WO2024055186A1 - 一种运动评估方法及系统 - Google Patents

一种运动评估方法及系统 Download PDF

Info

Publication number
WO2024055186A1
WO2024055186A1 PCT/CN2022/118674 CN2022118674W WO2024055186A1 WO 2024055186 A1 WO2024055186 A1 WO 2024055186A1 CN 2022118674 W CN2022118674 W CN 2022118674W WO 2024055186 A1 WO2024055186 A1 WO 2024055186A1
Authority
WO
WIPO (PCT)
Prior art keywords
motion
signal
evaluation
feedback
motion signal
Prior art date
Application number
PCT/CN2022/118674
Other languages
English (en)
French (fr)
Inventor
黎美琪
刘嘉
苏雷
周鑫
廖风云
齐心
Original Assignee
深圳市韶音科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市韶音科技有限公司 filed Critical 深圳市韶音科技有限公司
Priority to PCT/CN2022/118674 priority Critical patent/WO2024055186A1/zh
Publication of WO2024055186A1 publication Critical patent/WO2024055186A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer

Definitions

  • This specification relates to the technical field of signal detection and evaluation, and in particular to a motion evaluation method and system.
  • Embodiments of this specification provide a motion assessment method, which method includes: acquiring a motion signal of an object, where the motion signal includes a signal characterizing the motion state of the object; and determining an evaluation related to the motion signal based on the motion signal. Standard; the motion signal is evaluated based on the evaluation criterion.
  • the evaluating the motion signal based on the evaluation criterion includes: evaluating the motion signal based on the evaluation criterion, the result of the evaluation including an error type; and based on the result of the evaluation Provide evaluation feedback.
  • performing evaluation feedback based on the results of the evaluation includes: determining a target feedback method among multiple feedback methods based on the results of the evaluation or the user type of the object, and the multiple feedback methods Notify the object through different feedback times or feedback types; and provide feedback according to the target feedback method.
  • the motion signal includes at least one of a posture signal, an electromyographic signal, a mechanical signal, an electrocardiographic signal, a respiratory signal, and a sweat signal.
  • determining the evaluation criteria related to the motion signal based on the motion signal includes: performing action recognition on the object based on the motion signal, determining the action type of the object; and based on the motion signal.
  • the motion type determines the evaluation criteria associated with the motion signal.
  • performing action recognition on the object based on the motion signal and determining the action type of the object includes: for each frame of motion signal, determining whether to perform action recognition; and in response to performing action recognition Based on the judgment result, action recognition is performed based on one or more frames of motion signals to determine the action type of the object.
  • determining an evaluation criterion related to the motion signal based on the action type includes: determining a target part corresponding to the action type based on the action type; and determining an evaluation criterion based on the evaluation criterion.
  • Evaluating the motion signal includes: acquiring a motion signal of the target part; and evaluating the motion signal of the target part based on the evaluation standard.
  • the evaluation of the motion signal of the target part based on the evaluation criterion includes: determining a reference part based on the target part; determining the amplitude of the motion signal of the target part and the reference part. a ratio between amplitudes of motion signals of the parts; determining whether the ratio is less than a ratio threshold; and in response to the ratio being less than the ratio threshold, determining that the result of the evaluation is a compensation error.
  • the evaluation of the motion signal of the target part based on the evaluation criterion includes: determining the amplitude of the motion signal; determining whether the amplitude of the motion signal is less than a first motion amplitude; and In response to the amplitude of the motion signal being less than the first motion amplitude, the result of the evaluation is determined to be a compensation error.
  • the evaluation of the motion signal of the target part based on the evaluation criteria includes:
  • determining an amplitude of the motion signal determining whether the amplitude of the motion signal is less than a second motion amplitude; and in response to the amplitude of the motion signal being less than the second motion amplitude, determining a result of the evaluation for efficiency errors.
  • the motion signal includes a first signal and a second signal
  • evaluating the motion signal of the target part based on the evaluation criterion includes: identifying a first characteristic value of the first signal and the first signal. the second characteristic value of the second signal; determining the time difference between the first characteristic value of the first signal and the second characteristic value of the second signal; determining whether the time difference is greater than a time difference threshold; and responding to the If the time difference is greater than the time difference threshold, the result of the evaluation is determined to be an efficiency error.
  • the evaluation of the motion signal based on the evaluation criterion includes: determining a target part corresponding to the motion signal based on the evaluation criterion, and the target part includes at least two parts of the object. symmetrical parts; obtaining the motion signals of the at least two symmetrical parts; and evaluating the motion signals of the at least two symmetrical parts based on the evaluation criteria.
  • the evaluation of the motion signals of the at least two symmetrical parts based on the evaluation criteria includes: determining a signal difference of the motion signals of the at least two symmetrical parts; determining whether the signal difference is greater than a signal difference threshold; and in response to the signal difference being greater than the signal difference threshold, determining that the result of the evaluation is a symmetry error.
  • the evaluation of the motion signal based on the evaluation criterion includes: determining the target part corresponding to the motion signal based on the evaluation criterion; determining the frequency of the motion signal of the target part; and Based on the frequency and the evaluation criteria, the fatigue status of the target site is determined.
  • the evaluation of the motion signal based on the evaluation standard includes: determining the target part corresponding to the motion signal based on the evaluation standard; obtaining the motion signal of the target part; based on the The motion signal determines the evaluation parameter of the target part; and based on the evaluation parameter and the evaluation standard, determines the damage type or damage level of the target part.
  • the evaluation parameter includes at least one of internal rotation angle, abduction angle, or motion acceleration of the target site.
  • the method further includes evaluating the motion signal based on a motion evaluation model.
  • Embodiments of this specification also provide a motion evaluation feedback method.
  • the method includes: acquiring a motion signal of an object, where the motion signal includes a signal characterizing the motion state of the object; and evaluating the motion signal based on evaluation criteria related to the motion signal. Evaluate the motion signal; determine a target feedback method among multiple feedback methods based on the results of the evaluation, and the multiple feedback methods notify the object through different feedback times or feedback types; perform evaluation based on the target feedback method feedback.
  • the feedback time includes timely feedback or end-of-motion feedback.
  • the feedback type includes: at least one of voice feedback, biofeedback, and text feedback.
  • the method further includes: performing action recognition on the object based on the motion signal, and determining the action type of the object.
  • determining a target feedback method among multiple feedback methods based on the results of the evaluation includes: determining based on at least one of the action type, the user type of the object, or the results of the evaluation. The target feedback method among the multiple feedback methods.
  • the motion signal includes at least one of a posture signal, an electromyographic signal, a mechanical signal, an electrocardiographic signal, a respiratory signal, and a sweat signal.
  • Embodiments of this specification also provide a motion evaluation system.
  • the system includes: an acquisition module, configured to acquire a motion signal of an object, where the motion signal includes a signal characterizing the motion state of the object; and a determination module, configured based on the The motion signal determines an evaluation criterion related to the motion signal; an evaluation module is configured to evaluate the motion signal based on the evaluation criterion.
  • Embodiments of this specification also provide a motion evaluation feedback system.
  • the system includes: an acquisition module for acquiring motion signals of an object, where the motion signals include signals characterizing the motion status of the object; and an evaluation module for acquiring motion signals based on The motion signal-related evaluation criteria evaluate the motion signal; a feedback module is used to determine a target feedback mode among multiple feedback modes based on the evaluation results, and the multiple feedback modes use different feedback times or Notify the object of the feedback type; and perform evaluation feedback according to the target feedback method.
  • Embodiments of this specification also provide a computer-readable storage medium.
  • the storage medium includes executable instructions. When executed by at least one processor, the executable instructions cause the at least one processor to execute the instructions described in this specification. Movement assessment method or movement assessment feedback method.
  • Figure 1 is a schematic diagram of a motion assessment system according to some embodiments of the present specification
  • Figure 3 is a schematic flowchart of a motion assessment method according to some embodiments of this specification.
  • Figure 4 is a flowchart of an exemplary method of determining evaluation criteria according to some embodiments of this specification
  • Figure 5 is a flowchart of an exemplary method of evaluating motion signals according to some embodiments of the present specification
  • Figure 6 is a schematic diagram of the electromyographic signal and posture signal of the target part in the bicep curl movement according to some embodiments of this specification;
  • Figure 7 is a schematic diagram of the electromyographic signal and posture signal of the target part in the seated chest pressing movement according to some embodiments of this specification;
  • Figure 8 is a flowchart of another exemplary method of evaluating motion signals according to some embodiments of this specification.
  • Figure 9 is a flowchart of yet another exemplary method of evaluating motion signals according to some embodiments of this specification.
  • Figure 10A is a schematic diagram of the electromyographic signal of the target part during the dumbbell lateral raise movement according to some embodiments of this specification;
  • Figure 10B is a schematic diagram of the electromyographic signal of the target part during the barbell bicep curl movement according to some embodiments of this specification;
  • Figure 11 is a flow chart of a motion assessment feedback method according to some embodiments of this specification.
  • embodiments of this specification provide a movement evaluation method and system that can identify user movement errors and help the user correct the errors, so as to reduce injuries caused by the user during exercise while ensuring exercise effects.
  • Figure 1 is a schematic diagram of a motion assessment system according to some embodiments of the present specification.
  • the motion evaluation system 100 may include a signal acquisition device 110 , a storage device 120 , a processing device 130 , a terminal device 140 and a network 150 .
  • the various components in motion assessment system 100 can be connected in a variety of ways.
  • the signal collection device 110 may be connected to the storage device 120 and/or the processing device 130 through the network 150, or may be directly connected to the storage device 120 and/or the processing device 130.
  • the storage device 120 may be connected to the processing device 130 directly or through the network 150 .
  • the terminal device 140 may be connected to the storage device 120 and/or the processing device 130 through the network 150, or may be directly connected to the storage device 120 and/or the processing device 130.
  • the signal acquisition device 110 can collect motion signals from the object to be evaluated 114 (eg, a user).
  • the motion signal may refer to a signal generated by the object to be evaluated 114 during motion, and the motion signal may be used to characterize the motion state of the object to be evaluated 114 .
  • Exemplary motion signals may include posture signals, electromyographic signals, mechanical signals, electrocardiographic signals, respiratory signals, sweat signals, etc.
  • the signal acquisition device 110 may include a posture signal acquisition device 111 , an electromyographic signal acquisition device 112 and a mechanical signal acquisition device 113 .
  • the attitude signal collection device 111 may include a speed sensor, an inertial sensor (eg, an acceleration sensor, an angular velocity sensor (eg, a gyroscope), etc.), an optical sensor (eg, an optical distance sensor, a video/image collector), Acoustic distance sensor, tension sensor, etc. or any combination thereof.
  • the signal acquisition device 110 may include multiple attitude signal acquisition devices 111, which may be disposed at different parts of the object to be evaluated 114, or have different acquisition angles and/or relative to the object to be evaluated 114. distance.
  • the electromyographic signal collection device 112 may include one or more electrodes.
  • the myoelectric signal collection device 112 may include multiple electrodes, which may be used to attach to different parts of the subject 114 to be evaluated (eg, chest, back, elbow, leg, abdomen, wrist, etc.) combination to collect electromyographic signals from different parts of the object 114 to be evaluated.
  • the mechanical signal acquisition device 113 may include a pressure sensor.
  • pressure sensors can be installed at different parts of the object to be evaluated 114 to collect pressure signals from different parts.
  • the mechanical signal of the object to be evaluated can also be calculated based on the posture signal and the electromyographic signal.
  • the signal collection device 110 may also include an electrocardiogram signal collection device, a respiratory signal collection device, a sweat signal collection device (not shown in Figure 1), etc.
  • the ECG signal collection device may include multiple electrodes, and the multiple electrodes may be used to fit with different parts of the object 114 to be evaluated to collect ECG signals of the object 114 to be evaluated.
  • the respiratory signal collection device may include a respiratory frequency sensor, a flow sensor, etc., respectively used to detect the respiratory frequency, gas flow and other signals of the object to be evaluated 114 during exercise.
  • the sweat signal collection device may include multiple electrodes in contact with the skin of the subject 114 to be evaluated, for detecting the sweat flow rate of the subject 114 to be evaluated, analyzing sweat components, etc.
  • the signal collection device 110 can have an independent power supply, which can send the collected data to other components (for example, a storage device) in the motion evaluation system 100 through wired or wireless means (such as Bluetooth, WiFi, etc.) 120, processing equipment 130, terminal equipment 140).
  • the signal collection device 110 can send the collected motion signals of the object to be evaluated 114 to the storage device 120, the processing device 130, the terminal device 140, etc. through the network 150.
  • the motion signals collected by the signal collection device 110 can be processed by the processing device 130 .
  • the processing device 130 can identify the action type of the object to be evaluated 114 based on the motion signal, and evaluate the current action of the object to be evaluated 114 based on the evaluation criteria related to the action type to obtain a corresponding evaluation result.
  • the processing device 130 can directly evaluate the motion signal based on the evaluation criteria related to the motion signal without identifying the action type of the object to be evaluated, and obtain the evaluation result.
  • the evaluation results may be sent to the storage device 120 for recording, or to the terminal device 140 for feedback to the user.
  • Network 150 may facilitate the exchange of information and/or data.
  • Network 150 may include any suitable network capable of facilitating the exchange of information and/or data with system 100 .
  • at least one component of the motion evaluation system 100 eg, signal acquisition device 110, storage device 120, processing device 130, terminal device 140
  • the processing device 130 may obtain the motion signal from the signal acquisition device 110 and/or the storage device 120 through the network 150 .
  • the processing device 130 can obtain user operation instructions from the terminal device 140 through the network 150.
  • Exemplary operation instructions can include but are not limited to setting user information (for example, gender, age, height, weight, disease history, etc.), selecting Sports modes (for example, running, skipping, swimming, muscle training, etc.), set exercise time, etc.
  • network 150 may be any form of wired or wireless network, or any combination thereof.
  • network 150 may include a cable network, a wired network, a fiber optic network, a telecommunications network, an intranet, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network ( MAN), Public Switched Telephone Network (PSTN), Bluetooth network, ZigBee network, Near Field Communication (NFC) network, etc. or any combination thereof.
  • network 150 may include at least one network access point through which at least one component of athletic assessment system 100 may connect to network 150 to exchange data and/or information.
  • Storage device 120 may store data, instructions, and/or any other information.
  • the storage device 120 may store data obtained from the signal acquisition device 110, the processing device 130, and/or the terminal device 140.
  • the storage device 120 may store motion signals collected by the signal collection device 110 .
  • storage device 120 may store data and/or instructions for processing device 130 to perform or use to complete the example methods described in this specification.
  • storage device 120 may include mass memory, removable memory, volatile read-write memory, read-only memory (ROM), etc., or any combination thereof.
  • Exemplary mass storage may include magnetic disks, optical disks, solid state disks, and the like.
  • storage device 120 may be implemented on a cloud platform.
  • the cloud platform may include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, internal cloud, multi-tier cloud, etc. or any combination thereof.
  • storage device 120 may be connected to network 150 to communicate with at least one other component in motion evaluation system 100 (eg, signal acquisition device 110, processing device 130, terminal device 140). At least one component of the athletic evaluation system 100 may access data, instructions, or other information stored in the storage device 120 through the network 150 .
  • the storage device 120 may be directly connected or communicated with one or more components (eg, signal acquisition device 110, terminal device 140) in the motion evaluation system 100.
  • the storage device 120 may be part of the signal acquisition device 110 and/or the processing device 130 .
  • the processing device 130 may process data and/or information obtained from the signal acquisition device 110 , the storage device 120 , the terminal device 140 and/or other components of the motion evaluation system 100 .
  • the processing device 130 can obtain the motion signal of the object to be evaluated 114 from any one or more of the signal acquisition device 110, the storage device 120, or the terminal device 140, and process the motion signal to determine its corresponding action. type.
  • the processing device 130 may obtain an evaluation criterion according to the action type corresponding to the motion signal, and evaluate the motion signal according to the evaluation criterion.
  • the processing device 130 may directly determine the evaluation criteria related to the motion signal based on the motion signal, and evaluate the motion signal based on the evaluation criteria related to the motion signal to obtain the evaluation result. In some embodiments, the processing device 130 may obtain pre-stored computer instructions from the storage device 120 and execute the computer instructions to implement the motion assessment method described in this specification.
  • processing device 130 may be a single server or a group of servers. Server groups can be centralized or distributed. In some embodiments, processing device 130 may be local or remote. For example, the processing device 130 can access information and/or data from the signal collection device 110, the storage device 120 and/or the terminal device 140 through the network 150. As another example, the processing device 130 may be directly connected to the signal acquisition device 110, the storage device 120 and/or the terminal device 140 to access information and/or data. In some embodiments, the processing device 130 may be implemented on a cloud platform.
  • the cloud platform may include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, inter-cloud cloud, multi-cloud, etc. or any combination thereof.
  • the terminal device 140 may receive, send and/or display data.
  • the received data may include data collected by the signal collection device 110, data stored by the storage device 120, evaluation results generated by the processing device 130, etc.
  • the data received and/or displayed by the terminal device 140 may include motion signals collected by the signal acquisition device 110 , the action type of the object to be evaluated 114 determined by the processing device 130 based on the motion signals, the processing device 130 based on the determined evaluation criteria, and the processing device 130 determines the action type of the object 114 based on the motion signals. 130 Evaluation results generated based on evaluation standards, etc.
  • the sent data may include input data and instructions from users (eg, fitness instructors, subjects to be evaluated), etc.
  • the terminal device 140 can send the operation instructions input by the user to the signal collection device 110 through the network 150 to control the signal collection device 110 to perform corresponding data collection.
  • the terminal device 140 may send the evaluation instruction input by the user to the processing device 130 through the network 150 .
  • the terminal device 140 may include a mobile device 141, a tablet computer 142, a laptop computer 143, etc., or any combination thereof.
  • the mobile device 141 may include a mobile phone, a personal digital assistant (PDA), a medical mobile terminal, etc., or any combination thereof.
  • the terminal device 140 may include an input device (such as a keyboard, a touch screen), an output device (such as a display, a speaker), and the like.
  • processing device 130 may be part of terminal device 140.
  • the above description of the motion assessment system 100 is only for example and illustration, and does not limit the scope of application of this specification.
  • various modifications and changes can be made to the motion evaluation system 100 under the guidance of this description.
  • such modifications and changes remain within the scope of this specification.
  • the signal acquisition device 110 may include more or fewer functional components.
  • Figure 2 is a block diagram of a motion evaluation device according to other embodiments of this specification.
  • the motion evaluation device 200 shown in FIG. 2 can be applied to the motion evaluation system 100 shown in FIG. 1 in the form of software and/or hardware.
  • it can be configured to process in the form of software and/or hardware.
  • the device 130 and/or the terminal device 140 are used to evaluate the motion signals collected by the signal collection device 110 .
  • the motion evaluation device 200 may include an acquisition module 210 , a determination module 220 , an evaluation module 230 and a feedback module 240 .
  • the acquisition module 210 may be used to acquire the motion signal of the object 114 to be evaluated.
  • the motion signal can be obtained from any one or more of the signal acquisition device 110, the storage device 120, or the terminal device 140.
  • the motion signal may include electromyographic signal, posture signal, mechanical signal, electrocardiographic signal, respiratory signal, sweat signal, etc.
  • the motion signal please refer to other locations in this specification (for example, FIG. 1, FIG. 3 and their related descriptions), and will not be described again here.
  • the determination module 220 may be used to determine evaluation criteria related to the motion signal. In some embodiments, the determination module 220 may directly determine the evaluation criteria related to the motion signal. In some embodiments, the determination module 220 may perform motion recognition on the object 114 based on the motion signal, determine the motion type of the object 114, and determine evaluation criteria related to the motion signal based on the motion type.
  • the evaluation criterion may refer to a criterion for evaluating whether a certain action is performed correctly based on the motion signal.
  • the evaluation module 230 may be configured to evaluate the motion signal of the object to be evaluated 114 acquired by the acquisition module 210 based on the evaluation criteria determined by the determination module 220, to determine the evaluation result of the action performed by the object to be evaluated 114.
  • the evaluation results may include whether there is an error in the action, the type of error, the level of the error, etc.
  • the feedback module 240 may be used to feed back the evaluation results generated by the evaluation module 230 to the user. In some embodiments, the feedback module 240 may determine the timing of feeding back the evaluation results according to the current action stage and/or sports scene of the object to be evaluated 114 . In some embodiments, the feedback module 240 may determine the feedback method and/or content of the evaluation results according to the user type (eg, novice user, amateur user, professional user, etc.).
  • the user type eg, novice user, amateur user, professional user, etc.
  • the motion evaluation device 200 and its modules shown in Figure 2 can be implemented in various ways.
  • the system and its modules may be implemented in hardware, software, or a combination of software and hardware.
  • the hardware part can be implemented using dedicated logic; the software part can be stored in the memory and executed by an appropriate instruction execution system, such as a microprocessor or specially designed hardware.
  • an appropriate instruction execution system such as a microprocessor or specially designed hardware.
  • processor control code for example on a carrier medium such as a disk, CD or DVD-ROM, such as a read-only memory (firmware).
  • Such code is provided on a programmable memory or a data carrier such as an optical or electronic signal carrier.
  • the system and its modules in this specification may not only be implemented by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc. , can also be implemented by, for example, software executed by various types of processors, or can also be implemented by a combination of the above-mentioned hardware circuits and software (for example, firmware).
  • the motion evaluation device 200 is provided for illustrative purposes only and is not intended to limit the scope of this specification. It can be understood that those skilled in the art can arbitrarily combine various modules or form a subsystem to connect with other modules according to the description of this specification without departing from this principle.
  • the acquisition module 210, the determination module 220, the evaluation module 230 and the feedback module 240 described in Figure 2 can be different modules in one system, or one module can implement the functions of two or more modules mentioned above.
  • the motion evaluation device 200 may further include a recognition module, configured to perform motion recognition on the object based on motion signals and determine the motion type of the object. Such deformations are within the scope of this manual.
  • Figure 3 is a flowchart of an exemplary motion assessment method in accordance with some embodiments of the present specification.
  • method 300 may be performed by processing logic, which may include hardware (eg, circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., running on a processing device to perform hardware emulation). instructions), etc. or any combination thereof.
  • processing logic may include hardware (eg, circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., running on a processing device to perform hardware emulation). instructions), etc. or any combination thereof.
  • one or more operations in the method 300 of the motion assessment method shown in FIG. 3 may be implemented by the processing device 130 and/or the terminal device 140 shown in FIG. 1 .
  • the method 300 may be stored in the storage device 120 in the form of instructions, and may be called and/or executed by the processing device 130 and/or the terminal device 140 .
  • the following uses the processing device 130 as an example to describe the execution process of the method
  • a method 300 of a motion assessment method may include:
  • Step 310 Obtain the motion signal of the object.
  • step 310 may be performed by acquisition module 210.
  • the motion signal may refer to a signal generated by the object to be evaluated during motion.
