Muscle activity detection method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of physiological detection, and discloses a muscle activity detection method and device, computer equipment and a storage medium, and the method comprises the steps: collecting a target electromyographic signal; feature points in a first electromyographic signal segment and a second electromyographic signal segment in the target electromyographic signal are obtained, the duration of the first electromyographic signal segment is longer than that of the second electromyographic signal segment, and the end points of the first electromyographic signal segment and the second electromyographic signal segment are the same; and determining the activity state information of the target muscle based on the relationship between the feature points in the second electromyographic signal segment and the feature points in the first electromyographic signal segment. The accuracy of muscle activity detection can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of physiological detection, and particularly to a method and device for detecting muscle activity, a computer device, and a storage medium. Background Art

[0002] Muscle movement generates corresponding electromyogram (EMG) signals. Therefore, theoretically, it is feasible to detect muscle activity based on EMG signals. Detecting muscle activity is also a type of detection required in multiple technical fields. For example, in the field of virtual reality, detecting muscle activity can better achieve human-computer interaction. Another example is in the medical field. Uterine contractions, as an important indicator for childbirth monitoring, run through the entire childbirth process. During labor, insufficient uterine contractions may lead to an unsmooth progress of labor; however, if uterine activity is too strong, it may lead to insufficient placental blood perfusion, and even fetal hypoxia and acidosis, resulting in adverse maternal and fetal outcomes. Therefore, paying attention to the situation of uterine contractions throughout the labor process and taking corresponding intervention measures in a timely manner play a crucial role in reversing adverse maternal and fetal outcomes. That is to say, accurately determining the activity of uterine smooth muscle is crucial during childbirth. However, currently, it is still difficult to accurately determine the information related to muscle activity based on EMG signals. For example, the detection accuracy of the active segment is still not high. Summary of the Invention

[0003] In view of this, the present invention provides a method and device for detecting muscle activity, a computer device, and a storage medium to solve the problem of low accuracy in detecting muscle activity.

[0004] In a first aspect, the present invention provides a method for detecting muscle activity, the method comprising:

[0005] Collecting a target EMG signal;

[0006] Respectively obtaining characteristic points in a first EMG signal segment and a second EMG signal segment in the target EMG signal, the duration of the first EMG signal segment is greater than that of the second EMG signal segment, and the end points of the first EMG signal segment and the second EMG signal segment are the same;

[0007] Based on the relationship between the characteristic points in the second EMG signal segment and the characteristic points in the first EMG signal segment, determining the activity state information of the target muscle.

[0008] In an optional implementation manner, the characteristic point is an extreme point;

[0009] Respectively obtaining characteristic points in a first EMG signal segment and a second EMG signal segment in the target EMG signal, comprising:

[0010] Obtaining the amplitude mean of the first EMG signal segment;

[0011] Obtain the extreme points in the second EMG signal segment whose amplitudes are greater than or equal to the mean amplitude.

[0012] In an optional implementation manner, based on the relationship between the feature points in the second EMG signal segment and the feature points in the first EMG signal segment, determine the activity state information of the target muscle, including:

[0013] If the ratio of the number of feature points in the current second EMG signal segment to the number of feature points in the current first EMG signal segment is greater than the first preset threshold, it is determined that the target muscle is in the starting state of activity.

[0014] In an optional implementation manner, based on the relationship between the feature points in the second EMG signal segment and the feature points in the first EMG signal segment, determine the activity state information of the target muscle, including:

[0015] For the second EMG signal segment after detecting that the target muscle is in the starting state of activity, if the proportion of the signals with amplitudes greater than the target mean amplitude in the current second EMG signal segment is less than the termination threshold, it is determined that the target muscle is in the ending state of activity;

[0016] Wherein, the target mean amplitude is the mean amplitude of the first EMG signal segment when it is determined that the target muscle is in the starting state of activity.

[0017] In an optional implementation manner, after collecting the target EMG signal, it further includes:

[0018] Calculate the energy envelope value of the target EMG signal;

[0019] Fit the calculated energy envelope value;

[0020] Determine the first contraction intensity of the target muscle based on the fitted value.

[0021] In an optional implementation manner, calculating the energy envelope value of the target EMG signal includes:

[0022] Obtain the EMG signal at the first moment and the EMG signals within a preset duration before the first moment from the target EMG signal;

[0023] Calculate the energy values of the EMG signals within the preset duration and the EMG signal at the first moment as the energy envelope value at the first moment.

[0024] In an optional implementation manner, the activity state information includes at least one of the activity start time, activity end time, contraction intensity, contraction intensity peak, contraction duration, contraction area, contraction frequency, contraction average intensity, average contraction duration, median frequency, and sample entropy.

[0025] In an optional implementation manner, the method further includes:

[0026] Receive the operation of the user;

[0027] Determine the activity status information item according to the operation of the user.

[0028] In an optional implementation manner, the method further includes:

[0029] Display the activity status information of the target muscle and the target EMG signal on the same screen.

[0030] In a second aspect, the present invention provides a muscle activity detection device, and the device includes:

[0031] An acquisition module, configured to acquire a target EMG signal;

[0032] An acquisition module, configured to respectively acquire feature points in a first EMG signal segment and a second EMG signal segment in the target EMG signal, the duration of the first EMG signal segment is greater than that of the second EMG signal segment, and the endpoints of the first EMG signal segment and the second EMG signal segment are the same;

[0033] A determination module, configured to determine the activity status information of the target muscle based on the relationship between the feature points in the second EMG signal segment and the feature points in the first EMG signal segment.

