肉群的运动量情况、肌电数据强度变化信息及本次运动中错误动作数据等，用户可以通过运动数据来了解本次运动训 练的具体情况。运动建议主要包括针对肌肉群的运动量提出的下次运动应加强或应减弱的运动建议数据、针对此次运动中出现的错误动作数据生成的运动指导数据以及一些运动技巧建议。推荐食谱则是针对此次运动训练为用户推荐的运动食谱，为用户提供一个科学健康的运动食谱。
在本发明实施例三中，为了生成所需的运动数据，在已存储好的肌电数据中，对被测的各个肌肉群的肌电数据进行分析，根据各个肌肉群运动时的肌电数据强度，判断其运动训练中的运动量情况，并根据预存的标准动作对运动训练中的每个动作进行对比分析，并记录其错误动作、错误次数等错误动作数据。运动建议则是在生成了运动数据之后，对运动数据进行分析，并根据其中的不足进行一一建议所得出的数据，如运动数据中显示用户各个肌肉群的运动量均过大，即用户运动训练过度，此时运动建议中，会提醒用户注意降低运动训练的强度。运动评估报告中的推荐食谱，需要综合用户的肌电数据、肌电数据相应的时间戳以及个人数据来进行生成。在本发明实施例三中，技术人员会预设好一份运动饮食表，运动饮食食谱表中设置好了用户运动量、运动时间、个人数据与食物种类的对应关系，如运动量较大、运动时间超过一小时的用户，应当补充一些含糖饮料和一些含糖食物，针对体型瘦弱的用户还应该补充一些蛋白质丰富的食物。在读取出存储好的肌电数据、肌电数据相应的时间戳以及个人数据后，由肌电数据相应的时间戳确定用户具体的运动时间，根据运动饮食食谱表选取好相应的推荐食物，最终生成一份适合用户此次运动锻炼的运动食谱。
在本发明实施例三的基础之上，作为本发明的一个优选实施例，在进行运动建议生成的时候，还会读取用户的个人数据，并结合用户的个人信息来生成最终的运动建议。
在本发明实施例三中，通过采集到的用户肌电数据对用户此次运动训练进行评估，并给出相应的运动数据、运动建议，使得用户能更好的了解本次运动训练的效果，以及自己在运动中的一些问题与不足，用户在接下来的运动训练 中能针对性的进行改进，在进行运动训练的同时保证好自己的肌肉安全，避免出现肌肉疲劳或肌肉损伤。通过生成相应的推荐食谱，可以更好地帮助用户恢复体力，缓解肌肉疲劳状态。
作为S104的一个具体实现方式，作为本发明的实施例四，如图4所示，包括：
S401，获取用户的身体素质信息。
其中，身体素质信息则是指用户的耐力等级γ、恢复力等级δ等人体的体质信息。对于身体素质信息，需要预先对用户的耐力、恢复力等人体的体质进行等级评定，并将评定好的耐力等级γ、恢复力等级δ等导入可穿戴装置进行存储，以备使用。
S402，将个人数据及肌电数据导入疲劳预测模型，生成疲劳预测报告。
由于不同身体素质的人，即使进行相同强度的运动训练，其产生疲劳的时间也全然不同，即会对最终生成的预测所需时间T residual产生影响，为了得到更为准确的T residual，本发明实施例四中，将耐力等级γ及恢复力等级δ加入了最终的T residual计算公式，具体公式如下：
Figure PCTCN2018072325-appb-000003
其中，α是耐力最高等级γ max与恢复力最高等级δ max之和的平均值，即：
Figure PCTCN2018072325-appb-000004
由于不同身体素质的人，在运动后的恢复力会有较大差别，在本发明实施例四中，获取用户的身体素质信息，不仅可以改进T residual的计算，同时还可以基于恢复力等级δ以及用户的性别年龄等信息为用户提供休息建议，并通过疲劳预测报告反馈给用户。
在本发明实施例四中，通过综合考虑用户的身体素质信息，来对最终到达肌肉疲劳的预测所需时间T residual进行修正，提升了T residual的准确性，同时还能为用户提供适合用户自身情况的休息建议。
作为S104的另一个具体实现方式，作为本发明的实施例五，如图5所示， S104包括：
S501，获取样本选择指令，并根据样本选择指令从肌电数据或预设的肌电数据样本库中，选取出肌电数据样本。