  • the motion signal can be used to characterize the motion state of the object to be evaluated, which can include electromyographic signals, posture signals, mechanical signals, electrocardiographic signals, respiratory signals, sweat signals, etc., or any combination thereof.
  • electromyographic signals may be used to characterize the technical accuracy (eg, sequence of muscle recruitment) and risk of injury (eg, degree of fatigue) of the subject's current movement to be assessed.
  • myoelectric signals can be collected through one or more electrodes that are attached to the object to be evaluated. For example, multiple electrodes can be attached to different parts of the subject to be evaluated (for example, chest, back, elbow, leg, abdomen, wrist, etc.) to collect electromyographic signals from different parts of the subject to be evaluated.
  • the attitude signal may include information such as the angle, velocity, and acceleration of each joint, or the Euler angle, angular velocity, and angular acceleration of each human body part.
  • the posture signal may also be used to characterize the technical accuracy (eg, joint angles, force sequence, etc.) and injury risk (eg, acromion impingement) of the current movement of the subject to be evaluated.
  • the posture signal may be collected through a posture signal collection device (for example, the posture signal collection device 111 shown in FIG. 1 ).
  • Exemplary gesture signal collection devices may include speed sensors, inertial sensors (e.g., acceleration sensors, angular velocity sensors (e.g., gyroscopes), etc.), optical sensors (e.g., optical distance sensors, video/image collectors), acoustic distance sensors, Tension sensor, etc. or any combination thereof.
  • inertial sensors e.g., acceleration sensors, angular velocity sensors (e.g., gyroscopes), etc.
  • optical sensors e.g., optical distance sensors, video/image collectors
  • acoustic distance sensors e.g., acoustic distance sensors, Tension sensor, etc. or any combination thereof.
  • the mechanical signal may refer to the corresponding force at the joint part of the subject to be evaluated or the force detected by the sports equipment, which may be used to characterize the risk of injury (for example, pressure at the ankle, pressure at the knee, etc.).
  • the mechanical signal can be obtained through a mechanical sensor.
  • the mechanical sensor may include a pressure sensor, and pressure signals at different parts of the object to be evaluated may be acquired based on the pressure sensor as the mechanical signal of the object to be evaluated.
  • the mechanical signal can be calculated based on the posture signal and the electromyographic signal.
  • the electrocardiogram signal may refer to a signal used to represent the heart activity of the subject to be evaluated.
  • the ECG signal can be collected through an ECG signal collection device.
  • the ECG signal collection device may include multiple electrodes, and the multiple electrodes may be used to fit with different parts of the subject to be evaluated to collect ECG signals of the subject to be evaluated.
  • the respiratory signal may refer to a signal representing the breathing condition of the subject to be evaluated.
  • the respiratory signal can be collected through a respiratory signal collecting device.
  • the respiratory signal collection device may include a respiratory frequency sensor, a flow sensor, etc., respectively used to detect the respiratory frequency, gas flow and other data of the subject to be evaluated during exercise.
  • the sweat signal may refer to a signal indicating the sweating condition of the subject to be evaluated.
  • the sweat signal can be collected through a sweat signal collection device.
  • the sweat signal collection device may include a plurality of electrodes in contact with the skin of the subject to be evaluated, for detecting the sweat flow rate of the subject to be evaluated or analyzing sweat components.
  • ECG signals, respiratory signals, sweat signals, etc., or any combination thereof can be used to characterize the risk of injury (e.g., fatigue level) of the subject's current movement to be evaluated.
  • the processing device 130 may directly acquire the motion signal from the signal acquisition device (eg, signal acquisition device 110).
  • the motion signal may be stored in a storage device (eg, storage device 120), and the processing device 130 may obtain the motion signal from the storage device.
  • Step 320 Determine evaluation criteria related to the motion signal based on the motion signal. In some embodiments, step 320 may be performed by determination module 220.
  • the evaluation criteria may refer to criteria for evaluating whether a certain action is correctly performed based on a motion signal.
  • the evaluation criteria may include a target part, a target motion signal corresponding to the target part, an evaluation parameter standard corresponding to the target motion signal, or the like, or any combination thereof.
  • the target part may refer to a part to be evaluated when a user performs a certain action.
  • the target motion signal may refer to a motion signal that specifically needs to be evaluated for the target part, for example, one or more of a posture signal, an electromyographic signal, a mechanical signal, an electrocardiogram signal, a breathing signal, a sweat signal, etc.
  • the evaluation parameter standard may refer to a parameter used to evaluate a target motion signal and its corresponding parameter value or parameter range.
  • the evaluation standard can be used to evaluate the motion signal to determine whether there is an error in the motion corresponding to the motion signal and the type of error.
  • exemplary error types may include impairment errors, compensation errors, efficiency errors, symmetry errors, etc., or any combination thereof.
  • An injury error can mean that the movement error may cause damage to the human body.
  • Compensatory errors can refer to errors in using non-target parts (e.g., muscles) to assist in exerting force.
  • Efficiency errors can refer to when performing movements in a certain movement pattern, the range of movement is too large or too small, leaving the target part at a non-optimal level of activation.
  • Symmetry error can refer to the imbalance of force exerted by two symmetrical parts of the human body (for example, bilateral symmetry, front-to-back symmetry).
  • the evaluation results may also include a rating of the error type.
  • error levels for injury errors may include severe, moderate, mild, etc.
  • the evaluation criteria may include criteria for evaluating different error types.
  • the target parts and/or target motion signals to be evaluated may be different for different error types.
  • the evaluation parameter standards corresponding to different target motion signals of different target parts can also be different.
  • the evaluation criteria may include one or more criteria for evaluating one or more error types.
  • the evaluation criteria may include criteria for evaluating preset error types. For example, the user can select an error type that needs to be evaluated through a terminal device (eg, the terminal device 140), and the processing device 130 can determine the evaluation criteria based on the error type selected by the user.
  • the evaluation criteria may also include evaluation criteria corresponding to all error types, for evaluating whether there is an error in the motion signal for each error type.
  • the evaluation criteria may include a first evaluation criterion that may evaluate a first error type related to the subject's action type.
  • Exemplary first error types may include compensation errors, efficiency errors, and the like.
  • the processing device 130 may perform motion recognition on the object based on the motion signal, determine the motion type of the object, and determine a first evaluation criterion related to the motion signal based on the motion type. .
  • motion recognition of objects and determination of evaluation criteria please refer to other locations in this specification (for example, Figure 4 and its related descriptions), and will not be described again here.
  • the evaluation criteria may include a second evaluation criterion that may be used to evaluate a second error type that is independent of the subject's action type.
  • Exemplary second error types may include damage errors, symmetry errors, and the like.
  • the processing device 130 may directly determine the target part and its target signal in the evaluation criteria, and evaluate the target signal based on the evaluation parameter criteria.
  • the second evaluation criterion may be determined directly based on the motion signal. For example, evaluation criteria related to the motion signal may be set in advance, and the processing device 130 may obtain the evaluation criteria and evaluate the motion signal.
  • processing device 130 may also determine evaluation criteria based on information related to the object.
  • Information related to the object may include the object's gender, age, height, weight, health status, etc.
  • different subjects for example, males and females, adults and minors, healthy people and subjects with a history of disease, etc.
  • different evaluation standards for example, males and females, adults and minors, healthy people and subjects with a history of disease, etc.
  • the evaluation criteria may be stored in the storage device 120, and the processing device 130 may determine the corresponding evaluation criteria directly or based on the action type.
  • Step 330 Evaluate the motion signal based on the evaluation criterion.
  • step 330 may be performed by evaluation module 230.
  • the processing device 130 may evaluate the motion signal based on the evaluation criteria and determine the evaluation result.
  • the evaluation results may include whether there is an error in the motion corresponding to the motion signal and the type of the error. In some embodiments, for one or more error types, the evaluation results may also include a rating of the error type. By way of example only, error levels for injury errors may include severe, moderate, mild, etc.
  • the processing device 130 may evaluate the motion signal according to a preset evaluation sequence. For example, the processing device 130 may first determine whether there is an injury error in the movement of the object to be evaluated based on the evaluation criteria, and then determine the compensation error when it is determined that there is no injury error in the movement of the object to be evaluated.
  • the processing device 130 may make an efficiency error judgment when it is determined that there is no compensation error during the movement of the object to be evaluated.
  • an efficiency error judgment when it is determined that there is no compensation error during the movement of the object to be evaluated.
  • the processing device 130 may also provide evaluation feedback based on the evaluation result.
  • the processing device 130 can provide evaluation feedback through multiple feedback methods, which can notify the user (eg, the object to be evaluated or the coach) through different feedback times and/or feedback types.
  • the feedback time may include timely feedback or end-of-exercise feedback (for example, feedback after a single cycle of action, feedback after a single training session, feedback after stopping exercise, etc.).
  • Feedback types may include voice feedback, biofeedback (eg, electrical stimulation), text feedback, graphical interface feedback, etc., or any combination thereof.
  • the feedback type may also be determined according to the user who needs feedback.
  • the feedback type may also include professional feedback, general feedback, etc.
  • the professional feedback may refer to feedback to the user in relatively professional language
  • ordinary feedback may refer to feedback to the user in easy-to-understand language.
  • the processing device 130 may determine a target feedback method among multiple feedback methods based on the evaluation result, action type, user type of the object, etc., or any of them, so as to provide feedback according to the target feedback method. For example, the processing device 130 can determine whether there is a damage error in the object's current action based on the evaluation result. If there is a damage error, the processing device 130 can determine the feedback time to be timely feedback and the feedback method to be voice feedback, so that the feedback information can be transmitted through voice.
  • the processing device 130 may determine that the feedback time is end-of-motion feedback, and the feedback method is text and/or graphical interface. feedback.
  • the processing device 130 may determine the feedback time to be end-of-exercise feedback.
  • the evaluation results can be displayed through professional feedback.
  • ordinary feedback can be selected to display the evaluation. result.
  • the target feedback methods adopted may include but are not limited to the above methods.
  • electrical stimulation can be applied to the part where the error occurs through electrodes to prompt that there is an action error in the corresponding part.
  • the processing device 130 may feedback the evaluation results to the user according to the feedback method selected or set by the user.
  • the processing device 130 when the processing device 130 feeds back the evaluation results to the user, it can also show the user the correct way to exercise to guide the user to exercise scientifically.
  • the motion signal may be evaluated based on a motion evaluation model.
  • the motion assessment model can be a machine learning model, which can be obtained after training with several training samples.
  • the method 300 may further include the step of performing action recognition on the object based on the motion signal.
  • the method 300 may further include the step of providing evaluation feedback based on the evaluation results.
  • method 400 may be performed by processing logic, which may include hardware (eg, circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., running on a processing device to perform hardware emulation). instructions), etc. or any combination thereof.
  • processing logic may include hardware (eg, circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., running on a processing device to perform hardware emulation). instructions), etc. or any combination thereof.
  • one or more operations in the method 400 shown in FIG. 4 may be implemented by the processing device 130 and/or the terminal device 140 shown in FIG. 1 .
  • the method 400 may be stored in the storage device 120 in the form of instructions, and may be called and/or executed by the processing device 130 and/or the terminal device 140 .
  • step 320 in motion assessment method 300 may be implemented by method 400 .
  • method 400 may be performed by determination module 220. The following uses the processing device 130 as an example to describe the execution process of the method 400.
  • method 400 may include:
  • Step 410 Perform action recognition on the object based on the motion signal to determine the action type of the object.
  • the processing device 130 may perform motion recognition on the object to be evaluated based on the motion signal, and determine the motion type of the object to be evaluated.
  • the processing device 130 can determine the action type of the object to be evaluated through one or more motion signals collected within a preset time period or continuous motion signals within a preset duration. For example, the processing device 130 can cache 1 ⁇ 10 seconds of continuous motion signal data, and then identify the action type of the object to be evaluated through the cached 1 ⁇ 10 seconds of continuous motion signal data.
  • the processing device 130 can extract one or more frames of motion signal data from the cached 1 to 10 seconds of continuous motion signal data, and then identify the action type of the object to be evaluated based on the one or more frames of motion signal data.
  • the processing device 130 may collect a frame of motion signal data at intervals (such as 0.5 seconds, 1 second, etc.) after detecting that the object to be evaluated begins to move, and then identify the object to be evaluated based on the collected motion signal data.
  • the object's action type such as 0.5 seconds, 1 second, etc.
  • the processing device 130 may determine whether to perform action recognition. In response to the judgment result of action recognition, the processing device 130 may perform action recognition based on one or more frames of motion signals to determine the action type of the object to be evaluated. For example only, in some embodiments, processing device 130 may determine the motion type of the object based on the gesture signal. In some embodiments, for each frame of gesture signal, the processing device 130 may determine whether to perform action recognition. For example, for each frame of gesture signal, the processing device 130 may determine whether the signal duration corresponding to the current frame meets the preset duration threshold.
  • the processing device 130 may determine whether the number of frames corresponding to the current frame meets the preset frame number threshold. For another example, for each frame of gesture signal, the processing device 130 may determine whether the difference between the current frame gesture signal and the gesture signal of the previous frame (eg, the first frame, the previous frame, etc.) satisfies the preset difference threshold. For example only, the difference between the gesture signals may include the movement distance of the same part on the object in the current frame and the previous frame. Further, in response to the judgment result of action recognition, the processing device 130 may perform action recognition based on one or more frames of gesture signals to determine the action type of the object. For example, if the number of frames corresponding to the current frame meets the preset frame number threshold, the processing device 130 may determine to perform action recognition and perform action recognition based on one or more frames of gesture signals.
  • the processing device 130 may perform action recognition based on an action recognition model.
  • the output results of the action recognition model may include but are not limited to action type, number of actions, etc.
  • the action recognition model can identify the user's action type as sitting and clasping chest based on motion signals.
  • the action recognition model may be a trained machine learning model.
  • the action recognition model may be pre-trained by the processing device 130 and stored in the storage device 120, and the processing device 130 may access the storage device 120 to obtain the action recognition model.
  • the action recognition model can be trained based on sample information.
  • the sample information may include motion signals when professionals (eg, fitness coaches) and/or non-professionals exercise.
  • the motion signal in the sample information may be a signal that has undergone processing (eg, segmentation processing, glitch processing, conversion processing, etc.).
  • motion signals can be used as input to a machine learning model to train the machine learning model.
  • the feature information corresponding to the motion signal can also be used as the input of the machine learning model to train the machine learning model.
  • the frequency information and amplitude information of the electromyographic signal can be used as input to the machine learning model.
  • the angular velocity of the attitude signal and the angular velocity direction/acceleration value of the angular velocity can be used as input to the machine learning model.
  • the action start point, action midpoint, and action end point of the motion signal can be used as input to the machine learning model.
  • the machine learning model may include a linear classification model (LR), a support vector machine model (SVM), a naive Bayes model (NB), a K-nearest neighbor model (KNN), a decision tree model (DT), an ensemble One or more of the models (RF/GDBT, etc.) etc.
  • sample information (each segment of motion signal) from different action types can be labeled.
  • the sample information comes from the motion signal generated when the user performs a sitting position and presses the chest, which can be marked as “1", where "1" is used to represent the "sitting position and presses the chest”; the sample information comes from the movement signal generated when the user performs a bicep curl. It can be marked as "2”, where "2" is used to represent "bicep curl”.
  • the motion signal feature information corresponding to different action types (for example, the frequency information, amplitude information of the electromyographic signal, the angular velocity of the posture signal, the angular velocity direction, the angular velocity value of the angular velocity, etc.) is different.
  • the labeled sample information is used as the input of the machine learning model.
  • an action recognition model for identifying the user's action type can be obtained.
  • Inputting motion signals and/or corresponding feature information into the machine learning model can output the corresponding action type.
  • action types may also be identified in other ways.
  • the processing device 130 may identify action types based on preset rules.
  • the order of force exertion of relevant muscles in different action types is different, and the preset rule may be the order of force exertion of relevant muscles.
  • An action matching database or action matching model can be built based on preset rules.
  • the processing device 130 may determine the sequence of muscle force exertion based on the motion signal, and determine the action type based on the action matching database or action matching model. More description of action recognition can be found in the international application PCT/CN2021/081931 filed on March 19, 2021, the entire content of which is incorporated into this specification by reference.
  • the processing device 130 may be based on two or more signals among posture signals, electromyographic signals, mechanical signals, electrocardiographic signals, respiratory signals, sweat signals, etc. Identifies the object's action type. For example, the type of action currently being performed by the subject to be evaluated can be determined based on both the posture signal and the electromyographic signal. Just as an example, for two action types whose posture signals are relatively close, the electromyographic signal can be combined for action recognition to distinguish two different action types.
  • the posture signals corresponding to the first half cycle of the forward curl and the second half cycle of the forward arm flexion are relatively consistent, and the activation signals of the biceps brachii corresponding to the two actions are relatively consistent.
  • the force pattern is inconsistent.
  • the forward curling action and the forward arm flexion and extension action can be distinguished based on the difference in electromyographic signals.
  • Step 420 Determine evaluation criteria related to the motion signal based on the motion type.
  • the evaluation criteria may include a target part, a target motion signal corresponding to the target part, an evaluation parameter standard corresponding to the target motion signal, etc., or any combination thereof.
  • processing device 130 may determine the target site based on the type of motion.
  • the target part can refer to the key part to perform a certain action.
  • the processing device 130 may determine the critical site as a target site to be evaluated.
  • the processing device 130 may acquire the target motion signal of the target part, and then evaluate the target motion signal based on the evaluation parameter standard.
  • evaluation criteria may be related to error types.
  • the target motion signals corresponding to compensation errors and efficiency errors can be different.
  • the evaluation parameter standards corresponding to the target motion signal can also be different. Therefore, after determining the target part, the processing device 130 can perform motion evaluation based on different evaluation criteria for different error types. More details on the evaluation of motion signals for different error types can be referred to other locations in this specification (for example, Figures 5-9 and their related descriptions), and will not be described again here.
  • Figure 5 is a flowchart of an exemplary method of evaluating motion signals according to some embodiments of the present specification.
  • method 500 may be performed by processing logic, which may include hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., running on a processing device to perform hardware emulation). instructions), etc. or any combination thereof.
  • processing logic may include hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., running on a processing device to perform hardware emulation). instructions), etc. or any combination thereof.
  • one or more operations in the method 500 shown in FIG. 5 may be implemented by the processing device 130 and/or the terminal device 140 shown in FIG. 1 .
  • the method 500 may be stored in the storage device 120 in the form of instructions, and may be called and/or executed by the processing device 130 and/or the terminal device 140 .
  • step 320 and/or step 330 in motion assessment method 300 may be implemented by method 500 .
  • method 500 may be performed by determination module 220 and/or evaluation module 230 .
  • motion assessment for a first error type related to an action type (eg, compensation error, efficiency error, etc.) may be implemented by method 500 .
  • the following uses the processing device 130 as an example to describe the execution process of the method 500.
  • method 500 may include:
  • Step 510 Determine the target part corresponding to the action type based on the action type.
  • the processing device 130 can determine the target part based on the action type, so as to evaluate the motion signal of the target part.
  • the target area may include the pectoralis major.
  • Step 520 Obtain the motion signal of the target part.
  • the processing device 130 may evaluate the target motion signal corresponding to the target part based on the evaluation criteria.
  • different target motion signals need to be evaluated for different error types.
  • the target motion signal may include electromyographic signals of the target site.
  • the target motion signal may include the electromyographic signal and/or the posture signal of the target part.
  • Step 530 Evaluate the motion signal of the target part based on the evaluation criterion.
  • the evaluation criteria may include evaluation parameter criteria corresponding to the target motion signal of the target site.
  • the evaluation parameter standard may refer to parameters used to evaluate the target motion signal and their corresponding parameter values or parameter ranges.
  • the parameter may include a ratio between the amplitude of the motion signal of the target part and the amplitude of the motion signal of the reference part, and the corresponding parameter value or parameter range may include a ratio threshold.
  • the reference part may refer to other parts than the target part.
  • the processing device 130 may determine a ratio between the amplitude of the motion signal of the target part and the amplitude of the motion signal of the reference part, and determine whether the ratio is less than a ratio threshold. If the ratio is less than the ratio threshold, it can mean that the target part does not exert force correctly, but uses non-target parts to assist in exerting force. Thus, the evaluation result of the action currently performed by the object to be evaluated can be determined as a compensation error.
  • the ratio between the amplitude of the motion signal of the target part and the amplitude of the motion signal of the reference part when one or more objects correctly perform the action of the current action type can be obtained, and based on one or more Ratio determines the ratio threshold.
  • the target motion signal to be evaluated may include the electromyographic signal of the target part
  • the parameters may include the amplitude of the electromyographic signal of the target part and the electromyographic signal of the reference part.
  • the processing device 130 may determine the ratio between the amplitudes of the electromyographic signals of the target part and the amplitude of the electromyographic signals of the reference part, and determine whether the ratio is less than a ratio threshold. If the ratio is less than the ratio threshold, the evaluation result of the action currently performed by the object to be evaluated can be determined as a compensation error.
  • the parameter may include the amplitude of the motion signal, and the corresponding parameter value or parameter range may include the first motion amplitude.
  • the processing device 130 may determine the amplitude of the motion signal and determine whether the amplitude of the motion signal is less than the first motion amplitude. If the amplitude of the motion signal of the object to be evaluated is smaller than the first motion amplitude, it may mean that the target part does not exert force correctly, but uses non-target parts to assist in exerting force. Thus, the evaluation result of the action currently performed by the object to be evaluated can be determined as a compensation error.
  • the motion signal of the target part when one or more objects correctly performs an action of the current action type can be obtained, and the preset motion amplitude is determined based on the motion signal of one or more objects.
  • the target motion signal to be evaluated may include the electromyographic signal of the target part, and the parameters may include the amplitude of the electromyographic signal of the target part, the corresponding parameter value or The parameter range may include the first electromyographic amplitude.
  • the parameter may include the amplitude of the motion signal of the target part, and the corresponding parameter value or parameter range may include the second motion amplitude.
  • the processing device 130 may determine the amplitude of the motion of the target part and determine whether the amplitude of the motion signal is less than the second motion amplitude. If the amplitude is smaller than the second movement amplitude, it may mean that the target part has not reached the optimal exercise state. Thus, the evaluation result of the action currently performed by the object to be evaluated can be determined as an efficiency error.