[0034] In a third aspect, the present invention provides a computer device, including: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the muscle activity detection method according to the first aspect or any corresponding implementation manner thereof.

[0035] In a fourth aspect, the present invention provides a computer-readable storage medium, and computer instructions are stored on the computer-readable storage medium, and the computer instructions are used to cause a computer to execute the muscle activity detection method according to the first aspect or any corresponding implementation manner thereof.

[0036] The muscle activity detection method provided by the present invention determines muscle activity through the relationship between the feature points in the current electromyogram (EMG) signal segment and the feature points in a longer EMG signal segment including the current EMG signal segment, improving the accuracy of muscle activity detection. When the muscle activity detection method provided by the present invention is applied to uterine contraction (uterine contraction) activity monitoring, it can not only achieve safe and stable monitoring of uterine contraction conditions, but also accurately obtain various relevant parameters (i.e., activity status information) of uterine contractions. Specifically, by collecting surface electrical signals on the surface of a pregnant woman's body through surface electrodes, problems such as increased infection possibility and the need for amniotic membrane rupture monitoring brought by invasive monitoring devices are avoided, providing a safe monitoring method. Moreover, the surface uterine electrical signal originates from the electrical activity of the maternal uterine smooth muscle, is not affected by factors such as the obesity degree of the pregnant woman, monitoring posture, and straps, and does not emit energy to the mother's body, enabling safe and stable monitoring for a long time. When the embodiments of the present invention are applied to the muscle activity detection of skeletal muscle, it can be used to detect the activation of skeletal muscle and calculate the characteristic parameter values of skeletal muscle EMG (which belong to activity status information) to analyze the activation pattern of skeletal muscle. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0038] Figure 1 is a schematic flowchart of the muscle activity detection method according to an embodiment of the present invention;

[0039] Figure 2 is a schematic sliding window diagram for obtaining the first EMG signal segment and the second EMG signal segment according to an embodiment of the present invention;

[0040] Figure 3 is a schematic flowchart of another muscle activity detection method according to an embodiment of the present invention;

[0041] Figure 4 is a schematic diagram of the uterine EMG monitoring interface according to an embodiment of the present invention;

[0042] Figure 5 is a schematic diagram of another uterine EMG monitoring interface according to an embodiment of the present invention;

[0043] Figure 6 is a schematic diagram of another uterine EMG monitoring interface according to an embodiment of the present invention;

[0044] Figure 7It is a structural block diagram of a muscle activity detection device according to an embodiment of the present invention;

[0045] Figure 8 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Specific embodiments

[0046] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0047] The muscle activity detection method provided by the embodiments of the present invention can be applicable to the activity detection of uterine muscles. The activities of uterine muscles mainly refer to uterine contractions. Currently, the detection methods mainly include palpation, internal monitoring, and external monitoring. Among them, manual palpation is easy to implement, but the threshold of palpation is affected by the thickness of the pregnant woman's abdominal wall, the degree of muscle tension, and the work experience of obstetric medical staff. Moreover, it is difficult to touch both the onset and regression stages of uterine contractions with relatively low intrauterine pressure. Therefore, important parameters such as the accurate intensity and duration of uterine contractions cannot be known through palpation. With the development of electronic technology, continuous quantitative detection of uterine contractions through electronic monitoring devices has become a reality. Internal monitoring mainly uses an intrauterine pressure catheter (IUPC) equipped with a pressure sensor placed on the presenting part of the fetus to accurately measure the pressure data in the uterine cavity. The IUPC detection method has high accuracy and is therefore regarded as the gold standard for uterine contraction activity detection. However, this method is an invasive detection. Implementing internal monitoring requires amniotic membrane rupture and placement of the detection catheter, which increases the risk of intrauterine infection and may cause complications such as uterine perforation, fetal bleeding injury, and even placental abruption. In recent years, external tocodynamometry (TOCO) has often been used clinically to monitor uterine contractions by detecting changes in the shape of the uterine abdominal wall through a uterine contraction pressure probe strapped to the abdomen. This method is non-invasive and easy to operate, but the detection results are affected by various factors: the obesity degree of the pregnant woman, the placement position of the probe, and the tightness of the elastic bandage all affect the accuracy of the detection results.

[0048] Aiming at the deficiencies in the current uterine activity monitoring technology, the surface myoelectric signals of the uterine muscles on the abdominal wall of pregnant women collected by surface electrode patches can be used to non-invasively obtain stable uterine activity conditions.

[0049] The muscle activity detection method provided by the embodiments of the present invention can also be applicable to the activity detection of skeletal muscles.

[0050] In addition, in view of the problem of low accuracy in detecting muscle activity based on electromyography signals at present, the embodiments of the present invention provide a muscle activity detection method that can improve the accuracy of detecting muscle activity based on electromyography signals.

[0051] According to the embodiments of the present invention, an embodiment of a muscle activity detection method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0052] In this embodiment, a muscle activity detection method is provided, which can be used in a computer device. Figure 1 is a flowchart of the muscle activity detection method according to the embodiments of the present invention, as Figure 1 shown, the process includes the following steps:

[0053] Step S101, collect target electromyography signals.

