WO2016091130A1 - 一种培训辅助设备和培训辅助方法 - Google Patents

一种培训辅助设备和培训辅助方法 Download PDF

Info

Publication number
WO2016091130A1
WO2016091130A1 PCT/CN2015/096532 CN2015096532W WO2016091130A1 WO 2016091130 A1 WO2016091130 A1 WO 2016091130A1 CN 2015096532 W CN2015096532 W CN 2015096532W WO 2016091130 A1 WO2016091130 A1 WO 2016091130A1
Authority
WO
WIPO (PCT)
Prior art keywords
signal
stimulation
optimal
myoelectric
training
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/CN2015/096532
Other languages
English (en)
French (fr)
Inventor
唐宇欣
闫文闻
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Galaxy Raintai Technology Co Ltd
Original Assignee
Beijing Galaxy Raintai Technology Co Ltd
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 Beijing Galaxy Raintai Technology Co Ltd filed Critical Beijing Galaxy Raintai Technology Co Ltd
Priority to JP2016559257A priority Critical patent/JP6507419B2/ja
Priority to KR1020167026312A priority patent/KR20160124890A/ko
Priority to EP15868270.8A priority patent/EP3235540A4/en
Priority to US15/314,918 priority patent/US20170095200A1/en
Publication of WO2016091130A1 publication Critical patent/WO2016091130A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
    • A61N1/00—Electrotherapy; Circuits therefor
    • A61N1/18—Applying electric currents by contact electrodes
    • A61N1/32—Applying electric currents by contact electrodes alternating or intermittent currents
    • A61N1/36—Applying electric currents by contact electrodes alternating or intermittent currents for stimulation
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/48—Other medical applications
    • A61B5/4836—Diagnosis combined with treatment in closed-loop systems or methods
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Measuring devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor or mobility of a limb
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/25—Bioelectric electrodes therefor
    • A61B5/279—Bioelectric electrodes therefor specially adapted for particular uses
    • A61B5/296—Bioelectric electrodes therefor specially adapted for particular uses for electromyography [EMG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/389—Electromyography [EMG]
    • A61B5/395—Details of stimulation, e.g. nerve stimulation to elicit EMG response
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/389—Electromyography [EMG]
    • A61B5/397—Analysis of electromyograms
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7225—Details of analogue processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
    • A61N1/00—Electrotherapy; Circuits therefor
    • A61N1/02—Details
    • A61N1/025—Digital circuitry features of electrotherapy devices, e.g. memory, clocks, processors
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
    • A61N1/00—Electrotherapy; Circuits therefor
    • A61N1/18—Applying electric currents by contact electrodes
    • A61N1/20—Applying electric currents by contact electrodes continuous direct currents
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
    • A61N1/00—Electrotherapy; Circuits therefor
    • A61N1/18—Applying electric currents by contact electrodes
    • A61N1/32—Applying electric currents by contact electrodes alternating or intermittent currents
    • A61N1/36—Applying electric currents by contact electrodes alternating or intermittent currents for stimulation
    • A61N1/36003—Applying electric currents by contact electrodes alternating or intermittent currents for stimulation of motor muscles, e.g. for walking assistance
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
    • A61N1/00—Electrotherapy; Circuits therefor
    • A61N1/18—Applying electric currents by contact electrodes
    • A61N1/32—Applying electric currents by contact electrodes alternating or intermittent currents
    • A61N1/36—Applying electric currents by contact electrodes alternating or intermittent currents for stimulation
    • A61N1/36014—External stimulators, e.g. with patch electrodes
    • A61N1/3603—Control systems
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
    • A61N1/00—Electrotherapy; Circuits therefor
    • A61N1/18—Applying electric currents by contact electrodes
    • A61N1/32—Applying electric currents by contact electrodes alternating or intermittent currents
    • A61N1/36—Applying electric currents by contact electrodes alternating or intermittent currents for stimulation
    • A61N1/36014—External stimulators, e.g. with patch electrodes
    • A61N1/3603—Control systems
    • A61N1/36031—Control systems using physiological parameters for adjustment
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
    • A61N1/00—Electrotherapy; Circuits therefor
    • A61N1/18—Applying electric currents by contact electrodes
    • A61N1/32—Applying electric currents by contact electrodes alternating or intermittent currents
    • A61N1/36—Applying electric currents by contact electrodes alternating or intermittent currents for stimulation
    • A61N1/36042—Applying electric currents by contact electrodes alternating or intermittent currents for stimulation of grafted tissue, e.g. skeletal muscle
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2503/00—Evaluating a particular growth phase or type of persons or animals
    • A61B2503/12—Healthy persons not otherwise provided for, e.g. subjects of a marketing survey
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2505/00—Evaluating, monitoring or diagnosing in the context of a particular type of medical care
    • A61B2505/09—Rehabilitation or training
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
    • A61B2562/02—Details of sensors specially adapted for in-vivo measurements
    • A61B2562/0219—Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
    • A61B2562/02—Details of sensors specially adapted for in-vivo measurements
    • A61B2562/0223—Magnetic field sensors
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Measuring devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor or mobility of a limb
    • A61B5/1116—Determining posture transitions