  • the second motion amplitude may be determined based on the amplitude of the motion signal of the target part when one or more objects correctly perform an action of the current action type.
  • the target motion signal that needs to be evaluated may include the electromyographic signal or the posture signal of the target part, and the parameters may include the amplitude of the electromyographic signal or the posture signal of the target part,
  • the corresponding parameter value or parameter range may include the second electromyographic amplitude or the second gesture amplitude.
  • the first motion amplitude and the second motion amplitude may be different values.
  • the processing device 130 may first determine whether there is a compensation error in the target part based on the first motion amplitude, and then determine whether there is an efficiency error in the target part based on the second motion amplitude.
  • the target motion signal to be evaluated may include a first signal and a second signal
  • the parameters may include a time difference between a characteristic value of the first signal and a characteristic value of the second signal
  • the corresponding parameter value or Parameter ranges may include time difference thresholds.
  • the processing device 130 may determine the first characteristic value of the first signal and the second characteristic value of the second signal, determine the corresponding time difference between the first characteristic value and the second characteristic value, and determine whether the time difference is greater than a time difference threshold, If the time difference is greater than the time difference threshold, the evaluation result of the action currently performed by the object to be evaluated is determined to be an efficiency error.
  • the first characteristic value and the second characteristic value may refer to the characteristic values in the first signal and the second signal that can reflect the motion of the object to be evaluated, such as the maximum value and/or the minimum value of the amplitude; the first characteristic value and the second characteristic value
  • the corresponding time difference between the two characteristic values can be understood as the difference between the signal acquisition time corresponding to the first characteristic value and the signal acquisition time corresponding to the second characteristic value.
  • the first signal and the second signal may respectively include the electromyographic signal and the posture signal of the target part, and the parameters may include the characteristic value and posture of the electromyographic signal of the target part.
  • the time difference between the characteristic values of a signal may be understood as the difference between the signal acquisition time corresponding to the first characteristic value and the signal acquisition time corresponding to the second characteristic value.
  • FIG. 6 is a schematic diagram of the electromyographic signal and posture signal of the target part in the biceps curl movement according to some embodiments of this specification.
  • the electromyographic signal of the target site may refer to the electromyographic signal of the biceps brachii, which may be expressed as a curve 610 in which the electromyographic amplitude changes with time.
  • the attitude signal of the target part can be represented as a curve 620 in which the angle between the big arm and the forearm changes with time.
  • the amplitude corresponding to the curve 620 can be based on the maximum value of the angle between the big arm and the forearm (i.e. 180°).
  • the abscissa intervals 601, 602, 603, 604, and 605 shown in Figure 6 respectively represent the time from the beginning to the end of the bicep curl movement of the 1-5 groups. Alternatively or additionally, the time at which the action begins may be determined based on the gesture signal. Taking a single biceps curl in interval 601 as an example, the subject to be evaluated starts performing biceps curls from a state where the arms are nearly straight (that is, the angle between the upper arm and the forearm is close to 180°). As time goes by, , the amplitude of the electromyographic signal of the biceps brachii gradually increases, and the amplitude of the corresponding posture signal gradually decreases.
  • FIG. 7 is a schematic diagram of the electromyographic signal and posture signal of the target part in the seated chest pressing action according to some embodiments of this specification.
  • the electromyographic signal of the target site may refer to the electromyographic signal of the chest muscle, which may be expressed as a curve 710 in which the electromyographic amplitude changes with time.
  • the posture signal of the target part can be represented as a curve 720 in which the angle between the upper arm and the front of the body changes with time, wherein the amplitude corresponding to the curve 720 can be based on the maximum value of the angle between the upper arm and the front of the body (i.e.
  • the abscissa intervals 701, 702, 703, and 704 shown in Figure 7 respectively represent the time from the beginning to the end of the 1-4 groups of seated chest pressing movements. Taking the single sitting chest pressing movement in interval 701 as an example, the subject to be evaluated starts to perform the sitting chest pressing movement from a state where the upper arm is close to straight (that is, the angle between the upper arm and the front of the body is close to 90°). As time goes by, With the increase, the amplitude of the electromyographic signal of the chest muscles gradually increases, and the amplitude of the corresponding posture signal gradually decreases.
  • the amplitude of the electromyographic signal reaches the maximum value C, it means that the chest muscles have reached the optimal training state.
  • the current sitting chest pressing movement can be ended and the next sitting chest pressing movement can be started.
  • the amplitude of the electromyographic signal gradually decreases, the upper arm gradually returns from the forward state to a nearly straight state, and the amplitude of the corresponding posture signal gradually increases. . Therefore, ending the current sitting chest pressing action when the amplitude of the electromyographic signal reaches the maximum value can fully exercise the target part while avoiding continuing to perform the current action after the target part reaches the optimal exercise state, thus ensuring Movement efficiency.
  • the processing device 130 may determine the time difference corresponding to the maximum amplitude value of the electromyographic signal and the maximum amplitude value of the gesture signal, and determine whether the time difference is greater than a time difference threshold.
  • time difference is less than the time difference threshold, it can mean that the time corresponding to the maximum amplitude of the electromyographic signal coincides with or is close to the time corresponding to the maximum amplitude of the posture signal, and the biceps curling action can achieve optimal or better movement efficiency. If the time difference is greater than the time difference threshold, the evaluation result of the action currently performed by the object to be evaluated can be determined as an efficiency error.
  • processing device 130 may determine the location of compensation based on motion type.
  • the compensation parts may refer to parts that may be compensated in this type of movement.
  • the target area can include the pectoralis major, but there may be a compensatory error of using the middle and upper trapezius muscles to assist in force generation.
  • the processing device 130 may target the mid-upper trapezius muscle as a compensatory site and evaluate motion signals of the compensatory site.
  • the processing device 130 can determine whether the amplitude of the electromyographic signal of the middle and upper trapezius muscles is greater than the preset electromyographic amplitude corresponding to the middle and upper trapezius muscles. If so, the evaluation result of the current action of the subject to be evaluated can be Determined to be a compensation error.
  • the above embodiment uses electromyographic signals as an example to perform motion evaluation to compensate for errors.
  • the processing device 130 can also perform motion evaluation to compensate for errors based on other motion signals. For example, during the seated chest-clamping exercise, when there is a compensatory error in assisting force exertion by the middle and upper trapezius muscles, the subject's shoulder joint may also rise.
  • the processing device 130 can also determine the shoulder joint lifting angle of the subject to be evaluated based on the posture signal, and determine whether the lifting angle is greater than an angle threshold (for example, 15°). If so, the evaluation result of the action currently performed by the object to be evaluated can be determined as a compensation error. For another example, motion assessment to compensate for errors can also be performed based on other mechanical signals. As an example only, when a compensatory error of wrist turning occurs, the subject's lower palm may bear more stress. Thus, the pressure signals of different parts of the palm can be obtained through the pressure sensor, and based on the pressure, it can be determined whether the object to be evaluated has a compensatory error in turning the wrist.
  • an angle threshold for example 15°
  • method 500 may also include the step of evaluating impairment errors.
  • the processing device 130 can determine whether there is an injury error during the movement of the object to be evaluated. If not, the action type can be determined, and determine whether there is a compensation error during the movement of the object to be evaluated. If not, further evaluation of efficiency errors can be made.
  • method 800 is a flowchart of another exemplary method of evaluating motion signals according to some embodiments of the present specification.
  • method 800 may be performed by processing logic, which may include hardware (eg, circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., running on a processing device to perform hardware emulation). instructions), etc. or any combination thereof.
  • processing logic may include hardware (eg, circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., running on a processing device to perform hardware emulation). instructions), etc. or any combination thereof.
  • one or more operations in the method 800 shown in FIG. 8 may be implemented by the processing device 130 and/or the terminal device 140 shown in FIG. 1 .
  • the method 800 may be stored in the storage device 120 in the form of instructions, and may be called and/or executed by the processing device 130 and/or the terminal device 140 .
  • step 330 in motion assessment method 300 may be implemented by method 800.
  • method 800 may be performed by evaluation module 230.
  • motion assessment for symmetry errors may be implemented by method 800 .
  • the following uses the processing device 130 as an example to describe the execution process of the method 800.
  • method 800 may include:
  • Step 810 Determine the target part corresponding to the motion signal based on the evaluation criterion.
  • the target part corresponding to the motion signal may be determined based on the evaluation criteria. For example, parts prone to symmetry errors can be set as target parts in the evaluation criteria. For another example, any part that generates a motion signal can be set as a target part in the evaluation criteria.
  • the processing device 130 may determine the target part corresponding to the motion signal based on the evaluation standard, thereby evaluating the motion signal of the target part.
  • the target part may include at least two symmetrical parts of the object to be evaluated, such as two parts that are left and right symmetric or front and rear symmetric, etc.
  • Step 820 Obtain motion signals of the at least two symmetrical parts.
  • the processing device 130 may evaluate the target motion signal corresponding to the target part based on the evaluation criteria.
  • different target motion signals need to be evaluated for different error types.
  • the target motion signals to be evaluated may include electromyographic signals or posture signals of symmetrical parts.
  • Step 830 Evaluate motion signals of the at least two symmetrical parts based on the evaluation criteria.
  • the evaluation criteria may include evaluation parameter criteria corresponding to the target motion signal of the target site.
  • the evaluation parameter standard may refer to parameters used to evaluate the target motion signal and their corresponding parameter values or parameter ranges.
  • the parameter may include a signal difference between motion signals of symmetrical parts, and the corresponding parameter value or parameter range may include a signal difference threshold.
  • the processing device 130 can determine the signal difference of the motion signal of the symmetrical part, and determine whether the amplitude difference is greater than the signal difference threshold. If the amplitude difference is greater than the signal difference threshold, it may indicate that the exercise status of the symmetrical part is different, so the object to be evaluated will be The evaluation result of the currently performed action was determined to be a symmetry error.
  • the target motion signal to be evaluated may include the electromyographic signal of the symmetrical part, and the parameters may include the amplitude difference between the electromyographic signals of the symmetrical part, and the corresponding parameter value
  • the parameter range may include an amplitude difference threshold.
  • the target motion signal to be evaluated may include the posture signal of the symmetrical part, and the parameters may include the signal difference between the posture signals of the symmetrical part, the corresponding parameter value or parameter
  • the range may include a signal difference threshold.
  • the processing device 130 may determine the difference between posture signals (eg, joint angles, etc.) of the symmetrical parts at the same time, and use the difference at one time or the average of the differences at multiple times as the difference between the symmetrical parts.
  • Signal difference between attitude signals If the signal difference is greater than the signal difference threshold, it can indicate that the exercise status of the symmetrical parts is different, so the evaluation result of the current action of the object to be evaluated is determined to be a symmetry error.
  • the above threshold (for example, time difference threshold, amplitude difference threshold, signal difference threshold, etc.) can be determined through any one or more of historical experience, data statistics, and model prediction.
  • motion evaluation of symmetry errors can also be performed based on mechanical signals.
  • a pressure sensor can be used to obtain pressure signals corresponding to symmetrical parts of the object to be evaluated (e.g., buttocks, palms of both hands), and based on the pressure signals, it is determined whether there are symmetry errors in the object to be evaluated (e.g., asymmetrical sitting posture, excessive force on both hands) asymmetry, etc.).
  • the method 800 may further include the step of determining whether the object to be evaluated performs a symmetrical movement based on the motion signal.
  • the processing device 130 may further perform an evaluation of symmetry errors.
  • Figure 9 is a flowchart of yet another exemplary method of evaluating motion signals according to some embodiments of this specification.
  • method 900 may be performed by processing logic, which may include hardware (eg, circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., running on a processing device to perform hardware emulation). instructions), etc. or any combination thereof.
  • processing logic may include hardware (eg, circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., running on a processing device to perform hardware emulation). instructions), etc. or any combination thereof.
  • one or more operations in the method 900 shown in FIG. 9 may be implemented by the processing device 130 and/or the terminal device 140 shown in FIG. 1 .
  • the method 900 may be stored in the storage device 120 in the form of instructions, and may be called and/or executed by the processing device 130 and/or the terminal device 140 .
  • step 330 in motion assessment method 300 may be implemented by method 900 .
  • method 900 may be performed by evaluation module 230.
  • motion assessment for impairment errors may be accomplished by method 900 .
  • the following uses the processing device 130 as an example to describe the execution process of the method 900.
  • method 900 may include:
  • Step 910 Determine the target part corresponding to the motion signal based on the evaluation standard.
  • the target part corresponding to the motion signal may be determined based on the evaluation criteria. For example, parts prone to injury errors can be set as target parts in the evaluation criteria. For another example, any part that generates a motion signal can be set as a target part in the evaluation criteria.
  • the processing device 130 may determine the target part corresponding to the motion signal based on the evaluation standard, thereby evaluating the motion signal of the target part.
  • Step 920 Obtain the motion signal of the target part.
  • the processing device 130 may evaluate the target motion signal corresponding to the target part based on the evaluation criteria.
  • different target motion signals need to be evaluated for different error types.
  • the target motion signals to be evaluated may include electromyographic signals or posture signals of the target part.
  • Step 930 Evaluate the motion signal of the target part based on the evaluation criterion.
  • the evaluation criteria may include evaluation parameter criteria corresponding to the target motion signal of the target site.
  • the evaluation parameter standard may refer to parameters used to evaluate the target motion signal and their corresponding parameter values or parameter ranges.
  • the impairment error is not related to the type of movement of the subject being evaluated, but rather is related to the body structure and/or movement pattern of the subject being evaluated.
  • Exemplary injury errors may include excessive muscle fatigue, joint movement too quickly, excessive elbow hyperextension, shoulder spike impingement, core instability, etc.
  • damage errors may include fatigue conditions.
  • the parameters in the evaluation criteria corresponding to the fatigue state may include the frequency and/or amplitude of the motion signal of the target part, and the corresponding parameter values or parameter ranges may include frequency-related thresholds, etc.
  • the processing device 130 may determine the fatigue status of the target part based on the frequency of the motion signal and the evaluation criteria.
  • the parameters in the evaluation criteria corresponding to the fatigue state may include the frequency and/or amplitude of the electromyographic signal of the target part, and the corresponding parameter value or parameter range may include an electromyographic frequency-related threshold, for example, electromyographic frequency amplitude, EMG frequency amplitude slope, etc.
  • different fatigue levels may correspond to different damage levels.
  • the damage level may represent the magnitude of the risk or probability of causing damage.
  • the treatment device 130 can determine the damage level based on the fatigue level of the target site.
  • FIG. 10A is a schematic diagram of the electromyographic signal of the target part in the dumbbell lateral raise movement according to some embodiments of this specification
  • FIG. 10B is a diagram of the barbell biceps curl movement according to some embodiments of this specification.
  • the target part can include the left and/or right deltoid muscle of the human body. This manual takes the right deltoid muscle as an example.
  • FIG 10A shows a curve in which the amplitude of the electromyographic signal of the right deltoid muscle changes with the number of sets of movements
  • the curve of the change in the number of groups where L 1 and L′ 1 respectively represent the amplitude curve and frequency curve of the electromyographic signal corresponding to the first group of movements; L 2 and L′ 2 respectively represent the electromyographic signal corresponding to the second group of movements.
  • the user can continue to perform dumbbell lateral raises multiple times until fatigue occurs.
  • the target part can include the left and/or right biceps of the human body. This manual takes the right biceps as an example.
  • Figure 10B shows a curve in which the amplitude of the electromyographic signal of the right biceps brachii changes with the number of sets of movements, and (b) shows the curve of the amplitude of the electromyographic signal of the right biceps brachii. A plot of frequency as a function of the number of sets of movements.
  • the EMG frequency threshold may include a center frequency value of the electromyographic signal when the target site is in a normal state.
  • different tips or suggestions may be provided to the user for different levels of injury risks, for example, suggesting that the user reduce the speed of exercise or stop exercising, etc.
  • the parameters in the evaluation criteria corresponding to the damage error may include evaluation parameters related to the motion signal of the target part.
  • the parameters in the evaluation criteria corresponding to the damage error may include evaluation parameters related to the posture signal of the target part.
  • Exemplary evaluation parameters may include internal rotation angle, abduction angle, movement speed, movement acceleration, etc. of the target site, or any combination thereof. For example, in the high pull-down movement, the repeated internal rotation and lifting pattern of the upper arm will cause the humerus tendons, ligaments, etc. to repeatedly impact the upper acromion (the outermost side of the clavicle and the outermost side of the scapula), causing an acromion impact injury.
  • the degree of acromion impact injury is related to the internal rotation angle, abduction angle, elevation angle, movement speed, movement acceleration, etc. of the target part. Therefore, acromion impact injuries can be divided into different injury levels based on the internal rotation angle, abduction angle, elevation angle, movement speed, and movement acceleration of the target part. For example, in the high pull-down movement, the initial position is when the hands are raised to 120° with the palms facing down.
  • the internal rotation angle of the upper arms is 0 to 15° and the duration is greater than the preset time (for example, 15 seconds , 30 seconds, etc.), it can be determined that there is a risk of primary injury in the current exercise; when the internal rotation angle of the upper arm is 15° ⁇ 30° and the duration is greater than the preset time (for example, 15 seconds, 30 seconds, etc.), it can be determined that There is a risk of moderate injury in the current exercise.
  • the internal rotation angle of the upper arm is greater than 30° and the duration is greater than the preset time (for example, 15 seconds, 30 seconds, etc.), it can be determined that the risk of severe injury is present in the current exercise.
  • the human body's core stability, movement coherence or movement stability will drop sharply.
  • the decline in the core stability of the human body can be manifested in the posture signal as an increase in the angular velocity zero-crossing rate in the posture signal of the core part (for example, the waist); the decline in action coherence can be manifested in the posture signal as the target part's posture signal.
  • the motion amplitude decreases, the motion cycle time increases, etc.; the decrease in motion stability can be manifested in the attitude signal as an increase in the angular velocity zero-crossing rate in the attitude signal of the target part, etc.
  • the processing device 130 can determine the fatigue state or damage level of the target part based on the posture signal.
  • damage error assessment may also be performed based on other motion signals.
  • the parameters in the evaluation criteria corresponding to the damage error e.g., fatigue state
  • the parameters in the evaluation criteria corresponding to the damage error may include evaluation parameters related to the ECG signal, respiratory signal, sweat signal, etc. of the target site, or any combination thereof. For example, when the frequency of the ECG signal of the subject to be evaluated is greater than the ECG signal frequency threshold, it can be determined that the subject to be evaluated is in a fatigue state.
  • the frequency of the respiratory signal of the subject to be evaluated is greater than the respiratory signal frequency threshold, it may be determined that the subject to be evaluated is in a fatigue state.
  • the sweat amount of the subject to be evaluated for example, the amount of sweat per unit time
  • Figure 11 is a flow chart of a motion assessment feedback method according to some embodiments of this specification.
  • process 1100 may be performed by processing logic, which may include hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., running on a processing device to perform hardware emulation). instructions), etc. or any combination thereof.
  • processing logic may include hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (e.g., running on a processing device to perform hardware emulation). instructions), etc. or any combination thereof.
  • one or more operations in the process 1100 of the motion assessment method shown in FIG. 11 may be implemented by the processing device 130 and/or the terminal device 140 shown in FIG. 1 .
  • process 1100 may include:
  • Step 1110 Obtain the motion signal of the object.
  • step 1110 may be performed by acquisition module 210.
  • the motion signal in step 1110 may refer to a signal generated by the object to be evaluated during motion.
  • the motion signal can be used to characterize the motion state of the object to be evaluated, which can include electromyographic signals, posture signals, mechanical signals, electrocardiographic signals, respiratory signals, sweat signals, etc., or any combination thereof.
  • electromyographic signals can include electromyographic signals, posture signals, mechanical signals, electrocardiographic signals, respiratory signals, sweat signals, etc., or any combination thereof.
  • Step 1120 Evaluate the motion signal based on evaluation criteria related to the motion signal.
  • step 1120 may be performed by evaluation module 230.
  • the processing device 130 may directly evaluate the motion signal based on evaluation criteria related to the motion signal without identifying the action type of the object to be evaluated.
  • evaluation criteria related to motion signals can be set.
  • the processing device 130 can obtain the evaluation criteria, evaluate the motion signal, and determine the evaluation result.
  • the evaluation results may include whether there is an error in the motion corresponding to the motion signal and the type of the error.
  • evaluating motion signals please refer to the relevant descriptions in steps 320-330, which will not be described again here.
  • motion evaluation model can also be used to evaluate the motion signal of the object to be evaluated. It can be understood that the motion evaluation model can be trained by a large number of training samples. The training samples may include multiple sets of motion data and labels corresponding to each set of motion data, and the labels may include error types corresponding to the motion data.
  • Step 1130 Determine a target feedback method among multiple feedback methods based on the evaluation results.
  • Step 1140 Perform evaluation feedback according to the target feedback method.
  • steps 1130 and 1140 may be performed by feedback module 240.
  • the processing device may determine a target feedback method for displaying the evaluation results from multiple feedback methods based on the evaluation results, wherein the multiple feedback methods may notify the user through different feedback times and/or feedback types.
  • the evaluation feedback please refer to the relevant description in step 330, which will not be described again here.
  • Possible beneficial effects brought by embodiments of this specification include but are not limited to: (1) By evaluating the motion signal of the object to be evaluated, the motion errors of the object to be evaluated during the movement can be identified and help correct the errors, thereby Help users exercise scientifically; (2) Identify the action type of the object to be evaluated through motion signals, determine the evaluation standards related to the motion type, and then evaluate the motion signals of the object to be evaluated based on the evaluation standards, which can ensure to a certain extent The accuracy of the evaluation results; (3) By finely dividing the types of motion errors and combining multiple dimensions of motion signals to judge the motion signals, errors in the motion of the object to be evaluated can be more accurately identified , which is more conducive to the user's injury prevention and ability improvement; (4) By determining the target feedback method for displaying the evaluation results to the user based on the evaluation results, the action type of the object to be evaluated, and the user type, it is possible to determine the target feedback method that is more suitable for the user. Required feedback time and feedback type.
  • the possible beneficial effects may be any one or a combination of the above, or any other possible beneficial effects.
  • numbers are used to describe the quantities of components and properties. It should be understood that such numbers used to describe the embodiments are modified by the modifiers "about”, “approximately” or “substantially” in some examples. Grooming. Unless otherwise stated, “about,” “approximately,” or “substantially” means that the stated number is allowed to vary by ⁇ 20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending on the desired features of the individual embodiment. In some embodiments, numerical parameters should account for the specified number of significant digits and use general digit preservation methods. Although the numerical ranges and parameters used to identify the breadth of ranges in some embodiments of this specification are approximations, in specific embodiments, such numerical values are set as accurately as is feasible.