[0054] Specifically, a non-invasive surface electrode (Surface Electrode, a conductive device placed on the skin surface for stimulating or recording electrical signals) can be attached to the skin surface closest to the target muscle or other skin surfaces more suitable for collecting the electromyography signals of the target muscle, and then the skin surface electrical signals are collected and converted into digital signals, so as to safely and stably obtain and record real-time surface electrical signals. For example, if the target muscle is the uterine muscle, then it is attached to the maternal abdominal wall corresponding to the uterus, and the surface electrical signals of the maternal abdominal wall are collected and converted into digital signal data, and real-time surface electrical signals are safely and stably obtained and recorded. The surface electrode can be a single-channel electrode or a multi-channel electrode.

[0055] In addition, since the surface electrical signals collected by the surface electrode may contain many other electrical signals in addition to the electromyography signals of the target muscle, it is necessary to perform filtering processing on them before using them as target electromyography signals. For example, if a surface electrode is used to collect the surface electrical signals of the maternal abdominal wall, in addition to the collected uterine electromyography, it also contains many other physiological electrical signals of the mother or fetus, such as maternal electrocardiogram, fetal electrocardiogram, maternal skeletal muscle electromyography, etc. In addition, there are also some motion artifact interferences and power frequency interferences, etc., but there are large band differences between these interferences and the main components of the uterine electromyography. Therefore, a band-pass filter can be used to filter out the interference signals and separate the pure uterine electromyography signals from the surface electrical signals of the pregnant woman's abdominal wall as the target electromyography signals.

[0056] Step S102: Obtain the feature points in the first EMG signal segment and the second EMG signal segment in the target EMG signal respectively. The duration of the first EMG signal segment is greater than that of the second EMG signal segment. Please refer to Figure 2 , the end points of the first EMG signal segment (with a duration of W1) and the second EMG signal segment (with a duration of W2) are the same.

[0057] Among them, the feature points can specifically be extreme points, points satisfying the preset threshold range limit, zero-crossing points or zero-crossing points after threshold removal. The zero-crossing points after threshold removal can be the zero-crossing points after subtracting or adding a preset value to each point in the EMG signal segment. A zero-crossing point refers to a point where the signal value of the previous point is greater than zero and the signal value of the next point is less than zero, or the signal value of the previous point is less than zero and the signal value of the next point is greater than zero.

[0058] Specifically, please refer to Figure 2 , two sliding windows (with durations of W1 and W2 respectively) can be set. The sliding step sizes of the two sliding windows are the same, and the window length of one sliding window is equal to the duration of the first EMG signal segment, so that the first EMG signal segment (the EMG signal segment within the sliding window with a longer window length is the first EMG signal segment) can be obtained from the target EMG signal, and the window length of the other sliding window is equal to the duration of the second EMG signal segment, so that the second EMG signal segment (the EMG signal segment within the sliding window with a shorter window length is the second EMG signal segment) can be obtained from the target EMG signal. If it is to detect the muscle activity situation in real time based on the target EMG signal collected in real time, then the last point of the two sliding windows can both be the current real-time sampling point.

[0059] Step S103: Determine the activity state information of the target muscle based on the relationship between the feature points in the second EMG signal segment and the feature points in the first EMG signal segment.

[0060] The relationship between the feature points in the second EMG signal segment and the feature points in the first EMG signal segment can be the ratio of quantities, the ratio of the maximum signal values of the feature points, the ratio of the sum of the energies of the feature points, etc. For example, when the muscle is contracting, the EMG shows a dense peak electrical activity signal and there is an obvious increase in amplitude. The muscle activity can be determined by the ratio of the number of extreme points in the current EMG signal segment to the number of extreme points in a longer EMG signal segment including the current EMG signal segment.

[0061] The activity state information includes at least one of the activity start time, activity end time, contraction intensity (referring to the contraction intensity during the muscle activity stage, that is, the contraction intensity between the activity start time and the activity end time), peak contraction intensity, contraction duration, contraction area, contraction frequency, average contraction intensity, average contraction duration, median frequency, sample entropy, etc.

[0062] The main difficulty in determining muscle activity based on electromyogram (EMG) signals lies in the difficulty of distinguishing whether the muscle is in an active state and the accurate start and end times of the activity. The muscle activity detection method provided in this embodiment determines muscle activity through the relationship between the feature points in the current EMG signal segment and the feature points in a longer EMG signal segment including the current EMG signal segment, improving the accuracy of muscle activity detection. When the muscle activity detection method provided in the embodiments of the present invention is applied to the monitoring of uterine contractions (uterine contractions), it can not only achieve safe and stable monitoring of uterine contraction conditions, but also accurately obtain various relevant parameters (i.e., activity state information) of uterine contractions. Specifically, by collecting surface electrical signals on the body surface of pregnant women through surface electrodes, problems such as increased infection possibility and the need for amniotic membrane rupture monitoring brought by invasive monitoring devices are avoided, providing a safe monitoring approach. And the surface uterine electrical signal originates from the electrical activity of the maternal uterine smooth muscle, is not affected by factors such as the obesity degree of pregnant women, monitoring posture, and straps, and does not emit energy to the mother body, and can be monitored safely and stably for a long time. When the embodiments of the present invention are applied to the detection of muscle activity of skeletal muscle, it can be used to detect the activation of skeletal muscle, and can also calculate the characteristic parameter values of skeletal muscle EMG (belonging to activity state information) to analyze the activation pattern of skeletal muscle.