Definitions

  • the invention relates to the technical field of computer applications, in particular to a training auxiliary device and a training assistant method.
  • an electro-stimulation training device has been proposed in the prior art, that is, a computer-programmed manner is pre-set in the processing module to preset an electrical stimulation training program, and the processing module directly controls the digital model according to the program.
  • the converter DAC
  • the converter emits an analog signal to a constant current source, which in turn generates a constant current from a constant current source, and a plurality of constant current sources are connected to a plurality of electrodes that electrically stimulate the fingers or arms, respectively. Users wearing such devices will be able to After the electric stimulation on the instrument, the passive action is passively performed, so as to achieve the purpose of automatically pulling the user to play.
  • this approach has the following drawbacks:
  • the electrical stimulation used is at least tens of mA.
  • the long-term high current stimulation may cause potential damage to the skin tissue and is not suitable for users such as children.
  • the present invention provides a training aid and a training aid method, so as to get rid of the location and time constraints and improve the training effect.
  • the invention provides a training auxiliary device, which comprises: an acquisition unit, a main control unit and a discharge unit;
  • the collecting unit is configured to collect an electromyogram signal of a specific part of the user during the action implementation, and perform amplification filtering to output to the main control unit;
  • the main control unit is configured to determine an optimal myoelectric signal according to the received myoelectric signal, form an stimulation signal by using an optimal electromyogram signal, and output the stimulation signal to the discharge unit;
  • the discharge unit is configured to form a stimulation current according to the stimulation signal, and apply the stimulation current to a specific part of a user.
  • the collecting unit comprises: a detecting electrode, an amplifying module and a filtering module;
  • the detecting electrode is disposed at a specific part of the user, and is configured to collect an electromyogram signal of a specific part of the user and output the signal to the amplifying module;
  • the amplifying module is configured to perform amplification processing on the myoelectric signal and output the signal to the filtering module;
  • the filtering module is configured to filter the EMG signal output by the amplification module and output the signal to the main control unit.
  • the main control unit includes: an analog to digital conversion module, a processing module, and a digital to analog conversion module;
  • the analog-to-digital conversion module is configured to perform analog-to-digital conversion on the myoelectric signal output by the collecting unit, obtain a digital myoelectric signal, and output the signal to the processing module;
  • the processing module is configured to determine an optimal myoelectric signal by using the received digital electromyogram signal, and use an optimal electromyogram signal to output a stimulation signal, and output the stimulation signal to the digital-to-analog conversion module;
  • the digital-to-analog conversion module is configured to perform digital-to-analog conversion on the received stimulation signal and output the same to the discharge unit.
  • the training auxiliary device further includes: a communication unit;
  • the stimulation signal is equivalent to the optimal electromyographic signal after the terminal device analyzes and compares the collected myoelectric signals to determine an optimal electromyogram signal; or, the acquired myoelectric signal
  • the signal is analyzed and compared to determine an optimal myoelectric signal, and the optimal electromyogram signal is sent to the terminal device through the communication unit, and the stimulation signal returned by the terminal device is acquired by the communication unit
  • the stimulation signal is equivalent to the terminal device utilizing the optimal myoelectric signal.
  • the processing module determines the optimal myoelectric signal
  • the specific implementation the received digital electromyography signal is analyzed, the indicators of the current action are obtained, and the EMG signal of the current action is compared with the EMG signal of the previous action, and the indicators are determined.
  • Optimal EMG signal When the specific implementation: the received digital electromyography signal is analyzed, the indicators of the current action are obtained, and the EMG signal of the current action is compared with the EMG signal of the previous action, and the indicators are determined. Optimal EMG signal.
  • the processing module when the processing module utilizes the optimal electromyographic signal equivalent stimulation signal, the processing module specifically performs: determining a periodic signal matching the optimal electromyographic signal power, and performing the periodic signal Zoomed in as a stimulus signal.
  • the frequency of the periodic signal is more than twice the frequency of the myoelectric signal.
  • the amplification factor G adopted by the processing module when amplifying the periodic signal satisfies V*G ⁇ R*I, and the V is the highest intensity of the optimal myoelectric signal.
  • R is the equivalent resistance of the human body
  • the I is the intensity of the stimulation current that can be received by the human body without pain.
  • the training auxiliary device further includes: a nine-axis sensor
  • the nine-axis sensor is configured to collect motion data of a user and output the data to the processing module;
  • the processing module is further configured to further determine an optimal myoelectric signal in conjunction with the motion data.
  • the discharge unit includes: a forward side adder, a voltage controlled constant current source, and a discharge electrode;
  • the forward side adder is configured to convert the stimulation signal output by the main control unit into a bipolar signal, and output the bipolar signal to the voltage controlled constant current source;
  • the voltage controlled constant current source is configured to output a corresponding stimulation current according to the input bipolar signal
  • the discharge electrode is configured to apply a stimulation current output by the voltage-controlled constant current source to a specific part of a user.
  • the collecting unit and the discharging unit respectively have N channels, the N is a positive integer greater than 1, and the channel of the collecting unit and the channel of the discharging unit are in one-to-one correspondence. ;
  • the discharge unit further includes: a multiplex selection module, configured to perform channel selection by the control of the main control unit, and sequentially send the bipolar signal outputted by the forward side adder to the corresponding channel for voltage control Stream source module.
  • a multiplex selection module configured to perform channel selection by the control of the main control unit, and sequentially send the bipolar signal outputted by the forward side adder to the corresponding channel for voltage control Stream source module.
  • the detecting electrode in the collecting unit and the discharging electrode in the discharging unit may share the differential electrode in a frequency division manner.
  • the invention also provides a training assisting method, the training assisting method comprising:
  • the optimal electromyographic signal is determined according to the amplified and filtered myoelectric signal, and the optimal electromyographic signal is used to form the stimulation signal;
  • a stimulation current is generated based on the stimulation signal, and the stimulation current is applied to a specific portion of the user.
  • the determining the optimal myoelectric signal according to the amplified and filtered myoelectric signal, and forming the stimulation signal by using the optimal electromyogram signal comprises:
  • the stimulation signal is digital-to-analog converted.
  • the digital myoelectric signals are analyzed and compared, and determining the optimal myoelectric signals includes:
  • the digital electromyography signal is analyzed to obtain various indicators of the action
  • the EMG signal of this operation is compared with the EMG signal of the previous action to determine the optimal EMG signal.
  • the utilizing the optimal electromyographic signal equivalent to the stimulation signal comprises:
  • a periodic signal matching the optimal electromyographic signal power is determined, and the periodic signal is amplified to be a stimulation signal.
  • the frequency of the periodic signal is more than twice the frequency of the myoelectric signal.
  • the magnification G used in amplifying the periodic signal satisfies V*G ⁇ R*I
  • the V is the highest intensity of the optimal myoelectric signal
  • R is the human body. Equivalent resistance
  • the I is the intensity of the stimulation current that can be received by the human body without pain.
  • the method further comprises: collecting motion data of the user by using a nine-axis sensor, and further combining the motion data when determining the optimal myoelectric signal.
  • forming the stimulation current according to the stimulation signal comprises:
  • the bipolar signal is used as an input signal of a voltage-controlled constant current source to obtain a stimulation current outputted by the voltage-controlled constant current source.
  • the present invention adopts a closed-loop myoelectric stimulation mode in which the "acquisition-stimulation" type electromyogram signal and the stimulation signal are equivalent, based on the optimal electromyogram signal during the implementation of the specific training object action.
  • Stimulation the action of the training object gradually tends to develop in an optimal direction, and the step-by-step method of the present invention compares the fixed program in the prior art. The way is more helpful to improve the training effect.
  • the invention does not limit the constraints of location and time.
  • FIG. 1 is a structural diagram of a training auxiliary device according to an embodiment of the present invention.
  • FIG. 2 is a schematic diagram showing a periodic relationship between an electromyogram signal and a stimulation signal according to an embodiment of the present invention
  • FIG. 3 is a schematic structural diagram of a training auxiliary device according to an embodiment of the present invention.
  • FIG. 4 is a schematic structural diagram of an electrode plate of a training auxiliary device according to an embodiment of the present invention.
  • FIG. 5 is a schematic diagram of a preferred example of a training auxiliary device according to an embodiment of the present invention.
  • FIG. 6 is a flowchart of a training assistance method according to an embodiment of the present invention.
  • FIG. 7 is a flowchart of a method for forming a stimulation signal according to an embodiment of the present invention.
  • the core idea of the invention is to collect the myoelectric signal of the specific part of the user during the action implementation, and adopt the closed-loop myoelectric stimulation of the equivalent stimulation type, that is, the most accurate determination of the myoelectric signal during the implementation of the collected action.
  • the excellent electromyographic signal which is formed by the optimal electromyographic signal, acts on the specific part of the user to achieve the effect of enhancing muscle memory, so that the training object tends to play in its optimal direction.
  • EMG signals are a comprehensive result of the complex temporal and spatial activity of subepidermal muscle activity at the surface of the skin.
  • the myoelectric signal originates from motor neurons in the spinal cord.
  • the axons of the motor neurons extend to the muscle fibers and are coupled to the muscle fibers via the endplate region.
  • the EMG signal has the following characteristics:
  • the human surface EMG signal is very weak, from a few microvolts to a few millivolts.
  • EMG signal has cross-change, is a disordered AC voltage signal, it is muscled with The muscle tension generated during the movement is roughly proportional, and the myoelectric signals collected at different strengths are also different.
  • the mean square value of the myoelectric signal is also time-varying, and the signal is non-stationary, which can be understood as amplitude-modulated noise.
  • the spectrum of the surface of the human skin surface is between 0 and 1000 Hz.
  • the maximum frequency of the power spectrum is determined by the muscle, usually between 10 and 200 Hz.
  • the main energy of the myoelectric signal is below 200 Hz, and the low frequency characteristics of the myoelectric signal. Obviously, the frequency band is fixed.
  • the physiological basis of the present invention is that the specific joint motion of the limb is controlled by its corresponding muscle group, and the myoelectric signal on the skin surface not only reflects the degree of flexion and extension of the joint, but also obtains the shape, position and motion information of the gesture in real time.
  • EMG signal acquisition can distinguish dozens of gestures, and the correct rate is higher than 90%.
  • instrumental music as an example, during the playing process, it is basically the continuous movement of the arms and fingers.
  • the EMG signal acquisition can well record the complete playing process.
  • EMG signal acquisition can help users record the information of the piano, used for basic fingering training, hand shape training, and covers many elements such as rhythm and consistency. Since the EMG signal is derived from the human's own electrical signal, it has direct and natural characteristics.
  • the EMG signal measured from the skin surface of the muscle surface is a safe way to extract EMG signals.
  • the muscles of the human body have a memory effect. After the same action is repeated many times, the muscles will form a conditioned reflex. The speed at which human muscles gain memory is very slow, but once they are acquired, the rate of forgetting is very slow. People who learn instrumental music generally feel that after practicing more, they don’t seem to be the brain to direct their fingers. When they touch a certain chord or a certain key, the fingers will naturally form a chord shape or move naturally to the piano key. The finger seems to It's moving on your own. In contrast, it takes a lot of time to recite the position or spectrum of the chords. This means that people's brains don't remember these things, but people make memories of specific parts of the muscles after a long period of repetition. .
  • the training auxiliary device may include three parts as shown in FIG. 1 : the collecting unit 00 , the main control unit 10 and the discharging unit 20 , and may further include a nine-axis sensor 30 and a communication unit 40 . .
  • the collecting unit 00 is responsible for collecting the myoelectric signal of the specific part of the user during the implementation of the action, performing amplification filtering and outputting to the main control unit 00.
  • the main control unit 10 is responsible for determining an optimal myoelectric signal according to the myoelectric signal output by the collecting unit 00, forming a stimulation signal by using the optimal myoelectric signal, and outputting the stimulation signal to the discharge unit 20, and the discharge unit 20 according to the stimulation signal A stimulus current is generated to act on a specific part of the user.
  • the collecting unit 00 may specifically include: a detecting electrode 01, an amplifying module 02, and a filtering module 03.
  • the detecting electrode 01 is in contact with the skin and is disposed at a specific part of the user.
  • the specific part is determined according to a specific training item, and the detecting electrode 01 may be more than one quantity.
  • the detecting electrode 01 can be set to a plurality of fingers; if it is a ball training, the detecting electrode 01 can be placed at a finger, a wrist, an arm, or the like.
  • the electrode 01 can collect the myoelectric signal of the specific part of the user, for example, the user plays a piano, and the detecting electrode 01 can collect the myoelectric signal of the user's finger.
  • the amplifying module 02 is responsible for amplifying the myoelectric signal collected by the detecting electrode 01. Since the myoelectric signal on the surface of the human body is very weak, from a few microvolts to several millivolts, the amplified myoelectric signal can become a kind of A signal that can be measured and processed. Here, the magnification of the amplification module 02 can be determined according to the processing capability and accuracy of the main control unit 10.
  • the filtering module 03 is responsible for filtering the myoelectric signals processed by the amplification module 02, and then outputting the filtered electromyogram signals to the main control unit 10. Since the myoelectric signal is collected by the skin surface detecting electrode 01, the collecting process is susceptible to the surrounding environment, such as the inherent noise of the electronic component, the moving noise of the detecting electrode 01 and the skin contact surface, The environmental noise caused by electromagnetic radiation, etc., the filtering module 03 filters these noises, usually by means of band pass filtering.
  • one detecting electrode 01, the amplifying module 02 and the filtering module 03 constitute one channel, and more than one channel may exist in the collecting unit 00, and the electromyogram signals of different parts are respectively collected, amplified and filtered, and output to the main unit. Control unit 10.
  • the main control unit 10 may include an analog to digital conversion module (ADC) 11, a processing module 12, and a digital to analog conversion module (DAC) 13.
  • ADC analog to digital conversion module
  • DAC digital to analog conversion module
  • the ADC 11 is responsible for performing analog-to-digital conversion of the myoelectric signals output by the acquisition unit 00 to obtain a digital myoelectric signal, which is then supplied to the processing module 12.
  • the processing module 12 is responsible for determining the optimal myoelectric signal, using the optimal myoelectric signal to form a stimulation signal and providing it to the DAC 13.
  • the processing module 12 stores and analyzes the myoelectric signals from the collecting unit 00, and obtains various indicators of the current action, such as the accuracy, tension, and rhythm accuracy of the action, and the specific indicators can be specifically trained. Project decision.