由上述S104可知，在计算IMDF和IMNF时，需要选定一份肌肉运动的肌电数据样本。在本发明实施例五中，肌电数据样本分为两类：第一类、预存肌电数据样本，由用户穿着可穿戴装置提前录制好的运动时的肌电数据，如用户在正常运动训练前，在穿着可穿戴装置的情况下进行了一次长跑训练，将采集到的实际肌电数据进行保存，作为后续的长跑肌电数据样本。第二类、实时肌电数据样本，是指用户正处于运动训练状态时，此次运动训练的实时肌电数据，如用户在穿着可穿戴装置的情况下进行跑步训练，且已经跑了5分钟，此时，此次跑步训练中已记录的5分钟的肌电数据，被称为实时肌电数据样本。
其中，第一类的预设肌电数据样本，会被预存储在肌电数据样本库中以便调用。第一类预设肌电数据可被选择调用的特性，使得用户能更加灵活的安排自己的运动训练，如通过选择预设肌电数据进行疲劳预测发现，对于单位时间内运动强度较大的短跑冲刺，用户可能会在极短的时间内发生肌肉疲劳，但对于单位时间内运动强度较小的长跑，用户可能在较长一段时间内，都不会发生肌肉疲劳，此时用户可选择性的进行一段时间的长跑训练，在保障自己不会发生肌肉疲劳的同时，又能继续进行运动训练。
肌肉疲劳预测实际应用时，可能会出现两种情况：
1、获知自己的预测剩余时间T residual后，用户出于安全考虑，停止了运动训练。
2、获知自己的预测剩余时间T residual后，用户继续进行运动训练。
对于情况1，用户停止了运动训练，此时没有实时肌电数据样本，只能选取第一类的预存肌电数据样本，来进行IMDF和IMNF变化趋势图或变化趋势函数公式的拟合，以及后续的预测所需时间T residual的计算。由于肌电数据样本库中存储着多种运动项目的肌电数据样本，如长跑肌电数据样本、短跑肌电数 据样本、跳远肌电数据样本等，此时用户需要根据自己的实际运动项目，输入相应的样本选择指令，以选择自己实际所需的肌电数据样本。
对于情况2，用户继续运动训练时，肌肉的实际状态在实时改变，此时若使用预存肌电数据样本进行预测所需时间T residual的计算，会导致计算的结果不够准确，因此，针对情况2，可选取实时肌电数据样本，来进行IMDF和IMNF变化趋势图或变化趋势函数公式的拟合。
在本发明实施例五中，在进行肌肉疲劳预测时，用户需要根据自己的实际情况，选取相应类型的肌电数据样本，并输入相应的样本选择指令。
S502，将肌电数据及肌电数据样本导入疲劳预测模型，生成疲劳预测报告。
在S501选取好肌电数据样本之后，根据肌电数据样本进行IMDF和IMNF变化趋势图或变化趋势函数公式的拟合，并根据采集到的肌电数据计算用户的IMDF和IMNF，利用得出的变化趋势图或变化趋势函数公式对用户的IMDF和IMNF进行计算，最后根据公式(3)计算出最终的预测所需时间T residual。
本发明实施例五中，针对不同的用户实际需求，提供了两类肌电数据样本的选择，通过不同场景使用不同肌电数据样本预测，极大的提高了肌肉疲劳预测的准确度。
作为S104的一个具体实现方式，作为本发明的实施例六，如图6所示，S104包括：
S601，对采集到的肌电数据按照对应肌肉所属肌肉群进行分类。
由于一项运动中，各个肌肉群的运动强度可能会大不相同，如足球运动时，腿部肌群运动强度远远大于其他肌肉群，因此，腿部肌群产生肌肉疲劳的时间往往也远短于其他肌肉群。若以采集到的所有肌电数据作为预测的数据，即使腿部肌群已经开始出现肌肉疲劳，也可能会因为受到其他肌肉群肌电数据的影响，导致腿部肌群的疲劳判断与疲劳预测不够准确。
为了解决上述不同肌肉群肌电信号互相影响，导致肌肉疲劳判断与疲劳预测不准确的问题，增强疲劳预警的有效性，本发明实施例六中，按照不同肌肉 群为标准进行肌电数据分类，对每个肌肉群分别进行疲劳预测。
S602，将不同肌肉群对应的肌电数据分别导入疲劳预测模型，生成相应的疲劳预测报告。
本发明实施例六中，通过对不同肌肉群的肌电数据分别处理预测，使得用户能实时准确掌握自己每一个肌肉群的疲劳状况，使得对肌肉疲劳的预警变得更为精确有效。