Landscapes

  • Engineering & Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

本说明书实施例提供一种运动评估方法及系统。所述运动评估方法包括：获取对象的运动信号，所述运动信号包括表征所述对象运动状态的信号；基于所述运动信号确定与所述运动信号相关的评估标准；基于所述评估标准对所述运动信号进行评估。

Description

一种运动评估方法及系统 技术领域
本说明书涉及信号检测与评估技术领域，特别涉及一种运动评估方法及系统。
背景技术
随着人们对身体健康以及科学运动的关注，运动监控设备正在极力发展。目前已有一些设备(例如手表、手环等)能够识别简单的日常运动行为(如跑步、走路、简单的球类运动等)，这些设备识别出动作类型后能够给出简易的动作统计参数(如跑步速度、走路步数、击球次数等)，且一般是一长段时间后给出反馈的。但是，目前上述设备暂时无法判断用户的运动动作或运动方式正确与否，尤其无法给用户实时的反馈。
由于错误的运动不仅达不到想要的健身效果，而且还可能会对人体造成伤害，因此，有必要研究一种能够实时识别用户运动错误并帮助用户纠正错误，从而确保用户科学运动的运动评估方法。
发明内容
本说明书实施例提供一种运动评估方法，所述方法包括：获取对象的运动信号，所述运动信号包括表征所述对象运动状态的信号；基于所述运动信号确定与所述运动信号相关的评估标准；基于所述评估标准对所述运动信号进行评估。
在一些实施例中，所述基于所述评估标准对所述运动信号进行评估，包括：基于所述评估标准评估所述运动信号，所述评估的结果包括错误类型；以及基于所述评估的结果进行评估反馈。
在一些实施例中，所述基于所述评估的结果进行评估反馈，包括：基于所述评估的结果或所述对象的用户类型确定多种反馈方式中的目标反馈方式，所述多种反馈方式通过不同的反馈时间或反馈类型通知所述对象；以及根据所述目标反馈方式进行反馈。
在一些实施例中，所述运动信号包括姿态信号、肌电信号、力学信号、心电信号、呼吸信号、汗液信号中的至少一个。
在一些实施例中，所述基于所述运动信号确定与所述运动信号相关的评估标准，包括：基于所述运动信号对所述对象进行动作识别，确定所述对象的动作类型；以及基于所述运动类型确定与所述运动信号相关的评估标准。
在一些实施例中，所述基于所述运动信号对所述对象进行动作识别，确定所述对象的动作类型，包括：对于每一帧运动信号，判断是否进行动作识别；以及响应于进行动作识别的判断结果，基于一帧或多帧运动信号进行动作识别，确定所述对象的动作类型。
在一些实施例中，所述基于所述动作类型确定与所述运动信号相关的评估标准，包括：基于所述动作类型确定与所述动作类型对应的目标部位；所述基于所述评估标准对所述运动信号进行评估，包括：获取所述目标部位的运动信号；以及基于所述评估标准评估所述目标部位的所述运动信号。
在一些实施例中，所述基于所述评估标准评估所述目标部位的运动信号，包括：基于所述目标部位确定参考部位；确定所述目标部位的所述运动信号的幅值与所述参考部位的运动信号的幅值之间的比值；判断所述比值是否小于比值阈值；以及响应于所述比值小于所述比值阈值，确定所述评估的结果为代偿错误。
在一些实施例中，所述基于所述评估标准评估所述目标部位的运动信号，包括：确定所述运动信号的幅值；判断所述运动信号的幅值是否小于第一运动幅值；以及响应于所述运动信号的幅值小于第一运动幅值，确定所述评估的结果为代偿错误。
在一些实施例中，所述基于所述评估标准评估所述目标部位的运动信号，包括：
确定所述运动信号的幅值；判断所述运动信号的幅值是否小于第二运动幅值；以及响应于所述运动信号的幅值小于所述第二运动幅值，确定所述评估的结果为效率错误。
在一些实施例中，所述运动信号包括第一信号和第二信号，所述基于所述评估标准评估所述目标部位的运动信号，包括：识别所述第一信号的第一特征值以及所述第二信号的第二特征值；确定所述第一信号的第一特征值与所述第二信号的第二特征值之间的时间差；判断所述时间差是否大于时间差阈值；以及响应于所述时间差大于所述时间差阈值，确定所述评估的结果为效率错误。
在一些实施例中，所述基于所述评估标准对所述运动信号进行评估，包括：基于所述评估 标准确定所述运动信号对应的目标部位，所述目标部位包括所述对象的至少两个对称部位；获取所述至少两个对称部位的所述运动信号；以及基于所述评估标准评估所述至少两个对称部位的所述运动信号。
在一些实施例中，所述基于所述评估标准评估所述至少两个对称部位的所述运动信号，包括：确定所述至少两个对称部位的运动信号的信号差；判断所述信号差是否大于信号差阈值；以及响应于所述信号差大于所述信号差阈值，确定所述评估的结果为对称性错误。
在一些实施例中，所述基于所述评估标准对所述运动信号进行评估，包括：基于所述评估标准确定所述运动信号对应的目标部位；确定所述目标部位的运动信号的频率；以及基于所述频率以及所述评估标准，确定所述目标部位的疲劳状态。
在一些实施例中，所述基于所述评估标准对所述运动信号进行评估，包括：基于所述评估标准确定所述运动信号对应的目标部位；获取所述目标部位的运动信号；基于所述运动信号确定所述目标部位的评估参数；以及基于所述评估参数以及所述评估标准，确定所述目标部位的损伤类型或损伤等级。
在一些实施例中，所述评估参数包括所述目标部位的内旋角度、外展角度、或运动加速度中的至少一种。
在一些实施例中，所述方法还包括：基于运动评估模型对所述运动信号进行评估。
本说明书实施例还提供一种运动评估反馈方法，所述方法包括：获取对象的运动信号，所述运动信号包括表征所述对象运动状态的信号；基于与所述运动信号相关的评估标准对所述运动信号进行评估；基于所述评估的结果确定多种反馈方式中的目标反馈方式，所述多种反馈方式通过不同的反馈时间或反馈类型通知所述对象；根据所述目标反馈方式进行评估反馈。
在一些实施例中，所述反馈时间包括及时反馈或运动结束反馈。
在一些实施例中，所述反馈类型包括：语音反馈、生物反馈、文字反馈中的至少一种。
在一些实施例中，所述方法还包括：基于所述运动信号对所述对象进行动作识别，确定所述对象的动作类型。
在一些实施例中，所述基于所述评估的结果确定多种反馈方式中的目标反馈方式，包括：基于所述动作类型、所述对象的用户类型或所述评估的结果中的至少一个确定所述多种反馈方式中的目标反馈方式。
在一些实施例中，所述运动信号包括姿态信号、肌电信号、力学信号、心电信号、呼吸信号、汗液信号中的至少一个。
本说明书实施例还提供一种运动评估系统，所述系统包括：获取模块，用于获取对象的运动信号，所述运动信号包括表征所述对象运动状态的信号；确定模块，用于基于所述运动信号确定与所述运动信号相关的评估标准；评估模块，用于基于所述评估标准对所述运动信号进行评估。
本说明书实施例还提供一种运动评估反馈系统，所述系统包括：获取模块，用于获取对象的运动信号，所述运动信号包括表征所述对象运动状态的信号；评估模块，用于基于与所述运动信号相关的评估标准对所述运动信号进行评估；反馈模块，用于基于所述评估的结果确定多种反馈方式中的目标反馈方式，所述多种反馈方式通过不同的反馈时间或反馈类型通知所述对象；以及根据所述目标反馈方式进行评估反馈。
本说明书实施例还提供一种计算机可读存储介质，所述存储介质存包括可执行指令，当由至少一个处理器执行时，所述可执行指令使所述至少一个处理器执行本说明所述的运动评估方法或运动评估反馈方法。
附加的特征将在下面的描述中部分地阐述，并且对于本领域技术人员来说，通过查阅以下内容和附图将变得显而易见，或者可以通过实例的产生或操作来了解。本说明书的特征可以通过实践或使用以下详细实例中阐述的方法、工具和组合的各个方面来实现和获得。
附图说明
本说明书将以示例性实施例的方式进一步说明，这些示例性实施例将通过附图进行详细描述。这些实施例并非限制性的，在这些实施例中，相同的编号表示相同的结构，其中：
图1是根据本说明书一些实施例所示的运动评估系统的示意图；
图2是根据本说明书另一些实施例所示的运动评估装置的模块图；
图3是根据本说明书一些实施例所示的运动评估方法的流程示意图；
图4是根据本说明书一些实施例所示的确定评估标准的示例性方法的流程图；
图5是根据本说明书一些实施例所示的对运动信号进行评估的示例性方法的流程图；
图6是根据本说明书一些实施例所示的二头弯举动作中目标部位的肌电信号和姿态信号的示意图；
图7是根据本说明书一些实施例所示的坐姿推胸动作中目标部位的肌电信号和姿态信号的示意图；
图8是根据本说明书一些实施例所示的对运动信号进行评估的另一示例性方法的流程图；
图9是根据本说明书一些实施例所示的对运动信号进行评估的又一示例性方法的流程图；
图10A是根据本说明书一些实施例所示的哑铃侧平举动作中目标部位的肌电信号的示意图；
图10B是根据本说明书一些实施例所示的杠铃二头弯举动作中目标部位的肌电信号的示意图；
图11是根据本说明书一些实施例所示的运动评估反馈方法的流程图。
具体实施方式
为了更清楚地说明本说明书的实施例的技术方案，下面将对实施例描述中所需要使用的附图作简单的介绍。显而易见地，下面描述中的附图仅仅是本说明书的一些示例或实施例，对于本领域的普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图将本说明书应用于其他类似情景。应当理解，给出这些示例性实施例仅仅是为了使相关领域的技术人员能够更好地理解进而实现本说明书，而并非以任何方式限制本说明书的范围。除非从语言环境中显而易见或另做说明，图中相同标号代表相同结构或操作。
如本说明书和权利要求书中所示，除非上下文明确提示例外情形，“一”、“一个”、“一种”和/或“该”等词并非特指单数，也可包括复数。一般说来，术语“包括”与“包含”仅提示包括已明确标识的步骤和元素，而这些步骤和元素不构成一个排它性的罗列，方法或者设备也可能包含其他的步骤或元素。术语“基于”是“至少部分地基于”。术语“一个实施例”表示“至少一个实施例”；术语“另一实施例”表示“至少一个另外的实施例”。
在本说明书的描述中，需要理解的是，术语“第一”、“第二”等仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”等特征可以明示或者隐含地包括至少一个该特征。在本说明书的描述中，“多个”的含义是至少两个，例如两个、三个等，除非另有明确具体的限定。
在运动健身领域，大多数常见的健身动作错误类型超过50种，即使是运动模式比较单一的跑步运动，常见的错误类型也超过30种。众所周知，错误的运动不仅达不到想要的健身效果，而且还可能会对人体造成损伤。针对该问题，本说明书实施例提供一种能够识别用户运动错误并帮助用户纠正错误的运动评估方法和系统，以在保证运动效果的同时减少用户在运动过程中造成的损伤。
下面结合附图对本说明书实施例提供的运动评估方法和系统进行详细说明。
图1是根据本说明书一些实施例所示的运动评估系统的示意图。
参照图1，在一些实施例中，运动评估系统100可以包括信号采集装置110、存储设备120、处理设备130、终端设备140以及网络150。运动评估系统100中的各个部件可以以多种方式相连接。例如，信号采集装置110可以与存储设备120和/或处理设备130通过网络150连接，也可以与存储设备120和/或处理设备130直接连接。又例如，存储设备120可以与处理设备130直接连接或通过网络150连接。又例如，终端设备140可以与存储设备120和/或处理设备130通过网络150连接，也可以与存储设备120和/或处理设备130直接连接。
信号采集装置110可以对待评估对象114(例如，用户)进行运动信号采集。所述运动信号可以指待评估对象114在运动过程中所产生的信号，所述运动信号可以用于表征待评估对象114的运动状态。示例性的运动信号可以包括姿态信号、肌电信号、力学信号、心电信号、呼吸信号、汗液信号等。在一些实施例中，如图1所示，信号采集装置110可以包括姿态信号采集装置111，肌电信号采集装置112以及力学信号采集装置113。在一些实施例中，姿态信号采集装置111可以包括速度传感器、惯性传感器(例如，加速度传感器、角速度传感器(例如陀螺仪)等)、光学传感器(例如，光学距离传感器、视频/图像采集器)、声学距离传感器、拉力传感器等或其任意组合。例如，信号采集装置110可以包括多个姿态信号采集装置111，该多个姿态信号采集装置111可以设置在待评估对象114的不同部位，或者相对于待评估对象114具有不同的采集角度和/或距离。在一些实施例中，肌电信号采集装置112可以包括一个或多个电极。例如，肌电信号采集装置112可 以包括多个电极，所述多个电极可以用于与待评估对象114的不同部位(例如，胸部、背部、肘部、腿部、腹部、腕部等)贴合，以采集待评估对象114不同部位的肌电信号。在一些实施例中，力学信号采集装置113可以包括压力传感器。例如，可以在待评估对象114的不同部位设置压力传感器，从而采集不同部位的压力信号。在一些实施例中，还可以基于姿态信号和肌电信号计算得到待评估对象的力学信号。在一些实施例中，信号采集装置110还可以包括心电信号采集装置、呼吸信号采集装置、汗液信号采集装置(图1中未示出)等。例如，心电信号采集装置可以包括多个电极，所述多个电极可以用于与待评估对象114的不同部位贴合，以采集待评估对象114的心电信号。再例如，呼吸信号采集装置可以包括呼吸频率传感器、流量传感器等，分别用于检测待评估对象114在运动过程中的呼吸频率、气体流量等信号。又例如，汗液信号采集装置可以包括与待评估对象114的皮肤接触的多个电极，用于检测待评估对象114的汗液流量、分析汗液成分等。在一些实施例中，信号采集装置110可以具有独立的电源，其可以通过有线或无线(例如蓝牙、WiFi等)的方式将采集的数据发送给运动评估系统100中的其他部件(例如，存储设备120、处理设备130、终端设备140)。
在一些实施例中，信号采集装置110可以通过网络150将其采集的待评估对象114的运动信号发送至存储设备120、处理设备130、终端设备140等。在一些实施例中，可以通过处理设备130对信号采集装置110所采集的运动信号进行处理。例如，处理设备130可以基于运动信号识别待评估对象114正在进行的动作类型，并基于该动作类型相关的评估标准对待评估对象114的当前动作进行评估，得到相应的评估结果。再例如，处理设备130可以在不识别待评估对象的动作类型的情况下，直接基于运动信号相关的评估标准对运动信号进行评估，得到评估结果。在一些实施例中，该评估结果可以发送至存储设备120进行记录，或者发送至终端设备140以反馈给用户。
网络150可以促进信息和/或数据的交换。网络150可以包括能够促进系统100的信息和/或数据交换的任何合适的网络。在一些实施例中，运动评估系统100的至少一个组件(例如，信号采集装置110、存储设备120、处理设备130、终端设备140)可以通过网络150与运动评估系统100中至少一个其他组件交换信息和/或数据。例如，处理设备130可以通过网络150从信号采集装置110和/或存储设备120获得运动信号。又例如，处理设备130可以通过网络150从终端设备140获得用户操作指令，示例性的操作指令可以包括但不限于设定用户信息(例如，性别、年龄、身高、体重、疾病史等)、选择运动模式(例如，跑步、跳绳、游泳、肌肉训练等)、设定运动时间等。
在一些实施例中，网络150可以为任意形式的有线或无线网络，或其任意组合。仅作为示例，网络150可以包括缆线网络、有线网络、光纤网络、远程通信网络、内部网络、互联网、局域网络(LAN)、广域网络(WAN)、无线局域网络(WLAN)、城域网(MAN)、公共开关电话网络(PSTN)、蓝牙网络、ZigBee网络、近场通讯(NFC)网络等或其任意组合。在一些实施例中，网络150可以包括至少一个网络接入点，运动评估系统100的至少一个组件可以通过接入点连接到网络150以交换数据和/或信息。
存储设备120可以储存数据、指令和/或任何其他信息。在一些实施例中，存储设备120可以存储从信号采集装置110、处理设备130和/或终端设备140获得的数据。例如，存储设备120可以存储信号采集装置110采集的运动信号。在一些实施例中，存储设备120可以存储处理设备130用来执行或使用来完成本说明书中描述的示例性方法的数据和/或指令。在一些实施例中，存储设备120可以包括大容量存储器、可移动存储器、易失性读写存储器、只读存储器(ROM)等或其任意组合。示例性的大容量存储器可以包括磁盘、光盘、固态磁盘等。在一些实施例中，存储设备120可以在云平台上实现。仅作为示例，所述云平台可以包括私有云、公共云、混合云、社区云、分布云、内部云、多层云等或其任意组合。
在一些实施例中，存储设备120可以连接到网络150以与运动评估系统100中的至少一个其他组件(例如，信号采集装置110、处理设备130、终端设备140)通信。运动评估系统100中的至少一个组件可以通过网络150访问存储设备120中存储的数据、指令或其他信息。在一些实施例中，存储设备120可以与运动评估系统100中的一个或以上组件(例如，信号采集装置110、终端设备140)直接连接或通信。在一些实施例中，存储设备120可以是信号采集装置110和/或处理设备130的一部分。
处理设备130可以处理从信号采集装置110、存储设备120、终端设备140和/或运动评估系统100的其他组件获得数据和/或信息。在一些实施例中，处理设备130可以从信号采集装置110、存储设备120或终端设备140中任意一个或多个获得待评估对象114的运动信号，通过对运动信号进行处理以确定其对应的动作类型。在一些实施例中，处理设备130可以根据运动信号所对应的动 作类型获取评估标准，并根据该评估标准对运动信号进行评估。在一些实施例中，处理设备130可以直接基于运动信号确定与所述运动信号相关的评估标准，并基于运动信号相关的评估标准对运动信号进行评估，得到评估结果。在一些实施例中，处理设备130可以从存储设备120获取预先存储的计算机指令，并执行该计算机指令以实现本说明书所描述的运动评估方法。