  • the EMG signal of this action is compared with the EMG signal of the previous action to determine the optimal EMG signal, and the optimal EMG signal is used to equivalent the stimulation signal. If the determined optimal EMG signal has not changed, the previously determined stimulation signal is still used, and if the determined optimal EMG signal changes, the new optimal EMG signal is used to equate the stimulus. After the signal, replace the previously determined stimulus signal.
  • the user controls the playing by the movement of the finger.
  • the movement of the finger is mainly controlled by the muscle group of the forearm, so the user will generate a corresponding sequence of the EMG signal during the playing process, through the electromyogram
  • the analysis of the signal sequence extracts the time domain and/or frequency characteristics of the signal for fine-grained analysis of the playing action to obtain various indicators.
  • the user's arm In the standard playing state, the user's arm is in a relaxed state, and only when the playing moment will the muscle electrical signal be generated.
  • the amplitude and duration of the EMG signal can be judged by the algorithm, and the degree of exertion and tension of the user when playing can be further inferred.
  • the user When the amplitude is larger or the duration is longer, the user is in a state of tension.
  • the rhythm of the user's finger playing By analyzing the peak interval of the user's myoelectric signal, the rhythm of the user's finger playing can be judged, and the accuracy of the user's playing rhythm can be known by comparing with the standard musical rhythm; and the machine learning algorithm by finger action can
  • the finger used by the user's button is recognized, that is, the sequence of the finger played by the user is determined, and the correctness of the action is further analyzed.
  • the determination of the various indicators of the action is schematically introduced. How to determine the action indicators is not the key content of the invention.
  • the process of using the optimal myoelectric signal equivalent to the stimulation signal is described below. Since the myoelectric signal is a statistical result of a series of action potentials, the potential of each muscle fiber cannot be recovered, so the equivalent power method can be used, specifically the equivalent optimal electromyogram signal with a power-matched periodic signal, and then The power-matched periodic signal is amplified and used as a stimulation signal, and the periodic signal may be a sine wave, a square wave, or the like.
  • the EMG signal intensity corresponding to each sampling point can be obtained at a fixed sampling frequency, because the frequency of the stimulation signal may not coincide with the frequency of the EMG signal, preferably more than twice the frequency of the EMG signal, so in each sampling The interval of points can emit more than two periods of stimulation signals, as shown in FIG.
  • the power of the stimulation signal is closely related to the amplitude, and the intensity of the optimal EMG signal according to each cycle is equivalent to the amplitude of the stimulation signal for more than two periods corresponding to the intensity.
  • magnification is required after the power equivalent is performed, that is, the stimulation signal needs to be amplified by a fixed multiple.
  • the magnification here is determined by three factors: the intensity of the stimulation current I can receive under the painless sense of the human body, the highest intensity of the optimal EMG signal, and the equivalent resistance R of the human body.
  • the magnification G only needs to satisfy the following inequality: V*G ⁇ R*I.
  • the intensity of the stimulus current acceptable to the human body is 1 mA
  • the highest intensity of the acquired EMG signal is 5 mV
  • the equivalent resistance of the human body is 1 K ⁇ .
  • the magnification can be taken as 200.
  • the DAC 13 then performs digital-to-analog conversion on the stimulation signal obtained by the processing module 12 and outputs it to the discharge unit 20.
  • the processing module 12 may perform the above process of determining an optimal myoelectric signal and an equivalent stimulation signal, and another implementation manner, that is, the processing module 12 passes the collected myoelectric signal through the communication unit 40.
  • a terminal device such as a mobile phone, a tablet computer, a PC, or even an integrated circuit, etc.
  • the terminal device performs the above process of determining an optimal myoelectric signal and an equivalent stimulation signal, and then returns the stimulation signal to the communication unit 40,
  • the communication unit 40 is provided to the processing module 12.
  • the processing module 12 determines the optimal myoelectric signal by using the collected myoelectric signals, and then sends the optimal myoelectric signal to the terminal device through the communication unit 40, and the terminal device performs the above equivalent.
  • the process of stimulating the signal is then returned to the communication unit 40, which is provided by the communication unit 40 to the processing module 12.
  • the nine-axis sensor 30 can collect motion data.
  • the nine-axis sensor 30 is composed of a three-axis gyroscope, a three-axis acceleration sensor, and a three-axis magnetic induction sensor.
  • the processing module can transmit the motion data collected by the nine-axis sensor 30 together with the myoelectric signal to the terminal.
  • the motion data collected by the nine-axis sensor 30 can be converted into motion velocity, motion displacement, real-time attitude, etc. in a three-dimensional space, and combined with the electromyogram signal, can provide the necessary dynamic capture information for the processing module 12 to analyze and determine the optimal myoelectric signal. .
  • the discharge cell 20 may specifically include a forward side adder 21, a voltage controlled constant current source 23, and a discharge electrode 24.
  • the forward side adder 21 is responsible for converting the stimulation signal output from the main control unit 10 into a bipolar signal, and then outputting it to the voltage controlled constant current source 23.
  • the voltage controlled constant current source 23 is configured to output a corresponding stimulation current according to the input bipolar signal.
  • the stimulation current output by the voltage-controlled constant current source 23 is independent of the load resistance and is only related to the input voltage, that is, the output stimulation current is controlled by the voltage of the bipolar signal.
  • the discharge electrode 24 applies a stimulation current output from the voltage-controlled constant current source 23 to the skin of a specific portion of the user.
  • each of the channels may include a forward side adder 21, a voltage controlled constant current source 23, and a discharge electrode 24.
  • the multiplex selection module 22 can be provided in the discharge unit 20, in which case only one DAC 13 is required in the main control unit 10 and discharged. Only one forward side adder 21 is required in unit 20.
  • the multiplex selection module 22 performs channel selection by the control of the processing module 12 in the main control unit 10, and then sequentially transmits the bipolar signals to the corresponding voltage-controlled constant current source module 23 in time division.
  • the same electrode can be used for the acquisition and discharge, that is, the detection electrode and the discharge electrode can share the electrode, that is, a differential electrode is used in common.
  • the stimulation signal and the myoelectric signal can be used in different frequency bands, so that the acquisition process and the discharge process can work simultaneously.
  • the acquisition and stimulation can be performed simultaneously for the same part of the muscle, and the user's data can be completely saved while stimulating. That is, setting the frequency of the stimulation signal outside the frequency band of the myoelectric signal, consider The frequency of the EMG signal is between 10 and 200 Hz, so the frequency of the stimulation signal should be less than 10 Hz or greater than 200 Hz.
  • the stimulation signal needs to be discharged once at each sampling point according to the sampling signal (acquired myoelectric signal) during the discharge process, and considering the cutoff frequency of the filtering portion, the stimulation signal should be selected to be twice the sampling rate of the collected myoelectric signal. the above.
  • the effective frequency of the myoelectric signal itself is below 500 Hz, and the sampling rate is 1000 Hz. If the frequency of the stimulation signal during the discharge process is higher than 2000 Hz, the myoelectric signal of the skin is collected while the device is discharging, because the filter module has bandpassed the myoelectric signal. Filtering, the frequency band selection is lower than 1000Hz, so the stimulation signal of the device itself can be well filtered out, and the stimulation signal is not mixed into the collected myoelectric signal. In this case, the acquisition of the EMG signal does not conflict with the stimulation signal, achieving the purpose of synchronous operation of the acquisition and discharge.
  • the preferred structure of the training aid can be as shown in FIG.
  • the structure of the training auxiliary device can be modularized, and the acquisition unit and its corresponding discharge unit can be integrated together, and the detection electrode and the discharge electrode share a differential electrode, that is, the amplification module, the filter module, the voltage-controlled constant current source, and The differential electrodes are integrated on one electrode plate, and the main control unit is integrated on one electrode plate, so that the main control unit can communicate with multiple electrode plates at the same time, as shown in FIG. 4 .
  • the above-mentioned amplification module 02 can adopt the AD8220, and the AD8220 is an operation amplifier with less noise, and the common mode rejection ratio is also superior.
  • the filter module 03 can implement two band-pass filters by using the LM358 to implement two second-order filters, one low-pass filter and one high-pass filter.
  • the low-pass filter has a resistance of 10.7K, a capacitance of 0.1uf, and a cutoff frequency of 400Hz.
  • the high-pass filter has a resistance of 160K, a capacitance of 0.1uf, and a cutoff frequency of 10Hz.
  • the ADC 11 can be an ADS1298 analog-to-digital converter chip with 8 channels and 24 bits for portable devices.
  • the ADS1298 includes eight low-noise PGAs (programmable gain amplifiers) and eight high-resolution synchronous sampling ADCs that consume only 1mW per channel, reducing power consumption by up to 95 compared to discrete implementations. %, thereby increasing the portability of the device.
  • the processing module 12 can use the STM32F103, which is a commonly used enhanced series of microcontrollers with a 32-bit Cortex-M3 and a maximum operating frequency of 72 MHz.
  • the STM21F103 has a built-in dual DAC, and the DAC 13 of the present invention can be implemented with only one internal DAC.
  • the nine-axis sensor 30 can be used with the MPU-9400.
  • the MPU-9400 is the world's first nine-axis motion sensing tracking component, including a three-axis gyroscope, a three-axis accelerometer, and a three-axis magnetic sensor. It is low power, low cost, and high. Performance of consumer electronics chips.
  • the MPU-9400 includes InvenSense's motion sensing fusion algorithms and motion correction.
  • the attitude fusion solution of the three-axis gyroscope, the three-axis acceleration sensor and the three-axis magnetic induction sensor is processed by using the DMP (Digital Motion Processing Module) built in the MPU-9400.
  • DMP Digital Motion Processing Module
  • the Euler angle obtained by the solution is used to convert the three-axis original acceleration value to obtain the three-axis acceleration from the body coordinate system to the geographic coordinate system.
  • the three-axis angular velocity and the vertical vertical ground acceleration generated by the forearm movement during the action implementation are used as a real-time dynamic analysis basis, giving the user an intuitive and accurate action effect. Fusion of raw data output and DMP processing of three-axis gyroscope, three-axis acceleration sensor and three-axis magnetic induction sensor
  • the data output interface is I2C (two-wire serial bus), and the data refresh rate can reach 200Hz, which provides high real-time performance for motion control and recognition.
  • the multiplex selection module 22 can be a 74 LS 401, and the 74 LS 401 is an 8-to-1 multiplexer. In the embodiment of the present invention, six channels are used, and the three-line input terminal is controlled by the processing module 12 to select an output channel.
  • the multiplexer module 22 has a switching delay of less than 50 ns, which is negligible relative to human muscle movement, so a multiplexed scheme is feasible.
  • the voltage-controlled constant current source 23 can be used with the LT1639.
  • the maximum stimulus signal strength is 20mA, and the load is assumed to be 1k ⁇ .
  • the LT1639 is required to provide 20V.
  • this embodiment uses the LT1639 quad op amp chip.
  • the LT1639 uses a ⁇ 40V operating voltage.
  • the LT1640 is used for voltage conversion.
  • the LT1640 is designed by Linear for high power systems with a current limit of 350mA and an input voltage range of 1.2V to 40V, suitable for the LT1639. Its input can be operated as low as 1V and the output voltage is as high as 34V.
  • the communication unit 40 can adopt the ESP8266, which is a complete and self-contained wifi network solution, which greatly saves the volume.
  • the training assistance method flow executed by the above training auxiliary device provided by the present invention is as shown in FIG. 6, and mainly includes the following steps:
  • step 601 the myoelectric signal of the specific part of the user during the action implementation is collected, and the myoelectric signal is amplified and filtered.
  • This step is performed by the collection unit of the training auxiliary device.
  • the collection unit of the training auxiliary device For details, refer to the description in the device embodiment, and details are not described herein.
  • an optimal myoelectric signal is determined according to the amplified and filtered myoelectric signal, and the optimal electromyographic signal is used to form a stimulation signal.
  • This step is performed by the main control unit of the training auxiliary device. Specifically, the following sub-steps may be included as shown in FIG. 7:
  • Step 701 Perform analog-to-digital conversion on the amplified and filtered myoelectric signal to obtain a digital myoelectric signal.
  • This step is performed by the ADC in the main control unit of the training aid.
  • Step 702 Analyze the digital myoelectric signals to determine an optimal myoelectric signal.
  • This step is performed by the processing module in the main control unit.
  • the digital electromyogram signal can be analyzed to obtain various indicators of the current action, such as the accuracy, tension, and rhythm accuracy of the action, and specific indicators. It can be determined by a specific training program.
  • the EMG signal of this operation is compared with the EMG signal of the previous action to determine the optimal EMG signal.
  • the motion data collected by the nine-axis sensor can be further combined to determine the optimal myoelectric signal.
  • Step 703 Equivalent of the stimulation signal using the optimal myoelectric signal.
  • This step is also performed by the processing module in the main control unit, and uses a power equivalent method to determine a periodic signal that matches the optimal EMG signal power, and the periodic signal is amplified to be a stimulation signal.
  • the frequency of the periodic signal is more than twice the frequency of the myoelectric signal.
  • the above periodic signal may be a sine wave, a square wave or the like.
  • the EMG signal intensity corresponding to each sampling point can be obtained at a fixed sampling frequency, because the frequency of the stimulation signal may not coincide with the frequency of the EMG signal, preferably more than twice the frequency of the EMG signal, so in each sampling The interval between points can emit more than two periods of stimulation signals.
  • the power of the stimulation signal is closely related to the amplitude, and the intensity of the optimal EMG signal according to each cycle is equivalent to the amplitude of the stimulation signal for more than two periods corresponding to the intensity.
  • the magnification G used satisfies: V*G ⁇ R*I, where V is the highest intensity of the optimal myoelectric signal, R is the equivalent resistance of the human body, and I is the painless feeling of the human body.
  • V is the highest intensity of the optimal myoelectric signal
  • R is the equivalent resistance of the human body
  • I is the painless feeling of the human body. The intensity of the stimulus current received.
  • Step 704 Perform digital-to-analog conversion on the stimulation signal.
  • This step is performed by the DAC module in the main control unit.
  • a stimulation current is generated based on the stimulation signal, and the stimulation current is applied to a specific portion of the user.
  • This step is performed by the discharge unit of the myoelectric acquisition device. Firstly, the stimulation signal is converted into a bipolar signal, and then the bipolar signal is used as an input signal of the voltage-controlled constant current source to obtain a stimulation current outputted by the voltage-controlled constant current source, and finally the stimulation electrode applies a stimulation current to a specific part of the user.
  • the above-mentioned training auxiliary device and training assisting method provided by the present invention are applicable to training of musical instruments such as piano and guitar, and can also be applied to sports training such as golf and tennis.
  • the units described as separate components may or may not be physically separate. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing module, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional units.
  • the above-described integrated unit implemented in the form of a software functional unit can be stored in a computer readable storage medium.
  • the software functional unit described above is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor to perform the methods of various embodiments of the present invention. Part of the steps.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like, which can store program codes. .