本发明实施例中，通过实时监测用户是否处于肌肉疲劳，对用户进行疲劳预警，使得用户能够及时发觉自己的肌肉疲劳状态。通过采集到的用户的肌电数据对用户进行肌肉疲劳预测，使得用户在出现疲劳之前的一段时间内，就对用户进行有效的预警，同时结合用户的身体素质信息及选取不同的肌电数据样本来对用户的肌肉疲劳进行预测，使得对肌肉疲劳的预测准确性得到了极大的保障。通过对不同肌肉群进行预测，也使得用户能够精确地掌握每个肌肉群的肌肉疲劳状况，获知肌肉群肌肉疲劳的提前预警。
应理解，上述实施例中各步骤的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本发明实施例的实施过程构成任何限定。
对应于上文实施例的运动训练预警方法，图7示出了本发明实施例七提供的运动训练预警装置的结构框图，为了便于说明，仅示出了与本发明实施例相关的部分。
参照图7，该运动训练预警装置包括：
采集模块71，用于采集用户的肌电数据。
判断模块72，用于对肌电数据进行处理判断用户是否处于肌肉疲劳状态。
警告模块73，用于当判断结果为用户处于肌肉疲劳状态时，输出警告信号。
预测模块74，用于当判断结果为用户未处于肌肉疲劳状态时，将肌电数据导入疲劳预测模型，生成疲劳预测报告，疲劳预测报告中包括用户达到肌肉疲 劳状态的预测所需时间。
进一步地，运动训练预警装置，还包括：
识别模块，用于识别当前的运动项目，并读取运动项目对应的标准动作。
对比模块，用于根据肌电数据识别用户的运动动作，并将运动动作与标准动作进行对比，得到动作对比数据。
指导模块，用于根据动作对比数据输出动作指导数据。
进一步地，运动训练预警装置，还包括：
运动评估模块，用于肌电数据导入运动评估模型，生成运动评估报告，运动评估报告中包括本次运动训练的运动数据、运动调整建议或推荐食谱。
进一步地，预测模块74，包括：
数据获取子模块，用于获取用户的身体素质信息。
第一预测子模块，用于将个人数据及肌电数据导入疲劳预测模型，生成疲劳预测报告。
进一步地，预测模块74，包括：
指令获取子模块，用于获取样本选择指令，并根据样本选择指令从肌电数据或预设的肌电数据样本库中，选取出肌电数据样本。
第二预测子模块，用于将肌电数据及肌电数据样本导入疲劳预测模型，生成疲劳预测报告。
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，仅以上述各功能单元、模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能单元、模块完成，即将所述装置的内部结构划分成不同的功能单元或模块，以完成以上描述的全部或者部分功能。实施例中的各功能单元、模块可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中，上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。另外，各功能单元、模块的具体名称也只是为了便于相互区分，并不用于限制本申请的保护范围。上 述系统中单元、模块的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本发明的范围。
在本发明所提供的实施例中，应该理解到，所揭露的装置和方法，可以通过其它的方式实现。例如，以上所描述的系统实施例仅仅是示意性的，例如，所述模块或单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通讯连接可以是通过一些接口，装置或单元的间接耦合或通讯连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明实施例的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存 储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)或处理器(processor)执行本发明实施例各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围，均应包含在本发明的保护范围之内。