在一些实施例中，处理设备130可以是单一服务器或服务器组。服务器组可以是集中式的或分布式的。在一些实施例中，处理设备130可以是本地或远程的。例如，处理设备130可以通过网络150从信号采集装置110、存储设备120和/或终端设备140访问信息和/或数据。又例如，处理设备130可以直接连接到信号采集装置110、存储设备120和/或终端设备140以访问信息和/或数据。在一些实施例中，处理设备130可以在云平台上实现。例如，云平台可以包括私有云、公共云、混合云、社区云、分布式云、云间云、多云等或其任意组合。
终端设备140可以接收、发送和/或显示数据。所述接收的数据可以包括信号采集装置110采集的数据、存储设备120存储的数据、处理设备130生成的评估结果等。例如，终端设备140接收和/或显示的数据可以包括信号采集装置110采集的运动信号、处理设备130基于运动信号确定的待评估对象114的动作类型、处理设备130基于确定的评估标准、处理设备130基于评估标准生成的评估结果等。所述发送的数据可以包括用户(例如，健身教练、待评估对象)的输入数据和指令等。例如，终端设备140可以将用户输入的操作指令通过网络150发送给信号采集装置110，以控制信号采集装置110进行相应的数据采集。又例如，终端设备140可以将用户输入的评估指令通过网络150发送给处理设备130。
在一些实施例中，终端设备140可以包括移动设备141、平板计算机142、膝上型计算机143等或其任意组合。例如，移动设备141可以包括移动电话、个人数字助理(PDA)、医用移动终端等或其任意组合。在一些实施例中，终端设备140可以包括输入设备(如键盘、触摸屏)、输出设备(如显示器、扬声器)等。在一些实施例中，处理设备130可以是终端设备140的一部分。
应当注意的是，上述有关运动评估系统100的描述仅仅是为了示例和说明，而不限定本说明书的适用范围。对于本领域技术人员来说，在本说明书的指导下可以对运动评估系统100进行各种修正和改变。然而，这些修正和改变仍在本说明书的范围之内。例如，信号采集装置110的可以包括更多或更少的功能组件。
图2是根据本说明书另一些实施例所示的运动评估装置的模块图。在一些实施例中，图2所示的运动评估装置200可以以软件和/或硬件的方式应用到图1所示的运动评估系统100，例如，可以以软件和/或硬件的形式配置到处理设备130和/或终端设备140，以用于评估信号采集装置110所采集的运动信号。
参照图2，在一些实施例中，运动评估装置200可以包括获取模块210、确定模块220、评估模块230以及反馈模块240。
获取模块210可以用于获取待评估对象114的运动信号。例如，可以从信号采集装置110、存储设备120或终端设备140中的任意一者或多者处获取运动信号。在一些实施例中，该运动信号可以包括肌电信号、姿态信号、力学信号、心电信号、呼吸信号、汗液信号等。关于运动信号的更多细节可以参照本说明书的其他位置(例如，图1、图3及其相关描述)，此处不再赘述。
确定模块220可以用于确定与运动信号相关的评估标准。在一些实施例中，确定模块220可以直接确定与运动信号相关的评估标准。在一些实施例中，确定模块220可以基于运动信号对对象114进行动作识别，确定对象114的动作类型，并基于动作类型确定与运动信号相关的评估标准。所述评估标准可以指用于基于运动信号评估某一动作是否被正确执行的标准。
评估模块230可以用于基于确定模块220确定的评估标准对获取模块210获取的待评估对象114的运动信号进行评估，以确定待评估对象114进行的动作的评估结果。仅作为示例，所述评估结果可以包括所述动作是否存在错误、错误的类型、错误的等级等。
反馈模块240可以用于将评估模块230生成的评估结果反馈给用户。在一些实施例中，反馈模块240可以根据待评估对象114当前的动作阶段和/或运动场景确定反馈评估结果的时机。在一些实施例中，反馈模块240可以根据用户类型(例如新手用户、业余爱好者用户、专业用户等)确定评估结果的反馈方式和/或内容。
关于上述各个模块的更多细节可以参照本说明书的其他位置(例如图3-11部分及其相关描述)，此处不再赘述。
应当理解，图2所示的运动评估装置200及其模块可以利用各种方式来实现。例如，在一些实施例中，系统及其模块可以通过硬件、软件或者软件和硬件的结合来实现。其中，硬件部分可 以利用专用逻辑来实现；软件部分则可以存储在存储器中，由适当的指令执行系统，例如微处理器或者专用设计硬件来执行。本领域技术人员可以理解上述的方法和系统可以使用计算机可执行指令和/或包含在处理器控制代码中来实现，例如在诸如磁盘、CD或DVD-ROM的载体介质、诸如只读存储器(固件)的可编程的存储器或者诸如光学或电子信号载体的数据载体上提供了这样的代码。本说明书的系统及其模块不仅可以有诸如超大规模集成电路或门阵列、诸如逻辑芯片、晶体管等的半导体、或者诸如现场可编程门阵列、可编程逻辑设备等的可编程硬件设备的硬件电路实现，也可以用例如由各种类型的处理器所执行的软件实现，还可以由上述硬件电路和软件的结合(例如，固件)来实现。
需要注意的是，上述关于运动评估装置200的描述仅出于说明性目的而提供，并不旨在限制本说明书的范围。可以理解，对于本领域的技术人员来说，可以根据本说明书的描述，在不背离这一原理的情况下，对各个模块进行任意组合，或者构成子系统与其他模块连接。例如，图2中所述的获取模块210、确定模块220、评估模块230以及反馈模块240可以是一个系统中的不同模块，也可以是一个模块实现上述的两个或两个以上模块的功能。再例如，运动评估装置200还可以包括识别模块，用于基于运动信号对所述对象进行动作识别，确定所述对象的动作类型。诸如此类的变形，均在本说明书的保护范围之内。
图3是根据本说明书一些实施例所示的示例性运动评估方法的流程图。在一些实施例中，方法300可以通过处理逻辑来执行，该处理逻辑可以包括硬件(例如，电路、专用逻辑、可编程逻辑、微代码等)、软件(运行在处理设备上以执行硬件模拟的指令)等或其任意组合。在一些实施例中，图3所示的运动评估方法的方法300中的一个或多个操作可以通过图1所示的处理设备130和/或终端设备140实现。例如，方法300可以以指令的形式存储在存储设备120中，并由处理设备130和/或终端设备140执行调用和/或执行。下文以处理设备130为例描述方法300的执行过程。
参照图3，在一些实施例中，运动评估方法的方法300可以包括：
步骤310，获取对象的运动信号。在一些实施例中，步骤310可以由获取模块210执行。
在一些实施例中，运动信号可以指待评估对象在运动过程中所产生的信号。在一些实施例中，所述运动信号可以用于表征待评估对象的运动状态，其可以包括肌电信号、姿态信号、力学信号、心电信号、呼吸信号、汗液信号等或其任意组合。在一些实施例中，肌电信号可以用于表征待评估对象的当前运动的技术准确性(例如，肌肉募集顺序)和损伤风险(例如，疲劳程度)。在一些实施例中，可以通过与待评估对象贴合的一个或多个电极采集得到肌电信号。例如，可以将多个电极可以与待评估对象的不同部位(例如，胸部、背部、肘部、腿部、腹部、腕部等)贴合，以采集待评估对象不同部位的肌电信号。
姿态信号可以包括各关节角度、速度、加速度，或者各人体部位的欧拉角、角速度、角加速度等信息。在一些实施例中，姿态信号也可以用于表征待评估对象的当前运动的技术准确性(例如，关节角度、发力顺序等)和损伤风险(例如，肩峰撞击)。在一些实施例中，可以通过姿态信号采集装置(例如，图1所示的姿态信号采集装置111)采集姿态信号。示例性的姿态信号采集装置可以包括速度传感器、惯性传感器(例如，加速度传感器、角速度传感器(例如陀螺仪)等)、光学传感器(例如，光学距离传感器、视频/图像采集器)、声学距离传感器、拉力传感器等或其任意组合。
力学信号可以指待评估对象关节部位处对应的受力或运动器材检测到的受力，其可以用于表征损伤风险(例如，脚踝处压力、膝盖处压力等)。在一些实施例中，力学信号可以通过力学传感器得到。例如，所述力学传感器可以包括压力传感器，可以基于所述压力传感器获取待评估对象上不同部位的压力信号作为待评估对象的力学信号。在一些实施例中，力学信号可以基于姿态信号和肌电信号计算得到。
心电信号可以指用于表示待评估对象的心脏活动情况的信号。在一些实施例中，可以通过心电信号采集装置采集心电信号。例如，心电信号采集装置可以包括多个电极，所述多个电极可以用于与待评估对象的不同部位贴合，以采集待评估对象的心电信号。呼吸信号可以指用于表示待评估对象的呼吸情况的信号。在一些实施例中，可以通过呼吸信号采集装置采集呼吸信号。例如，呼吸信号采集装置可以包括呼吸频率传感器、流量传感器等，分别用于检测待评估对象在运动过程中的呼吸频率、气体流量等数据。汗液信号可以指用于表示待评估对象的出汗情况的信号。在一些实施例中，可以通过汗液信号采集装置采集汗液信号。例如，汗液信号采集装置可以包括与待评估对象的皮肤接触的多个电极，用于检测待评估对象的汗液流量或分析汗液成分等。在一些实施例中，心电信号、呼吸信号、汗液信号等或其任意组合可以用于表征待评估对象的当前运动的损伤风险(例 如，疲劳程度)。
在一些实施例中，处理设备130可以直接从信号采集装置(例如，信号采集装置110)获取运动信号。在一些实施例中，运动信号可以存储在存储设备(例如，存储设备120)中，处理设备130可以从存储设备获取运动信号。
步骤320，基于所述运动信号确定与所述运动信号相关的评估标准。在一些实施例中，步骤320可以由确定模块220执行。
在一些实施例中，所述评估标准可以指用于基于运动信号评估某一动作是否被正确执行的标准。在一些实施例中，评估标准可以包括目标部位、所述目标部位对应的目标运动信号、所述目标运动信号对应的评估参数标准等或其任意组合。所述目标部位可以指用户在执行某一动作时待评估的部位。所述目标运动信号可以指该目标部位具体需要评估的运动信号，例如，姿态信号、肌电信号、力学信号、心电信号、呼吸信号、汗液信号等中的一个或多个。所述评估参数标准可以指用于评估目标运动信号的参数及其对应的参数值或参数范围。
在一些实施例中，评估标准可以用于评估运动信号，从而确定运动信号对应的运动是否存在错误以及错误类型。在一些实施例中，示例性的错误类型可以包括损伤错误、代偿错误、效率错误、对称性错误等或其任意组合。损伤错误可以指该运动错误可能会对人体造成损伤。代偿错误可以指使用非目标部位(例如，肌肉)辅助发力的错误。效率错误可以指以一定的动作模式做动作时，动作范围过大或过小，使目标部位处于非最佳激活程度。对称性错误可以指人体上两个对称(例如，两侧对称、前后对称)部位发力不平衡的情况。在一些实施例中，对于一个或多个错误类型，所述评估结果还可以包括所述错误类型的等级。仅作为示例，损伤错误的错误等级可以包括重度、中度、轻度等。
在一些实施例中，评估标准可以包括用于评估不同错误类型的标准。例如，对于不同的错误类型，需评估的目标部位和/或目标运动信号可以不同。相应地，不同目标部位的不同目标运动信号对应的评估参数标准也可以不同。由此，在对运动信号进行评估时，评估标准可以包括用于评估一个或多个错误类型的一个或多个标准。在一些实施例中，评估标准中可以包括对预设的错误类型进行评估的标准。例如，用户可以通过终端设备(例如，终端设备140)选择需要评估的错误类型，处理设备130可以基于用户选择的错误类型确定评估标准。在一些实施例中，评估标准中还可以包括与全部错误类型对应的评估标准，用于对每个错误类型评估运动信号是否存在错误。
在一些实施例中，评估标准可以包括第一评估标准，所述第一评估标准可以评估与对象的动作类型相关的第一错误类型。示例性的第一错误类型可以包括代偿错误、效率错误等。在评估所述对象的运动是否存在代偿错误或效率错误时，处理设备130可以基于运动信号对对象进行动作识别，确定对象的动作类型，并基于运动类型确定与运动信号相关的第一评估标准。关于对对象进行动作识别以及确定评估标准的更多细节可以参照本说明书的其他位置(例如，图4及其相关描述)，此处不再赘述。
在一些实施例中，评估标准可以包括第二评估标准，所述第二评估标准可以用于评估与对象的动作类型无关的第二错误类型。示例性的第二错误类型可以包括损伤错误、对称性错误等。在评估所述对象的运动是否存在损伤错误或对称性错误时，处理设备130可直接确定评估标准中的目标部位及其目标信号，并基于评估参数标准对目标信号进行评估。在一些实施例中，第二评估标准可以直接基于运动信号确定。例如，可以预先设置与运动信号相关的评估标准，处理设备130可以获取所述评估标准，并对运动信号进行评估。
在一些实施例中，处理设备130还可以基于与对象相关的信息确定评估标准。与对象相关的信息可以包括对象的性别、年龄、身高、体重、健康状况等。例如，对于同一个动作类型，不同的对象(例如，男性和女性、成年人和未成年人、健康人士和存在疾病史的对象等)可以对应不同的评估标准。
在一些实施例中，评估标准可以存储在存储设备120中，处理设备130可以直接确定或基于动作类型确定对应的评估标准。
步骤330，基于所述评估标准对所述运动信号进行评估。在一些实施例中，步骤330可以由评估模块230执行。
在一些实施例中，处理设备130可以基于评估标准评估运动信号，确定评估结果。所述评估结果可以包括所述运动信号对应的运动是否存在错误以及错误类型。在一些实施例中，对于一个或多个错误类型，所述评估结果还可以包括所述错误类型的等级。仅作为示例，损伤错误的错误等级可以包括重度、中度、轻度等。在一些实施例中，处理设备130可以根据预设的评估顺序对运动 信号进行评估。例如，处理设备130可以先基于评估标准判断待评估对象在运动过程中是否存在损伤错误，并在确定待评估对象在运动过程中不存在损伤错误时再进行代偿错误的判断。进一步地，处理设备130可以在确定待评估对象在运动过程中不存在代偿错误时再进行效率错误的判断。关于基于评估标准对运动信号进行评估的更多细节可以参照本说明书的其他位置(例如，图5-9及其相关描述)，此处不再赘述。
在一些实施例中，在得到对象当前进行的动作的评估结果之后，处理设备130还可以基于评估结果进行评估反馈。在一些实施例中，处理设备130可以通过多种反馈方式进行评估反馈，所述多种反馈方式可以通过不同的反馈时间和/或反馈类型通知用户(例如，待评估对象或教练)。例如，反馈时间可以包括及时反馈或运动结束反馈(例如，单周期动作后反馈、单次训练后反馈、停止运动后反馈等)。反馈类型可以包括语音反馈、生物反馈(例如，电刺激)、文字反馈、图形界面反馈等或其任意组合。在一些实施例中，还可以根据需反馈的用户确定反馈类型。例如，根据反馈用户的不同，反馈类型还可以包括专业反馈、普通反馈等。所述专业反馈可以指通过相对较为专业的语言向用户进行反馈，普通反馈可以指通过通俗易懂的语言向用户进行反馈。在一些实施例中，处理设备130可以基于评估结果、动作类型、对象的用户类型等或其任意租个确定多种反馈方式中的目标反馈方式，从而根据目标反馈方式进行反馈。例如，处理设备130可以基于评估结果确定对象当前进行的动作是否存在损伤错误，如果存在损伤错误，处理设备130可以确定反馈时间为及时反馈，且反馈方式为语音反馈，从而可以将反馈信息通过语音及时反馈给对象，以防止或减少对象在运动过程中受到的损伤。再例如，如果对象当前进行的动作不存在损伤错误，但存在另一种错误类型，例如，对称性错误，处理设备130可以确定反馈时间为运动结束反馈，且反馈方式为文字和/或图形界面反馈。再例如，考虑到在向对象进行评估反馈时可能会分散对象的注意力，因此，为了避免对象在运动过程中因注意力不集中增加风险，当对象当前进行的动作类型不适合立即反馈时(例如，大重量动作)，处理设备130可以确定反馈时间为运动结束反馈。又例如，当对象的用户类型为专业健身人士(例如，健身教练)时，可以通过专业反馈展现评估结果，而当用户为运动新人时，为了便于用户理解评估结果，则可以选择普通反馈展现评估结果。
需要说明的是，以上反馈方式仅为举例说明，在本说明书实施例中，所采用的目标反馈方式可以包括但不限于上述方式。例如，在一些实施例中，可以通过电极向存在错误的部分施加电刺激，以提示对应部位存在动作错误。再例如，在一些实施例中，处理设备130可以根据用户选择或设定的反馈方式将评估结果反馈给用户。又例如，在一些实施例中，处理设备130在向用户反馈评估结果时，还可以向用户展示正确的运动方式，以指导用户科学运动。
需要说明的是，以上关于对运动信号进行评估的方式仅为示例性说明，在本说明书的一些实施例中，可以采用其他的方式对运动信号进行评估。例如，可以基于运动评估模型对该运动信号进行评估。在一些实施例中，该运动评估模型可以是机器学习模型，其可以通过若干训练样本训练后得到。
应当注意的是，上述有关方法300的描述仅仅是为了示例和说明，而不限定本说明书的适用范围。对于本领域技术人员来说，在本说明书的指导下可以对方法300进行各种修正和改变。然而，这些修正和改变仍在本说明书的范围之内。例如，方法300还可以包括基于运动信号对对象进行动作识别的步骤。再例如，方法300还可以包括基于评估结果进行评估反馈的步骤。
图4是根据本说明书一些实施例所示的确定评估标准的示例性方法的流程图。在一些实施例中，方法400可以通过处理逻辑来执行，该处理逻辑可以包括硬件(例如，电路、专用逻辑、可编程逻辑、微代码等)、软件(运行在处理设备上以执行硬件模拟的指令)等或其任意组合。在一些实施例中，图4所示的方法400中的一个或多个操作可以通过图1所示的处理设备130和/或终端设备140实现。例如，方法400可以以指令的形式存储在存储设备120中，并由处理设备130和/或终端设备140执行调用和/或执行。在一些实施例中，运动评估方法300中的步骤320可以通过方法400来实现。在一些实施例中，方法400可以由确定模块220执行。下文以处理设备130为例描述方法400的执行过程。
参照图4，在一些实施例中，方法400可以包括：
步骤410，基于运动信号对对象进行动作识别，确定所述对象的动作类型。