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Animal Behavior & Ethology (AREA)
  • Veterinary Medicine (AREA)
  • Biomedical Technology (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Molecular Biology (AREA)
  • Medical Informatics (AREA)
  • Physics & Mathematics (AREA)
  • Pathology (AREA)
  • Surgery (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Physiology (AREA)
  • Signal Processing (AREA)
  • Dentistry (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Transplantation (AREA)
  • Rheumatology (AREA)
  • Power Engineering (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Psychiatry (AREA)
  • Physical Education & Sports Medicine (AREA)
  • Electrotherapy Devices (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
  • Neurology (AREA)

Abstract

一种培训辅助设备和培训辅助方法，该培训辅助设备包括采集单元（00）、主控单元（10）和放电单元（20）；采集单元（00），用于采集用户特定部位在动作实施过程中的肌电信号，进行放大滤波后输出给主控单元（10）；主控单元（10），用于根据接收到的肌电信号确定最优的肌电信号，利用最优的肌电信号形成刺激信号，并将刺激信号输出给放电单元（20）；放电单元（20），用于根据刺激信号形成刺激电流，并将刺激电流作用于用户特定部位。通过采用"采集-刺激"式的肌电信号与刺激信号等效的闭环肌电刺激方式，使培训对象的动作逐渐趋向于最优的方向发展，这种循序渐进的方式相比较现有技术中采用固定程式的方式更有助于提高培训效果。另外，并不限制地点和时间的约束。