[0063] In this embodiment, a muscle activity detection method is provided, which can be used in computer devices, etc. Figure 3 It is a flowchart of the muscle activity detection method according to the embodiments of the present invention, as Figure 3 shown, and this process includes the following steps:

[0064] Step S201, collect the target EMG signal. For details, please refer to Figure 1 Step S101 of the embodiment shown, which will not be elaborated here.

[0065] Step S202, respectively obtain the feature points in the first EMG signal segment and the second EMG signal segment in the target EMG signal. The duration of the first EMG signal segment is greater than that of the second EMG signal segment, and the endpoints of the first EMG signal segment and the second EMG signal segment are the same.

[0066] Here, the number of extreme value points in the first EMG signal segment and the second EMG signal segment in the target EMG signal can be respectively obtained.

[0067] Specifically, the above step S202 includes:

[0068] Step S2021, obtain the amplitude mean RES of the first EMG signal segment. The specific calculation formula is as follows:

[0069]

[0070] Among them, i is the sampling point (time) number of the first electromyogram signal segment, EHG is the electromyogram signal amplitude, and W1 is the total number of sampling points (duration) of the first electromyogram signal segment.

[0071] Step S2022: Count the number of extreme points in the second electromyogram signal segment whose amplitude is greater than or equal to the average amplitude.

[0072] Considering that there may be peak electrical activity signals in the muscle in the inactive state, but the amplitude in this case is generally small. Therefore, this embodiment can exclude this situation based on the amplitude to further improve the accuracy of muscle activity detection.

[0073] Step S203: Determine the activity state information of the target muscle based on the relationship between the feature points in the second electromyogram signal segment and the feature points in the first electromyogram signal segment.

[0074] Specifically, the activity state information of the target muscle can be determined based on the ratio of the number of extreme points in the second electromyogram signal segment to the number of extreme points in the first electromyogram signal segment.

[0075] The ratio PER of the number of extreme points in the second electromyogram signal segment (here it refers to the number of extreme points in the second electromyogram signal segment whose amplitude is greater than or equal to the average amplitude) to the number of extreme points in the first electromyogram signal segment is:

[0076]

[0077] Among them, j is the sampling point (time) number of the second electromyogram signal segment, and W2 is the total number of sampling points (duration) of the second electromyogram signal segment.

[0078] Specifically, the above step S203 includes:

[0079] Determining the activity state information of the target muscle based on the relationship between the feature points in the second electromyogram signal segment and the feature points in the first electromyogram signal segment includes:

[0080] If the ratio of the number of feature points in the current second electromyogram signal segment to the number of feature points in the current first electromyogram signal segment is greater than the first preset threshold, it is determined that the target muscle is in the starting state of activity.

[0081] The feature points here can be extreme points.

[0082] Two sliding windows can be set here. The sliding steps of the two sliding windows are the same, and the window length of one sliding window is equal to the duration W1 of the first EMG signal segment, so that the first EMG signal segment can be obtained from the target EMG signal. The window length of the other sliding window is equal to the duration W2 of the second EMG signal segment, so that the second EMG signal segment can be obtained from the target EMG signal. If the muscle activity is detected in real time based on the real-time acquired target EMG signal, then the last points of the two sliding windows can both be the current real-time sampling points. Then, calculate the ratio of the number of extreme points in the EMG signal segments within the two sliding windows each time they slide in sequence (specifically, the ratio of the number of extreme points in the second EMG signal segment to the number of extreme points in the first EMG signal segment). If the ratios statistically obtained from multiple initial slides are all less than the second preset threshold TH2, and then the ratio statistically obtained from one slide is greater than the first preset threshold TH1, then it can be considered that the second EMG signal segment obtained from that slide is the EMG signal corresponding to the starting segment of the activity. Specifically, the starting point of the second EMG signal segment can be used as the starting moment of the muscle activity.

[0083] In other alternative specific implementation manners, the above step S203 includes:

[0084] If the ratio of the number of extreme points in the current second EMG signal segment to the number of extreme points in the current first EMG signal segment is greater than the first preset threshold TH1, and the ratios of the number of extreme points in the historical second EMG signal segment to the number of extreme points in the historical first EMG signal segment are all less than the second preset threshold TH2, then it is determined that the target muscle is in the starting state of activity. Among them, the time difference between the end point of the historical second EMG signal segment and the end point of the current second EMG signal segment is not greater than the preset duration threshold; the first preset threshold is greater than or equal to the second preset threshold. Here, considering that muscle activity is in batches, for example, uterine contractions occur one by one, each lasting for a period of time and then ending, and there is an interval between adjacent uterine contractions. When judging the starting state of muscle activity, it is necessary to ensure that the muscle is first in a static state and then in an active state. If only judging that the muscle is in an active state, then at this time it may not be the start of muscle activity, and the starting moment of muscle activity may be at an earlier moment. Therefore, here it is necessary to judge whether the most recent EMG signal segment represents that the muscle is in an active state, that is, to judge whether the ratio of the number of feature points in the historical second EMG signal segment to the number of feature points in the historical first EMG signal segment is less than the second preset threshold TH2, and the preset duration threshold of the time difference between the end point of the historical second EMG signal segment and the end point of the current second EMG signal segment can be determined according to the time interval between adjacent activities of the target muscle.