Claims (10)

  1. 一种运动训练预警方法，其特征在于，包括：
    控制可穿戴装置中的采集模块采集用户的肌电数据；
    对所述肌电数据进行处理判断所述用户是否处于肌肉疲劳状态；
    当判断结果为所述用户处于所述肌肉疲劳状态时，输出警告信号；
    当判断结果为所述用户未处于所述肌肉疲劳状态时，将所述肌电数据导入疲劳预测模型，生成疲劳预测报告，所述疲劳预测报告中包括所述用户达到所述肌肉疲劳状态的预测所需时间。
  2. 如权利要求1所述的运动训练预警方法，其特征在于，在所述控制可穿戴装置中的采集模块采集用户的肌电数据之后，还包括：
    识别当前的运动项目，并读取所述运动项目对应的标准动作；
    根据所述肌电数据识别用户的运动动作，并将所述运动动作与所述标准动作进行对比，得到动作对比数据；
    根据所述动作对比数据输出动作指导数据。
  3. 如权利要求1所述的运动训练预警方法，其特征在于，在所述控制可穿戴装置中的采集模块采集用户的肌电数据之后，还包括：
    将所述肌电数据导入运动评估模型，生成运动评估报告，所述运动评估报告中包括本次运动训练的运动数据、运动调整建议或推荐食谱。
  4. 如权利要求1所述的运动训练预警方法，其特征在于，所述将所述肌电数据导入疲劳预测模型，生成疲劳预测报告，包括：
    获取所述用户的身体素质信息；
    将所述个人数据及所述肌电数据导入所述疲劳预测模型，生成所述疲劳预测报告。
  5. 如权利要求1所述的运动训练预警方法，其特征在于，所述将所述肌电数据导入疲劳预测模型，生成疲劳预测报告，包括：
    获取样本选择指令，并根据所述样本选择指令从所述肌电数据或预设的肌 电数据样本库中，选取出肌电数据样本；
    将所述肌电数据及所述肌电数据样本导入所述疲劳预测模型，生成所述疲劳预测报告。
  6. 一种运动训练预警装置，其特征在于，包括：
    采集模块，用于采集用户的肌电数据；
    判断模块，用于对所述肌电数据进行处理判断所述用户是否处于肌肉疲劳状态；
    警告模块，用于当判断结果为所述用户处于所述肌肉疲劳状态时，输出警告信号；
    预测模块，用于当判断结果为所述用户未处于所述肌肉疲劳状态时，将所述肌电数据导入疲劳预测模型，生成疲劳预测报告，所述疲劳预测报告中包括所述用户达到所述肌肉疲劳状态的预测所需时间。
  7. 如权利要求6所述的装置，其特征在于，还包括：
    识别模块，用于识别当前的运动项目，并读取所述运动项目对应的标准动作；
    对比模块，用于根据所述肌电数据识别用户的运动动作，并将所述运动动作与所述标准动作进行对比，得到动作对比数据；
    指导模块，用于根据所述动作对比数据输出动作指导数据。
  8. 如权利要求6所述的装置，其特征在于，还包括：
    运动评估模块，用于所述肌电数据导入运动评估模型，生成运动评估报告，所述运动评估报告中包括本次运动训练的运动数据、运动调整建议或推荐食谱。
  9. 如权利要求6所述的装置，其特征在于，所述预测模块，包括：
    数据获取子模块，用于获取所述用户的身体素质信息；
    第一预测子模块，用于将所述个人数据及所述肌电数据导入所述疲劳预测模型，生成所述疲劳预测报告。
  10. 如权利要求6所述的装置，其特征在于，所述预测模块，包括：
    指令获取子模块，用于获取样本选择指令，并根据所述样本选择指令从所述肌电数据或预设的肌电数据样本库中，选取出肌电数据样本；
    第二预测子模块，用于将所述肌电数据及所述肌电数据样本导入所述疲劳预测模型，生成所述疲劳预测报告。
PCT/CN2018/072325 2017-05-25 2018-01-12 一种运动训练预警方法及装置 WO2018214524A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710377573.X 2017-05-25
CN201710377573.XA CN108211307B (zh) 2017-05-25 2017-05-25 一种运动训练预警方法及装置