Description

一种培训辅助设备和培训辅助方法
本申请要求了申请日为2014年12月9日，申请号为201410749425.2发明名称为“一种培训辅助设备和培训辅助方法”的中国专利申请的优先权。
技术领域
本发明涉及计算机应用技术领域，特别涉及一种培训辅助设备和培训辅助方法。
背景技术
随着人们物质和文化生活的飞速发展，艺术、体育等培训市场空间巨大并且前景广阔。以器乐类培训领域为例，目前大多数采用的培训方式为人工培训，即家长选择器乐老师来给孩子做培训，然而，这种方式一方面家长在没有专业知识的前提下缺乏选择老师的判断标准，无法评估学生训练效果。老师往往是一对一培训，教学效率低下，并且造成家长的培训成本巨大，也往往受到地域、时间的约束。
为了降低培训成本，教育效率，摆脱地域和时间的约束，又出现了音频和视频的教学方式，即通过互联网或者通过计算机本地存储的资源，学生通过音频和视频上的教程来进行学习。但这种方式主要依靠自我学习，培训效果较差。
为了解决上述的问题，现有技术中又有人提出了一种电刺激式的培训装置，即预先采用计算机编程的方式在处理模块中预置电刺激培训程序，处理模块按照该程序直接控制数模转换器(DAC)发射模拟信号到恒流源，进而由恒流源产生恒定电流，多个恒流源连接到多个电极，这些电极分别对手指或是手臂进行电刺激。佩戴这样的设备的用户就能够 在乐器上受到电刺激后被动的做出连续动作，从而在形式上达到牵引用户自动弹奏的目的。然而，这种方式存在以下缺陷：
1)采用固定的程序，并没有对用户进行具体的区分，无论是大人还是小孩，处于何种演奏水平，都采用同样的刺激信号且不具备循序渐进的功能，因此培训效果并不好。
2)采用的电刺激至少是数十mA，长时期的大电流刺激会对皮肤组织造成潜在的伤害，并不适宜孩子之类的用户。
发明内容
有鉴于此，本发明提供了一种培训辅助设备和培训辅助方法，以便于摆脱地点和时间的约束，提高培训效果。
具体技术方案如下：
本发明提供了一种培训辅助设备，该培训辅助设备包括：采集单元、主控单元和放电单元；
所述采集单元，用于采集用户特定部位在动作实施过程中的肌电信号，进行放大滤波后输出给所述主控单元；
所述主控单元，用于根据接收到的肌电信号确定最优的肌电信号，利用最优的肌电信号形成刺激信号，并将刺激信号输出给所述放电单元；
所述放电单元，用于根据所述刺激信号形成刺激电流，并将所述刺激电流作用于用户特定部位。
根据本发明一优选实施方式，所述采集单元包括：检测电极、放大模块和滤波模块；
所述检测电极设置于用户特定部位，用于采集用户特定部位的肌电信号并输出给所述放大模块；
所述放大模块，用于将所述肌电信号进行放大处理后输出给所述滤波模块；
所述滤波模块，用于对所述放大模块输出的肌电信号进行滤波处理后输出给所述主控单元。
根据本发明一优选实施方式，所述主控单元包括：模数转换模块、处理模块和数模转换模块；
所述模数转换模块，用于将所述采集单元输出的肌电信号进行模数转换，得到数字肌电信号后输出给所述处理模块；
所述处理模块，用于利用接收到的数字肌电信号确定最优的肌电信号，利用最优的肌电信号等效出刺激信号，将刺激信号输出给数模转换模块；
所述数模转换模块，用于对接收到的刺激信号进行数模转换后输出给所述放电单元。
根据本发明一优选实施方式，该培训辅助设备还包括：通讯单元；
所述处理模块在确定最优的肌电信号时，具体执行：将采集到的肌电信号通过所述通讯单元发送给终端设备，通过所述通讯单元获取由所述终端设备返回的刺激信号，所述刺激信号是所述终端设备对采集到的肌电信号进行分析和比对确定出最优的肌电信号后利用最优的肌电信号等效出的；或者，将采集到的肌电信号进行分析和比对后确定出最优的肌电信号，通过所述通讯单元将所述最优的肌电信号发送给终端设备，通过所述通讯单元获取由所述终端设备返回的刺激信号，所述刺激信号是所述终端设备利用所述最优的肌电信号等效出的。
根据本发明一优选实施方式，所述处理模块在确定最优的肌电信号 时，具体执行：对接收到的数字肌电信号进行分析，得到本次动作的各项指标，将本次动作的肌电信号与以往动作的肌电信号进行各项指标的比对，确定其中最优的肌电信号。
根据本发明一优选实施方式，所述处理模块在利用最优的肌电信号等效刺激信号时，具体执行：确定与所述最优的肌电信号功率匹配的周期信号，将该周期信号进行放大后作为刺激信号。
根据本发明一优选实施方式，所述周期信号的频率是肌电信号频率的两倍以上。
根据本发明一优选实施方式，所述处理模块在对所述周期信号进行放大时采用的放大倍数G满足V*G<R*I，所述V为所述最优的肌电信号的最高强度，R为人体等效电阻，所述I为人体无痛感下能接收的刺激电流强度。
根据本发明一优选实施方式，该培训辅助设备还包括：九轴传感器；
所述九轴传感器用于采集用户的运动数据并输出给所述处理模块；
所述处理模块，还用于进一步结合所述运动数据确定最优的肌电信号。
根据本发明一优选实施方式，所述放电单元包括：正向侧加法器、压控恒流源以及放电电极；
所述正向侧加法器，用于将所述主控单元输出的刺激信号转换成双极信号，将所述双极信号输出给所述压控恒流源；
所述压控恒流源，用于依据输入的双极信号输出对应的刺激电流；
所述放电电极，用于将所述压控恒流源输出的刺激电流作用于用户特定部位。
根据本发明一优选实施方式，所述采集单元和所述放电单元分别存在N个通道，所述N为大于1的正整数，且所述采集单元的通道和所述放电单元的通道一一对应；
所述放电单元还包括：多路选择模块，用于受所述主控单元的控制进行通道选择，将所述正向侧加法器输出的双极信号分时依次发送到对应通道的压控恒流源模块。
根据本发明一优选实施方式，所述采集单元中的检测电极和所述放电单元中的放电电极可以以频分的方式共用差分电极。
本发明还提供了一种培训辅助方法，该培训辅助方法包括：
采集用户特定部位在动作实施过程中的肌电信号，对所述肌电信号进行放大滤波；
根据放大滤波后的肌电信号确定最优的肌电信号，利用最优的肌电信号形成刺激信号；
根据所述刺激信号形成刺激电流，并将所述刺激电流作用于用户特定部位。
根据本发明一优选实施方式，所述根据放大滤波后的肌电信号确定最优的肌电信号，利用最优的肌电信号形成刺激信号包括：
将放大滤波后的肌电信号进行模数转换，得到数字肌电信号；
对所述数字肌电信号进行分析比对，确定最优的肌电信号；
利用最优的肌电信号等效出刺激信号；
对所述刺激信号进行数模转换。
根据本发明一优选实施方式，对所述数字肌电信号进行分析比对，确定最优的肌电信号包括：
对所述数字肌电信号进行分析，得到本次动作的各项指标；
将本次动作的肌电信号与以往动作的肌电信号进行各项指标的比对，确定最优的肌电信号。
根据本发明一优选实施方式，所述利用最优的肌电信号等效出刺激信号包括：
确定与所述最优的肌电信号功率匹配的周期信号，将该周期信号进行放大后作为刺激信号。
根据本发明一优选实施方式，所述周期信号的频率是肌电信号频率的两倍以上。
根据本发明一优选实施方式，在将所述周期信号进行放大时采用的放大倍数G满足V*G<R*I，所述V为所述最优的肌电信号的最高强度，R为人体等效电阻，所述I为人体无痛感下能接收的刺激电流强度。
根据本发明一优选实施方式，该方法还包括：利用九轴传感器采集用户的运动数据，在所述确定最优的肌电信号时进一步结合所述运动数据。
根据本发明一优选实施方式，根据所述刺激信号形成刺激电流包括：
将所述刺激信号转换成双极信号；
将所述双极信号作为压控恒流源的输入信号，得到压控恒流源输出的刺激电流。
由以上技术方案可以看出，本发明采用“采集-刺激”式的肌电信号与刺激信号等效的闭环肌电刺激方式，基于特定培训对象动作实施过程中最优的肌电信号而进行的刺激，使培训对象的动作逐渐趋向于最优的方向发展，本发明这种循序渐进的方式相比较现有技术中采用固定程式 的方式更有助于提高培训效果。另外，发明并不限制地点和时间的约束。
附图说明
图1为本发明实施例提供的培训辅助设备结构图；
图2为本发明实施例提供的肌电信号与刺激信号的周期关系示意图；
图3为本发明实施例提供的培训辅助设备的一种优选结构示意图；
图4为本发明实施例提供的培训辅助设备的电极板结构示意图；
图5为本发明实施例提供的培训辅助设备的一种优选实例图；
图6为本发明实施例提供的培训辅助方法的流程图；
图7为本发明实施例提供的形成刺激信号的方法流程图。
具体实施方式
为了使本发明的目的、技术方案和优点更加清楚，下面结合附图和具体实施例对本发明进行详细描述。
本发明的核心思想在于，采集用户的特定部位在动作实施过程中的肌电信号，采用采集等效刺激式的闭环肌电刺激，即利用采集到的动作实施过程中的肌电信号确定出最优的肌电信号，由最优的肌电信号形成刺激信号作用于用户的特定部位，达到增强肌肉记忆的效果，使培训对象弹奏趋向于其最优的方向发展。
为了方便理解，首先对肌电信号进行简单介绍。肌电信号是一种复杂的表皮下肌肉活动在皮肤表面处的时间和空间上的综合结果。肌电信号发源于脊髓中的运动神经元，运动神经元的细胞体轴突伸展到肌纤维处，经终板区与肌纤维耦合。
肌电信号具有以下特征：人体表面肌电信号非常微弱,从几微伏到几毫伏。肌电信号具有交变性，是一种无序的交流电压信号，它与肌肉冲 动时产生的肌张力大致成比例，不同力度下采集得到的肌电信号也是不同的。在肌肉持续变化时，肌电信号的均方值也是时变的，信号是非平稳的，可理解为调幅噪声。人体皮肤表面肌电信号的频谱范围为0～1000Hz之间，功率谱的最大频率随肌肉而定，通常在10～200Hz之间，肌电信号的主要能量集中在200Hz以下，肌电信号低频特性明显，频段固定。
本发明的生理学基础是：肢体的特定关节运动由其对应的肌肉群控制，而皮肤表面的肌电信号不仅能反映关节的伸屈程度，还能实时得到手势的形状、位置和运动信息。目前已有文献显示采用肌电信号采集的方式可以分辨数十种手势动作，正确率高于90％。以器乐弹奏为例，在弹奏过程中基本是手臂和手指的连续运动，肌电信号采集可以很好地记录完整的弹奏过程。肌电信号采集可以帮助用户记录弹琴信息，用于进行基础指法的训练、手形训练，同时涵盖节奏，连贯性等诸多要素。由于肌电信号是来源于人自身的电信号，具有直接、自然的特点，从肌肉表面皮肤处所测的肌电信号是一种安全的肌电信号提取方式。
人体的肌肉是具有记忆效应的，同一种动作重复多次之后，肌肉就会形成条件反射。人体肌肉获得记忆的速度十分缓慢，但一旦获得，遗忘的速度也十分缓慢。学习器乐的人都普遍感受到练习多了熟练了以后好像不要大脑指挥手指，在碰到某个和弦或者某个键的时候手指会自然摆成和弦的形状或者自然移动到钢琴键旁边，手指似乎是自己在动，相比之下，背出和弦的位置或者谱子倒是需要很多时间，这就说明人们的大脑并没有记住这些，而是人们经过长时间的重复使特定部位的肌肉产生了记忆。
基于以上理论基础，本发明提供的培训辅助设备可以如图1中所示，主要包括三个部分：采集单元00、主控单元10和放电单元20，还可以包括九轴传感器30和通讯单元40。
采集单元00负责采集用户特定部位在动作实施过程中的肌电信号，进行放大滤波后输出给主控单元00。主控单元10负责根据采集单元00输出的肌电信号确定最优的肌电信号，利用最优的肌电信号形成刺激信号，并将刺激信号输出给放电单元20，由放电单元20根据刺激信号形成刺激电流作用于用户特定部位。
其中采集单元00可以具体包括：检测电极01、放大模块02和滤波模块03。检测电极01接触皮肤，设置于用户特定部位，该特定部位根据具体培训项目确定，检测电极01可以是一个以上数量。例如，如果是钢琴培训，可以将检测电极01设置于多根手指；如果是球类培训，可以将检测电极01置于手指、手腕、手臂等处。当用户在动作实施过程中，做出连续动作，则电极01能够采集到用户特定部位的肌电信号，例如用户弹奏一段钢琴，检测电极01能够采集到用户手指的肌电信号。
放大模块02负责将检测电极01采集的肌电信号进行放大处理，由于人体表面的肌电信号十分微弱，从几微伏到几毫伏，因此需要经过放大后肌电信号才能够变成一种可测量和处理的信号。这里放大模块02的放大倍数可以根据主控单元10处理能力和精度来确定。
滤波模块03负责将经放大模块02处理过的肌电信号进行滤波处理，然后将滤波处理后的肌电信号输出给主控单元10。由于肌电信号是通过至于皮肤表面检测电极01采集到的，采集过程中容易受到周围环境的影响，例如电子元器件的固有噪声、检测电极01与皮肤接触面的移动噪声、 电磁辐射引起的环境噪声等等，滤波模块03将这些噪声进行过滤，通常采用的是带通滤波的方式。
需要说明的是，一个检测电极01、放大模块02和滤波模块03构成一个通道，在采集单元00中可以存在一个以上的通道，分别采集不同部位的肌电信号并进行放大和滤波后输出给主控单元10。
如图1中所示，主控单元10可以包括：模数转换模块(ADC)11、处理模块12和数模转换模块(DAC)13。其中ADC 11负责将采集单元00输出的肌电信号进行模数转换，得到数字肌电信号，然后提供给处理模块12。