[0085] Specifically, the above step S203 may further include:

[0086] For the second EMG signal segment after detecting that the target muscle is in the starting state of activity, if the proportion of signals with amplitudes greater than the target amplitude mean value in the current second EMG signal segment is less than the termination threshold, it is determined that the target muscle is in the ending state of activity;

[0087] Among them, the target amplitude mean value is the amplitude mean value of the first EMG signal segment when it is determined that the target muscle is in the starting state of activity.

[0088] That is to say, after determining the start of muscle activity, the method for judging whether the muscle activity ends is different from the method for judging whether the muscle activity starts. Moreover, when determining the start of muscle activity, if the number of extreme points in the second EMG signal segment refers to the number of extreme points with amplitudes greater than or equal to the amplitude mean value in the second EMG signal segment, then there is no need to recalculate the amplitude mean value when judging whether the muscle activity ends. Specifically, the start time or end time of the second EMG signal segment on which the end of muscle activity is determined can be used as the end time of muscle activity.

[0089] In addition, the specific values of the first preset threshold and the second preset threshold need to consider the ratio of the duration of the second EMG signal segment to the duration of the first EMG signal segment.

[0090] In other optional specific implementation manners, after collecting the target EMG signal, it further includes:

[0091] Step S104, calculating the energy envelope value of the target EMG signal; see the following for details.

[0092] Step S105, fitting the calculated energy envelope value;

[0093] Specifically, the fitting method can be a sine function, an S-shaped function, a logarithmic function, or a composite function. For uterine EMG, when selecting a fitting function, it is necessary to make the fitted envelope curve have a good correlation with the uterine contractions collected by the contraction gold standard IUPC in terms of contraction frequency, contraction intensity, and contraction duration as much as possible.

[0094] Step S106, determining the first contraction intensity of the target muscle based on the fitting value. This first contraction intensity is the contraction intensity directly obtained from the target EMG signal and does not distinguish between muscle activity segments and non-activity segments (i.e., resting segments). When this first contraction intensity is plotted as a curve, it is continuous on the time axis.

[0095] The muscle activity detection method provided by the embodiments of the present invention, when detecting uterine contractions, determines the contraction intensity by extracting the envelope information of uterine EMG, which has higher consistency with the intrauterine pressure detected by IUPC.

[0096] In some optional implementation manners, calculating the energy envelope value of the target EMG signal includes:

[0097] Obtain the EMG signal at the first moment and the EMG signal within a preset time duration before the first moment from the target EMG signal;

[0098] Calculate the energy values of the EMG signal within the preset time duration and the EMG signal at the first moment as the energy envelope value at the first moment.

[0099] Specifically, a sliding window L can be set, and then the energy value of the EMG signal segment within the sliding window L can be calculated as the envelope value, specifically as the envelope value Envelope at the end point of the sliding window L. The energy envelope calculation formula is:

[0100]

[0101] where l is the sampling point (moment) number within the sliding window L, and L is the total number of sampling points within the sliding window L.

[0102] In the embodiments of the present invention, the activity state information includes at least one of the activity start moment, activity end moment, contraction intensity (referring to the contraction intensity during the muscle activity stage), peak contraction intensity, contraction duration, contraction area, contraction frequency, average contraction intensity, average contraction duration, median frequency, and sample entropy. Of course, the activity state information may also include other time-frequency domain or entropy feature parameter values, such as amplitude mean, root mean square value, average frequency, etc., as well as average time-frequency domain or entropy feature parameter values.

[0103] When implementing uterine contraction detection, the uterine contraction start moment, uterine contraction end moment, contraction intensity, peak contraction intensity, contraction duration, contraction area, contraction frequency, average contraction intensity, average contraction duration, etc. can quantitatively reflect the uterine contraction situation, facilitating medical staff to intuitively observe the uterine activity of pregnant women.

[0104] Among them, the median frequency MF can be calculated by the following formula:

[0105]

[0106] where k is the sampling point number, start is the activity start moment number, end is the activity end moment number, f k is the EMG signal frequency, and P k is the EMG signal power spectral value.

[0107] The sample entropy can be calculated in the following manner:

[0108] Ⅰ. Obtain the EMG signals as u(1), u(2), …, u(N), define the comparison vector dimension m, and the similarity metric value r;

[0109] II. Reconstruct the m-dimensional vectors X(1), X(2), …, X(N - m + 1), where X(i) = [u(i), u(i + 1), …, u(i + m - 1)]; for 1 ≤ i ≤ N - m + 1, count the number of vectors that satisfy the following conditions:

[0110]

[0111] where d|X, X * | is defined as d|X, X * | = max|u(a) - u * (a)|, X ≠ X * ; u(a) is an element when the vector is X, d represents the distance between the vectors X(i) and X(j), and the value range of j is determined by the maximum value of the corresponding elements [1, N - m = 1], but i ≠ j;

[0112] III. Calculate the average value for all i values, denoted as B m (r), that is:

[0113]

[0114] IV. Let k = m + 1, repeat step II to obtain the sample entropy

[0115] Through the above-described solution, the start time of the activity, the end time of the activity, and the contraction intensity can be obtained. Moreover, the contraction intensity of the target muscle determined based on the fitting value is a contraction intensity that changes with time. Therefore, the maximum contraction value between the start time of the activity and the end time of the activity can be obtained as the contraction peak value. The activity duration of this muscle activity can also be calculated based on the start time of the activity and the end time of the activity, and the contraction area can be calculated based on the activity duration and the contraction intensity. Furthermore, the contraction frequency, the average contraction intensity, and the average contraction duration within the monitoring period can be calculated. For uterine activity monitoring, these parameters are relatively important clinical data.

[0116] In addition, the embodiments of the present invention can also exclude some muscle activity segments according to the obtained activity state information. For example, for uterine contractions, if the calculated uterine contraction peak value is small or the uterine contraction duration is short, it is considered not a uterine contraction activity.

[0117] In some optional specific embodiments, the method provided by the embodiments of the present invention further includes:

[0118] Simultaneously display the activity state information of the target muscle and the target electromyogram signal on the same screen. Among them, the target electromyogram signal can be displayed in the form of a graph, and some parameter items (such as the contraction intensity) in the activity state information can also be displayed in the form of a graph.

[0119] Specifically, the target EMG signal and the first contraction intensity curve obtained based on the envelope information of the target EMG signal can be simultaneously displayed on the interface. For the contraction intensity between the activity start time and the activity end time in the first contraction intensity, it can be marked by means such as highlighting and specified colors. In this way, the user can not only observe and analyze the activity state information of the target muscle but also observe the target EMG signal for comprehensive judgment. Here, taking the detection of uterine contraction (i.e., labor contraction) activity as an example, the isolated pure uterine EMG signal and the calculated labor contraction intensity curve can be recorded and traced in real time on the uterine EMG monitoring interface. When clinically collecting and recording uterine EMG, some medical staff need the labor contraction intensity curve to reflect the true labor contraction frequency and intensity of the pregnant woman. For example, during the labor process, the change in abdominal wall pressure may be caused by the pregnant woman's exertion. Whether it is IUPC or TOCO, it is impossible to distinguish between the pregnant woman's exertion and the true labor contraction. Since uterine EMG collects the EMG signal of the uterine smooth muscle, it will not be unable to judge the true labor contraction due to the pregnant woman's exertion. And some medical staff need to focus on the uterine EMG signal itself to obtain more relevant information. For example, for pregnant women with threatened preterm labor in the second trimester, in addition to observing the labor contraction of the pregnant woman, the characteristics of uterine EMG also need to be concerned. Compared with the uterine EMG signal of normal pregnant women in labor, the uterine EMG signal of pregnant women with threatened preterm labor symptoms shows more irregularity, with an average frequency not concentrated and a low sample entropy. Just showing the labor contraction intensity cannot reflect the uterine EMG characteristics corresponding to the labor contraction and is not sufficient to provide more useful information for doctors. Therefore, as Figure 4 shown, the simultaneous display of the uterine EMG signal and the calculated labor contraction intensity curve helps to provide intuitive labor contraction conditions and detailed uterine EMG characteristic information for medical staff. In addition, when actually collecting the uterine EMG signal to calculate the labor contraction intensity, the uterine EMG signal will inevitably be interfered by certain signals, resulting in an obvious change in the amplitude of the signal. When only calculating and displaying the labor contraction intensity curve, this part of the interference is very likely to be introduced into the calculation and lead to an untrue labor contraction waveform. As Figure 5 shown by the dashed box in, but when the labor contraction intensity curve and the uterine EMG signal are displayed on the same screen and combined with uterine EMG analysis, it can be clearly seen that the waveform characteristics of the uterine EMG signal in this section are significantly different from those of the uterine EMG during true labor contraction. Thus, it can help medical staff exclude untrue labor contractions caused by interference to reflect the true uterine activity of the pregnant woman. At the same time, other activity state information other than the contraction intensity can also be displayed. The specific steps can be as follows:

[0120] Step 1: Enter the information of the pregnant woman under monitoring, such as name, age, and gestational week, on the real-time uterine EMG monitoring interface, record and display it on the monitoring interface, which is also convenient for offline viewing after the monitoring is completed.

[0121] Step 2: Display the traced curves of the uterine myoelectric signals and the uterine contraction intensity on the real-time monitoring interface of uterine myoelectricity respectively. The uterine contraction intensity curve is above the uterine myoelectric signal curve and aligned according to the acquisition time, so that the uterine myoelectric signal value and its corresponding uterine contraction intensity at the corresponding time point can be observed.

[0122] Step 3: When tracing the uterine myoelectricity and uterine contraction intensity curves, highlight the uterine myoelectric signals and uterine contraction intensity curves during the corresponding uterine contractions according to the calculated starting time (the start moment of the contraction activity) and ending time (the end moment of the contraction activity) of the uterine contractions, so as to prompt in real time that there is a uterine contraction during this period. Mark the time and intensity corresponding to the peak value of the uterine contraction, and display the time-frequency domain parameters and non-linear characteristic parameters, etc. of the uterine contraction in the uterine myoelectricity analysis window. Display the calculated characteristic parameters (belonging to the activity state information) corresponding to the uterine contraction beside the uterine myoelectric signal on the display screen. The characteristic parameters include but are not limited to the duration, uterine contraction area, median frequency, average frequency, sample entropy, etc.

[0123] In addition, for uterine contraction detection, the external uterine contraction pressure value can also be collected and displayed on the same screen as the uterine myoelectric signal value to exclude false uterine contraction waves caused by interference of the external uterine contraction pressure or uterine myoelectricity, and improve the accuracy of uterine contraction monitoring.

[0124] The embodiment of the present invention can visually display the myoelectric signal and the muscle activity-related parameters obtained based on the myoelectric signal.