Publications (1)

Publication Number Publication Date
WO2018214524A1 true WO2018214524A1 (zh) 2018-11-29

Family

ID=62658119

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/072325 WO2018214524A1 (zh) 2017-05-25 2018-01-12 一种运动训练预警方法及装置

Country Status (2)

Country Link
CN (1) CN108211307B (zh)
WO (1) WO2018214524A1 (zh)

Families Citing this family (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109846480B (zh) * 2018-08-09 2021-10-29 江汉大学 一种检测肌肉综合性疲劳度的方法、装置及存储介质
CN109091142B (zh) * 2018-08-09 2020-12-15 江汉大学 一种检测肌肉内源性疲劳度的方法、装置及存储介质
CN109044276A (zh) * 2018-08-09 2018-12-21 江汉大学 一种检测肌肉内源性疲劳度的方法、装置及存储介质
CN109259761B (zh) * 2018-08-09 2021-01-08 江汉大学 一种检测肌肉内源性疲劳度的方法、装置及存储介质
CN110870769B (zh) * 2018-09-03 2022-08-09 香港理工大学深圳研究院 一种肌肉疲劳等级的检测方法及设备
CN109259762A (zh) * 2018-11-02 2019-01-25 郑州大学 一种基于多变量数据融合的肌肉疲劳综合测评装置
CN109550222A (zh) * 2019-01-09 2019-04-02 浙江强脑科技有限公司 电子健身训练方法、系统及可读存储介质
CN109645996B (zh) * 2019-02-21 2022-04-08 广州爱听贝科技有限公司 一种子宫收缩乏力监测方法、系统、智能终端和存储介质
US20220047222A1 (en) * 2020-08-11 2022-02-17 bOMDIC, Inc. Method for determining injury risk of user taking exercise
CN111968724B (zh) * 2020-10-21 2020-12-29 北京妙医佳健康科技集团有限公司 一种运动推荐方法和装置
CN112244882B (zh) * 2020-10-30 2023-06-02 北京中科心研科技有限公司 一种基于多模态生理数据的疾病预警方法和装置
CN114504334B (zh) * 2022-02-07 2024-04-26 苏州微创畅行机器人有限公司 状态预测方法、装置、计算机设备和存储介质
WO2024138311A1 (zh) * 2022-12-26 2024-07-04 深圳市韶音科技有限公司 一种运动数据处理方法及系统

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050049517A1 (en) * 2003-09-03 2005-03-03 Motorola, Inc. Electromyogram method and apparatus
CN102068264A (zh) * 2009-11-23 2011-05-25 财团法人资讯工业策进会 挥击动作的肌能状态分析系统及方法
CN104107134A (zh) * 2013-12-10 2014-10-22 中山大学 基于肌电反馈的上肢训练方法及系统
CN105147251A (zh) * 2015-08-19 2015-12-16 宁波工程学院 基于多通道sEMG的肌肉疲劳动态预测方法
KR20160022002A (ko) * 2014-08-19 2016-02-29 연세대학교 원주산학협력단 실시간 근피로도 경고 시스템 및 이를 위한 근피로도 측정 방법
CN106344012A (zh) * 2015-11-16 2017-01-25 闽南师范大学 一种运动疲劳肌电信号采集装置
CN106691474A (zh) * 2016-11-25 2017-05-24 中原电子技术研究所（中国电子科技集团公司第二十七研究所） 融合脑电信号与生理信号的疲劳检测系统