处理模块12负责确定最优的肌电信号，利用最优的肌电信号形成刺激信号并提供给DAC 13。处理模块12会对来自采集单元00的肌电信号进行存储并进行分析，得到本次动作的各项指标，例如动作的正确度、紧张感、节奏准确性等指标，具体指标可以由具体的培训项目决定。将本次动作的肌电信号与以往动作的肌电信号进行各项指标比对，确定其中最优的肌电信号，利用最优的肌电信号等效出刺激信号。如果确定出的最优肌电信号未发生改变，则仍采用之前确定出的刺激信号，如果确定出的最优的肌电信号发生改变，则利用新的最优的肌电信号等效出刺激信号后，替换掉之前确定出的刺激信号。
以钢琴弹奏为例，用户通过手指的移动来控制弹奏，手指的移动主要由前臂的肌肉群来控制，因此用户在弹奏的过程中会产生对应的肌电信号序列，通过对肌电信号序列的分析，提取信号的时域和/或频率特征以进行细粒度的弹奏动作分析，从而得到各项指标。在标准弹奏状态下，用户的手臂处于放松状态，只有在弹奏的瞬间才会有肌肉电信号的产生， 通过算法能够判断出肌电信号的幅度大小以及持续时间，进一步可以推断出用户弹奏时的用力程度以及紧张程度，当幅度越大或者持续时间越长时，表明用户处于紧张状态。而通过分析用户肌电信号出现的峰值间隔，可以判断出用户手指弹奏的节奏，与标准的乐谱节奏相比较就可以知道用户弹奏节奏的准确性；而通过手指动作的机器学习算法，可以识别出用户按键所使用的手指，即确定出用户弹奏的手指序列，并进一步分析动作的正确性。这里仅仅示意性地对动作各项指标的确定做介绍，具体如何确定出动作各项指标并不是本发明所限制的重点内容。
下面对利用最优的肌电信号等效出刺激信号的过程进行描述。由于肌电信号是一系列动作电位的统计结果，无法恢复出各肌肉纤维的电位，因此可以采用等效功率的方法，具体就是以功率匹配的周期信号等效最优的肌电信号，然后将该功率匹配的周期信号进行放大后作为刺激信号，该周期信号可以是正弦波、方波等。可以在固定的采样频率下，得到每个采样点对应的肌电信号强度，因为刺激信号的频率可能与肌电信号的频率不一致，优选是肌电信号频率的两倍以上，因此在每个采样点的间隔时间可以发射两个以上周期的刺激信号，如图2中所示。刺激信号的功率与幅度密切相关，根据每一个周期的最优的肌电信号的强度等效成对应强度下两个周期以上的刺激信号的幅度。
另外，由于肌电信号的微弱性，在进行功率等效之后需要一个放大倍数，即需要将刺激信号进行固定倍数的放大。这里的放大倍数由三种因素决定：人体无痛感下能接收的刺激电流强度I、最优的肌电信号的最高强度V以及人体等效电阻R。放大倍数G只需要满足以下不等式即可：V*G<R*I。
普遍地，人体无痛感下能接受的刺激电流强度为1mA，采集到的肌电信号的最高强度为5mV，人体等效电阻取1KΩ，此时放大倍数就可以取200。
然后DAC 13将处理模块12得到的刺激信号进行数模转换后输出给放电单元20。
另外，需要说明的是，处理模块12可以执行上述确定最优的肌电信号以及等效出刺激信号的过程，还有一种实现方式，即处理模块12将采集到的肌电信号通过通讯单元40发送给终端设备(例如手机、平板电脑、PC甚至集成电路等)，由终端设备执行上述确定最优的肌电信号以及等效出刺激信号的过程，然后将刺激信号返回给通讯单元40，由通讯单元40提供给处理模块12。
还存在一种实现方式，即处理模块12利用采集到的肌电信号确定最优的肌电信号，然后将最优的肌电信号通过通讯单元40发送给终端设备，由终端设备执行上述等效出刺激信号的过程，然后将刺激信号返回给通讯单元40，由通讯单元40提供给处理模块12。
另外，九轴传感器30可以采集到运动数据。九轴传感器30由三轴陀螺仪、三轴加速度传感器以及三轴磁感应传感器，处理模块可以将九轴传感器30采集到的运动数据与肌电信号一同传输给终端。九轴传感器30采集的运动数据可以转化为三维空间内的运动速度、运动位移、实时姿态等，结合肌电信号，能够为处理模块12分析并确定最优的肌电信号提供必要的动态捕捉信息。
如图1中所示，放电单元20可以具体包括正向侧加法器21、压控恒流源23以及放电电极24。
正向侧加法器21负责将主控单元10输出的刺激信号转换成双极信号，然后输出给压控恒流源23。
压控恒流源23用于依据输入的双极信号输出对应的刺激电流。压控恒流源23输出的刺激电流与负载电阻无关，只与输入电压相关，即输出的刺激电流由双极信号的电压控制。
放电电极24将压控恒流源23输出的刺激电流作用于用户特定部位的皮肤。
当采样单元00存在N个通道时，对应的放电单元20中也存在N个通道，对应的在主控单元10中也存在N个DAC 13。采样单元00与放电单元20的通道一一对应，一个通道的检测电极01与刺激电极24通常设置于同一用户部位。在放电单元20中，每个通道可以都包括正向侧加法器21、压控恒流源23以及放电电极24。
但为了减少正向侧加法器21和DAC 13的数量，降低成本和体积代价，可以在放电单元20中设置多路选择模块22，此时，主控单元10中仅需要一个DAC 13，且放电单元20中仅需要一个正向侧加法器21。
多路选择模块22受主控单元10中的处理模块12的控制进行通道选择，然后将双极信号分时依次发送到对应的压控恒流源模块23。
由于采集的过程和放电的过程是一对可逆的过程，因此采集和放电可以采用同一块电极，也就是说，检测电极和放电电极可以共用电极，即共同采用一个差分电极。在此可以将刺激信号和肌电信号采用差异频段，使得采集过程和放电过程可以同时工作。优选地，可以使得采集与刺激针对同一部位的肌肉同时工作，可以在刺激的同时完整保存用户的数据。也就是说，将刺激信号的频率设定在肌电信号的频带之外，考虑 到肌电信号频率几种在10～200Hz之间，因此刺激信号的频率应小于10Hz或者大于200Hz。由于放电过程中刺激信号又需要依照采样信号(采集的肌电信号)在每个采样点一次放电，同时考虑滤波部分的截止频率，刺激信号应选择为采集的肌电信号的采样率的两倍以上。肌电信号本身的有效频率在500Hz以下，采样率为1000Hz，如果放电过程的刺激信号频率高于2000Hz，在设备放电的同时采集皮肤的肌电信号，因滤波模块对肌电信号做了带通滤波，频带选择低于1000Hz，因此可以很好的滤除设备自身的刺激信号，不让采集到的肌电信号中混入刺激信号。这种情况下，肌电信号的采集与刺激信号就不冲突，达到了采集与放电同步工作的目的。
检测电极和放电电极共用差分电极时，培训辅助设备的优选结构可以如图3中所示。
另外，培训辅助设备的结构可以采用模块化的方式，可以将采集单元及其对应的放电单元集成在一起，检测电极和放电电极共用差分电极，即将放大模块、滤波模块、压控恒流源以及差分电极集成在一块电极板上，主控单元集成在一块电极板上，这样主控单元可同时与多块电极板通讯，如图4中所示。
作为一种优选的实施方式，如图5中所示，上述的放大模块02可以采用AD8220，AD8220是噪声较小的运算放大器，共模抑制比也较优。滤波模块03可以采用LM358实现两个二阶滤波器，一个低通滤波器一个高通滤波器，从而实现带通滤波器的功能。其中低通滤波器的电阻10.7K，电容0.1uf，截止频率400Hz；高通滤波器的电阻160K，电容0.1uf，截止频率10Hz。
ADC 11可以采用ADS1298的模数转换芯片，其具有8通道24位，适用于便携式设备。另外，ADS1298包含8个低噪声PGA(programmable gain amplifier，可编程增益放大器)，8个高分辨率同步采样ADC，每通道的功耗仅为1mW，与分立实施相比，其功耗降幅高达95％，从而提高设备的便携性。
处理模块12可以采用STM32F103，它是一款常用的增强型系列微控制器，内核是32位的Cortex-M3，最高工作频率达72MHz。STM21F103内置双通道DAC，本发明中的DAC 13可以仅采用其内部一个DAC实现。
九轴传感器30可以采用MPU-9400，MPU-9400为全球首例九轴运动感测追踪组件，包括三轴陀螺仪、三轴加速度传感器和三轴磁感应传感器，是低功耗、低成本、高性能的消费性电子芯片。MPU-9400包含InvenSense的运动感测融合演算与运动校正。
为了节约处理模块主芯片固件的运算压力，减少指令执行数，通过使用MPU-9400内置的DMP(数字运动处理模块)处理三轴陀螺仪、三轴加速度传感器及三轴磁感应传感器的姿态融合解算，只需要对传感器硬件输出的机体姿态四元数参数转换成为欧拉角，即得到机体在三个轴向上的姿态角度，大大节约了硬件的运算资源，提高了系统的鲁棒性。同时利用求解得出的欧拉角，把三轴向的原始加速度值进行转换，得到从机体坐标系转换至地理坐标系下的三轴向加速度。此时在动作实施过程中前手臂运动产生的三轴向角速度、纵向垂直地面的加速度作为实时动态分析依据，给予用户直观且准确的动作效果。三轴陀螺仪、三轴加速度传感器及三轴磁感应传感器的原始数据输出与DMP处理后的融合 数据输出接口为I2C(两线式串行总线)，数据刷新频率可达200Hz，为运动控制和识别提供了较高的实时性。
多路选择模块22可以采用74LS401，74LS401是8选1的多路选择器，本发明实施例中采用其6个通道，通过处理模块12控制其三线输入端，选择输出通道。多路选择器模块22切换延时低于50ns，相对于人的肌肉运动可以忽略不计，因此多路切换的方案是可行的。
压控恒流源23可以采用LT1639，刺激信号强度最大设计为20mA，负载假设取1kΩ，要求LT1639能提供20V电压。考虑到低功耗的要求和参数要求，以及电路微型化，本实施例采用LT1639四运放芯片。LT1639使用±40V工作电压，考虑到肌电刺激的微型化、低功耗要求，选用LT1640完成电压转换。LT1640是Linear公司专为具有350mA电流限制和1.2V至40V输入电压范围的高功率系统设计，适合LT1639供电。其输入低至1V仍可工作，输出电压高达34V。
通讯单元40可以采用ESP8266，它是一个完整且自成体系的wifi网络解决方案，极大的节省了体积。
本发明提供的上述培训辅助设备所执行的培训辅助方法流程如图6所示，主要包括以下步骤：
在步骤601中，采集用户特定部位在动作实施过程中的肌电信号，对肌电信号进行放大滤波。
本步骤由培训辅助设备的采集单元执行，具体参见设备实施例中的描述，在此不再赘述。
在步骤602中，根据放大滤波后的肌电信号确定最优的肌电信号，利用最优的肌电信号形成刺激信号。
本步骤由培训辅助设备的主控单元执行，具体可以如图7中所示包括以下子步骤：
步骤701：将放大滤波后的肌电信号进行模数转换，得到数字肌电信号。
本步骤由培训辅助设备的主控单元中的ADC执行。
步骤702：对数字肌电信号进行分析比对，确定最优的肌电信号。
本步骤由主控单元中的处理模块执行，具体地，可以对数字肌电信号进行分析，得到本次动作的各项指标，例如动作的正确度、紧张感、节奏准确性等指标，具体指标可以由具体的培训项目决定。将本次动作的肌电信号与以往动作的肌电信号进行各项指标的比对，确定最优的肌电信号。
除此之外，还可以进一步结合九轴传感器采集的运动数据来确定最优的肌电信号。
步骤703：利用最优的肌电信号等效出刺激信号。
本步骤同样由主控单元中的处理模块执行，采用功率等效的方式，确定与最优的肌电信号功率匹配的周期信号，将该周期信号进行放大后作为刺激信号。优选地，该周期信号的频率是肌电信号频率的两倍以上。
上述的周期信号可以是正弦波、方波等。可以在固定的采样频率下，得到每个采样点对应的肌电信号强度，因为刺激信号的频率可能与肌电信号的频率不一致，优选是肌电信号频率的两倍以上，因此在每个采样点的间隔时间可以发射两个以上周期的刺激信号。刺激信号的功率与幅度密切相关，根据每一个周期的最优的肌电信号的强度等效成对应强度下两个周期以上的刺激信号的幅度。
在对周期信号进行放大时，采用的放大倍数G满足：V*G<R*I，其中V为最优的肌电信号的最高强度，R为人体等效电阻，I为人体无痛感下能接收的刺激电流强度。
步骤704：对刺激信号进行数模转换。
本步骤由主控单元中的DAC模块执行。
继续参见图6，在步骤603中，根据所述刺激信号形成刺激电流，并将刺激电流作用于用户特定部位。
本步骤由肌电采集设备的放电单元执行。首先将刺激信号转换成双极信号，然后将双极信号作为压控恒流源的输入信号，得到压控恒流源输出的刺激电流，最终由放电电极将刺激电流作用于用户特定部位。
本发明提供的上述培训辅助设备和培训辅助方法适用于诸如钢琴、吉他等乐器培训，也可以适用于诸如高尔夫、网球等运动类培训。
在本发明所提供的几个实施例中，应该理解到，所揭露的系统，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理模块中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能单元的形式实现。
上述以软件功能单元的形式实现的集成的单元，可以存储在一个计算机可读取存储介质中。上述软件功能单元存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)或处理模块(processor)执行本发明各个实施例所述方法的部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述仅为本发明的较佳实施例而已，并不用以限制本发明，凡在本发明的精神和原则之内，所做的任何修改、等同替换、改进等，均应包含在本发明保护的范围之内。