处理设备130可以基于运动信号对待评估对象进行动作识别，并确定待评估对象的动作类型。在一些实施例中，处理设备130可以通过在预设时间段内采集的一个或多个运动信号或预设时长内的连续运动信号确定待评估对象的动作类型，例如，处理设备130可以缓存1～10秒的连续运动信号数据，然后通过缓存的1～10秒连续运动信号数据识别待评估对象的动作类型。又例如，处理 设备130可以在缓存的1～10秒连续运动信号数据中提取一帧或多帧运动信号数据，然后基于该一帧或多帧运动信号数据识别待评估对象的动作类型。在一些实施例中，处理设备130可以在检测到待评估对象开始运动后每隔一段时间(例如0.5秒、1秒等)采集一帧运动信号数据，然后基于已采集的运动信号数据识别待评估对象的动作类型。
在一些实施例中，为了确定待评估对象的动作类型，对于每一帧运动信号，处理设备130可以判断是否进行动作识别。响应于进行动作识别的判断结果，处理设备130可以基于一帧或多帧运动信号进行动作识别，确定待评估对象的动作类型。仅作为示例，在一些实施例中，处理设备130可以基于姿态信号确定对象的动作类型。在一些实施例中，对于每一帧姿态信号，处理设备130可以判断是否进行动作识别。例如，对于每一帧姿态信号，处理设备130可以判断当前帧对应的信号时长是否满足预设时长阈值。再例如，对于每一帧姿态信号，处理设备130可以判断当前帧对应的帧数是否满足预设帧数阈值。又例如，对于每一帧姿态信号，处理设备130可以判断当前帧姿态信号与之前帧(例如，第一帧、前一帧等)的姿态信号之间的差值是否满足预设差值阈值。仅作为示例，所述姿态信号之间的差值可以包括对象上相同部位在当前帧与之前帧中的移动距离。进一步地，响应于进行动作识别的判断结果，处理设备130可以基于一帧或多帧姿态信号进行动作识别，确定对象的动作类型。例如，如果当前帧对应的帧数满足预设帧数阈值，处理设备130可以确定进行动作识别，并基于一帧或多帧姿态信号进行动作识别。
在一些实施例中，处理设备130可以基于动作识别模型进行动作识别。在一些实施例中，动作识别模型的输出结果可以包括但不限于动作类型、动作数量等。例如，动作识别模型可以根据运动信号识别用户的动作类型为坐姿夹胸。在一些实施例中，所述动作识别模型可以是训练好的机器学习模型。在一些实施例中，动作识别模型可以预先由处理设备130训练，并存储在存储设备120中，处理设备130可以访问存储设备120以获取动作识别模型。
在一些实施例中，动作识别模型可以基于样本信息训练得到。样本信息可以包括专业人员(例如，健身教练)和/或非专业人员运动时的运动信号。在一些实施例中，样本信息中的运动信号可以是经过处理(例如，分段处理、毛刺处理和转换处理等)的信号。在一些实施例中，运动信号可以作为机器学习模型的输入来对机器学习模型进行训练。在一些实施例中，运动信号对应的特征信息也可以作为机器学习模型的输入来对机器学习模型进行训练。例如，可以将肌电信号的频率信息和幅值信息作为机器学习模型的输入。又例如，可以将姿态信号的角速度、角速度方向/角速度的加速度值作为机器学习模型的输入。再例如，可以将运动信号的动作开始点、动作中间点和动作结束点作为机器学习模型的输入。在一些实施例中，机器学习模型可以包括线性分类模型(LR)、支持向量机模型(SVM)、朴素贝叶斯模型(NB)、K近邻模型(KNN)、决策树模型(DT)、集成模型(RF/GDBT等)等中的一种或多种。在一些实施例中，训练识别用户动作类型的机器学习模型时，可以将来自不同动作类型的样本信息(每段运动信号)进行打标签处理。例如，样本信息来自用户执行坐姿夹胸时产生的运动信号可以标记为“1”，这里的“1”用于表征“坐姿夹胸”；样本信息来自用户执行二头弯举时产生的运动信号可以标记为“2”，这里的“2”用于表征“二头弯举”。不同动作类型对应的运动信号特征信息(例如，肌电信号的频率信息、幅值信息、姿态信号角速度、角速度方向、角速度的角速度值等)不同，将打标签的样本信息作为机器学习模型的输入来对机器学习模型进行训练，可以得到用于识别用户动作类型的动作识别模型，在该机器学习模型中输入运动信号和/或对应的特征信息识可以输出对应的动作类型。
在一些实施例中，还可以通过其他方式识别动作类型。例如，处理设备130可以基于预设规则识别动作类型。仅作为示例，不同动作类型中相关肌肉的发力顺序不同，所述预设规则可以是相关肌肉的发力顺序。可以基于预设规则构建动作匹配数据库或动作匹配模型。在进行动作类型识别时，处理设备130可以基于运动信号确定肌肉发力顺序，并根据动作匹配数据库或动作匹配模型确定动作类型。关于动作识别的更多描述可以在2021年3月19日提交的国际申请PCT/CN2021/081931中找到，其全部内容通过引用并入本说明书。
在一些实施例中，为了提高动作类型识别的准确性，处理设备130可以基于姿态信号、肌电信号、力学信号、心电信号、呼吸信号、汗液信号等中的两种或两种以上的信号识别对象的动作类型。例如，可以同时基于姿态信号和肌电信号来确定待评估对象当前正在进行的动作类型。仅作为示例，对于姿态信号较为接近的两种动作类型，可以结合肌电信号进行动作识别，以区分两种不同的动作类型。以前向弯举动作和前向臂屈伸动作为例，前向弯举动作的前半周期和前向臂屈的后半周期对应的姿态信号较为一致，而两种动作对应的肱二头肌的发力模式不一致。由此，可以基于肌电信号的区别区分前向弯举动作和前向臂屈伸动作。
步骤420，基于所述运动类型确定与所述运动信号相关的评估标准。
在一些实施例中，评估标准可以包括目标部位、所述目标部位对应的目标运动信号、所述目标运动信号对应的评估参数标准等或其任意组合。在一些实施例中，处理设备130可以基于动作类型确定目标部位。目标部位可以指执行某一动作的关键部位。处理设备130可以将所述关键部位确定为待评估的目标部位。在一些实施例中，一个动作类型所对应的目标部位可以是一个或多个。进一步地，处理设备130可以获取该目标部位的目标运动信号，然后基于评估参数标准评估该目标运动信号。在一些实施例中，评估标准可以与错误类型相关。例如，对于同一动作类型，代偿错误和效率错误对应的目标运动信号可以不同。相应地，目标运动信号对应的评估参数标准也可以不同。由此，在确定目标部位后，对于不同的错误类型，处理设备130可以基于不同的评估标准进行运动评估。关于针对不同错误类型对运动信号进行评估的更多细节可以参照本说明书的其他位置(例如，图5-9及其相关描述)，此处不再赘述。
应当注意的是，上述有关方法400的描述仅仅是为了示例和说明，而不限定本说明书的适用范围。对于本领域技术人员来说，在本说明书的指导下可以对方法400进行各种修正和改变。然而，这些修正和改变仍在本说明书的范围之内。
图5是根据本说明书一些实施例所示的对运动信号进行评估的示例性方法的流程图。在一些实施例中，方法500可以通过处理逻辑来执行，该处理逻辑可以包括硬件(例如，电路、专用逻辑、可编程逻辑、微代码等)、软件(运行在处理设备上以执行硬件模拟的指令)等或其任意组合。在一些实施例中，图5所示的方法500中的一个或多个操作可以通过图1所示的处理设备130和/或终端设备140实现。例如，方法500可以以指令的形式存储在存储设备120中，并由处理设备130和/或终端设备140执行调用和/或执行。在一些实施例中，运动评估方法300中的步骤320和/或步骤330可以通过方法500来实现。在一些实施例中，方法500可以由确定模块220和/或评估模块230执行。在一些实施例中，针对与动作类型相关的第一错误类型(例如，代偿错误、效率错误等)的运动评估可以通过方法500实现。下文以处理设备130为例描述方法500的执行过程。
参照图5，在一些实施例中，方法500可以包括：
步骤510，基于动作类型确定与所述动作类型对应的目标部位。
在一些实施例中，对于不同的动作类型，需要评估的目标部位不同，处理设备130可以基于动作类型确定目标部位，从而对目标部位的运动信号进行评估。仅作为示例，对于类型为坐姿夹胸的动作，目标部位可以包括胸大肌。
步骤520，获取所述目标部位的运动信号。
在一些实施例中，处理设备130可以基于评估标准对目标部位所对应的目标运动信号进行评估。在一些实施例中，针对不同的错误类型，需要评估的目标运动信号不同。例如，对于代偿错误，目标运动信号可以包括目标部位的肌电信号。再例如，对于效率错误，目标运动信号可以包括目标部位的肌电信号和/或姿态信号。
步骤530，基于所述评估标准评估所述目标部位的所述运动信号。
在一些实施例中，评估标准可以包括与目标部位的目标运动信号对应的评估参数标准。所述评估参数标准可以指用于评估目标运动信号的参数及其对应的参数值或参数范围。
在一些实施例中，所述参数可以包括目标部位的运动信号的幅值与参考部位的运动信号的幅值之间的比值，对应的参数值或参数范围可以包括比值阈值。所述参考部位可以指除目标部位的其他部位。处理设备130可以确定目标部位的运动信号的幅值与参考部位的运动信号的幅值之间的比值，并判断该比值是否小于比值阈值。若该比值小于比值阈值，可以表示目标部位没有正确发力，而是使用非目标部位辅助发力。由此，可以将待评估对象当前进行的动作的评估结果确定为代偿错误。在一些实施例中，可以获取一个或多个对象在正确执行当前动作类型的动作时目标部位的运动信号的幅值与参考部位的运动信号的幅值之间的比值，并基于一个或多个比值确定比值阈值。仅作为示例，在与代偿错误对应的评估标准中，需要评估的目标运动信号可以包括目标部位的肌电信号，所述参数可以包括目标部位的肌电信号的幅值与参考部位的肌电信号的幅值之间的比值，处理设备130可以确定目标部位的肌电信号的幅值与参考部位的肌电信号的幅值之间的比值，并判断该比值是否小于比值阈值。若该比值小于比值阈值，可以将待评估对象当前进行的动作的评估结果确定为代偿错误。
在一些实施例中，所述参数可以包括运动信号的幅值，对应的参数值或参数范围可以包括第一运动幅值。处理设备130可以确定运动信号的幅值，并判断该运动信号的幅值是否小于第一运动幅值。若待评估的对象的运动信号的幅值小于第一运动幅值，可以表示目标部位没有正确发力， 而是使用非目标部位辅助发力。由此，可以将待评估对象当前进行的动作的评估结果确定为代偿错误。在一些实施例中，可以获取一个或多个对象在正确执行当前动作类型的动作时目标部位的运动信号，并基于一个或多个对象的运动信号确定预设运动幅值。仅作为示例，在与代偿错误对应的评估标准中，需要评估的目标运动信号可以包括目标部位的肌电信号，所述参数可以包括目标部位的肌电信号的幅值，对应的参数值或参数范围可以包括第一肌电幅值。
在一些实施例中，所述参数可以包括目标部位的运动信号的幅值，对应的参数值或参数范围可以包括第二运动幅值。处理设备130可以确定目标部位的运动的幅值，并判断运动信号的幅值是否小于第二运动幅值。若该幅值小于第二运动幅值，可以表示目标部位没有达到最佳锻炼状态。由此，可以将待评估对象当前进行的动作的评估结果确定为效率错误。在一些实施例中，可以基于一个或多个对象在正确执行当前动作类型的动作时目标部位的运动信号的幅值确定第二运动幅值。仅作为示例，在与效率错误对应的评估标准中，需要评估的目标运动信号可以包括目标部位的肌电信号或姿态信号，所述参数可以包括目标部位的肌电信号或姿态信号的幅值，对应的参数值或参数范围可以包括第二肌电幅值或第二姿态幅值。在一些实施例中，第一运动幅值与第二运动幅值可以是不同的值。例如，在对同一个目标部位的同一种运动信号(例如，肌电信号)进行代偿错误和效率错误的评估时，代偿错误对应的评估标准中的第一运动幅值可以小于效率错误对应的评估标准中的第二运动幅值。可选地或附加地，处理设备130可以先基于第一运动幅值判断目标部位是否存在代偿错误，再基于第二运动幅值判断目标部位是否存在效率错误。
在一些实施例中，需要评估的目标运动信号可以包括第一信号和第二信号，所述参数可以包括第一信号的特征值和第二信号的特征值之间的时间差，对应的参数值或参数范围可以包括时间差阈值。处理设备130可以确定第一信号的第一特征值和第二信号的第二特征值，确定该第一特征值与第二特征值之间所对应的时间差，并判断该时间差是否大于时间差阈值，若该时间差大于时间差阈值，则将待评估对象当前进行的动作的评估结果确定为效率错误。其中，第一特征值和第二特征值可以指第一信号和第二信号中能够体现待评估对象的运动情况的特征值，例如幅值最大值和/或最小值；第一特征值与第二特征值之间所对应的时间差可以理解为第一特征值所对应的信号采集时间与第二特征所对应的信号采集时间之间的差值。仅作为示例，在与效率错误对应的评估标准中，第一信号和第二信号可以分别包括目标部位的肌电信号和姿态信号，所述参数可以包括目标部位的肌电信号的特征值和姿态信号的特征值之间的时间差。
以二头弯举动作为例进行示例性说明，图6是根据本说明书一些实施例所示的二头弯举动作中目标部位的肌电信号和姿态信号的示意图。结合图6所示，目标部位的肌电信号可以指肱二头肌的肌电信号，其可以表现为肌电幅值随时间变化的曲线610。目标部位的姿态信号可以表示为大臂和小臂的夹角随时间变化的曲线620，其中，曲线620对应的幅值可以是基于大臂和小臂的夹角最大值(即180°)对当前夹角进行归一化获得的归一化数值。图6中所示的横坐标区间601、602、603、604、605分别表示第1-5组二头弯举动作从动作开始至动作结束的时间。可选地或附加地，可以基于姿态信号确定动作开始的时间。以区间601中的单次二头弯举动作为例，待评估对象由手臂接近平直状态(即大臂和小臂的夹角接近180°)开始进行二头弯举动作，随着时间的增加，肱二头肌的肌电信号幅值逐渐增大，对应的姿态信号的幅值逐渐减小。当肌电信号的幅值达到最大值A时，表示肱二头肌达到最佳锻炼状态，此时可以结束当前次的二头弯举动作并开始下一次二头弯举动作。相应地，在结束当前次的二头弯举动作的过程中，肌电信号的幅值逐渐减小，手臂由弯曲状态逐渐恢复至接近平直状态，对应的姿态信号的幅值逐渐增大。由此，在肌电信号的幅值达到最大值时结束当前次的二头弯举动作，可以在充分锻炼目标部位的同时，避免在目标部位达到最佳锻炼状态后继续执行当前动作，从而可以保证运动效率。也就是说，如图6所示，当肌电信号的幅值最大值A对应的时间与姿态信号的幅值最小值B对应的时间重合时，二头弯举动作可以达到最佳运动效率。
以坐姿推胸动作为例进行另一示例性说明，图7是根据本说明书一些实施例所示的坐姿推胸动作中目标部位的肌电信号和姿态信号的示意图。结合图7所示，目标部位的肌电信号可以指胸肌的肌电信号，其可以表现为肌电幅值随时间变化的曲线710。目标部位的姿态信号可以表示为大臂与身体正前方的夹角随时间变化的曲线720，其中，曲线720对应的幅值可以是基于大臂与身体正前方的夹角最大值(即180°)对当前夹角进行归一化获得的归一化数值。图7中所示的横坐标区间701、702、703、704分别表示第1-4组坐姿推胸动作从动作开始至动作结束的时间。以区间701中的单次坐姿推胸动作为例，待评估对象由大臂接近平直状态(即大臂和与身体正前方夹角接近90°)开始进行坐姿推胸动作，随着时间的增加，胸肌的肌电信号幅值逐渐增大，对应的姿态信号 的幅值逐渐减小。当肌电信号的幅值达到最大值C时，表示胸肌达到最佳锻炼状态，此时可以结束当前次的坐姿推胸动作并开始下一次坐姿推胸动作。相应地，在结束当前次的坐姿推胸动作的过程中，肌电信号的幅值逐渐减小，大臂由向前状态逐渐恢复至接近平直状态，对应的姿态信号的幅值逐渐增大。由此，在肌电信号的幅值达到最大值时结束当前次的坐姿推胸动作，可以在充分锻炼目标部位的同时，避免在目标部位达到最佳锻炼状态后继续执行当前动作，从而可以保证运动效率。也就是说，当肌电信号的幅值最大值C对应的时间与姿态信号的幅值最小值D对应的时间重合时，坐姿推胸动作可以达到最佳运动效率。而如图7所示，肌电信号的幅值最大值C对应的时间与姿态信号的幅值最小值D对应的时间差较大，相应地，坐姿推胸动作无法达到最佳运动效率。在一些实施例中，处理设备130可以确定肌电信号的幅值最大值与姿态信号的幅值最大值所对应的时间差，并判断该时间差是否大于时间差阈值。若该时间差小于时间差阈值，可以表示肌电信号的幅值最大值对应的时间与姿态信号的幅值最大值对应的时间重合或接近，二头弯举动作可以达到最佳或较佳运动效率。若该时间差大于时间差阈值，可以将待评估对象当前进行的动作的评估结果确定为效率错误。
需要说明的是，以上关于与动作类型相关的第一错误类型的运动评估的方式仅为示例性说明，在一些实施例中，可以采用其他的方式进行第一错误类型的运动评估。在一些实施例中，在对代偿错误的运动评估中，处理设备130可以基于动作类型确定代偿部位。所述代偿部位可以指在该运动类型的运动中可能代偿的部位。例如，在坐姿夹胸运动中，目标部位可以包括胸大肌，但是有可能出现使用中上斜方肌辅助发力的代偿错误。处理设备130可以将中上斜方肌作为代偿部位，并评估所述代偿部位的运动信号。例如，处理设备130可以判断中上斜方肌的肌电信号的幅值是否大于中上斜方肌对应的预设肌电幅值，若是，则可以将待评估对象当前进行的动作的评估结果确定为代偿错误。上述实施例以肌电信号为例进行代偿错误的运动评估，在一些实施例中，处理设备130还可以基于其他运动信号进行代偿错误的运动评估。例如，在坐姿夹胸运动中，当出现中上斜方肌辅助发力的代偿错误时，待评估对象的肩关节也可能会上提。由此，处理设备130还可以基于姿态信号确定待评估对象的肩关节上提角度，并判断该上提角度是否大于角度阈值(例如，15°)。若是，则可以将待评估对象当前进行的动作的评估结果确定为代偿错误。再例如，还可以基于其他力学信号进行代偿错误的运动评估。仅作为示例，当出现翻腕的代偿错误时，待评估对象的下手掌可能承担更多的压力。由此，可以通过压力传感器获取手掌的不同部位的压力信号，并基于压力确定待评估对象是否存在翻腕的代偿错误。
应当注意的是，上述有关方法500的描述仅仅是为了示例和说明，而不限定本说明书的适用范围。对于本领域技术人员来说，在本说明书的指导下可以对方法500进行各种修正和改变。然而，这些修正和改变仍在本说明书的范围之内。例如，方法500还可以包括对损伤错误进行评估的步骤。处理设备130可以判断待评估对象在运动过程中是否存在损伤错误，若否，可以确定动作类型，并判断待评估对象在运动过程中是否存在代偿错误。若否，可以进一步进行效率错误的评估。