[0125] In some optional specific embodiments, the method provided by the embodiment of the present invention further includes:

[0126] Receiving the operation of the user;

[0127] Determining the activity state information item according to the operation of the user.

[0128] In this embodiment, since there are many types of activity state information, but different users may be concerned about different activity state information. Therefore, specific activity state information items are designed here for the user to select. For the activity state information items not selected by the user, there is no need to calculate, display, or only calculate but not display.

[0129] That is, the specific activity state information items (which can also be called parameter items) to be displayed can be determined according to the selection instruction of the operator, and then calculated and displayed. For example, as Figure 6 shown, medical staff select the uterine contraction and uterine myoelectricity-related parameters to be concerned on the uterine myoelectricity display interface. This is because different medical staff need to be concerned about different parameters.

[0130] Further, due to the individual differences in the amplitude of EMG, and in order to observe more details of EMG signals, the display interface can also be set with a function to adjust the display amplitude range. By adjusting the amplitude range, it is possible to observe the overall change of the EMG amplitude and also magnify the local change trend of the EMG curve.

[0131] On the real-time EMG display interface, it is also possible to select an EMG signal segment according to requirements for calculation and analysis to obtain corresponding parameter values. For example, select a non-contraction segment or a signal segment containing contractions for overall analysis of uterine EMG over a long period of time, realizing the analysis of uterine EMG characteristic parameters not limited to the contraction segment.

[0132] In this embodiment, a muscle activity detection device is also provided. This device is used to implement the above-mentioned embodiments and preferred implementation manners, and those that have been described will not be repeated. As used hereinafter, the term "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0133] This embodiment provides a muscle activity detection device, as Figure 7 shown, including:

[0134] An acquisition module 601, configured to acquire target EMG signals;

[0135] An obtaining module 602, configured to respectively obtain characteristic points in a first EMG signal segment and a second EMG signal segment in the target EMG signals. The duration of the first EMG signal segment is greater than that of the second EMG signal segment, and the endpoints of the first EMG signal segment and the second EMG signal segment are the same;

[0136] A determination module 603, configured to determine the activity state information of the target muscle based on the relationship between the characteristic points in the second EMG signal segment and the characteristic points in the first EMG signal segment.

[0137] In some alternative implementation manners, the characteristic points are extreme points; the obtaining module 602 includes:

[0138] An amplitude mean obtaining unit, configured to obtain the amplitude mean of the first EMG signal segment;

[0139] An obtaining unit, configured to obtain the extreme points in the second EMG signal segment whose amplitudes are greater than or equal to the amplitude mean.

[0140] In some alternative implementation manners, the determination module 603 includes:

[0141] A starting determination unit, configured to determine that the target muscle is in an active starting state when the ratio of the number of feature points in the current second electromyogram signal segment to the number of feature points in the current first electromyogram signal segment is greater than a first preset threshold.

[0142] In some alternative embodiments, the determination module 603 includes:

[0143] An ending determination unit, configured to determine that the target muscle is in an active ending state when the proportion of signals with amplitudes greater than the target amplitude mean value in the current second electromyogram signal segment is less than an ending threshold, and the current second electromyogram signal segment is an electromyogram signal segment after detecting that the target muscle is in an active starting state;

[0144] Wherein, the target amplitude mean value is the amplitude mean value of the first electromyogram signal segment when determining that the target muscle is in an active starting state.

[0145] In some alternative embodiments, the device further includes:

[0146] A calculation module, configured to calculate the energy envelope value of the target electromyogram signal;

[0147] A fitting module, configured to fit the calculated energy envelope value;

[0148] A contraction intensity determination module, configured to determine the first contraction intensity of the target muscle based on the fitting value.

[0149] In some alternative embodiments, the calculation module includes:

[0150] A selection unit, configured to obtain the electromyogram signal at a first moment and the electromyogram signals within a preset duration before the first moment from the target electromyogram signal;

[0151] A calculation unit, configured to calculate the energy values of the electromyogram signals within the preset duration and the electromyogram signal at the first moment as the energy envelope value at the first moment.

[0152] In some alternative embodiments, the activity state information includes at least one of an activity start time, an activity end time, a contraction intensity, a contraction intensity peak value, a contraction duration, a contraction area, a contraction frequency, a contraction average intensity, an average contraction duration, a median frequency, and a sample entropy.

[0153] In some alternative embodiments, the device further includes:

[0154] A receiving module, configured to receive the user's operation;

[0155] A screening module, configured to determine the activity state information item according to the user's operation.

[0156] In some alternative embodiments, the device further includes:

[0157] A display module, configured to display the activity status information of the target muscle and the target myoelectric signal on the same screen.

[0158] The further function descriptions of the above-mentioned various modules and units are the same as those in the corresponding foregoing embodiments, and will not be elaborated herein.

[0159] The muscle activity detection device in this embodiment is presented in the form of functional units. Here, the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and a memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0160] An embodiment of the present invention further provides a computer device having the above-mentioned Figure 7 shown muscle activity detection device.

[0161] Please refer to Figure 8 , Figure 8 which is a schematic structural diagram of a computer device provided by an alternative embodiment of the present invention. As Figure 8 shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including a high-speed interface and a low-speed interface. Each component communicates with each other using different buses and can be installed on a common main board or installed in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in the memory or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some alternative embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a set of blade servers, or a multi-processor system). Figure 8 One processor 10 is taken as an example in

[0162] The processor 10 can be a central processing unit, a network processor, or a combination thereof. Among them, the processor 10 can further include a hardware chip. The above-mentioned hardware chip can be an application specific integrated circuit, a programmable logic device, or a combination thereof. The above-mentioned programmable logic device can be a complex programmable logic device, a field programmable gate array, a general array logic, or any combination thereof.