Claims (20)

  1. 一种培训辅助设备，其特征在于，该培训辅助设备包括：采集单元、主控单元和放电单元；
    所述采集单元，用于采集用户特定部位在动作实施过程中的肌电信号，进行放大滤波后输出给所述主控单元；
    所述主控单元，用于根据接收到的肌电信号确定最优的肌电信号，利用最优的肌电信号形成刺激信号，并将刺激信号输出给所述放电单元；
    所述放电单元，用于根据所述刺激信号形成刺激电流，并将所述刺激电流作用于用户特定部位。
  2. 根据权利要求1所述的培训辅助设备，其特征在于，所述采集单元包括：检测电极、放大模块和滤波模块；
    所述检测电极设置于用户特定部位，用于采集用户特定部位的肌电信号并输出给所述放大模块；
    所述放大模块，用于将所述肌电信号进行放大处理后输出给所述滤波模块；
    所述滤波模块，用于对所述放大模块输出的肌电信号进行滤波处理后输出给所述主控单元。
  3. 根据权利要求1所述的培训辅助设备，其特征在于，所述主控单元包括：模数转换模块、处理模块和数模转换模块；
    所述模数转换模块，用于将所述采集单元输出的肌电信号进行模数转换，得到数字肌电信号后输出给所述处理模块；
    所述处理模块，用于利用接收到的数字肌电信号确定最优的肌电信号，利用最优的肌电信号等效出刺激信号，将刺激信号输出给数模转换 模块；
    所述数模转换模块，用于对接收到的刺激信号进行数模转换后输出给所述放电单元。
  4. 根据权利要求3所述的培训辅助设备，其特征在于，该培训辅助设备还包括：通讯单元；
    所述处理模块在确定最优的肌电信号时，具体执行：将采集到的肌电信号通过所述通讯单元发送给终端设备，通过所述通讯单元获取由所述终端设备返回的刺激信号，所述刺激信号是所述终端设备对采集到的肌电信号进行分析和比对确定出最优的肌电信号后利用最优的肌电信号等效出的；或者，将采集到的肌电信号进行分析和比对后确定出最优的肌电信号，通过所述通讯单元将所述最优的肌电信号发送给终端设备，通过所述通讯单元获取由所述终端设备返回的刺激信号，所述刺激信号是所述终端设备利用所述最优的肌电信号等效出的。
  5. 根据权利要求3或4所述的培训辅助设备，其特征在于，所述处理模块在确定最优的肌电信号时，具体执行：对接收到的数字肌电信号进行分析，得到本次动作的各项指标，将本次动作的肌电信号与以往动作的肌电信号进行各项指标的比对，确定其中最优的肌电信号。
  6. 根据权利要求3所述的培训辅助设备，其特征在于，所述处理模块在利用最优的肌电信号等效刺激信号时，具体执行：确定与所述最优的肌电信号功率匹配的周期信号，将该周期信号进行放大后作为刺激信号。
  7. 根据权利要求6所述的培训辅助设备，其特征在于，所述周期信号的频率是肌电信号频率的两倍以上。
  8. 根据权利要求6所述的培训辅助设备，其特征在于，所述处理模块在对所述周期信号进行放大时采用的放大倍数G满足V*G<R*I，所述V为所述最优的肌电信号的最高强度，R为人体等效电阻，所述I为人体无痛感下能接收的刺激电流强度。
  9. 根据权利要求3所述的培训辅助设备，其特征在于，该培训辅助设备还包括：九轴传感器；
    所述九轴传感器用于采集用户的运动数据并输出给所述处理模块；
    所述处理模块，还用于进一步结合所述运动数据确定最优的肌电信号。
  10. 根据权利要求1所述的培训辅助设备，其特征在于，所述放电单元包括：正向侧加法器、压控恒流源以及放电电极；
    所述正向侧加法器，用于将所述主控单元输出的刺激信号转换成双极信号，将所述双极信号输出给所述压控恒流源；
    所述压控恒流源，用于依据输入的双极信号输出对应的刺激电流；
    所述放电电极，用于将所述压控恒流源输出的刺激电流作用于用户特定部位。
  11. 根据权利要求10所述的培训辅助设备，其特征在于，所述采集单元和所述放电单元分别存在N个通道，所述N为大于1的正整数，且所述采集单元的通道和所述放电单元的通道一一对应；
    所述放电单元还包括：多路选择模块，用于受所述主控单元的控制进行通道选择，将所述正向侧加法器输出的双极信号分时依次发送到对应通道的压控恒流源模块。
  12. 根据权利要求1所述的培训辅助设备，其特征在于，所述采集 单元中的检测电极和所述放电单元中的放电电极可以以频分的方式共用差分电极。
  13. 一种培训辅助方法，其特征在于，该培训辅助方法包括：
    采集用户特定部位在动作实施过程中的肌电信号，对所述肌电信号进行放大滤波；
    根据放大滤波后的肌电信号确定最优的肌电信号，利用最优的肌电信号形成刺激信号；
    根据所述刺激信号形成刺激电流，并将所述刺激电流作用于用户特定部位。
  14. 根据权利要求13所述的培训辅助方法，其特征在于，所述根据放大滤波后的肌电信号确定最优的肌电信号，利用最优的肌电信号形成刺激信号包括：
    将放大滤波后的肌电信号进行模数转换，得到数字肌电信号；
    对所述数字肌电信号进行分析比对，确定最优的肌电信号；
    利用最优的肌电信号等效出刺激信号；
    对所述刺激信号进行数模转换。
  15. 根据权利要求14所述的培训辅助方法，其特征在于，对所述数字肌电信号进行分析比对，确定最优的肌电信号包括：
    对所述数字肌电信号进行分析，得到本次动作的各项指标；
    将本次动作的肌电信号与以往动作的肌电信号进行各项指标的比对，确定最优的肌电信号。
  16. 根据权利要求14所述的培训辅助方法，其特征在于，所述利用最优的肌电信号等效出刺激信号包括：
    确定与所述最优的肌电信号功率匹配的周期信号，将该周期信号进行放大后作为刺激信号。
  17. 根据权利要求16所述的培训辅助方法，其特征在于，所述周期信号的频率是肌电信号频率的两倍以上。
  18. 根据权利要求16所述的培训辅助方法，其特征在于，在将所述周期信号进行放大时采用的放大倍数G满足V*G<R*I，所述V为所述最优的肌电信号的最高强度，R为人体等效电阻，所述I为人体无痛感下能接收的刺激电流强度。
  19. 根据权利要求13所述的培训辅助方法，其特征在于，该方法还包括：利用九轴传感器采集用户的运动数据，在所述确定最优的肌电信号时进一步结合所述运动数据。
  20. 根据权利要求13所述的培训辅助方法，其特征在于，根据所述刺激信号形成刺激电流包括：
    将所述刺激信号转换成双极信号；
    将所述双极信号作为压控恒流源的输入信号，得到压控恒流源输出的刺激电流。
PCT/CN2015/096532 2014-12-09 2015-12-07 一种培训辅助设备和培训辅助方法 Ceased WO2016091130A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
JP2016559257A JP6507419B2 (ja) 2014-12-09 2015-12-07 訓練支援装置及び訓練支援方法
KR1020167026312A KR20160124890A (ko) 2014-12-09 2015-12-07 훈련지원설비 및 훈련지원방법
EP15868270.8A EP3235540A4 (en) 2014-12-09 2015-12-07 Auxiliary device for training and auxiliary method for training
US15/314,918 US20170095200A1 (en) 2014-12-09 2015-12-07 Training assistance apparatus and training assistance method