图8是根据本说明书一些实施例所示的对运动信号进行评估的另一示例性方法的流程图。在一些实施例中，方法800可以通过处理逻辑来执行，该处理逻辑可以包括硬件(例如，电路、专用逻辑、可编程逻辑、微代码等)、软件(运行在处理设备上以执行硬件模拟的指令)等或其任意组合。在一些实施例中，图8所示的方法800中的一个或多个操作可以通过图1所示的处理设备130和/或终端设备140实现。例如，方法800可以以指令的形式存储在存储设备120中，并由处理设备130和/或终端设备140执行调用和/或执行。在一些实施例中，运动评估方法300中的步骤330可以通过方法800来实现。在一些实施例中，方法800可以由评估模块230执行。在一些实施例中，针对对称性错误的运动评估可以通过方法800实现。下文以处理设备130为例描述方法800的执行过程。
参照图8，在一些实施例中，方法800可以包括：
步骤810，基于所述评估标准确定所述运动信号对应的目标部位。
在一些实施例中，在针对对称性错误的运动评估中，可以基于评估标准确定运动信号对应的目标部位。例如，可以将易出现对称性错误的部位设置为评估标准中的目标部位。再例如，可以将产生运动信号的任意部位设置为评估标准中的目标部位。处理设备130可以基于评估标准确定运动信号对应的目标部位，从而对目标部位的运动信号进行评估。在一些实施例中，目标部位可以包括待评估对象的至少两个对称部位，例如左右对称或前后对称的两个部位等。
步骤820，获取所述至少两个对称部位的运动信号。
在一些实施例中，处理设备130可以基于评估标准对目标部位所对应的目标运动信号进行 评估。在一些实施例中，针对不同的错误类型，需要评估的目标运动信号不同。例如，对于对称性错误，需评估的目标运动信号可以包括对称部位的肌电信号或姿态信号。
步骤830，基于所述评估标准评估所述至少两个对称部位的运动信号。
在一些实施例中，评估标准可以包括与目标部位的目标运动信号对应的评估参数标准。所述评估参数标准可以指用于评估目标运动信号的参数及其对应的参数值或参数范围。
在一些实施例中，所述参数可以包括对称部位的运动信号之间的信号差，对应的参数值或参数范围可以包括信号差阈值。处理设备130可以确定对称部位的运动信号的信号差，并判断该幅值差是否大于信号差阈值，若该幅值差大于信号差阈值，可以表示对称部位的锻炼状态不同，因此将待评估对象当前进行的动作的评估结果确定为对称性错误。例如，在与对称性错误对应的评估标准中，需要评估的目标运动信号可以包括对称部位的肌电信号，所述参数可以包括对称部位的肌电信号之间的幅值差，对应的参数值或参数范围可以包括幅值差阈值。再例如，在与对称性错误对应的评估标准中，需要评估的目标运动信号可以包括对称部位的姿态信号，所述参数可以包括对称部位的姿态信号之间的信号差，对应的参数值或参数范围可以包括信号差阈值。仅作为示例，处理设备130可以确定对称部位在同一时间的姿态信号(例如，关节角度等)之间的差值，并将一个时间的差值或多个时间的差值平均值作为对称部位的姿态信号之间的信号差。若该信号差大于信号差阈值，可以表示对称部位的锻炼状态不同，因此将待评估对象当前进行的动作的评估结果确定为对称性错误。
在一些实施例中，上述阈值(例如，时间差阈值、幅值差阈值、信号差阈值等)可以通过历史经验、数据统计以及模型预测中的任意一种或多种方式确定。
需要说明的是，以上关于针对对称性错误的运动评估的方式仅为示例性说明，在一些实施例中，可以采用其他的方式进行对称性错误的运动评估，本说明书对此不做限制。例如，还可以基于力学信号进行对称性错误的运动评估。仅作为示例，可以使用压力传感器获取待评估对象的对称部位(例如，臀部、双手手掌)对应的压力信号，并根据压力信号确定待评估对象是否存在对称性错误(例如，坐姿不对称、双手用力不对称等)。
应当注意的是，上述有关方法800的描述仅仅是为了示例和说明，而不限定本说明书的适用范围。对于本领域技术人员来说，在本说明书的指导下可以对方法800进行各种修正和改变。然而，这些修正和改变仍在本说明书的范围之内。例如，方法800还可以包括基于运动信号判断待评估对象是否进行对称性动作的步骤。响应于待评估对象进行对称性动作，处理设备130可以进一步进行对称性错误的评估。
图9是根据本说明书一些实施例所示的对运动信号进行评估的又一示例性方法的流程图。在一些实施例中，方法900可以通过处理逻辑来执行，该处理逻辑可以包括硬件(例如，电路、专用逻辑、可编程逻辑、微代码等)、软件(运行在处理设备上以执行硬件模拟的指令)等或其任意组合。在一些实施例中，图9所示的方法900中的一个或多个操作可以通过图1所示的处理设备130和/或终端设备140实现。例如，方法900可以以指令的形式存储在存储设备120中，并由处理设备130和/或终端设备140执行调用和/或执行。在一些实施例中，运动评估方法300中的步骤330可以通过方法900来实现。在一些实施例中，方法900可以由评估模块230执行。在一些实施例中，针对损伤错误的运动评估可以通过方法900实现。下文以处理设备130为例描述方法900的执行过程。
参照图9，在一些实施例中，方法900可以包括：
步骤910，基于所述评估标准确定所述运动信号对应的目标部位。
在一些实施例中，在针对损伤错误的运动评估中，可以基于评估标准确定运动信号对应的目标部位。例如，可以将易出现损伤错误的部位设置为评估标准中的目标部位。再例如，可以将产生运动信号的任意部位设置为评估标准中的目标部位。处理设备130可以基于评估标准确定运动信号对应的目标部位，从而对目标部位的运动信号进行评估。
步骤920，获取所述目标部位的运动信号。
在一些实施例中，处理设备130可以基于评估标准对目标部位所对应的目标运动信号进行评估。在一些实施例中，针对不同的错误类型，需要评估的目标运动信号不同。例如，对于损伤错误，需评估的目标运动信号可以包括目标部位的肌电信号或姿态信号。
步骤930，基于所述评估标准评估所述目标部位的运动信号。
在一些实施例中，评估标准可以包括与目标部位的目标运动信号对应的评估参数标准。所述评估参数标准可以指用于评估目标运动信号的参数及其对应的参数值或参数范围。
在一些实施例中，损伤错误与待评估对象的动作类型无关，而是与待评估对象的身体结构 和/或运动方式相关。示例性的损伤错误可以包括肌肉过度疲劳、关节运动速度过快、肘部过度超伸、肩部尖峰撞击、核心不稳定等。例如，当目标部位的肌肉过度疲劳时，将不能为关节提供足够的链接力，容易造成损伤。由此，损伤错误可以包括疲劳状态。在一些实施例中，疲劳状态对应的评估标准中的参数可以包括目标部位的运动信号的频率和/或幅值，对应的参数值或参数范围可以包括频率相关阈值等。处理设备130可以基于运动信号的频率以及评估标准，确定目标部位的疲劳状态。例如，疲劳状态对应的评估标准中的参数可以包括目标部位的肌电信号的频率和/或幅值，对应的参数值或参数范围可以包括肌电频率相关阈值，例如，肌电频率幅值、肌电频率幅值斜率等。在一些实施例中，不同的疲劳程度可以对应不同的损伤等级。所述损伤等级可以表示造成损伤的风险或概率的大小。由此，处理设备130可以根据目标部位的疲劳程度确定损伤等级。
仅作为示例，图10A是根据本说明书一些实施例所示的哑铃侧平举动作中目标部位的肌电信号的示意图；图10B是根据本说明书一些实施例所示的杠铃二头弯举动作中目标部位的肌电信号的示意图。在哑铃侧平举动作中，目标部位可以包括人体左侧和/或右侧的三角肌，本说明书以右侧三角肌为例进行说明。在图10A中，(a)示出了右侧三角肌的肌电信号的幅值随动作的组数变化的曲线，(b)示出了右侧三角肌的肌电信号的频率随动作的组数变化的曲线，其中，L 1和L′ 1分别表示第一组动作对应的肌电信号的幅值曲线和频率曲线；L 2和L′ 2分别表示第二组动作对应的肌电信号的幅值曲线和频率曲线；L 3和L′ 3分别表示第三组动作对应的肌电信号的幅值曲线和频率曲线；L 4和L′ 4分别表示第四组动作对应的肌电信号的幅值曲线和频率曲线；L 5和L′ 5分别表示第五组动作对应的肌电信号的幅值曲线和频率曲线；L 6和L′ 6分别表示第六组动作对应的肌电信号的幅值曲线和频率曲线。在图10A所示的每一组动作中，用户可以持续进行多次哑铃侧平举作直至疲劳力竭。在杠铃二头弯举动作中，目标部位可以包括人体左侧和/或右侧的肱二头肌，本说明书以右侧肱二头肌为例进行说明。在图10B中，(a)示出了右侧肱二头肌的肌电信号的幅值随动作的组数变化的曲线，(b)示出了右侧肱二头肌的肌电信号的频率随动作的组数变化的曲线。结合图10A或图10B中的曲线(例如，曲线L 2和L′ 2)可知，在同一组动作中，随着动作次数的增加直至疲劳，肌电信号的幅值在上升到最大值H后开始下降，肌电信号的频率也将显著减小。因此，可以根据肌电频率与幅值对损伤风险等级进行划分。例如，当肌电幅值在达到最大值后开始下降，且肌电频率值低于肌电频率阈值的80％，可以确定当前运动存在初级损伤的风险；若肌电频率值低于该肌电频率阈值的70％，可以确定当前运动存在中级损伤的风险；若肌电频率低于该肌电频率阈值的50％，则可以确定当前运动存在重级损伤的风险。在一些实施例中，所述肌电频率阈值可以包括目标部位在正常状态时肌电信号的中心频率值。在一些实施例中，针对不同等级的损伤风险，可以给用户提供不同的提示或建议，例如，建议用户降低运动速度或者停止锻炼等。
在一些实施例中，损伤错误对应的评估标准中的参数可以包括与目标部位的运动信号相关的评估参数。例如，损伤错误对应的评估标准中的参数可以包括与目标部位的姿态信号相关的评估参数。示例性的评估参数可以包括目标部位的内旋角度、外展角度、运动速度、运动加速度等或其任意组合。例如，在高位下拉动作中，反复的大臂内旋和上抬的模式将导致肱骨肌腱、韧带等与上部肩峰(锁骨最外侧和肩胛骨最外侧)反复撞击，形成肩峰撞击损伤。在一些实施例中，肩峰撞击损伤的程度与目标部位的内旋角度、外展角度、上抬角度、运动速度、运动加速度等相关。由此，可以根据目标部位的内旋角度、外展角度、上抬角度、运动速度、运动加速度的不同区间，将肩峰撞击损伤分为不同的损伤等级。例如，在高位下拉动作中，以双手前平举上抬为120°且手心朝下时为初始位置，当大臂内旋角度为0～15°且持续时间大于预设时长(例如，15秒、30秒等)时，可以确定当前运动存在初级损伤的风险；当大臂内旋角度为15°～30°且持续时间大于预设时长(例如，15秒、30秒等)时，可以确定当前运动存在中级损伤的风险，当大臂内旋角度大于30°且持续时间大于预设时长(例如，15秒、30秒等)时，可以确定当前运动存在重级损伤的风险。再例如，在疲劳状态时，人体的核心稳定性、动作连贯性或动作稳定性等将急剧下降。其中，人体的核心稳定性的下降在姿态信号上可以表现为核心部位(例如，腰部)姿态信号中的角速度过零率增加；动作连贯性的下降在姿态信号上可以表现为目标部位姿态信号中的动作幅度下降、动作周期时间增加等；动作稳定性的下降在姿态信号上可以表现为目标部位姿态信号中的角速度过零率增加等。由此，处理设备130可以基于姿态信号确定目标部位的疲劳状态或损伤等级。
应当注意的是，上述有关方法900的描述仅仅是为了示例和说明，而不限定本说明书的适用范围。对于本领域技术人员来说，在本说明书的指导下可以对方法900进行各种修正和改变。然而，这些修正和改变仍在本说明书的范围之内。在一些实施例中，还可以基于其他运动信号进行损伤错误的评估。仅作为示例，损伤错误(例如，疲劳状态)对应的评估标准中的参数可以包括与目 标部位的心电信号、呼吸信号、汗液信号等或其任意组合相关的评估参数。例如，当待评估对象的心电信号的频率大于心电信号频率阈值时，可以确定待评估对象处于疲劳状态。再例如，当待评估对象的呼吸信号的频率大于呼吸信号频率阈值时，可以确定待评估对象处于疲劳状态。再例如，当基于汗液信号确定待评估对象的出汗量(例如，单位时间的出汗量)大于出汗量阈值时，可以确定待评估对象处于疲劳状态。
图11是根据本说明书一些实施例所示的运动评估反馈方法的流程图。在一些实施例中，流程1100可以通过处理逻辑来执行，该处理逻辑可以包括硬件(例如，电路、专用逻辑、可编程逻辑、微代码等)、软件(运行在处理设备上以执行硬件模拟的指令)等或其任意组合。在一些实施例中，图11所示的运动评估方法的流程1100中的一个或多个操作可以通过图1所示的处理设备130和/或终端设备140实现。
参照图11，在一些实施例中，流程1100可以包括：
步骤1110，获取对象的运动信号。在一些实施例中，步骤1110可以由获取模块210执行。
参照步骤310，在一些实施例中，步骤1110中的运动信号可以指待评估对象在运动过程中所产生的信号。在一些实施例中，所述运动信号可以用于表征待评估对象的运动状态，其可以包括肌电信号、姿态信号、力学信号、心电信号、呼吸信号、汗液信号等或其任意组合。关于获取运动信号的更多细节可以参考步骤310中的相关描述，此处不再赘述。
步骤1120，基于与所述运动信号相关的评估标准对所述运动信号进行评估。在一些实施例中，步骤1120可以由评估模块230执行。
在一些实施例中，处理设备130可以在不识别待评估对象的动作类型的情况下，直接基于运动信号相关的评估标准对运动信号进行评估。例如，可以设置与运动信号相关的评估标准。处理设备130可以获取所述评估标准，并对运动信号进行评估，确定评估结果。所述评估结果可以包括所述运动信号对应的运动是否存在错误以及错误类型。关于对运动信号进行评估的更多细节可以参考步骤320-330中的相关描述，此处不再赘述。
需要说明的是，以上关于运动信号的评估方式仅为示例性说明，在一些实施例中，可以采用其他的评估方式对待评估对象的运动信号进行评估。例如，还可以利用运动评估模型对待评估对象的运动信号进行评估。可以理解，该运动评估模型可以通过大量训练样本训练得到。其中，训练样本可以包括多组运动数据以及与每一组运动数据对应的标签，该标签可以包括运动数据所对应的错误类型。
步骤1130，基于所述评估的结果确定多种反馈方式中的目标反馈方式。
步骤1140，根据所述目标反馈方式进行评估反馈。
在一些实施例中，步骤1130和步骤1140可以由反馈模块240执行。在一些实施例中，处理设备可以基于评估结果从多种反馈方式中确定用于展示评估结果的目标反馈方式，其中，该多种反馈方式可以通过不同的反馈时间和/或反馈类型通知用户。关于评估反馈更多细节可以参步骤330中的相关描述，此处不再赘述。
本说明书实施例可能带来的有益效果包括但不限于：(1)通过对待评估对象的运动信号进行评估，可以识别出待评估对象在运动过程中存在的运动错误，并帮助其纠正错误，从而帮助用户科学运动；(2)通过运动信号对待评估对象的动作类型进行识别，并确定与该运动类型相关的评估标准，然后基于该评估标准对待评估对象的运动信号进行评估，可以在一定程度确保评估结果的准确性；(3)通过对运动的错误类型的精细划分，并通过多种运动信号的多个维度对运动信号进行组合判断，可以更准确的识别待评估对象在运动中存在的错误，从而更有利于用户的损伤预防和能力提升；(4)通过基于评估结果、待评估对象的动作类型以及用户类型来确定用于向用户展示评估结果的目标反馈方式，可以确定出更加符合用户需求的反馈时间和反馈类型。
需要说明的是，不同实施例可能产生的有益效果不同，在不同的实施例里，可能产生的有益效果可以是以上任意一种或几种的组合，也可以是其他任何可能获得的有益效果。
上文已对基本概念做了描述，显然，对于本领域技术人员来说，上述详细披露仅仅作为示例，而并不构成对本说明书的限定。虽然此处并没有明确说明，本领域技术人员可能会对本说明书进行各种修改、改进和修正。该类修改、改进和修正在本说明书中被建议，所以该类修改、改进、修正仍属于本说明书示范实施例的精神和范围。
同时，本说明书使用了特定词语来描述本说明书的实施例。如“一个实施例”、“一实施例”“一实施例”、和/或“一些实施例”意指与本说明书至少一个实施例相关的某一特征、结构或特点。因此，应强调并注意的是，本说明书中在不同位置两次或多次提及的“一实施例”或“一个 实施例”或“一个替代性实施例”并不一定是指同一实施例。此外，本说明书的一个或多个实施例中的某些特征、结构或特点可以进行适当的组合。
此外，除非权利要求中明确说明，本说明书所述处理元素和序列的顺序、数字字母的使用、或其他名称的使用，并非用于限定本说明书流程和方法的顺序。尽管上述披露中通过各种示例讨论了一些目前认为有用的发明实施例，但应当理解的是，该类细节仅起到说明的目的，附加的权利要求并不仅限于披露的实施例，相反，权利要求旨在覆盖所有符合本说明书实施例实质和范围的修正和等价组合。例如，虽然以上所描述的系统组件可以通过硬件设备实现，但是也可以只通过软件的解决方案得以实现，如在现有的服务器或移动设备上安装所描述的系统。
同理，应当注意的是，为了简化本说明书披露的表述，从而帮助对一个或多个发明实施例的理解，前文对本说明书实施例的描述中，有时会将多种特征归并至一个实施例、附图或对其的描述中。但是，这种披露方法并不意味着本说明书对象所需要的特征比权利要求中提及的特征多。实际上，实施例的特征要少于上述披露的单个实施例的全部特征。
一些实施例中使用了描述成分、属性数量的数字，应当理解的是，此类用于实施例描述的数字，在一些示例中使用了修饰词“大约”、“近似”或“大体上”来修饰。除非另外说明，“大约”、“近似”或“大体上”表明所述数字允许有±20％的变化。相应地，在一些实施例中，说明书和权利要求中使用的数值参数均为近似值，该近似值根据个别实施例所需特点可以发生改变。在一些实施例中，数值参数应考虑规定的有效数位并采用一般位数保留的方法。尽管本说明书一些实施例中用于确认其范围广度的数值域和参数为近似值，在具体实施例中，此类数值的设定在可行范围内尽可能精确。
针对本说明书引用的每个专利、专利申请、专利申请公开物和其他材料，如文章、书籍、说明书、出版物、文档等，特此将其全部内容并入本说明书作为参考。与本说明书内容不一致或产生冲突的申请历史文件除外，对本说明书权利要求最广范围有限制的文件(当前或之后附加于本说明书中的)也除外。需要说明的是，如果本说明书附属材料中的描述、定义、和/或术语的使用与本说明书所述内容有不一致或冲突的地方，以本说明书的描述、定义和/或术语的使用为准。
最后，应当理解的是，本说明书中所述实施例仅用以说明本说明书实施例的原则。其他的变形也可能属于本说明书的范围。因此，作为示例而非限制，本说明书实施例的替代配置可视为与本说明书的教导一致。相应地，本说明书的实施例不仅限于本说明书明确介绍和描述的实施例。