[0163] Among them, the memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above-mentioned embodiments.

[0164] The memory 20 may include a program storage area and a data storage area. The program storage area may store an operating system and application programs required for at least one function. The data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some alternative embodiments, the memory 20 may optionally include a memory remotely provided with respect to the processor 10, and these remote memories may be connected to the computer device through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0165] The memory 20 may include a volatile memory, such as a random access memory. The memory may also include a non-volatile memory, such as a flash memory, a hard disk, or a solid-state drive. The memory 20 may also include a combination of the above types of memories.

[0166] The computer device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30, and the output device 40 may be connected through a bus or other means. Figure 8 Taking the connection through the bus as an example.

[0167] The input device 30 may receive input digital or character information, and generate key signal inputs related to the user settings and function controls of the computer device, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad, a pointing stick, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED), and a tactile feedback device (e.g., a vibration motor), etc. The above display device includes but is not limited to a liquid crystal display, a light-emitting diode, a display, and a plasma display. In some alternative embodiments, the display device may be a touch screen.

[0168] The computer device further includes a communication interface for the computer device to communicate with other devices or a communication network.

[0169] Embodiments of the present invention also provide a computer-readable storage medium. The method according to the embodiments of the present invention can be implemented in hardware, firmware, or be implemented as computer code that can be recorded on a storage medium, or be implemented as computer code that is originally stored in a remote storage medium or a non-transitory machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored as such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code, and when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method shown in the above embodiments is implemented.

[0170] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for detecting muscle activity, characterized in that, The method includes: Collecting target electromyography (EMG) signals; Respectively obtaining characteristic points in a first EMG signal segment and a second EMG signal segment in the target EMG signals, wherein the duration of the first EMG signal segment is greater than that of the second EMG signal segment, and the end points of the first EMG signal segment and the second EMG signal segment are the same; Based on the relationship between the characteristic points in the second EMG signal segment and the characteristic points in the first EMG signal segment, determining activity state information of the target muscle.

2. The method according to claim 1, wherein The characteristic points are extreme points; The respectively obtaining characteristic points in a first EMG signal segment and a second EMG signal segment in the target EMG signals includes: Obtaining the amplitude mean value of the first EMG signal segment; Obtaining extreme points in the second EMG signal segment whose amplitudes are greater than or equal to the amplitude mean value.

3. The method according to claim 1 or 2, characterized in that The based on the relationship between the characteristic points in the second EMG signal segment and the characteristic points in the first EMG signal segment, determining the activity state information of the target muscle includes: If the ratio of the number of characteristic points in the current second EMG signal segment to the number of characteristic points in the current first EMG signal segment is greater than a first preset threshold, determining that the target muscle is in the starting state of activity.

4. The method according to claim 2, characterized in that, The based on the relationship between the characteristic points in the second EMG signal segment and the characteristic points in the first EMG signal segment, determining the activity state information of the target muscle includes: For the second EMG signal segment after detecting that the target muscle is in the starting state of activity, if the proportion of signals in the current second EMG signal segment whose amplitudes are greater than the target amplitude mean value is less than a termination threshold, determining that the target muscle is in the ending state of activity; Wherein, the target amplitude mean value is the amplitude mean value of the first EMG signal segment when determining that the target muscle is in the starting state of activity.

5. The method according to claim 1, wherein After collecting the target EMG signals, it further includes: Calculating the energy envelope value of the target EMG signals; Fitting the calculated energy envelope value; Based on the fitting value, determining the first contraction intensity of the target muscle.

6. The method according to claim 5, characterized in that, The calculating the energy envelope value of the target EMG signals includes: Obtaining the EMG signal at a first moment and the EMG signals within a preset duration before the first moment from the target EMG signals; Calculating the energy values of the EMG signals within the preset duration and the EMG signal at the first moment as the energy envelope value at the first moment.

7. The method according to claim 1, wherein The activity state information includes at least one of the activity start time, activity end time, contraction intensity, contraction intensity peak, contraction duration, contraction area, contraction frequency, contraction average intensity, average contraction duration, median frequency, and sample entropy.

8. The method according to claim 7, wherein It further includes: Receiving the operation of the user; Determining the activity state information item according to the operation of the user.

9. The method according to claim 1, wherein It further includes: Displaying the activity state information of the target muscle and the target EMG signals on the same screen.

10. A muscle activity detection device, characterized in that, The device includes: A collection module for collecting target EMG signals; An acquisition module, configured to respectively acquire feature points in a first myoelectric signal segment and a second myoelectric signal segment in the target myoelectric signal, wherein the duration of the first myoelectric signal segment is greater than that of the second myoelectric signal segment, and the endpoints of the first myoelectric signal segment and the second myoelectric signal segment are the same; A determination module, configured to determine activity state information of a target muscle based on the relationship between the feature points in the second myoelectric signal segment and the feature points in the first myoelectric signal segment.

11. A computer device, characterized in that, Comprising: A memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to execute the muscle activity detection method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, Computer instructions are stored on the computer-readable storage medium, and the computer instructions are used to cause a computer to execute the muscle activity detection method according to any one of claims 1 to 9.

Images