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410749425.2 2014-12-09
CN201410749425.2A CN104383637B (zh) 2014-12-09 2014-12-09 一种培训辅助设备和培训辅助方法

Publications (1)

Publication Number Publication Date
WO2016091130A1 true WO2016091130A1 (zh) 2016-06-16

Family

ID=52601650

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/096532 Ceased WO2016091130A1 (zh) 2014-12-09 2015-12-07 一种培训辅助设备和培训辅助方法

Country Status (6)

Country Link
US (1) US20170095200A1 (zh)
EP (1) EP3235540A4 (zh)
JP (1) JP6507419B2 (zh)
KR (1) KR20160124890A (zh)
CN (1) CN104383637B (zh)
WO (1) WO2016091130A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108211141A (zh) * 2018-01-16 2018-06-29 南京医科大学 一种基于肌电信号反馈的闭环疼痛超声理疗系统
CN115192049A (zh) * 2022-09-14 2022-10-18 深圳市心流科技有限公司 一种智能假肢的肌电采样频率调节方法

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104383637B (zh) * 2014-12-09 2015-12-02 北京银河润泰科技有限公司 一种培训辅助设备和培训辅助方法
CN104914991A (zh) * 2015-03-17 2015-09-16 广州大学 可穿戴智能手环手势识别方法及其装置
DK3251723T3 (da) * 2016-06-03 2019-08-05 West & Berg Holding Ab Hjælpemiddel til motionstræning med stimulator
CN106991868A (zh) * 2017-05-22 2017-07-28 肇庆学院 一种基于可矫正按弦手型的吉他夹式校音器
DK3804823T3 (da) * 2017-11-28 2023-07-24 West & Bergh Holding Ab Forbedret bevægelsestræningshjælp med stimulator
CN109464145B (zh) * 2018-12-25 2024-08-02 东莞晋杨电子有限公司 一种肌电采集装置
CN112229434A (zh) * 2020-10-23 2021-01-15 福建众益太阳能科技股份公司 一种微波感应器输出波形检测器
CN112233497B (zh) * 2020-10-23 2022-02-22 郑州幼儿师范高等专科学校 一种钢琴弹奏指力练习装置
WO2022153454A1 (ja) * 2021-01-14 2022-07-21 日本電信電話株式会社 脱力支援装置、脱力支援方法、及びプログラム
CN115137974A (zh) * 2021-03-31 2022-10-04 宏碁股份有限公司 决定低周波电流强度的方法及电子装置
CN114138111B (zh) * 2021-11-11 2022-09-23 深圳市心流科技有限公司 一种肌电智能仿生手的全系统控制交互方法
CN114177525A (zh) * 2021-11-30 2022-03-15 深圳清华大学研究院 神经肌肉电刺激器及其系统
CN116173407B (zh) * 2023-03-03 2023-10-03 南京中医药大学 基于肌电信号采集和中频电刺激的镇痛仪
CN119367682A (zh) * 2025-01-02 2025-01-28 首都医科大学宣武医院 基于动作捕捉与肌电反馈的集成式康复训练系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090005700A1 (en) * 2007-06-29 2009-01-01 The Regents Of The University Of California Multi-channel myoelectrical control using single muscle
CN101391129A (zh) * 2008-07-21 2009-03-25 天津大学 基于p300信号脑机接口智能化上肢康复训练器及信号处理方法
CN102886102A (zh) * 2012-09-25 2013-01-23 深圳英智科技有限公司 镜像运动神经调制系统
CN202751692U (zh) * 2012-04-13 2013-02-27 上海诺诚电气有限公司 便携式多生理参数反馈生物刺激仪
CN103495260A (zh) * 2013-06-04 2014-01-08 东南大学 一种基于肌电信号和传感器信号实现精细实时运动的控制方法
CN104383637A (zh) * 2014-12-09 2015-03-04 北京银河润泰科技有限公司 一种培训辅助设备和培训辅助方法

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4811742A (en) * 1985-06-11 1989-03-14 Verimed, Inc. Proportional response electrical muscle stimulation
US6631297B1 (en) * 2000-05-18 2003-10-07 Seung-Kee Mo Electrical clinical apparatus and electrical stimulation method using variant assignment method
JP2002143326A (ja) * 2000-11-15 2002-05-21 Ito Choutanpa Kk 筋肉トレーニング装置
JP3443777B1 (ja) * 2002-04-18 2003-09-08 学校法人慶應義塾 電気刺激装置
KR100624424B1 (ko) * 2004-06-10 2006-09-19 삼성전자주식회사 전기자극을 이용한 건강 훈련/모니터링 장치 및 방법
US7856264B2 (en) * 2005-10-19 2010-12-21 Advanced Neuromodulation Systems, Inc. Systems and methods for patient interactive neural stimulation and/or chemical substance delivery
US9314190B1 (en) * 2006-05-11 2016-04-19 Great Lakes Neurotechnologies Inc. Movement disorder recovery system and method
US8301258B2 (en) * 2008-08-14 2012-10-30 The Chinese University Of Hong Kong Methods and devices for preventing ankle sprain injuries
JP5630858B2 (ja) * 2009-08-11 2014-11-26 株式会社身のこなしラボラトリー コードレス小型筋電バイオフィードバック装置
US10814131B2 (en) * 2012-11-26 2020-10-27 Thync Global, Inc. Apparatuses and methods for neuromodulation
CN103142400B (zh) * 2013-03-20 2014-12-31 张栋 一种膈肌康复刺激信号的产生方法及一种膈肌功能康复器
EP3038700B1 (en) * 2013-08-27 2020-03-11 Halo Neuro, Inc. Method and system for providing electrical stimulation to a user

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090005700A1 (en) * 2007-06-29 2009-01-01 The Regents Of The University Of California Multi-channel myoelectrical control using single muscle
CN101391129A (zh) * 2008-07-21 2009-03-25 天津大学 基于p300信号脑机接口智能化上肢康复训练器及信号处理方法
CN202751692U (zh) * 2012-04-13 2013-02-27 上海诺诚电气有限公司 便携式多生理参数反馈生物刺激仪
CN102886102A (zh) * 2012-09-25 2013-01-23 深圳英智科技有限公司 镜像运动神经调制系统
CN103495260A (zh) * 2013-06-04 2014-01-08 东南大学 一种基于肌电信号和传感器信号实现精细实时运动的控制方法
CN104383637A (zh) * 2014-12-09 2015-03-04 北京银河润泰科技有限公司 一种培训辅助设备和培训辅助方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3235540A4 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108211141A (zh) * 2018-01-16 2018-06-29 南京医科大学 一种基于肌电信号反馈的闭环疼痛超声理疗系统
CN115192049A (zh) * 2022-09-14 2022-10-18 深圳市心流科技有限公司 一种智能假肢的肌电采样频率调节方法

Also Published As

Publication number Publication date
CN104383637A (zh) 2015-03-04
EP3235540A1 (en) 2017-10-25
CN104383637B (zh) 2015-12-02
JP2017511501A (ja) 2017-04-20
KR20160124890A (ko) 2016-10-28
JP6507419B2 (ja) 2019-05-08
EP3235540A4 (en) 2018-08-01
US20170095200A1 (en) 2017-04-06

Similar Documents

Publication Publication Date Title
CN104383637B (zh) 一种培训辅助设备和培训辅助方法
Mao et al. A health monitoring system based on flexible triboelectric sensors for intelligence medical internet of things and its applications in virtual reality
Costanza et al. Toward subtle intimate interfaces for mobile devices using an EMG controller
Milosevic et al. Design challenges for wearable EMG applications
CN110354387B (zh) 多触发方式的智能电刺激手部训练器及方法
CN104107134A (zh) 基于肌电反馈的上肢训练方法及系统
CN215017698U (zh) 康复训练运动模拟可视化系统
CN103495260B (zh) 一种基于肌电信号和传感器信号实现精细实时运动的控制方法
CN107981997B (zh) 一种基于人脑运动意图的智能轮椅控制方法及系统
CN107589782A (zh) 用于可穿戴设备的姿势控制接口的方法和装置
CN107456743A (zh) 运动指导方法及系统
CN107861628A (zh) 一种基于人体表面肌电信号的手部姿态识别系统
CN111317600A (zh) 一种假肢控制方法、装置、系统、设备和存储介质
CN104267807A (zh) 基于手部动作肌音信号的人机交互方法及交互系统
Simić et al. Wearable device for personalized EMG feedback-based treatments
Cannan et al. A wearable sensor fusion armband for simple motion control and selection for disabled and non-disabled users
Wu et al. A wireless surface EMG acquisition and gesture recognition system
CN110808091B (zh) 基于虚拟现实视听觉通路的感觉统合失调测训系统
Zhang et al. The HCI method for upper limb disabilities based on EMG and gyros
Matiuk et al. EMG pattern recognition for thumb muscle states using wearable sensing and adaptive neural network
Xu et al. A wearable, real-time sEMG gesture classifier based on E-tattoo and CDF-CNN for prosthetic control
Carrino et al. Gesture segmentation and recognition with an EMG-based intimate approach-an accuracy and usability study
Edlinger et al. Architectures of laboratory-PC and mobile pocket PC brain-computer interfaces
Troka et al. A biofeedback system that uses the game to study electrical muscle activity
Kubaščík et al. 6-channel band for advanced myoelectric signal analysis

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: 15868270

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2016559257

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 20167026312

Country of ref document: KR

Kind code of ref document: A

REEP Request for entry into the european phase

Ref document number: 2015868270

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2015868270

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 15314918

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE