Motion data processing method and motion monitoring system

Abstract

The motion data processing method and motion monitoring system provided by the present application can process the electromyographic signals from the frequency domain or time domain to identify abnormal signals in the electromyographic signals, such as mutation signals, missing signals, saturation signals, and oscillation signals caused by high-pass filters, etc. The motion data processing method and motion monitoring system can also sample the electromyographic signals through a data sampling algorithm, and predict the data at the time when the abnormal signal is located based on the sampled data, thereby obtaining predicted data, and using the predicted data to replace the abnormal signal and correct the abnormal signal. The motion data processing method and motion monitoring system can not only accurately identify abnormal signals, but also correct abnormal signals so that the corrected data is more consistent with the user's actual movement, thereby improving the user experience.

Description

Technical Field

[0001] The present application relates to the technical field of wearable devices, and in particular to a motion data processing method and a motion monitoring system. Background Art

[0002] As people pay more attention to scientific exercise and physical health, sports monitoring equipment is developing greatly. At present, sports monitoring equipment mainly monitors some physiological parameter information (such as electromyographic signals) of users during exercise, displays physiological data to users, and gives suggestions based on physiological data. In order to help users exercise more scientifically and effectively, sports monitoring equipment must have the function of displaying the force of each muscle (i.e., electromyographic signal amplitude) to users in real time. In order to provide users with a better user experience, sports monitoring equipment needs to smooth the electromyographic signals to obtain a smooth electromyographic energy map. However, in the prior art, when processing electromyographic signals, sports monitoring equipment cannot identify abnormal signals, such as abnormal electromyographic signals caused by clothing that does not fit, pulls, motion artifacts, etc., which makes the electromyographic energy map unstable and the user experience poor.

[0003] Therefore, it is necessary to provide a motion data processing method and a motion monitoring system that can identify and correct abnormal signals in real time. Summary of the Invention

[0004] The present application provides a motion data processing method and a motion monitoring system capable of identifying and correcting abnormal signals in real time.

[0005] In a first aspect, the present application provides a motion data processing method, comprising: acquiring in real time the electromyographic signal of the measurement position corresponding to the user's motion; determining an abnormal signal in the electromyographic signal based on the electromyographic signal; and correcting the abnormal signal.

[0006] In some embodiments, determining the abnormal signal in the electromyographic signal based on the electromyographic signal includes: processing the electromyographic signal in the time domain to determine the abnormal signal; or processing the electromyographic signal in the frequency domain to determine the abnormal signal.

[0007] In some embodiments, the processing of the electromyographic signal in the time domain to determine the abnormal signal includes: based on the time domain window of the electromyographic signal, selecting at least one time window from the time domain window of the electromyographic signal, wherein the at least one time window covers different time ranges respectively; and determining the abnormal signal based on characteristic information corresponding to the electromyographic signal in the at least one time window.

[0008] In some embodiments, the feature information includes at least one of amplitude information and statistical information of the amplitude information, and the statistical information of the amplitude information includes at least one of entropy, variance, standard deviation, standard deviation of standard deviation and zero-crossing rate of the amplitude information.

[0009] In some embodiments, the abnormal signal includes a mutation signal, the at least one time window includes multiple time windows, and the determining of the abnormal signal based on the characteristic information corresponding to the electromyographic signal in the at least one time window includes: determining multiple characteristic information corresponding to the electromyographic signals in the multiple time windows; and determining that the ratio of the characteristic information corresponding to the time window after the time range to the characteristic information corresponding to the time window before the time range exceeds a preset first threshold, and determining that the electromyographic signal in the time window after the time range is the mutation signal.

[0010] In some embodiments, the abnormal signal includes a missing signal, and determining the abnormal signal based on the characteristic information corresponding to the electromyographic signal in the at least one time window includes: determining at least one characteristic information corresponding to the electromyographic signal in the at least one time window; and determining that the electromyographic signal in the time window corresponding to the characteristic information in the at least one characteristic information that is lower than a pre-stored second threshold is the missing signal.

[0011] In some embodiments, the abnormal signal includes a saturation signal, and determining the abnormal signal based on the characteristic information corresponding to the electromyographic signal in the at least one time window includes: determining at least one characteristic information corresponding to the electromyographic signal in the at least one time window; and determining that the electromyographic signal in the time window corresponding to the at least one characteristic information that is higher than the pre-stored saturation characteristic information is the saturation signal.

[0012] In some embodiments, the electromyographic signal includes a signal obtained based on a DC removal algorithm, and the DC removal algorithm includes at least one of a de-averaging algorithm and a high-pass filtering algorithm.

[0013] In some embodiments, the abnormal signal also includes an oscillation signal caused by the high-pass filtering algorithm, and the processing of the electromyographic signal in the time domain to determine the abnormal signal includes: calculating the reference oscillation height and reference duration of the oscillation signal based on the filter parameters of the high-pass filtering algorithm; and matching the electromyographic signal with the reference oscillation height and the reference duration in real time, and determining the electromyographic signal corresponding to the signal interval in the electromyographic signal that matches the reference oscillation height and the reference duration as the oscillation signal.

[0014] In some embodiments, the processing of the electromyographic signal in the frequency domain to determine the abnormal signal includes: acquiring the frequency domain signal of the electromyographic signal in the frequency domain in real time based on a frequency domain conversion algorithm; determining the spectral characteristics of the frequency domain signal in real time; and determining the electromyographic signal corresponding to the frequency domain signal whose spectral characteristics do not meet preset conditions as the abnormal signal.

[0015] In some embodiments, the spectral characteristics include at least one of spectral shape, power spectral density, average power frequency, median frequency, and wavelet scale.

[0016] In some embodiments, the correction of the abnormal signal includes: real-time data sampling of the electromyographic signal before the abnormal signal to obtain sampling data; determining the predicted data corresponding to the moment of the abnormal signal based on the sampling data corresponding to the time domain window of the electromyographic signal; determining the correction data corresponding to the moment of the abnormal signal based on the prediction data; and correcting the abnormal signal using the correction data.

[0017] In some embodiments, the sampling data corresponding to the time domain window of the electromyographic signal is used to determine the predicted data corresponding to the moment when the abnormal signal is located, including at least one of the following situations: determining a fitting function based on the sampling data corresponding to the time domain window, and calculating the predicted data corresponding to the moment when the abnormal signal is located based on the fitting function; and calculating the predicted data corresponding to the moment when the abnormal signal is located based on a trained LSTM network and the sampling data corresponding to the time domain window.

[0018] In some embodiments, determining the correction data corresponding to the moment when the abnormal signal is located based on the predicted data includes: determining that the predicted data is within a preset range, and using the predicted data as the correction data, and the preset range includes a data range consisting of the maximum and minimum values of the electromyographic signal within the time domain window; or determining that the predicted data is not within the preset range, and using the sampling data corresponding to at least one frame of electromyographic signal adjacent to the abnormal signal as the correction data.

[0019] In a second aspect, the present application also provides a motion monitoring system comprising at least one storage medium and at least one processor, wherein the at least one storage medium stores at least one instruction set for motion data processing; the at least one processor is communicatively connected to the at least one storage medium, wherein, when the motion monitoring system is running, the at least one processor reads the at least one instruction set and implements the motion data processing method described in the first aspect of the present application.

[0020] It can be seen from the above technical solutions that the motion data processing method and motion monitoring system provided by the present application can process the electromyographic signals in the frequency domain or time domain to identify abnormal signals in the electromyographic signals, such as mutation signals, missing signals, saturation signals, and oscillation signals caused by high-pass filters, etc. The motion data processing method and motion monitoring system can also sample the electromyographic signals through a data sampling algorithm, and predict the data at the time when the abnormal signal is located based on the sampled data, thereby obtaining predicted data, and using the predicted data to replace the abnormal signal, thereby correcting the abnormal signal. The motion data processing method and motion monitoring system can not only accurately identify abnormal signals, but also correct the abnormal signals so that the corrected data is more consistent with the user's actual movement, thereby improving the user experience. The motion data processing method and motion monitoring system can also promptly remind the user of abnormal device wearing when an abnormal signal is identified, thereby making data collection more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The present application will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, like numbers represent like structures, wherein:

[0022] Figure 1 is a schematic diagram of an application scenario of a motion monitoring system according to some embodiments of the present application;

[0023] Figure 2 is a schematic diagram of exemplary hardware and / or software of a wearable device according to some embodiments of the present application;

[0024] Figure 3 is a schematic diagram of exemplary hardware and / or software of a computing device according to some embodiments of the present application;

[0025] Figure 4 is an exemplary structural diagram of a wearable device according to some embodiments of the present application;

[0026] Figure 5 is an exemplary flow chart of a motion monitoring method according to some embodiments of the present application;

[0027] Figure 6 is an exemplary flow chart of a motion data processing method according to some embodiments of the present application;

[0028] Figure 7 is an exemplary flow chart of processing electromyographic signals in the time domain according to some embodiments of the present application;

[0029] Figure 8 is a schematic diagram of mutation signals according to some embodiments of the present application;

[0030] Figure 9 is an exemplary flow chart for identifying mutation signals according to some embodiments of the present application;

[0031] Figure 10 is a schematic diagram of a missing signal according to some embodiments of the present application;

[0032] Figure 11 is an exemplary flow chart of identifying missing signals according to some embodiments of the present application;

[0033] Figure 12 is a schematic diagram of a saturation signal according to some embodiments of the present application;

[0034] Figure 13 is an exemplary flow chart of identifying a saturation signal according to some embodiments of the present application;

[0035] Figure 14 is a schematic diagram of an oscillation signal according to some embodiments of the present application;

[0036] Figure 15 is an exemplary flow chart of identifying an oscillation signal according to some embodiments of the present application;

[0037] Figure 16 is an exemplary flow chart of processing electromyographic signals in the frequency domain according to some embodiments of the present application;

[0038] Figure 17 is an exemplary flow chart of correcting abnormal signals according to some embodiments of the present application; and

[0039] Figure 18 Schematic diagram of an electromyographic signal and a corrected smooth curve according to some embodiments of the present application. DETAILED DESCRIPTION

[0040] To more clearly illustrate the technical solutions of the embodiments of this application, the following is a brief introduction to the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this application. Those skilled in the art can apply this application to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0041] It should be understood that the terms "system," "device," "unit," and / or "module" used herein are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, other terms may be substituted for the terms if they can achieve the same purpose.

[0042] As used in this application and the claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" are not intended to refer to the singular but may include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0043] Flowcharts are used in this application to illustrate the operations performed by the systems according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0044] The present application provides a motion monitoring system that can obtain motion signals of a user when exercising, wherein the motion signals include at least electromyographic signals, posture signals, electrocardiographic signals, respiratory rate signals, etc. The system can monitor the user's motion based on at least the characteristic information corresponding to the electromyographic signals or the characteristic information corresponding to the posture signals. For example, the user's motion type, number of motions, motion quality, motion time, or physiological parameter information when the user performs the motion can be determined by frequency information, amplitude information corresponding to the electromyographic signals and angular velocity, angular velocity direction and angular velocity value, angle, displacement information, stress, etc. corresponding to the posture signals. In some embodiments, the motion monitoring system can also generate feedback on the user's fitness movements based on the analysis results of the user's fitness movements to guide the user's fitness. For example, when the user's fitness movements are not standard, the motion monitoring system can send a prompt message to the user (for example, a voice prompt, a vibration prompt, an electric current stimulation, etc.). This motion monitoring system can be applied to wearable devices (for example, clothing, wristbands, helmets), medical testing equipment (for example, electromyographs), fitness equipment, etc. By acquiring the motion signals of the user during exercise, the motion monitoring system can accurately monitor and provide feedback on the user's movements without the participation of professionals, thereby improving the user's fitness efficiency while reducing the user's fitness costs.