Claims (26)

  1. 一种运动评估方法，其特征在于，所述方法包括：
    获取对象的运动信号，所述运动信号包括表征所述对象运动状态的信号；
    基于所述运动信号确定与所述运动信号相关的评估标准；
    基于所述评估标准对所述运动信号进行评估。
  2. 根据权利要求1所述的运动评估方法，其特征在于，所述基于所述评估标准对所述运动信号进行评估，包括：
    基于所述评估标准评估所述运动信号，所述评估的结果包括错误类型；以及
    基于所述评估的结果进行评估反馈。
  3. 根据权利要求2所述的运动评估方法，其特征在于，所述基于所述评估的结果进行评估反馈，包括：
    基于所述评估的结果或所述对象的用户类型确定多种反馈方式中的目标反馈方式，所述多种反馈方式通过不同的反馈时间或反馈类型通知所述对象；以及
    根据所述目标反馈方式进行反馈。
  4. 根据权利要求1所述的运动评估方法，其特征在于，所述运动信号包括姿态信号、肌电信号、力学信号、心电信号、呼吸信号、汗液信号中的至少一个。
  5. 根据权利要求1所述的运动评估方法，其特征在于，所述基于所述运动信号确定与所述运动信号相关的评估标准，包括：
    基于所述运动信号对所述对象进行动作识别，确定所述对象的动作类型；以及
    基于所述运动类型确定与所述运动信号相关的评估标准。
  6. 根据权利要求5所述的运动评估方法，其特征在于，所述基于所述运动信号对所述对象进行动作识别，确定所述对象的动作类型，包括：
    对于每一帧运动信号，判断是否进行动作识别；以及
    响应于进行动作识别的判断结果，基于一帧或多帧运动信号进行动作识别，确定所述对象的动作类型。
  7. 根据权利要求5所述的运动评估方法，其特征在于，
    所述基于所述动作类型确定与所述运动信号相关的评估标准，包括：
    基于所述动作类型确定与所述动作类型对应的目标部位；以及
    所述基于所述评估标准对所述运动信号进行评估，包括：
    获取所述目标部位的运动信号；以及
    基于所述评估标准评估所述目标部位的所述运动信号。
  8. 根据权利要求7所述的运动评估方法，其特征在于，所述基于所述评估标准评估所述目标部位的运动信号，包括：
    基于所述目标部位确定参考部位；
    确定所述目标部位的所述运动信号的幅值与所述参考部位的运动信号的幅值之间的比值；
    判断所述比值是否小于比值阈值；以及
    响应于所述比值小于所述比值阈值，确定所述评估的结果为代偿错误。
  9. 根据权利要求7所述的运动评估方法，其特征在于，所述基于所述评估标准评估所述目标部位的运动信号，包括：
    确定所述运动信号的幅值；
    判断所述运动信号的幅值是否小于第一运动幅值；以及
    响应于所述运动信号的幅值小于第一运动幅值，确定所述评估的结果为代偿错误。
  10. 根据权利要求9所述的运动评估方法，其特征在于，所述基于所述评估标准评估所述目标部位的运动信号，包括：
    确定所述运动信号的幅值；
    判断所述运动信号的幅值是否小于第二运动幅值；以及
    响应于所述运动信号的幅值小于所述第二运动幅值，确定所述评估的结果为效率错误。
  11. 根据权利要求7所述的运动评估方法，其特征在于，所述运动信号包括第一信号和第二信号，所述基于所述评估标准评估所述目标部位的运动信号，包括：
    识别所述第一信号的第一特征值以及所述第二信号的第二特征值；
    确定所述第一信号的第一特征值与所述第二信号的第二特征值之间的时间差；
    判断所述时间差是否大于时间差阈值；以及
    响应于所述时间差大于所述时间差阈值，确定所述评估的结果为效率错误。
  12. 根据权利要求1所述的运动评估方法，其特征在于，所述基于所述评估标准对所述运动信号进行评估，包括：
    基于所述评估标准确定所述运动信号对应的目标部位，所述目标部位包括所述对象的至少两个对称部位；
    获取所述至少两个对称部位的所述运动信号；以及
    基于所述评估标准评估所述至少两个对称部位的所述运动信号。
  13. 根据权利要求12所述的运动评估方法，其特征在于，所述基于所述评估标准评估所述至少两个对称部位的所述运动信号，包括：
    确定所述至少两个对称部位的运动信号的信号差；
    判断所述信号差是否大于信号差阈值；以及
    响应于所述信号差大于所述信号差阈值，确定所述评估的结果为对称性错误。
  14. 根据权利要求1所述的运动评估方法，其特征在于，所述基于所述评估标准对所述运动信号进行评估，包括：
    基于所述评估标准确定所述运动信号对应的目标部位；
    确定所述目标部位的运动信号的频率；以及
    基于所述频率以及所述评估标准，确定所述目标部位的疲劳状态。
  15. 根据权利要求1所述的运动评估方法，其特征在于，所述基于所述评估标准对所述运动信号进行评估，包括：
    基于所述评估标准确定所述运动信号对应的目标部位；
    获取所述目标部位的运动信号；
    基于所述运动信号确定所述目标部位的评估参数；以及
    基于所述评估参数以及所述评估标准，确定所述目标部位的损伤类型或损伤等级。
  16. 根据权利要求15所述的运动评估方法，其特征在于，所述评估参数包括所述目标部位的内旋角度、外展角度、或运动加速度中的至少一种。
  17. 根据权利要求1所述的运动评估方法，其特征在于，还包括：
    基于运动评估模型对所述运动信号进行评估。
  18. 一种运动评估反馈方法，其特征在于，所述方法包括：
    获取对象的运动信号，所述运动信号包括表征所述对象运动状态的信号；
    基于与所述运动信号相关的评估标准对所述运动信号进行评估；
    基于所述评估的结果确定多种反馈方式中的目标反馈方式，所述多种反馈方式通过不同的反馈时间或反馈类型通知所述对象；
    根据所述目标反馈方式进行评估反馈。
  19. 根据权利要求18所述的运动评估反馈方法，其特征在于，所述反馈时间包括及时反馈或运动结束反馈。
  20. 根据权利要求18所述的运动评估反馈方法，其特征在于，所述反馈类型包括：语音反馈、生物反馈、文字反馈中的至少一种。
  21. 根据权利要求18所述的运动评估反馈方法，其特征在于，还包括：
    基于所述运动信号对所述对象进行动作识别，确定所述对象的动作类型。
  22. 根据权利要求21所述的运动评估反馈方法，其特征在于，所述基于所述评估的结果确定多种反馈方式中的目标反馈方式，包括：
    基于所述动作类型、所述对象的用户类型或所述评估的结果中的至少一个确定所述多种反馈方式中的目标反馈方式。
  23. 根据权利要求18所述的运动评估反馈方法，其特征在于，所述运动信号包括姿态信号、肌电信号、力学信号、心电信号、呼吸信号、汗液信号中的至少一个。
  24. 一种运动评估系统，其特征在于，所述系统包括：
    获取模块，用于获取对象的运动信号，所述运动信号包括表征所述对象运动状态的信号；
    确定模块，用于基于所述运动信号确定与所述运动信号相关的评估标准；
    评估模块，用于基于所述评估标准对所述运动信号进行评估。
  25. 一种运动评估反馈系统，其特征在于，所述系统包括：
    获取模块，用于获取对象的运动信号，所述运动信号包括表征所述对象运动状态的信号；
    评估模块，用于基于与所述运动信号相关的评估标准对所述运动信号进行评估；
    反馈模块，用于基于所述评估的结果确定多种反馈方式中的目标反馈方式，所述多种反馈方式通过不同的反馈时间或反馈类型通知所述对象；以及
    根据所述目标反馈方式进行评估反馈。
  26. 一种计算机可读存储介质，其特征在于，包括可执行指令，当由至少一个处理器执行时，所述可执行指令使所述至少一个处理器执行如权利要求1～23中任一项所述的方法。
PCT/CN2022/118674 2022-09-14 2022-09-14 一种运动评估方法及系统 WO2024055186A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/118674 WO2024055186A1 (zh) 2022-09-14 2022-09-14 一种运动评估方法及系统

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/118674 WO2024055186A1 (zh) 2022-09-14 2022-09-14 一种运动评估方法及系统

Publications (1)

Publication Number Publication Date
WO2024055186A1 true WO2024055186A1 (zh) 2024-03-21

Family

ID=90274106

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/118674 WO2024055186A1 (zh) 2022-09-14 2022-09-14 一种运动评估方法及系统

Country Status (1)

Country Link
WO (1) WO2024055186A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2014145711A1 (en) * 2013-03-15 2014-09-18 Movement Training Systems Llc Systems and methods for evaluating physical performance
CN109864741A (zh) * 2019-01-30 2019-06-11 北京津发科技股份有限公司 基于肌电信号的周期性动作评估方法和装置、终端设备
CN110471529A (zh) * 2019-08-07 2019-11-19 北京卡路里信息技术有限公司 动作评分方法及装置
CN110502395A (zh) * 2019-08-09 2019-11-26 国网山西省电力公司 基于聚类的设备运行状态评估方法、终端设备及存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2014145711A1 (en) * 2013-03-15 2014-09-18 Movement Training Systems Llc Systems and methods for evaluating physical performance
CN109864741A (zh) * 2019-01-30 2019-06-11 北京津发科技股份有限公司 基于肌电信号的周期性动作评估方法和装置、终端设备
CN110471529A (zh) * 2019-08-07 2019-11-19 北京卡路里信息技术有限公司 动作评分方法及装置
CN110502395A (zh) * 2019-08-09 2019-11-26 国网山西省电力公司 基于聚类的设备运行状态评估方法、终端设备及存储介质

Similar Documents

Publication Publication Date Title
Novatchkov et al. Artificial intelligence in sports on the example of weight training
Fleisig et al. Kinetic comparison among the fastball, curveball, change-up, and slider in collegiate baseball pitchers
Spina et al. COPDTrainer: a smartphone-based motion rehabilitation training system with real-time acoustic feedback
CN109637625B (zh) 自学习式健身计划生成系统
US20160249832A1 (en) Activity Classification Based on Classification of Repetition Regions
KR101738678B1 (ko) 운동성 평가 시스템
US20070219059A1 (en) Method and system for continuous monitoring and training of exercise
US20190344121A1 (en) Exercise training adaptation using physiological data
De Pessemier et al. Heart rate monitoring, activity recognition, and recommendation for e-coaching
EP3042360A1 (en) System and method for identifying and interpreting repetitive motions
US9826923B2 (en) Motion analysis method
US20220019284A1 (en) Feedback from neuromuscular activation within various types of virtual and/or augmented reality environments
Maura et al. Literature review of stroke assessment for upper-extremity physical function via EEG, EMG, kinematic, and kinetic measurements and their reliability
US20200015712A1 (en) Gathering and Analyzing Posture and Movement Data
Malik et al. An intelligent recovery progress evaluation system for ACL reconstructed subjects using integrated 3-D kinematics and EMG features
US20200163615A1 (en) System and method for functional state and / or performance assessment and training program adjustment
Sun et al. IoT motion tracking system for workout performance evaluation: a case study on dumbbell
WO2024055186A1 (zh) 一种运动评估方法及系统
WO2022194281A1 (zh) 一种运动监控方法和设备
US20220047920A1 (en) Systems and methods for personalized fitness assessments and workout routines
Stuart et al. Sports medicine: bespoke player management
CN114376543A (zh) 一种基于心率和运动反馈调整运动组合方案的方法及系统
CN117732019A (zh) 一种运动评估方法及系统
Farrokhi et al. A decision tree-based smart fitness framework in IoT
TW202004773A (zh) 診斷認知功能以提供體適能矯正方案之系統及方法

Legal Events

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

Ref document number: 22958380

Country of ref document: EP

Kind code of ref document: A1