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FI126161B (en) * 2013-12-31 2016-07-29 Suunto Oy Communication module for monitoring personal performance and associated arrangements and procedures
TWI603717B (zh) * 2015-05-21 2017-11-01 博晶醫電股份有限公司 體力監測方法和裝置
CN104834384B (zh) * 2015-06-01 2017-10-13 凌亚 提高运动指导效率的装置及方法
CN105597298A (zh) * 2016-04-05 2016-05-25 哈尔滨工业大学 基于肌电信号及肢体动作检测的健身效果评价系统

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050049517A1 (en) * 2003-09-03 2005-03-03 Motorola, Inc. Electromyogram method and apparatus
CN102068264A (zh) * 2009-11-23 2011-05-25 财团法人资讯工业策进会 挥击动作的肌能状态分析系统及方法
CN104107134A (zh) * 2013-12-10 2014-10-22 中山大学 基于肌电反馈的上肢训练方法及系统
KR20160022002A (ko) * 2014-08-19 2016-02-29 연세대학교 원주산학협력단 실시간 근피로도 경고 시스템 및 이를 위한 근피로도 측정 방법
CN105147251A (zh) * 2015-08-19 2015-12-16 宁波工程学院 基于多通道sEMG的肌肉疲劳动态预测方法
CN106344012A (zh) * 2015-11-16 2017-01-25 闽南师范大学 一种运动疲劳肌电信号采集装置
CN106691474A (zh) * 2016-11-25 2017-05-24 中原电子技术研究所（中国电子科技集团公司第二十七研究所） 融合脑电信号与生理信号的疲劳检测系统

Also Published As

Publication number Publication date
CN108211307A (zh) 2018-06-29
CN108211307B (zh) 2019-11-12

Similar Documents

Publication Publication Date Title
WO2018214524A1 (zh) 一种运动训练预警方法及装置
WO2018214532A1 (zh) 健身运动数据的反馈方法及装置
Gillinov et al. Variable accuracy of wearable heart rate monitors during aerobic exercise
US20230009588A1 (en) Wearable device utilizing flexible electronics
Scott et al. Individualisation of speed thresholds does not enhance the dose-response determination in football training
WO2018214530A1 (zh) 运动员竞技状态评估方法及系统
US11246531B2 (en) Fatigue measurement in a sensor equipped garment
Clarke et al. Quantification of training load in Canadian football: application of session-RPE in collision-based team sports
JP6794259B2 (ja) アスレチック運動属性からのペースとエネルギー消費量の計算
CN105530858B (zh) 用于估计人员的心血管健康的系统和方法
CN109637625B (zh) 自学习式健身计划生成系统
FI124278B (fi) Mittalaite ja menetelmä rasitustilan indikoimiseksi
WO2018214527A1 (zh) 一种康复保健评估方法及装置
O'Reilly et al. Technology in strength and conditioning: assessing bodyweight squat technique with wearable sensors
US10603566B2 (en) Method and system for posture correction adapted to a sporting equipment
US20190046107A1 (en) Exercise application based on muscle stress measurement
US11779259B2 (en) Cognitive function evaluation device, cognitive function evaluation system, cognitive function evaluation method, and recording medium
WO2018214523A1 (zh) 一种肌电信号采集方法及装置
CA2770078C (en) Sensory testing data analysis by categories
Jimenez-Moreno et al. Analyzing walking speeds with ankle and wrist worn accelerometers in a cohort with myotonic dystrophy
US20140371886A1 (en) Method and system for managing performance of an athlete
JP6307457B2 (ja) 運動状態のフィードバック方法、システム、及びプログラム
JP6330009B2 (ja) 運動状態と心理状態とのフィードバック方法、システム、及びプログラム
CN108447562A (zh) 一种用户运动能力评估方法及系统
WO2022272170A1 (en) Muscle frequency fatigue, and associated algorithms, systems and methods

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18805827

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: 1205A 28.04.2020

122 Ep: pct application non-entry in european phase

Ref document number: 18805827

Country of ref document: EP

Kind code of ref document: A1