[0045] Figure 1 Schematic diagram of the application scenario of the motion monitoring system according to some embodiments of the present application. Figure 1 As shown, the motion monitoring system 100 may include a processing device 110, a network 120, a wearable device 130, and a mobile terminal device 140. The motion monitoring system 100 may obtain motion signals (e.g., electromyographic signals, posture signals, electrocardiographic signals, respiratory rate signals, etc.) used to represent the user's motion movements and monitor and provide feedback on the user's motion during exercise based on the user's motion signals.

[0046] For example, the motion monitoring system 100 can monitor and provide feedback on the user's movements during fitness. When the user wears the wearable device 130 to perform fitness exercises, the wearable device 130 can obtain the user's motion signals. The processing device 110 or the mobile terminal device 140 can receive and analyze the user's motion signals to determine whether the user's fitness movements are standardized, thereby monitoring the user's movements. Specifically, monitoring the user's movements may include determining the type of movement, the number of movements, the quality of the movement, the time of the movement, or the physiological parameter information of the user when performing the movement. Furthermore, the motion monitoring system 100 can generate feedback on the user's fitness movements based on the analysis results of the user's fitness movements to guide the user's fitness.

[0047] As another example, the motion monitoring system 100 can monitor and provide feedback on a user's running movements. For example, when a user wears the wearable device 130 and runs, the motion monitoring system 100 can monitor whether the user's running movements are standardized and whether the running time meets health standards. If the user runs for too long or has incorrect running movements, the fitness device can provide feedback to the user about their running status, prompting the user to adjust their running movements or running time.

[0048] In some embodiments, the processing device 110 can be used to process information and / or data related to user motion. For example, the processing device 110 can receive a user's motion signals (e.g., electromyographic signals, posture signals, electrocardiographic signals, respiratory rate signals, etc.) and further extract feature information corresponding to the motion signals (e.g., feature information corresponding to the electromyographic signals in the motion signals, feature information corresponding to the posture signals). In some embodiments, the processing device 110 can perform specific signal processing on the electromyographic signals or posture signals collected by the wearable device 130, such as signal segmentation, signal preprocessing (e.g., signal correction processing, filtering processing, etc.). In some embodiments, the processing device 110 can also determine whether the user's motion is correct based on the user's motion signals. For example, the processing device 110 can determine whether the user's motion is correct based on the feature information corresponding to the electromyographic signals (e.g., amplitude information, frequency information, etc.). For another example, the processing device 110 can determine whether the user's motion is correct based on the feature information corresponding to the posture signals (e.g., angular velocity, angular velocity direction, angular velocity acceleration, angle, displacement information, stress, etc.). For another example, the processing device 110 can determine whether the user's movements are correct based on the characteristic information corresponding to the electromyographic signal and the characteristic information corresponding to the posture signal. In some embodiments, the processing device 110 can also determine whether the user's physiological parameters during exercise meet health standards. In some embodiments, the processing device 110 can also issue corresponding instructions to provide feedback on the user's exercise status. For example, when a user is running, the motion monitoring system 100 detects that the user is running for too long. In this case, the processing device 110 can issue an instruction to the mobile terminal device 140 to prompt the user to adjust the running time. It should be noted that the characteristic information corresponding to the posture signal is not limited to the angular velocity, angular velocity direction, angular velocity acceleration, angle, displacement information, stress, etc. mentioned above, but can also be other characteristic information. Any parameter information that can be used to reflect the relative motion of the user's body can be used as characteristic information corresponding to the posture signal. For example, when the posture sensor is a strain gauge sensor, the bending angle and bending direction of the user's joints can be obtained by measuring the resistance of the strain gauge sensor that changes with the stretch length.

[0049] In some embodiments, the processing device 110 may be local or remote. For example, the processing device 110 may access information and / or data stored in the wearable device 130 and / or the mobile terminal device 140 through the network 120. In some embodiments, the processing device 110 may be directly connected to the wearable device 130 and / or the mobile terminal device 140 to access the information and / or data stored therein. For example, the processing device 110 may be located in the wearable device 130 and implement information interaction with the mobile terminal device 140 through the network 120. For another example, the processing device 110 may be located in the mobile terminal device 140 and implement information interaction with the wearable device 130 through the network. In some embodiments, the processing device 110 may be executed on a cloud platform.

[0050] In some embodiments, the processing device 110 can process data and / or information related to motion monitoring to perform one or more functions described in this application. In some embodiments, the processing device 110 can obtain motion signals collected by the wearable device 130 when the user is exercising. In some embodiments, the processing device 110 can send control instructions to the wearable device 130 or the mobile terminal device 140. The control instructions can control the switch state of the wearable device 130 and its various sensors, and can also control the mobile terminal device 140 to issue prompt information. In some embodiments, the processing device 110 may include one or more sub-processing devices (for example, a single-core processing device or a multi-core multi-core processing device).

[0051] Network 120 can facilitate the exchange of data and / or information within motion monitoring system 100. In some embodiments, one or more components within motion monitoring system 100 can transmit data and / or information to other components within motion monitoring system 100 via network 120. For example, motion signals collected by wearable device 130 can be transmitted to processing device 110 via network 120. For another example, a confirmation result regarding the motion signal by processing device 110 can be transmitted to mobile terminal device 140 via network 120. In some embodiments, network 120 can be any type of wired or wireless network.

[0052] Wearable device 130 refers to clothing or equipment with wearable functions. In some embodiments, wearable device 130 may include, but is not limited to, a top device 130-1, a pair of pants 130-2, a wristband device 130-3, and shoes 130-4. In some embodiments, wearable device 130 may include multiple sensors. The sensors can acquire various motion signals (e.g., electromyographic signals, posture signals, temperature information, heart rate, electrocardiogram signals, etc.) during user exercise. In some embodiments, the sensors may include, but are not limited to, one or more of an electromyographic sensor, a posture sensor, a temperature sensor, a humidity sensor, an electrocardiogram sensor, a blood oxygen saturation sensor, a Hall effect sensor, a skin conduction sensor, a rotation sensor, and the like. For example, an electromyographic sensor may be installed at a muscle location (e.g., the biceps, triceps, latissimus dorsi, trapezius, etc.) in top device 130-1. The electromyographic sensor can fit the user's skin and collect electromyographic signals during exercise. For another example, an electrocardiogram sensor may be installed near the left pectoral muscle in top device 130-1 to collect the user's electrocardiogram signals. For another example, a posture sensor can be set at the human muscle position (e.g., gluteus maximus, vastus lateralis, vastus medialis, gastrocnemius, etc.) in the pants device 130-2, and the posture sensor can collect the user's posture signal. In some embodiments, the wearable device 130 can also provide feedback on the user's movements. For example, when the movement of a certain part of the body does not meet the standard during exercise, the electromyographic sensor corresponding to the part can generate a stimulation signal (e.g., current stimulation or striking signal) to remind the user.

[0053] It should be noted that the wearable device 130 is not limited to Figure 1 The top device 130-1, pants device 130-2, wrist guard device 130-3 and shoe device 130-4 shown in the figure may also include other devices that require motion monitoring, such as helmet devices, knee pads, etc., which are not limited here. Any device that can use the motion monitoring method contained in this application is within the scope of protection of this application.

[0054] In some embodiments, the mobile terminal device 140 can obtain information or data from the motion monitoring system 100. In some embodiments, the mobile terminal device 140 can receive motion data processed by the processing device 110 and provide motion records based on the processed motion data. Exemplary feedback methods may include, but are not limited to, voice prompts, image prompts, video displays, text prompts, etc. In some embodiments, a user can obtain a motion record of their own motion during exercise through the mobile terminal device 140. For example, the mobile terminal device 140 can be connected to the wearable device 130 via the network 120 (e.g., a wired connection or a wireless connection), and the user can obtain a motion record of the user's motion during exercise through the mobile terminal device 140, and the motion record can be transmitted to the processing device 110 via the mobile terminal device 140. In some embodiments, the mobile terminal device 140 can include one of a mobile device 140-1, a tablet computer 140-2, a laptop computer 140-3, etc., or any combination thereof. In some embodiments, the mobile device 140-1 can include a mobile phone, a smart home device, a smart mobile device, a virtual reality device, an augmented reality device, etc., or any combination thereof. In some embodiments, smart home devices may include smart appliance control devices, smart monitoring devices, smart televisions, smart cameras, etc., or any combination thereof. In some embodiments, smart mobile devices may include smart phones, personal digital assistants (PDAs), gaming devices, navigation devices, POS devices, etc., or any combination thereof. In some embodiments, virtual reality devices and / or augmented reality devices may include virtual reality helmets, virtual reality glasses, virtual reality goggles, augmented reality helmets, augmented reality glasses, augmented reality goggles, etc., or any combination thereof.

[0055] In some embodiments, the motion monitoring system 100 may further include a database. The database may store data (e.g., initially set threshold conditions, etc.) and / or instructions (e.g., feedback instructions). In some embodiments, the database may store data obtained from the wearable device 130 and / or the mobile terminal device 140. In some embodiments, the database may store information and / or instructions for execution or use by the processing device 110 to perform the exemplary methods described in this application. In some embodiments, the database may be connected to the network 120 to communicate with one or more components of the motion monitoring system 100 (e.g., the processing device 110, the wearable device 130, the mobile terminal device 140, etc.). One or more components of the motion monitoring system 100 may access the data or instructions stored in the database via the network 120. In some embodiments, the database may be directly connected to or communicate with one or more components in the motion monitoring system 100. In some embodiments, the database may be part of the processing device 110.

[0056] Figure 2FIG is a schematic diagram of exemplary hardware and / or software of the wearable device 130 according to some embodiments of the present application. Figure 2 As shown, the wearable device 130 may include an acquisition module 210, a processing module 220 (also known as a processor), a control module 230 (also known as a main control, MCU, controller), a communication module 240, a power supply module 250 and an input / output module 260.

[0057] The acquisition module 210 can be used to acquire motion signals from a user during exercise. In some embodiments, the acquisition module 210 can include a sensor unit, which can be used to acquire one or more motion signals from a user during exercise. In some embodiments, the sensor unit can include, but is not limited to, one or more of an electromyographic sensor, a posture sensor, an electrocardiogram sensor, a respiratory sensor, a temperature sensor, a humidity sensor, an inertial sensor, a blood oxygen saturation sensor, a Hall effect sensor, a skin conduction sensor, a rotation sensor, and the like. In some embodiments, the motion signals can include one or more of an electromyographic signal, a posture signal, an electrocardiogram signal, a respiratory rate, a temperature signal, a humidity signal, and the like. The sensor unit can be placed at different locations on the wearable device 130 depending on the type of motion signal to be acquired. For example, in some embodiments, an electromyographic sensor (also known as an electrode element) can be placed at a muscle position on the human body, and the electromyographic sensor can be configured to acquire electromyographic signals from a user during exercise. The electromyographic signals and their corresponding characteristic information (e.g., frequency information, amplitude information, etc.) can reflect the state of the user's muscles during exercise. The posture sensor can be placed at different locations on the human body (e.g., at locations on the wearable device 130 corresponding to the torso, limbs, or joints), and the posture sensor can be configured to acquire posture signals from a user during exercise. The posture signal and its corresponding characteristic information (for example, angular velocity direction, angular velocity value, angular velocity acceleration value, angle, displacement information, stress, etc.) can reflect the user's posture during exercise. The electrocardiogram sensor can be set at a position around the human chest, and the electrocardiogram sensor can be configured to collect electrocardiogram data when the user exercises. The respiration sensor can be set at a position around the human chest, and the respiration sensor can be configured to collect respiration data (for example, respiratory frequency, respiratory amplitude, etc.) when the user exercises. The temperature sensor can be configured to collect temperature data (for example, body surface temperature) when the user exercises. The humidity sensor can be configured to collect humidity data of the external environment when the user exercises.

[0058] The processing module 220 can process data from the acquisition module 210, the control module 230, the communication module 240, the power supply module 250 and / or the input / output module 260. For example, the processing module 220 can process the motion signal of the user during the movement from the acquisition module 210. In some embodiments, the processing module 220 can pre-process the motion signal (e.g., electromyographic signal, posture signal) acquired by the acquisition module 210. For example, the processing module 220 performs segmented processing on the electromyographic signal or posture signal when the user is moving. For another example, the processing module 220 can pre-process the electromyographic signal when the user is moving (e.g., filtering processing, signal correction processing) to improve the quality of the electromyographic signal. For another example, the processing module 220 can determine the feature information corresponding to the posture signal based on the posture signal when the user is moving. In some embodiments, the processing module 220 can process instructions or operations from the input / output module 260. In some embodiments, the processed data can be stored in a memory or a hard disk. In some embodiments, the processing module 220 may transmit the processed data to one or more components of the motion monitoring system 100 via the communication module 240 or the network 120. For example, the processing module 220 may send the monitoring results of the user's motion to the control module 230, and the control module 230 may execute subsequent operations or instructions based on the motion determination results.

[0059] The control module 230 can be connected to other modules in the wearable device 130. In some embodiments, the control module 230 can control the operating status of other modules in the wearable device 130. For example, the control module 230 can control the power supply status (e.g., normal mode, power saving mode), power supply time, etc. of the power supply module 250. For another example, the control module 230 can control the input / output module 260 based on the user's movement determination result, and then control the mobile terminal device 140 to send feedback results of the user's movement to the user. When there is a problem with the user's movement during exercise (e.g., the movement does not meet the standard), the control module 230 can control the input / output module 260, and then control the mobile terminal device 140 to provide feedback to the user, so that the user can understand their own movement status in real time and adjust their movement. In some embodiments, the control module 230 can also control one or more sensors or other modules in the acquisition module 210 to provide feedback to the human body. For example, when the strength of a muscle in the user's movement is too strong, the control module 230 can control the electrode module at the muscle position to electrically stimulate the user to prompt the user to adjust the movement in time.

[0060] In some embodiments, the communication module 240 can be used for the exchange of information or data. In some embodiments, the communication module 240 can be used for communication between components within the wearable device 130. For example, the acquisition module 210 can send a user motion signal (e.g., an electromyographic signal, a posture signal, etc.) to the communication module 240, and the communication module 240 can send the motion signal to the processing module 220. In some embodiments, the communication module 240 can also be used for communication between the wearable device 130 and other components in the motion monitoring system 100. For example, the communication module 240 can send status information (e.g., switch status) of the wearable device 130 to the processing device 110, and the processing device 110 can monitor the wearable device 130 based on the status information. The communication module 240 can use wired, wireless, and wired / wireless hybrid technologies.

[0061] In some embodiments, the power supply module 250 can provide power to other components in the motion monitoring system 100 .

[0062] The input / output module 260 can acquire, transmit, and send signals. The input / output module 260 can connect or communicate with other components in the motion monitoring system 100. Other components in the motion monitoring system 100 can connect or communicate through the input / output module 260.

[0063] It should be noted that the above description of the motion monitoring system 100 and its modules is for convenience of description only and does not limit one or more embodiments of the present application to the scope of the embodiments cited. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the various modules, or form a subsystem connected to other modules, or omit one or more modules without deviating from this principle. For example, the acquisition module 210 and the processing module 220 can be one module, which can have the function of acquiring and processing user motion signals. For another example, the processing module 220 can also be not provided in the wearable device 130, but integrated in the processing device 110. Such variations are within the scope of protection of one or more embodiments of the present application.

[0064] Figure 3 300 is a schematic diagram of exemplary hardware and / or software of a computing device 300 according to some embodiments of the present application. In some embodiments, the processing device 110 and / or the mobile terminal device 140 can be implemented on the computing device 300. Figure 3 As shown, computing device 300 may include an internal communication bus 310 , a processor 320 , a read-only memory 330 , a random access memory 340 , a communication port 350 , an input / output interface 360 , a hard disk 370 , and a user interface 380 .

[0065] The internal communication bus 310 can implement data communication between various components in the computing device 300. For example, the processor 320 can send data to other hardware such as the memory or the input / output port 360 via the internal communication bus 310.

[0066] The processor 320 can execute computing instructions (program code) and perform the functions of the motion monitoring system 100 described in this application. The computing instructions may include programs, objects, components, data structures, processes, modules and functions (the functions refer to the specific functions described in this application). For example, the processor 320 can process the motion signals (e.g., electromyographic signals, posture signals) of the user during exercise obtained from the wearable device 130 and / or the mobile terminal device 140 of the motion monitoring system 100, and monitor the user's motion according to the motion signals of the user during exercise. For illustration purposes only, Figure 3 The computing device 300 in the embodiment only describes one processor, but it should be noted that the computing device 300 in this application may also include multiple processors.

[0067] The memory of the computing device 300 (e.g., read-only memory (ROM) 330, random access memory (RAM) 340, hard disk 370, etc.) can store data / information obtained from any other components of the motion monitoring system 100. In some embodiments, the memory of the computing device 300 can be located in the wearable device 130 or in the processing device 110. The memory also includes at least one instruction set stored in the memory. The instructions are computer program codes, which can include programs, routines, objects, components, data structures, processes, modules, etc. that execute the functions of the motion monitoring system 100 provided in the present application, including the motion data processing method provided in the present application.

[0068] The input / output interface 360 may be used to input or output signals, data, or information. In some embodiments, the input / output interface 360 may enable a user to interact with the motion monitoring system 100 .

[0069] The hard disk 370 can be used to store information and data generated by or received from the processing device 110. For example, the hard disk 370 can store user confirmation information of the user. In some embodiments, the hard disk 370 can be set in the processing device 110 or in the wearable device 130. The user interface 380 can enable interaction and information exchange between the computing device 300 and the user. In some embodiments, the user interface 380 can be used to present the motion record generated by the motion monitoring system 100 to the user. In some embodiments, the user interface 380 can include a physical display, such as a display with a speaker, an LCD display, an LED display, an OLED display, an electronic ink display (E-Ink), etc.

[0070] Figure 4 1 is an exemplary structural diagram of a wearable device according to some embodiments of the present application. In order to further describe the wearable device, a top is used as an example. Figure 4As shown, the wearable device 400 may include a top garment 410. The top garment 410 may include a top garment base 4110, at least one top garment processing module 4120, at least one top garment feedback module 4130, at least one top garment acquisition module 4140, and the like. The top garment base 4110 may refer to clothing worn on the upper torso of a person. In some embodiments, the top garment base 4110 may include a short-sleeved T-shirt, a long-sleeved T-shirt, a shirt, a jacket, and the like. The at least one top garment processing module 4120 and the at least one top garment acquisition module 4140 may be located in areas of the top garment base 4110 that conform to different parts of the human body. The at least one top garment feedback module 4130 may be located anywhere on the top garment base 4110, and the at least one top garment feedback module 4130 may be configured to provide feedback on the user's upper torso motion status. Exemplary feedback methods may include, but are not limited to, voice prompts, text prompts, pressure prompts, and current stimulation. In some embodiments, at least one upper garment acquisition module 4140 may include, but is not limited to, one or more of a posture sensor, an electrocardiogram (ECG) sensor, an electromyography (EMG) sensor, a temperature sensor, a humidity sensor, an inertial sensor, an acid-base sensor, an acoustic transducer, and the like. The sensors in the upper garment acquisition module 4140 may be placed at different locations on the user's body depending on the signal to be measured. For example, when a posture sensor is used to acquire posture signals during exercise, the posture sensor may be placed at locations within the upper garment base 4110 corresponding to the human torso, arms, or joints. For another example, when an electromyography (EMG) sensor is used to acquire EMG signals during exercise, the EMG sensor may be located near the muscles to be measured. In some embodiments, the posture sensor may include, but is not limited to, a triaxial acceleration sensor, a triaxial angular velocity sensor, a magnetic sensor, or any combination thereof. For example, a posture sensor may include a triaxial acceleration sensor and a triaxial angular velocity sensor. In some embodiments, the posture sensor may also include a strain sensor. A strain sensor may be a sensor that generates strain based on the deformation of the object under test. In some embodiments, the strain sensor may include but is not limited to one or more of a strain force sensor, a strain pressure sensor, a strain torque sensor, a strain displacement sensor, a strain acceleration sensor, etc. For example, the strain sensor can be set at the joint position of the user, and the bending angle and bending direction at the user's joint can be obtained by measuring the size of the resistance in the strain sensor that changes with the stretching length. It should be noted that in addition to the above-mentioned top garment base 4110, top processing module 4120, top feedback module 4130, and top acquisition module 4140, the top garment 410 may also include other modules, such as a power supply module, a communication module, an input / output module, etc. The top processing module 4120 and Figure 2 The processing module 220 is similar to the top acquisition module 4140. Figure 2The acquisition module 210 is similar to that in the upper garment 410. For a detailed description of each module in the upper garment 410, please refer to the present application. Figure 2 The relevant description in will not be repeated here.

[0071] Figure 5 FIG. 1 is an exemplary flow chart of a motion monitoring method according to some embodiments of the present application. Figure 5 As shown, process 500 may include:

[0072] In step 510, a motion signal of the user during exercise is obtained.

[0073] In some embodiments, step 510 may be performed by acquisition module 210. The motion signal refers to body parameter information of the user during exercise. In some embodiments, body parameter information may include, but is not limited to, one or more of electromyographic signals, posture signals, electrocardiographic signals, temperature signals, humidity signals, blood oxygen concentration, respiratory rate, and the like. In some embodiments, the electromyographic sensors in acquisition module 210 may collect electromyographic signals of the user during exercise. For example, when a user performs a seated chest press, the electromyographic sensors corresponding to the pectoral muscles and latissimus dorsi muscles in the wearable device may collect electromyographic signals from the corresponding muscle locations. For another example, when a user performs a squat, the electromyographic sensors corresponding to the gluteus maximus and quadriceps femoris muscles in the wearable device may collect electromyographic signals from the corresponding muscle locations. For another example, when a user runs, the electromyographic sensors corresponding to the gastrocnemius muscles in the wearable device may collect electromyographic signals from the gastrocnemius muscles. In some embodiments, the posture sensor in acquisition module 210 may collect posture signals of the user during exercise. For example, when a user performs a barbell bench press, a posture sensor in the wearable device corresponding to a location on the body, such as the triceps, can collect posture signals from the user's triceps. For another example, when a user performs a dumbbell fly, a posture sensor located at a location on the body, such as the deltoid, can collect posture signals from the user's deltoid. In some embodiments, acquisition module 210 may include multiple posture sensors, each capable of collecting posture signals from multiple body parts during exercise. These posture signals can reflect the relative motion between different body parts. For example, a posture signal from the arm and a posture signal from the torso can reflect the motion of the arm relative to the torso. In some embodiments, the posture signal is associated with the type of posture sensor. For example, when the posture sensor is a three-axis angular velocity sensor, the acquired posture signal is angular velocity information. For another example, when the posture sensor is a three-axis angular velocity sensor and a three-axis acceleration sensor, the acquired posture signal is both angular velocity information and acceleration information. For another example, if the posture sensor is a strain gauge sensor, it can be placed at the user's joints. By measuring the resistance of the strain gauge sensor, which changes with stretch, the posture signal obtained can include displacement information, stress, and other information. These posture signals can be used to characterize the bending angle and direction of the user's joints. It is important to note that any parameter information that can be used to reflect the relative motion of the user's body can be considered as feature information corresponding to the posture signal. Depending on the type of feature information, different types of posture sensors can be used to obtain it.

[0074] In some embodiments, the motion signal may include an electromyographic signal of a specific part of the user's body and a posture signal of the specific part. The electromyographic signal and the posture signal can reflect the motion state of the specific part of the user's body from different angles. Simply put, the posture signal of a specific part of the user's body can reflect the motion type, motion amplitude, motion frequency, etc. of the specific part. The electromyographic signal can reflect the muscle state of the specific part during exercise. In some embodiments, the electromyographic signal and / or posture signal of the same body part can be used to better assess whether the movement of the part is standard.

[0075] In step 520, the user's movement is monitored based on at least the characteristic information corresponding to the electromyographic signal or the characteristic information corresponding to the posture signal.

[0076] In some embodiments, this step may be performed by the processing module 220 and / or the processing device 110. In some embodiments, the characteristic information corresponding to the electromyographic signal may include, but is not limited to, one or more of frequency information, amplitude information, etc. The characteristic information corresponding to the posture signal refers to parameter information used to characterize the relative movement of the user's body. In some embodiments, the characteristic information corresponding to the posture signal may include, but is not limited to, one or more of angular velocity direction, angular velocity value, angular velocity acceleration value, etc. In some embodiments, the characteristic information corresponding to the posture signal may also include angle, displacement information (such as the stretching length in a strain sensor), stress, etc. For example, when the posture sensor is a strain sensor, the strain sensor can be set at the user's joint position, and by measuring the size of the resistance in the strain sensor that changes with the stretching length, the posture signal obtained may be displacement information, stress, etc., and these posture signals can characterize the bending angle and bending direction at the user's joint. In some embodiments, the processing module 220 and / or the processing device 110 can extract characteristic information corresponding to the electromyographic signal (e.g., frequency information, amplitude information) or characteristic information corresponding to the posture signal (e.g., angular velocity direction, angular velocity value, angular velocity acceleration value, angle, displacement information, stress, etc.), and monitor the user's movement based on the characteristic information corresponding to the electromyographic signal or the characteristic information corresponding to the posture signal. Monitoring the user's movement includes monitoring information related to the user's movement. In some embodiments, the movement-related information may include one or more of the user's movement type, number of movements, movement quality (e.g., whether the user's movement meets standards), movement duration, etc. The movement type refers to the fitness movement performed by the user during exercise. In some embodiments, the movement type may include, but is not limited to, one or more of seated chest press, squats, deadlifts, planks, running, swimming, etc. The number of movements refers to the number of times the user performs the movement during exercise. For example, if a user performs seated chest press 10 times during exercise, 10 times here refers to the number of movements. Movement quality refers to the standardization of the fitness movement performed by the user relative to standard fitness movements. For example, when a user performs a squat, processing device 110 can determine the user's action type based on feature information corresponding to action signals (electromyographic signals and posture signals) from specific muscle locations (gluteus maximus, quadriceps femoris, etc.), and determine the action quality of the user's squat based on the action signals of a standard squat. Action time refers to the time corresponding to one or more action types or the total time of the user's exercise process.

[0077] In some embodiments, the motion monitoring system 100 can also smooth the electromyographic signal to process the electromyographic signal into a smooth data curve, so as to display it to the user for viewing, making it easier for the user to monitor the motion process. In some embodiments, when acquiring the user's motion signal, other physiological parameter information of the user (e.g., heart rate signal), external conditions such as relative movement or compression between the acquisition module 210 and the human body during exercise may affect the quality of the motion signal, such as causing abnormal signals in the electromyographic signal, such as mutation signals, missing signals, saturation signals, and oscillation signals caused by high-pass filters, etc., affecting the monitoring of the user's motion. For ease of description, the mutation signal of the electromyographic signal can be described as a singular point. Exemplary singular points can include burr signals, discontinuous signals, etc. In some embodiments, the vibration caused by the user's heartbeat during exercise may cause the electromyographic signal to have mutation signals for a short period of time. In some embodiments, the user adjusts the position of the wearable device 130 during exercise, such as pulling clothes, tugging sleeves, etc., which may cause the electromyographic signal to have mutation signals for a short period of time. In some embodiments, when the wearable device 130 is not worn properly, such as when the clothing does not fit well or when some of the myoelectric sensors have poor contact for a short time or a long time, it may cause the myoelectric signal to have a sudden change signal for a short time or a long time. In some embodiments, there may be motion artifacts during the user's movement. The motion artifact here refers to the signal noise generated by the relative movement of the muscle at the position to be measured relative to the myoelectric module when the user moves during the acquisition of the myoelectric signal. The motion artifact may cause the myoelectric signal to have a sudden change signal for a short time or a long time. In some embodiments, when the wearable device 130 is not worn properly, such as when the clothing does not fit well or when some of the myoelectric sensors have poor contact for a short time or a long time, it may also cause the loss of myoelectric signals or the saturation of myoelectric signals. When the positive and negative electrodes of the myoelectric sensor are in poor contact, the positive and negative electrodes cannot collect the correct myoelectric signals. At this time, it may cause the phenomenon of signal loss in the myoelectric signal, that is, there may be a missing signal in the myoelectric signal. When the positive and negative electrodes in the myoelectric sensor are not in good contact, some of the positive and negative electrodes may collect myoelectric signals, while the other parts may collect power frequency signals. Since the amplitude of the power frequency signal is much higher than the myoelectric signal, this may cause saturation signals in the myoelectric signal, that is, the signal amplitude is too high to reach saturation. In some embodiments, when the motion monitoring system 100 uses a high-pass filter to remove DC from the myoelectric signal, the myoelectric signal after DC removal may contain oscillation signals.

[0078] In order to improve the user experience, the motion monitoring system 100 can also provide a motion data processing method to identify abnormal signals in the electromyographic signal and correct the identified abnormal signals so that the corrected abnormal signals are consistent with the motion signals of the user during actual exercise, thereby improving the user experience. The motion data processing method and motion monitoring system can also promptly remind the user of abnormalities in the device when abnormal signals are identified, thereby making data collection more accurate. The motion data processing method can be executed on the processing device 110 or on the wearable device 130. Specifically, it can be executed on the processing module 220 on the wearable device 130 or on the mobile terminal device 140. For ease of illustration, the following description will take the execution of the motion data processing method on the processing module 220 in the wearable device 130 as an example. In this case, the motion signal collected by the acquisition module 210 of the wearable device 130 can be directly transmitted to the processing module 220 for data processing, without having to be transmitted to the processing device 110 or the mobile terminal device 140 through the network, thereby reducing data transmission time, improving the efficiency of motion data processing, and further improving the real-time performance of motion data processing.

[0079] Figure 6 FIG. 6 is an exemplary flow chart of a motion data processing method 6000 according to some embodiments of the present application. Figure 6 As shown, method 6000 may include:

[0080] 6200: Acquires the electromyographic signals of the corresponding measurement positions during user movement in real time.

[0081] The electromyographic signal can be collected by the acquisition module 210. In some embodiments, the electromyographic sensor in the acquisition module 210 can collect the electromyographic signal of the user during exercise. For example, when the user performs a seated chest press, the electromyographic sensor corresponding to the pectoral muscle, latissimus dorsi muscle, etc. in the wearable device can collect the electromyographic signal of the corresponding muscle position of the user. For another example, when the user performs a squat, the electromyographic sensor corresponding to the gluteus maximus, quadriceps femoris, etc. in the wearable device can collect the electromyographic signal of the corresponding muscle position of the user. For another example, when the user performs a running exercise, the electromyographic sensor corresponding to the gastrocnemius muscle, etc. in the wearable device can collect the electromyographic signal of the gastrocnemius muscle, etc. The electromyographic signal can reflect the muscle state of the specific part during exercise. The real-time can be that the processing module 220 regularly obtains the electromyographic signal from the acquisition module 220 in a short time period.

[0082] In some embodiments, the electromyographic signal may be a signal directly acquired by the electromyographic sensor in the acquisition module 210. In some embodiments, the electromyographic signal may also be a signal obtained by performing a DC removal algorithm on the signal directly acquired by the electromyographic sensor. The DC removal algorithm may be a method for removing the DC component from the electromyographic signal by calculation. The DC removal algorithm includes at least one of a de-averaging algorithm and a high-pass filtering algorithm. In order to ensure the real-time performance of the DC removal algorithm, the de-averaging algorithm may be a frame-by-frame de-averaging algorithm.

[0083] When the de-meaning algorithm is used to remove DC from the electromyographic signal, a new abnormal signal may appear at the abnormal signal after the de-meaning calculation is performed on the abnormal signal. When the high-pass filter is used to remove DC from the electromyographic signal, an oscillating signal may appear at the jump point of the actual signal. In addition, the use of a high-pass filter may cause the electromyographic signal to have a convergence delay in the early stage. The oscillating signal is also an abnormal signal and may also affect the user's monitoring of the movement.

[0084] Through the study of high-pass filter, it is found that the smaller the cut-off frequency used by high-pass filter, the slower the convergence speed, and the longer the time spent in early stage convergence, which causes the signal convergence delay to be longer, and the real-time performance is worse. On the contrary, the larger the cut-off frequency used by high-pass filter, the faster the convergence speed, and the shorter the time spent in early stage convergence, which causes the signal convergence delay to be shorter, and the real-time performance is better. Meanwhile, the smaller the cut-off frequency used by high-pass filter, the lower the oscillation height of the oscillation signal caused by high-pass filter, and the shorter the duration of oscillation signal. On the contrary, the larger the cut-off frequency used by high-pass filter, the higher the oscillation height of the oscillation signal caused by high-pass filter, and the longer the duration of oscillation signal. In order to ensure the real-time performance of electromyographic signal, processing module 220 can, based on real-time performance, predetermine the preset range of convergence delay, and based on the relationship between cut-off frequency, convergence speed and convergence delay, determine the target range of cut-off frequency.

[0085] 6400: Based on the electromyographic signal, determine an abnormal signal in the electromyographic signal.

[0086] In some embodiments, step 6400 may be to pre-process the electromyographic signal in the frequency domain or time domain, and obtain characteristic information corresponding to the electromyographic signal based on the pre-processed electromyographic signal, thereby determining abnormal signals in the electromyographic signal to monitor the user's movement. Specifically, step 6400 may include:

[0087] 6420: Process the electromyographic signal in the time domain to determine the abnormal signal; or

[0088] 6440: Process the electromyographic signal in the frequency domain to determine the abnormal signal.

[0089] Figure 7 This is an exemplary flowchart of processing electromyographic signals in the time domain according to some embodiments of the present application. Figure 7 Shown is step 6420. Figure 7 As shown, step 6420 may include:

[0090] 6422: Based on the time domain window of the electromyographic signal, select at least one time window from the time domain window of the electromyographic signal.

[0091] The at least one time window covers different time ranges. In some embodiments, the time domain window may include at least one specific window. A specific window refers to a window selected from the time domain window with a specific time length. For example, if the time domain window of the electromyographic signal has a time length of 3 seconds, the time length of the specific window may be 100 ms. In some embodiments, the specific window may include at least one different time window. In some embodiments, the specific window may include a single time window. In some embodiments, the specific window may include multiple time windows. When the specific window includes multiple time windows, for example, the specific window may include a first time window and a second time window. The first time window may refer to a window with a corresponding time length within the specific window. For example, if the time length of the specific window is 100 ms, the time length of the first time window may be 80 ms. The second time window may refer to another window with a corresponding time length within the specific window. For example, if the time length of the specific window is 100 ms, the time length of the second time window may be 20 ms. In some embodiments, the first time window and the second time window may be consecutive time windows within the same specific window. In some embodiments, the first time window and the second time window may also be discontinuous or overlapping time windows within the same specific window. In some embodiments, the processing module 220 can, based on the time domain window of the electromyographic signal, slide and update the specific window in sequence according to a specific time length from the time starting point of the time domain window of the electromyographic signal, and can further divide the updated specific window into a first time window and a second time window. The specific time length mentioned here can be less than 1s, 2s, 3s, etc. For example, the processing module 220 can select a specific window with a specific time length of 100ms and divide the specific window into a first time window of 80ms and a second time window of 20ms. Furthermore, the specific window can be updated by sliding along the time direction. The sliding distance here can be the time length of the second time window (for example, 20ms), or other suitable time lengths, for example, 30ms, 40ms, etc. As mentioned above, different time windows cover different time ranges. For the convenience of description, we define the time range covered by the first time window as the prior time window, and the time range covered by the second time window as the subsequent time window. That is, the time range corresponding to the first time window is before the time range corresponding to the second time window.

[0092] In some embodiments, the time length corresponding to the first time window may be greater than the time length corresponding to the second time window. In some embodiments, the specific time length corresponding to the specific window may be less than 1s. In some embodiments, the ratio of the time length corresponding to the first time window to the time length corresponding to the second time window may be greater than 2. In some embodiments, the selection of the time length corresponding to the first time window, the time length corresponding to the second time window, and the specific time length corresponding to the specific window can, on the one hand, ensure that the shortest glitch signal length (for example, 40ms) can be removed and have a high signal-to-noise ratio, and on the other hand, can make the system's computational load relatively small, reduce the system's repeated computations, and reduce time complexity, thereby improving the system's computational efficiency and computational accuracy.

[0093] When the specific window includes a time window, the specific window may include a first time window or a second time window. For example only, when the specific window includes a time window, the specific window may include a second time window.

[0094] 6424: Determine the abnormal signal based on characteristic information corresponding to the electromyographic signal in the at least one time window.

[0095] In some embodiments, the characteristic information corresponding to the electromyographic signal includes at least one of amplitude information and statistical information of the amplitude information. In some embodiments, the amplitude information can be the average amplitude of the electromyographic signal corresponding to each time window in the at least one time window or the square of the average amplitude. In some embodiments, the statistical information of the amplitude information can include at least one of the entropy, variance, standard deviation, standard deviation of the standard deviation and zero-crossing rate of the amplitude information. Entropy can be regarded as a measure of the degree of disorder of a system. Variance, standard deviation and standard deviation of standard deviation can be used to evaluate the measure of the degree of discreteness of data. Zero-crossing rate refers to the ratio of the sign change of a signal, for example, the signal changes from a positive number to a negative number or vice versa.

[0096] In some embodiments, a normal electromyographic signal is generally a short-term stationary signal, that is, the mean and variance of the amplitude of the electromyographic signal within a certain period of time are stable or have small fluctuations, while abnormal signals such as mutation signals, missing signals or saturation signals are non-stationary signals. Therefore, the amplitude information of the electromyographic signal and the statistical information of the amplitude information are significantly different from the amplitude information of the abnormal signal and the statistical information of the amplitude information. The motion data processing method 6000 can identify abnormal signals based on the characteristic information corresponding to the electromyographic signal. In some embodiments, the processing module 220 can obtain the amplitude information or the statistical information of the amplitude information corresponding to the electromyographic signal in different time windows (for example, the first time window and / or the second time window) to determine the position of the abnormal signal. The specific description of determining the position of the abnormal signal based on the characteristic information corresponding to the electromyographic signal in different time windows will be described in detail later.

[0097] For ease of description, the following description uses amplitude information as an example. Those skilled in the art will appreciate that amplitude feature information, including statistical information of amplitude information, also falls within the scope of this specification. When the feature information includes statistical information of amplitude information, its identification method is the same as the identification method when the feature information is amplitude information, and this specification will not elaborate on this.

[0098] As mentioned above, in some embodiments, the abnormal signal may include a mutation signal. Figure 8 Schematic diagram of the mutation signal according to some embodiments of the present application. Figure 8 As shown, 001 in the figure is a mutation signal. As mentioned above, the mutation signal 001 of the electromyographic signal can be described by a singular point. Exemplary singular points may include glitch signals, discontinuous signals, etc. For the convenience of description, the following description will take the singular point as an example of a glitch signal. A singular point may be an electromyographic signal whose amplitude suddenly changes at a certain moment, causing the discontinuity of the signal. For another example, the electromyographic signal is relatively smooth in shape, and the amplitude of the electromyographic signal does not suddenly change, but the first-order differential of the electromyographic signal suddenly changes, and the first-order differential is discontinuous.

[0099] When identifying a sudden change signal, we illustrate the case where at least one time window includes multiple time windows. For ease of description, we use the example where the multiple time windows are a first time window and a second time window, and the example where the characteristic information is amplitude information. Those skilled in the art will appreciate that multiple time windows including more than two time windows also fall within the scope of protection of this specification.

[0100] Figure 9 is an exemplary flow chart for identifying mutation signals according to some embodiments of the present application. Figure 9 Step 6424 is shown. Figure 9As shown, step 6424 may include:

[0101] 6424-1: Determine multiple feature information corresponding to the electromyographic signals in the multiple time windows.

[0102] Step 6424-1 may be determining the characteristic information corresponding to the electromyographic signal in each of the multiple time windows. Multiple time windows correspond to multiple characteristic information, and the multiple time windows correspond one-to-one to the multiple characteristic information. Taking the multiple time windows including the first time window and the second time window as an example, the characteristic information is amplitude information as an example for explanation. In step 6424-1, the first amplitude information corresponding to the electromyographic signal in the first time window and the second amplitude information corresponding to the electromyographic signal in the second time window are determined. In some embodiments, the processing module 220 may select the time length of the first time window and the second time window, and extract the first amplitude information corresponding to the electromyographic signal within the time length of the first time window and the second amplitude information corresponding to the electromyographic signal within the time length of the second time window. In some embodiments, the first amplitude information may include the average amplitude of the electromyographic signal in the first time window or the square of the average amplitude of the electromyographic signal in the first time window, and the second amplitude information may include the average amplitude of the electromyographic signal in the second time window or the square of the average amplitude of the electromyographic signal in the second time window. For example, the processing module 220 can select a first time window length of 80ms and extract the first amplitude information corresponding to the electromyographic signal in the first time window, and the processing module 220 can select a second time window length of 20ms and extract the second amplitude information corresponding to the electromyographic signal in the second time window.

[0103] In some embodiments, the length of the first time window and the length of the second time window are selected based on the shortest glitch signal length and the computational complexity of the system. In some embodiments, the length of the first time window and the length of the second time window can be selected based on the characteristics of the glitch signal. The length of the ECG glitch signal is 40ms-100ms, the time interval between two glitch signals in the ECG signal can be approximately 1s, the two sides of the glitch signal peak are substantially symmetrical, and the amplitude distribution on both sides of the glitch signal is relatively even. In some embodiments, when the glitch signal is an ECG signal, a length shorter than the length of the glitch signal, for example, half the length of the glitch signal, can be selected as the length of the second time window. The length of the first time window can be greater than the length of the second time window, for example, four times the length of the second time window. In some embodiments, the length of the first time window is within the range of the glitch signal interval (approximately 1s) minus the length of the second time window. It should also be noted that the time length of the first time window and the time length of the second time window selected above are not limited to the above description, as long as the sum of the time length of the second time window and the time length of the first time window is less than the time interval of two adjacent glitch signals, or the time length of the second time window is less than the length of a single glitch signal, or the amplitude of the electromyographic signal in the second time window and the amplitude of the electromyographic signal in the first time window have good distinction.

[0104] 6424-2: Determine that the ratio of the characteristic information corresponding to the time window after the time range to the characteristic information corresponding to the time window before the time range exceeds a preset threshold, and determine that the electromyographic signal in the time window after the time range is the mutation signal.

[0105] As mentioned above, the time range corresponding to the first time window is before the time range corresponding to the second time window. That is, the time window with the time range in front is the first time window, and the time window with the time range in the back is the second time window. Calculating the ratio of the characteristic information corresponding to the time window with the time range in the back to the characteristic information corresponding to the time window with the time range in the front can be calculating the ratio of the characteristic information corresponding to the electromyographic signal in the second time window to the characteristic information corresponding to the electromyographic signal in the first time window, that is, the ratio of the second amplitude information corresponding to the electromyographic signal in the second time window to the first amplitude information corresponding to the electromyographic signal in the first time window.

[0106] In some embodiments, the processing module 220 may determine whether the ratio of the second amplitude information corresponding to the electromyographic signal in the second time window to the first amplitude information corresponding to the electromyographic signal in the first time window is greater than a first threshold. The first threshold here may be stored in the memory or hard disk of the wearable device 130, or may be stored in the processing device 110, or may be adjusted according to actual circumstances. In some embodiments, the processing module 220 may perform signal correction processing on the electromyographic signal in the second time window based on the determination result of the relationship between the ratio of the second amplitude information to the first amplitude information and the first threshold in step 6424-2. In some embodiments, if the processing module 220 determines that the ratio of the second amplitude information to the first amplitude information is greater than the first threshold, step 6424-2 may determine that the electromyographic signal in the second time window is a sudden change signal, and process the electromyographic signal in the second time window in step 6600 to correct the sudden change signal. In some embodiments, processing the electromyographic signal in the second time window may include performing signal correction processing on the electromyographic signal in the second time window based on electromyographic signals within a specific time range before or after the second time window. Details of step 6600 will be described in detail later.

[0107] In other embodiments, if the processing module 220 determines that the ratio of the second amplitude information to the first amplitude information is not greater than the first threshold, the processing module 220 may retain the electromyographic signal within the second time window. In some embodiments, the processing module 220 may retain the electromyographic signal within the second time window based on the judgment result of the magnitude relationship between the ratio of the second amplitude information to the first amplitude information and the first threshold. For example, in some embodiments, if the ratio of the second amplitude information to the first amplitude information is not greater than the first threshold, the electromyographic signal within the second time window corresponding to the second amplitude information is not a sudden change signal, and the electromyographic signal may be retained, that is, the electromyographic signal within the second time window is retained.

[0108] It should be noted that as the user's muscles exert force, the charge gradually accumulates and the amplitude of the electromyographic signal gradually increases. Therefore, in the absence of a glitch signal, the amplitude of the electromyographic signal in two adjacent time windows (for example, the first time window and the second time window) will not change suddenly. In some embodiments, judging and removing glitch signals in the electromyographic signal based on process 6424 can achieve real-time processing of the glitch signal, thereby enabling the wearable device 130 or mobile terminal device 140 to provide real-time feedback on the user's exercise status, helping the user to exercise more scientifically.

[0109] In some embodiments, the method of determining the singular point in the electromyographic signal may also include but is not limited to one or more of Fourier transform, wavelet transform, fractal dimension, etc., which will not be described in detail in this specification.

[0110] As previously mentioned, in some embodiments, the abnormal signal may include a missing signal. Figure 10 Schematic diagram of missing signals according to some embodiments of the present application. Figure 10 As shown in the figure, 002 is a missing signal. As mentioned above, the missing signal of the electromyographic signal can be caused by the complete separation of the positive and negative electrodes of the electromyographic sensor, resulting in signal loss. The amplitude of the missing signal is basically 0 or close to 0.

[0111] When identifying missing signals, we illustrate the example of at least one time window including one time window. For ease of description, we illustrate the example of at least one time window being a second time window and the example of the characteristic information being amplitude information. Those skilled in the art will appreciate that at least one time window including more than one time window also falls within the scope of protection of this specification.

[0112] Figure 11 FIG. 1 is an exemplary flow chart of identifying missing signals according to some embodiments of the present application. Figure 11 As shown, step 6424 may include:

[0113] 6424-3: Determine at least one feature information corresponding to the electromyographic signal in the at least one time window.

[0114] Step 6424-3 may involve determining characteristic information corresponding to the electromyographic signal in each of the at least one time window. At least one time window corresponds to at least one piece of characteristic information, and at least one time window has a one-to-one correspondence with at least one piece of characteristic information. This description will be made using the example of at least one time window including a second time window, and the characteristic information being amplitude information. This step is substantially the same as step 6424-1 and will not be further described here.

[0115] In some embodiments, the length of the second time window is selected based on the shortest missing signal length and the computational complexity of the system. In some embodiments, the length of the second time window can be selected based on the impact of the missing signal on the data sampling of the smooth curve. For example, the length of the second time window can be less than the time period of the data sampling. For example, half the length of the time period of the data sampling can be used as the time length of the second time window. It should also be noted that the length of the second time window selected above is not limited to the above description, as long as the length of the second time window is less than the length of the time period of the data sampling. Data sampling will be described in detail later.

[0116] 6424-4: Determine that the myoelectric signal in the time window corresponding to the feature information below a pre-stored second threshold value in the at least one feature information is the missing signal.

[0117] As mentioned above, the amplitude of the missing signal is basically 0 or close to 0. Therefore, the amplitude information of the missing signal is generally lower than the second threshold. The second threshold here can be stored in the memory or hard disk of the wearable device 130, or stored in the processing device 110, or adjusted according to actual conditions. The second threshold can be pre-calculated and stored before step 6424-4. In some embodiments, the second threshold can be the system background noise. The system background noise can be calculated based on the static electromyographic signal collected when the user is in a stationary state or the wearable device 130 is not in use. In some embodiments, the second threshold can also be based on the minimum statistical value of the historical electromyographic signal. For example, the minimum value of the normal electromyographic signal collected by the electromyographic sensor at a historical moment. Specifically, step 6424-4 can be to determine the size relationship between the feature information corresponding to the electromyographic signal in at least one feature information (such as the second time window) and the second threshold. In some embodiments, if the processing module 220 determines that the second amplitude information is less than the second threshold, step 6424-4 can determine that the electromyographic signal in the second time window is a missing signal, and process the electromyographic signal in the second time window through step 6600 to correct the missing signal. In some embodiments, processing the electromyographic signal in the second time window can include performing signal correction processing on the electromyographic signal in the second time window based on electromyographic signals within a specific time range before or after the second time window. The details of step 6600 will be described in detail later.

[0118] In other embodiments, if the processing module 220 determines that at least one characteristic information is higher than the second threshold, it is determined that there is no missing signal in at least one time window. For example, if the processing module 220 determines that the second amplitude information is greater than or not less than the second threshold, the processing module 220 can retain the electromyographic signal in the second time window. In some embodiments, the processing module 220 can retain the electromyographic signal in the second time window based on the judgment result of the size relationship between the second amplitude information and the second threshold. For example, in some embodiments, the second amplitude information is greater than or not less than the second threshold, the electromyographic signal in the second time window corresponding to the second amplitude information is not a missing signal, and the electromyographic signal can be retained, that is, the electromyographic signal in the second time window is retained.

[0119] As previously mentioned, in some embodiments, the abnormal signal may include a saturation signal. Figure 12 Schematic diagram of a saturation signal according to some embodiments of the present application. Figure 12 As shown in the figure, 003 is the saturation signal. As mentioned above, the saturation signal of the myoelectric signal can be caused by the partial separation of the positive and negative electrodes of the myoelectric sensor, resulting in signal saturation. The amplitude of the saturation signal is much higher than the normal myoelectric signal.

[0120] When identifying a saturated signal, we take the example of at least one time window including one time window. For ease of description, we take the example of the at least one time window being a second time window and the example of the characteristic information being amplitude information. Those skilled in the art will appreciate that the at least one time window including more than one time window also falls within the scope of protection of this specification.

[0121] Figure 13 FIG. 1 is an exemplary flow chart of identifying a saturation signal according to some embodiments of the present application. Figure 13 As shown, step 6424 may include:

[0122] 6424-5: Determine at least one feature information corresponding to the electromyographic signal in the at least one time window.

[0123] Step 6424-5 may involve determining characteristic information corresponding to the electromyographic signal in each of the at least one time window. At least one time window corresponds to at least one piece of characteristic information, and at least one time window has a one-to-one correspondence with at least one piece of characteristic information. This description will be made using the example of at least one time window including a second time window, and the characteristic information being amplitude information. This step is substantially the same as step 6424-1 and will not be further described here.

[0124] In some embodiments, the length of the second time window is selected based on the shortest saturation signal length and the computational complexity of the system. In some embodiments, the length of the second time window can be selected based on the impact of the saturation signal on the data sampling of the smooth curve. For example, the length of the second time window can be less than the time period of the data sampling. For example, half the length of the time period of the data sampling can be used as the time length of the second time window. It should also be noted that the length of the second time window selected above is not limited to the description above, as long as the length of the second time window is less than the length of the time period of the data sampling. Data sampling will be described in detail later.

[0125] 6424-6: Determine that the myoelectric signal in the time window corresponding to the feature information higher than the pre-stored saturation feature information in the at least one feature information is the saturation signal.

[0126] As previously mentioned, the amplitude of the saturation signal is much higher than that of a normal electromyographic signal. In some embodiments, the processing module 220 can determine whether at least one feature information is greater than the saturation feature information. The saturation feature information here can be stored in the memory or hard disk of the wearable device 130, or can be stored in the processing device 110, or adjusted according to actual conditions. The saturation feature information can be pre-calculated and stored before step 6424-6. The saturation feature information can be calculated based on the saturated electromyographic signal collected when the positive and negative electrodes of the electromyographic sensor are partially detached. Specifically, step 6424-6 can be to determine the magnitude relationship between the feature information corresponding to the electromyographic signal in at least one feature information (such as the second time window) and the saturation feature information. In some embodiments, if the processing module 220 determines that the second amplitude information is greater than the saturation feature information, step 6424-6 can determine that the electromyographic signal in the second time window is a saturated signal, and process the electromyographic signal in the second time window through step 6600 to correct the saturation signal. In some embodiments, processing the electromyographic signal in the second time window can include performing signal correction processing on the electromyographic signal in the second time window based on the electromyographic signal in a specific time range before or after the second time window. The details of step 6600 will be introduced in detail in the following description.

[0127] In other embodiments, if the processing module 220 determines that at least one characteristic information is less than the saturation characteristic information, it is determined that there is no saturation signal in at least one time window. For example, if the processing module 220 determines that the second amplitude information is not greater than or less than the saturation characteristic information, the processing module 220 can retain the electromyographic signal in the second time window. In some embodiments, the processing module 220 can retain the electromyographic signal in the second time window based on the judgment result of the size relationship between the second amplitude information and the saturation characteristic information. For example, in some embodiments, if the second amplitude information is not greater than or less than the saturation characteristic information, the electromyographic signal in the second time window corresponding to the second amplitude information is not a saturation signal, and the electromyographic signal can be retained, that is, the electromyographic signal in the second time window is retained.

[0128] As mentioned above, in some embodiments, the abnormal signal may include an oscillation signal caused by the high-pass filtering algorithm. Figure 14 is a schematic diagram of an oscillation signal according to some embodiments of the present application. Figure 14 As shown, 004 is the oscillation signal.

[0129] Figure 15 This is an exemplary flow chart of identifying an oscillation signal according to some embodiments of the present application. Figure 15 Step 6420 is shown. Figure 15 As shown, step 6420 may include:

[0130] 6426: Calculate a reference oscillation height and a reference duration of the oscillation signal based on the filter parameters of the high-pass filtering algorithm.

[0131] As previously mentioned, the smaller the cutoff frequency used by the high-pass filter, the lower the oscillation height of the oscillating signal caused by the high-pass filter, and the shorter the duration of the oscillating signal. Conversely, the larger the cutoff frequency used by the high-pass filter, the higher the oscillation height of the oscillating signal caused by the high-pass filter, and the longer the duration of the oscillating signal. The processing module 220 can calculate a reference oscillation height and a reference duration of the oscillating signal based on the cutoff frequency of the high-pass filter. The filter parameters include the cutoff frequency.

[0132] 6428: Match the electromyographic signal with the reference oscillation height and the reference duration in real time, and determine the electromyographic signal corresponding to the signal interval in the electromyographic signal that matches the reference oscillation height and the reference duration as the oscillation signal.

[0133] The processing module 220 can match the electromyographic signal with the reference oscillation height and reference duration corresponding to the oscillation signal to find the oscillation signal from the electromyographic signal. In some embodiments, if the processing module 220 determines that there is a signal interval in the electromyographic signal that matches the reference oscillation height and reference duration, the processing module 220 can determine that the electromyographic signal corresponding to the matched signal interval is an oscillation signal, and process the oscillation signal through step 6600 to correct the oscillation signal. In some embodiments, processing the oscillation signal may include performing signal correction processing on the oscillation signal based on the electromyographic signal within a specific time range before or after the oscillation signal. The details of step 6600 will be described in detail in the following description.

[0134] In other embodiments, if the processing module 220 determines that there is a signal interval in the electromyographic signal that does not match the reference oscillation height and the reference duration, the processing module 220 can determine that the electromyographic signal corresponding to the unmatched signal interval is not an oscillation signal, and the processing module can retain the electromyographic signal within the unmatched signal interval.

[0135] As previously described, step 6400 may further include step 6440: processing the electromyographic signal in the frequency domain to determine the abnormal signal. In some embodiments, processing the electromyographic signal in the frequency domain may include filtering the electromyographic signal in the frequency domain to select or retain components in a specific frequency range in the electromyographic signal in the frequency domain. In some embodiments, the frequency range of the electromyographic signal acquired by the acquisition module 210 is 1 Hz-1000 Hz, and the electromyographic signal may be filtered and electromyographic signals in a specific frequency range (e.g., 30 Hz-150 Hz) may be selected for subsequent processing. In some embodiments, the specific frequency range may be 10 Hz-500 Hz. Preferably, the specific frequency range may be 15 Hz-300 Hz. More preferably, the specific frequency range may be 30 Hz-150 Hz. In some embodiments, the filtering process may include low-pass filtering. In some embodiments, the low-pass filter may include an LC passive filter, an RC passive filter, an RC active filter, or a passive filter composed of special components. In some embodiments, the passive filter composed of special components may include one or more of a piezoelectric ceramic filter, a crystal filter, and a surface acoustic wave filter. It should be noted that the specific frequency range is not limited to the above range, and can also be other ranges, which can be selected according to actual conditions.

[0136] Figure 16 This is an exemplary flowchart of processing electromyographic signals in the frequency domain according to some embodiments of the present application. Figure 16 Shown is step 6440. Figure 16 As shown, step 6440 may include:

[0137] 6442: Based on a frequency domain conversion algorithm, obtain a frequency domain signal of the electromyographic signal in the frequency domain in real time.

[0138] The processing module 220 can perform frequency domain conversion on the electromyographic signal in the time domain in real time to obtain a frequency domain signal of the electromyographic signal in the frequency domain. The frequency domain conversion algorithm can be Fourier transform, wavelet transform, Laplace transform, Z transform, etc. When the processing module 220 executes step 6442, the frequency domain conversion can be performed with each frame of the electromyographic signal as the basic conversion unit. The processing module 220 can perform frequency domain conversion on the electromyographic signal frame by frame.

[0139] 6444: Determine the spectrum characteristics of the frequency domain signal in real time.

[0140] In some embodiments, the spectral characteristics of the frequency domain signal include at least one of spectral shape, power spectral density, average power frequency, median frequency and wavelet scale. In some embodiments, the frequency distribution of normal electromyographic signals is mainly concentrated in the frequency range of 20-400 Hz, the energy distribution area of normal electromyographic signals is mainly in the frequency range of 50-200 Hz, and the statistical mean of normal electromyographic signals is generally a Gaussian-like shape of a single peak. The spectral distribution shape of mutation signals, such as burr signals, is generally asymmetric, which is significantly different from the Gaussian-like shape of normal electromyographic signals. The frequency of the noise signal caused by motion artifacts is generally below 20 Hz. The frequency of the power frequency signal (i.e., saturation signal) collected due to the detachment of some electrodes of the electromyographic sensor is generally distributed at 50 Hz, and the spectrum of the saturation signal is flatter than that of the normal electromyographic signal. It can be seen that the spectral characteristics of normal electromyographic signals and abnormal signals are significantly different. The motion data processing method 6000 can identify abnormal signals from normal electromyographic signals based on the spectral characteristics of the frequency domain signals of the electromyographic signals. When executing step 6444 , the processing module 220 may determine the frequency spectrum characteristics of the frequency domain signal of each frame of the electromyographic signal frame by frame.

[0141] 6446: Determine the electromyographic signal corresponding to the frequency domain signal whose frequency spectrum characteristic does not meet the preset condition as the abnormal signal.

[0142] When executing step 6446, the processing module 220 can determine the spectral characteristics of the frequency domain signal of each frame of the electromyographic signal frame by frame based on the preset conditions. In some embodiments, the processing module 220 can determine whether the spectral characteristics of the frequency domain signal corresponding to the electromyographic signal of the current frame meet the preset conditions. Among them, the spectral characteristics of the normal electromyographic signal should meet the preset conditions. The abnormal signal does not meet the preset conditions. The preset conditions can be conditions derived from the statistical characteristics of the spectral characteristics of the normal electromyographic signal. The preset conditions can be stored in the memory or hard disk of the wearable device 130, or stored in the processing device 110, or adjusted according to actual conditions. In some embodiments, the processing module 220 can identify abnormal signals from normal electromyographic signals based on the judgment result of whether the spectral characteristics of the frequency domain signal in step 6446 meet the preset conditions, and perform signal correction processing on the abnormal signals. In some embodiments, if the processing module 220 determines that the frequency spectrum characteristics of the frequency domain signal corresponding to the electromyographic signal of the current frame do not meet the preset conditions, the electromyographic signal of the current frame that does not meet the preset conditions is determined to be an abnormal signal, and the abnormal signal is processed through step 6600 to correct the abnormal signal. In some embodiments, processing the abnormal signal may include performing signal correction processing on the abnormal signal based on the electromyographic signal within a specific time range before or after the abnormal signal. The details of step 6600 will be described in detail in the following description.

[0143] In other embodiments, if the processing module 220 determines that the spectrum characteristics of the frequency domain signal corresponding to the electromyographic signal of the current frame meet the preset conditions, the electromyographic signal of the current frame is not an abnormal signal, and the electromyographic signal can be retained, then the processing module 220 can retain the electromyographic signal of the current frame.

[0144] like Figure 6 As shown, the method 6000 may further include:

[0145] 6600: Correct the abnormal signal.

[0146] In some embodiments, method 6000 may further include performing signal correction processing on abnormal signals in real time. Signal correction processing refers to correcting abnormal signals (such as mutation signals, missing signals, saturation signals, and oscillation signals) in electromyographic signals. As previously described, in step 6400, the processing module 220 identifies abnormal signals in real time. In step 6600, the processing module 220 also corrects abnormal signals in real time. In other words, the processing module 220 can identify abnormal signals in real time and correct the abnormal signals in real time.

[0147] Figure 17 This is an exemplary flowchart of correcting abnormal signals according to some embodiments of the present application. Figure 17 Shown is step 6600. Figure 17 As shown, step 6600 may include:

[0148] 6620: Perform data sampling on the electromyographic signal before the abnormal signal in real time to obtain sampled data.

[0149] As mentioned above, the processing module 220 can identify abnormal signals in real time and correct the abnormal signals in real time. That is to say, when the processing module 220 identifies a new abnormal signal, it has already completed the correction processing for the abnormal signal that existed before the new abnormal signal. In other words, the electromyographic signal before the current abnormal signal is composed of a normal electromyographic signal and an abnormal signal that has been corrected, that is, there is no abnormal signal in the electromyographic signal before the current abnormal signal. In step 6620, the processing module 220 can complete the data sampling of the electromyographic signal before the current abnormal signal in real time, thereby obtaining the sampling data corresponding to the electromyographic signal before the current abnormal signal.

[0150] The data sampling can be based on electromyographic signals, and a number of discrete data, namely the sampled data, are obtained by sampling or other methods. The sampled data can be discrete data obtained after data sampling. Specifically, the data sampling method can be to obtain discrete data based on a specific time period. The specific time period can be of any length, for example, the specific time period can be the length of one frame, or the length of 0.5 frames, or even shorter, for example, averaging 10, 20, 30, or even more discrete data in one frame. The discrete data can be statistical data within the specific time period, for example, the data average value, median value, etc. within the specific time period.

[0151] 6640: Based on the sampling data corresponding to the time domain window of the electromyographic signal, determine the predicted data corresponding to the moment when the abnormal signal is located.

[0152] The processing module 220 may perform data fitting on the sampled data to obtain a fitted curve. In some embodiments, the processing module 220 may perform data fitting on the sampled data based on a fitting function to obtain the fitted curve. In some embodiments, the processing module 220 may also perform data fitting on the sampled data based on a neural network method to obtain the fitted curve.

[0153] In some embodiments, step 6640 may be to determine a fitting function based on the sampled data corresponding to the time domain window, and calculate the predicted data corresponding to the moment when the abnormal signal is located based on the fitting function. The fitting function may be a curve function of any form. In some embodiments, the fitting function may be a sine function or a cosine function. In some embodiments, the fitting function may be a function of different orders, such as a quadratic function, a cubic function, a quartic function, and the like. The independent variable in the fitting function is time, and the dependent variable is the amplitude of the electromyographic signal. In step 6640, the processing module 220 may perform data fitting based on the sampled data to determine the fitting function, and predict the electromyographic signal amplitude corresponding to the moment when the abnormal signal is located based on the fitting function to obtain the predicted data corresponding to the moment when the abnormal signal is located, and the predicted data may be the amplitude of the electromyographic signal corresponding to the moment when the abnormal signal is located.

[0154] In some embodiments, step 6640 may also be based on the sampled data corresponding to the time domain window and a trained LSTM network to calculate the predicted data corresponding to the moment when the abnormal signal is located. The LSTM (Long Short-Term Memory) network is a recurrent neural network that can learn long-term dependency information and make predictions. In some embodiments, the processing module 220 may also calculate the predicted data corresponding to the moment when the abnormal signal is located based on other recurrent neural networks, such as a GRU (Gated Recurrent Unit) network or an RNN (Recurrent Neural Network) network.

[0155] 6660: Based on the predicted data, determine the correction data corresponding to the moment when the abnormal signal occurs.

[0156] In step 6660, after obtaining the predicted data, the processing module 220 needs to determine whether the predicted data meets the usage requirements, that is, whether the predicted data is a reasonable electromyographic signal. As mentioned above, a normal electromyographic signal is generally a relatively stable signal. The processing module 220 can determine whether the predicted data is a reasonable electromyographic signal based on other electromyographic signals around the predicted data. In some embodiments, step 6660 may include:

[0157] 6662: Determine that the predicted data is within a preset range, and use the predicted data as the correction data; or

[0158] 6664: Determine that the predicted data is not within the preset range, and use the sampling data corresponding to at least one frame of electromyographic signal adjacent to the abnormal signal as the correction data.

[0159] The preset range may include a data range consisting of the maximum and minimum values of the electromyographic signal within the time domain window. Specifically, the processing module 220 may obtain the maximum and minimum values of the electromyographic signal within the time domain window preceding the abnormal signal and determine whether the predicted data falls between the maximum and minimum values. As previously described, the motion data processing method 6000 can identify abnormal signals in real time and correct them. Therefore, the electromyographic signal preceding the abnormal signal is a combination of a normal electromyographic signal and a corrected abnormal signal. That is, there are no abnormal signals in the electromyographic signals between the abnormal signals. Therefore, all electromyographic signals preceding the abnormal signal are normal and reasonable electromyographic signals. The processing module 220 may determine whether the predicted data is reasonable by determining whether the predicted data falls within the data range consisting of the maximum and minimum values of the electromyographic signal within the time domain window preceding the abnormal signal. In some embodiments, when the processing module 220 determines that the predicted data falls within the data range consisting of the maximum and minimum values of the electromyographic signal within the time domain window preceding the abnormal signal, the predicted data is determined to be a normal and reasonable electromyographic signal. In this case, the processing module 220 may use the predicted data as correction data to correct the abnormal signal. In some embodiments, when the processing module 220 determines that the predicted data is not within the data range consisting of the maximum and minimum values of the electromyographic signal in the time domain window before the abnormal signal, the predicted data is determined to be an abnormal or unreasonable electromyographic signal. At this time, the processing module 220 cannot use the predicted data as correction data to correct the abnormal signal. At this time, the processing module 220 can use the sampled data corresponding to at least one frame of electromyographic signal adjacent to the abnormal signal as the correction data. The sampled data corresponding to at least one frame of electromyographic signal adjacent to the abnormal signal can be a statistical value of multiple sampled data, such as an average value, a median value, and the like.

[0160] 6680: Use the correction data to correct the abnormal signal.

[0161] After determining the correction data, the processing module 220 may use the correction data to correct the abnormal signal. Specifically, the processing module 220 may use the correction data to replace the abnormal signal.

[0162] Figure 18 Schematic diagram of the electromyographic signal and the corrected smooth curve according to some embodiments of the present application. Figure 18As shown, 007 is an electromyographic signal and 008 is a smooth curve. It can be seen from this that the motion data processing method 6000 and motion monitoring system 100 provided by the present application can process the electromyographic signal from the frequency domain or time domain to identify abnormal signals in the electromyographic signal, such as mutation signals, missing signals, saturation signals and oscillation signals caused by high-pass filters, etc. The motion data processing method 6000 and motion monitoring system 100 can also sample the electromyographic signal through a data sampling algorithm, and predict the data at the moment of the abnormal signal based on the sampled data, thereby obtaining predicted data, and using the predicted data to replace the abnormal signal, thereby correcting the abnormal signal. The motion data processing method 6000 and motion monitoring system 100 can not only accurately identify abnormal signals, but also correct abnormal signals, so that the corrected data is more consistent with the user's actual movement, thereby improving user experience.

[0163] In some embodiments, the motion data processing method 6000 and the motion monitoring system 100 can also promptly remind the user of abnormal device wearing when an abnormal signal is identified, thereby making data collection more accurate. For example, when the motion data processing method 6000 identifies an abnormal signal (such as a missing signal or a saturated signal), the processing module 220 can send feedback information to the control module 230. The feedback information can be feedback that the wearable device 130 may be improperly worn or pulled during the user's exercise. The feedback information can also include prompting the user to adjust the position of the wearable device 130, etc. The control module 230 can control the input / output module 260 based on the feedback information, and then control the mobile terminal device 140 to send feedback results of the user's exercise to the user. In some embodiments, the control module 230 can also control one or more sensors or other modules in the acquisition module 210 to provide feedback to the human body. For example, when the electromyographic signal corresponding to a muscle of the user is abnormal during exercise, the control module 230 can control the electrode module at the muscle position to electrically stimulate the user to prompt the user to adjust the wearable device 130 in a timely manner.

[0164] In some embodiments, performing signal correction processing on abnormal signals in electromyographic signals in the time domain may further include removing singular points in the electromyographic signals, for example, deleting the singular points and the signals within a time range near the singular points. Alternatively, performing signal correction processing on electromyographic signals in the time domain may include correcting the singular points of the electromyographic signals according to the characteristic information of the electromyographic signals within a specific time range, for example, adjusting the amplitude of the singular points according to the signals around the singular points. In some embodiments, the characteristic information of the electromyographic signals may include one or more of amplitude information and statistical information of the amplitude information. The statistical information of the amplitude information (also known as amplitude entropy) refers to the distribution of the amplitude information of the electromyographic signals in the time domain. In some embodiments, after determining the position (for example, the corresponding time point) of the singular point in the electromyographic signal by a signal processing algorithm (for example, Fourier transform, wavelet transform, fractal dimension), the singular point may be corrected according to the electromyographic signals within a specific time range before or after the position of the singular point. For example, when the singular point is a mutation trough, the electromyographic signal at the mutation trough can be supplemented based on the characteristic information (e.g., amplitude information, statistical information of the amplitude information) of the electromyographic signal within a specific time range (e.g., 5ms-60ms) before or after the mutation trough.

[0165] In some embodiments, other methods may be used to perform signal correction processing on abnormal signals in electromyographic signals, such as high-pass method, low-pass method, band-pass method, wavelet transform reconstruction method, etc. In some embodiments, for application scenarios that are insensitive to low-frequency signals, a 100Hz high-pass filter may be used to remove glitch signals. In some embodiments, in addition to performing signal correction processing on electromyographic signals, other signal processing methods may also be performed on electromyographic signals, such as filtering processing, signal amplification, phase adjustment, etc. In some embodiments, the electromyographic signals of the user collected by the electromyographic sensor may be converted into digital electromyographic signals through an analog-to-digital converter (ADC), and the converted digital electromyographic signals may be filtered, and the filtering processing may filter out the power frequency signal and its harmonic signals, etc. In some embodiments, the processing of the electromyographic signals may also include removing the user's motion artifacts. The motion artifacts here refer to the signal noise generated when the muscles at the position to be measured move relative to the electromyographic module when the user moves during the process of acquiring the electromyographic signals.

[0166] It should be noted that the above description of process 6000 is for illustrative purposes only and does not limit the scope of application of this specification. Those skilled in the art, guided by this specification, may make various modifications and alterations to process 6000. For example, the identification and correction of sudden change signals in process 6000 is merely an example of a glitch signal. When the sudden change signal is a trough signal, the above steps and solutions may be adjusted, or other methods may be employed for signal correction processing. However, such modifications and alterations remain within the scope of this specification.

[0167] The basic concepts have been described above. It will be apparent to those skilled in the art that the detailed disclosure above is merely illustrative and does not limit the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and amendments to the present application. Such modifications, improvements, and amendments are suggested in the present application and remain within the spirit and scope of the exemplary embodiments of the present application.

[0168] At the same time, this application uses specific terms to describe the embodiments of this application. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a certain feature, structure, or characteristic related to at least one embodiment of this application. Therefore, it should be emphasized and noted that "one embodiment," "an embodiment," or "an alternative embodiment" mentioned twice or multiple times in different locations in this application does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this application may be appropriately combined.

Claims

1. A motion data processing method, characterized in that: include: Acquire, in real time, electromyographic signals measured by multiple sensors on a wearable device at measurement locations on the user's body corresponding to the user's movements when the user performs fitness exercises; Based on the electromyographic signal, determining an abnormal signal in the electromyographic signal; as well as Correcting the abnormal signal, Wherein, determining an abnormal signal in the electromyographic signal based on the electromyographic signal includes: Processing the electromyographic signal in the time domain to determine the abnormal signal, or Processing the electromyographic signal in the frequency domain to determine the abnormal signal, The correcting of the abnormal signal comprises: Performing data sampling on the electromyographic signal before the abnormal signal in real time to obtain sampling data, Based on the sampled data corresponding to the time domain window of the electromyographic signal, the predicted data corresponding to the moment of the abnormal signal is determined, Based on the predicted data, determining the correction data corresponding to the time when the abnormal signal occurs, and The abnormal signal is corrected using the correction data.

2. The motion data processing method according to claim 1, wherein: The processing of the electromyographic signal in the time domain to determine the abnormal signal includes: Based on the time domain window of the electromyographic signal, selecting at least one time window from the time domain window of the electromyographic signal, wherein the at least one time window covers different time ranges respectively; and The abnormal signal is determined based on the characteristic information corresponding to the electromyographic signal in the at least one time window.

3. The motion data processing method according to claim 2, wherein: The characteristic information includes at least one of amplitude information and statistical information of the amplitude information, and the statistical information of the amplitude information includes at least one of entropy, variance, standard deviation, standard deviation of the standard deviation, and zero-crossing rate of the amplitude information.

4. The motion data processing method according to claim 2, wherein: The abnormal signal includes a mutation signal, the at least one time window includes multiple time windows, and determining the abnormal signal based on feature information corresponding to the electromyographic signal in the at least one time window includes: Determining a plurality of feature information corresponding to the electromyographic signals in the plurality of time windows; and Determine that the ratio of the characteristic information corresponding to the time window after the time range to the characteristic information corresponding to the time window before the time range exceeds a preset first threshold, and determine that the electromyographic signal in the time window after the time range is the mutation signal.

5. The motion data processing method according to claim 2, wherein: The abnormal signal includes a missing signal, and determining the abnormal signal based on characteristic information corresponding to the electromyographic signal in the at least one time window includes: Determining at least one feature information corresponding to the electromyographic signal in the at least one time window; and Determine the myoelectric signal in the time window corresponding to the feature information below a pre-stored second threshold in the at least one feature information as the missing signal.

6. The motion data processing method according to claim 2, wherein: The abnormal signal includes a saturation signal, and determining the abnormal signal based on characteristic information corresponding to the electromyographic signal in the at least one time window includes: Determining at least one feature information corresponding to the electromyographic signal in the at least one time window; The myoelectric signal in the time window corresponding to the at least one characteristic information that is higher than the pre-stored saturation characteristic information is determined as the saturation signal.

7. The motion data processing method according to claim 1, wherein: The electromyographic signal includes a signal obtained based on a DC removal algorithm, and the DC removal algorithm includes at least one of a mean removal algorithm and a high-pass filtering algorithm.

8. The motion data processing method according to claim 7, wherein: The abnormal signal also includes an oscillation signal caused by the high-pass filtering algorithm, and the processing of the electromyographic signal in the time domain to determine the abnormal signal includes: Calculating a reference oscillation height and a reference duration of the oscillation signal based on filter parameters of the high-pass filtering algorithm; and The electromyographic signal is matched with the reference oscillation height and the reference duration in real time, and the electromyographic signal corresponding to the signal interval matching the reference oscillation height and the reference duration in the electromyographic signal is determined as the oscillation signal.

9. The motion data processing method according to claim 1, wherein: The processing of the electromyographic signal in the frequency domain to determine the abnormal signal includes: Based on a frequency domain conversion algorithm, a frequency domain signal of the electromyographic signal in the frequency domain is acquired in real time; determining the spectrum characteristics of the frequency domain signal in real time; and The myoelectric signal corresponding to the frequency domain signal whose frequency spectrum characteristic does not meet the preset condition is determined as the abnormal signal.

10. The motion data processing method according to claim 9, wherein: The spectrum characteristics include at least one of spectrum shape, power spectrum density, average power frequency, median frequency and wavelet scale.

11. The motion data processing method according to claim 1, wherein: The determining, based on the sampled data corresponding to the time domain window of the electromyographic signal, the predicted data corresponding to the moment of the abnormal signal, includes at least one of the following situations: Determining a fitting function based on the sampled data corresponding to the time domain window, and calculating the predicted data corresponding to the moment when the abnormal signal is located based on the fitting function; as well as Based on the sampled data corresponding to the time domain window and the trained LSTM network, the predicted data corresponding to the moment of the abnormal signal is calculated.

12. The motion data processing method according to claim 1, wherein: The determining, based on the predicted data, the correction data corresponding to the moment when the abnormal signal occurs, includes: Determining that the predicted data is within a preset range, and using the predicted data as the correction data, wherein the preset range includes a data range consisting of a maximum value and a minimum value of the electromyographic signal within the time domain window; or It is determined that the predicted data is not within the preset range, and sampling data corresponding to at least one frame of electromyographic signal adjacent to the abnormal signal is used as the correction data.

13. A motion monitoring system, characterized in that: include: at least one storage medium storing at least one instruction set for motion data processing; as well as at least one processor, in communication with the at least one storage medium; Wherein, when the motion monitoring system is running, the at least one processor reads the at least one instruction set and implements the motion data processing method according to any one of claims 1 to 12.

14. The motion monitoring system according to claim 13, wherein: Also includes: a wearable device, communicatively connected to the at least one processor; The wearable device includes: a base configured to be wearable on the user; as well as A plurality of sensors are mounted on the substrate to measure the myoelectric signals of the user.

Images