Signal identification method and device, electronic equipment and storage medium

Abstract

This disclosure provides a signal identification method, apparatus, electronic device, and storage medium. The method first determines whether the peak point is a candidate peak point when the first vector signal is a peak point in the signal sequence. If it is, the variance of the signal amplitude of the latest M candidate peak points is calculated to obtain the second signal variance. If the second signal variance is less than the first variance threshold, the target state is set to the first state value, and the signal identification step is executed. Otherwise, the target state is set to the second state value, and the signal identification step is executed when the peak point is a selectable peak point. The signal identification step is used to determine that the peak point signal in the latest P second intervals is a non-target signal when the variance of the latest P second intervals is less than the threshold and the proportion of the second state value in the latest P target states is less than the proportion threshold. This efficiently identifies high-frequency interference signals without the need for additional sensors.

Description

Technical Field

[0001] This disclosure relates to the field of signal recognition technology, and in particular to signal recognition methods, devices, electronic equipment and storage media. Background Technology

[0002] When processing signals to identify the device state represented by the signals, the acquired signals may sometimes become interference signals due to changes in the device state. The signal characteristics of interference signals may differ from those of the expected signals.

[0003] Taking step counting algorithms as an example, these algorithms are mainly used in fields such as motion tracking and health management. With the widespread use of smart wearable devices such as smartphones and fitness trackers, step counting algorithms have become an important tool for assessing daily activity levels. Step counting algorithms analyze sensor data (such as accelerometer data) to identify walking steps and thus estimate the number of steps. However, some everyday habits can cause step counting devices to collect signals that are not walking signals. For example, when a user shakes their leg, or when someone with a medical condition makes involuntary movements, the step counting device may misidentify these non-walking signals as walking signals and count them as steps, leading to inaccurate step counts. Summary of the Invention

[0004] To address at least one of the aforementioned technical problems, this disclosure provides a signal recognition method, apparatus, electronic device, and storage medium.

[0005] The first aspect of this disclosure proposes a signal recognition method, comprising: processing a collected raw signal to obtain a first vector signal; adding the first vector signal to a signal sequence; calculating the variance of the N most recently added first vector signals in the signal sequence to obtain a first signal variance; if the first vector signal is a peak point in the signal sequence, taking the interval between the peak point and the previous candidate peak point as a first interval, determining whether the peak point is a candidate peak point based on the signal amplitude of the peak point, the first signal variance, the recognition result of the previous signal recognition, and the first interval; if the peak point is a candidate peak point, calculating the variance of the signal amplitude of the M most recently added candidate peak points to obtain a second signal variance, and setting a target state when the second signal variance is less than a first variance threshold. The system first sets a state value and performs a signal identification step. If the peak point is not a candidate peak point, the target state is set to a second state value, with the interval between the peak point and the previous selectable peak point as the second interval. The system determines whether the peak point is a selectable peak point based on the signal amplitude of the peak point and the second interval. If the peak point is a selectable peak point, the system performs a signal identification step, wherein the candidate peak point belongs to the selectable peak point. The system also performs a signal identification step, calculating the variance of the latest P second intervals to obtain the interval variance, and determining the proportion of the second state value based on the latest P target states. If the interval variance is less than the second variance threshold and the proportion is lower than the proportion threshold, the peak point signal within the latest P second intervals is determined to be a non-target signal; otherwise, it is a target signal.

[0006] According to one embodiment of this disclosure, the original signal is a triaxial acceleration signal.

[0007] According to one embodiment of this disclosure, processing the acquired raw signal to obtain a first vector signal includes: performing vector synthesis on the acquired raw signal to obtain a vector synthesized signal; and smoothing the newly obtained K vector synthesized signals to obtain the first vector signal.

[0008] According to one embodiment of the present disclosure, smoothing the newly obtained K vector composite signals to obtain a first vector signal includes: averaging the newly obtained K vector composite signals and using the average value as the first vector signal.

[0009] According to one embodiment of this disclosure, the peak point is a point where the signal amplitude is greater than the signal amplitude of the adjacent signals on both sides.

[0010] According to one embodiment of this disclosure, the first variance threshold is determined based on the amplitude of the first signal variance. The amplitude range of the first signal variance is set with multiple segmented intervals, each segmented interval corresponding to a first variance threshold. The first variance threshold increases with the positive change of the position of the segmented interval.

[0011] According to one embodiment of this disclosure, the candidate peak point simultaneously meets the following requirements: the signal amplitude of the candidate peak point is greater than a first amplitude threshold, the corresponding first signal variance is greater than a third variance threshold, the recognition result of the previous signal recognition is the target signal, and the first interval is located within the interval range.

[0012] According to one embodiment of this disclosure, the optional peak point simultaneously satisfies the following requirements: the signal amplitude of the optional peak point is greater than a second amplitude threshold, the second interval is greater than an interval threshold, wherein the second amplitude threshold is less than the first amplitude threshold, and the interval threshold is less than the smaller endpoint of the two interval endpoints of the interval interval.

[0013] A second aspect of this disclosure provides a signal recognition device, comprising: a vector signal acquisition module, configured to process an acquired raw signal to obtain a first vector signal, and add the first vector signal to a signal sequence; a signal variance acquisition module, configured to calculate the variance of the N most recently added first vector signals in the signal sequence to obtain a first signal variance; a candidate peak determination module, configured to, if the first vector signal is a peak point in the signal sequence, take the interval between the peak point and the previous candidate peak point as a first interval, and determine whether the peak point is a candidate peak point based on the signal amplitude of the peak point, the first signal variance, the recognition result of the previous signal recognition, and the first interval; and a target state setting module, configured to, if the peak point is a candidate peak point, calculate the variance of the signal amplitude of the M most recently added candidate peak points to obtain a second signal variance, and set the target state to a first state when the second signal variance is less than a first variance threshold. The signal recognition module is configured to perform a signal recognition step; an optional peak determination module is configured to set the target state to a second state value if the peak point is not a candidate peak point, take the interval between the peak point and the previous optional peak point as the second interval, determine whether the peak point is an optional peak point based on the signal amplitude of the peak point and the second interval, and cause the signal recognition module to perform the signal recognition step when the peak point is an optional peak point, wherein the candidate peak point belongs to the optional peak point; and the signal recognition module is configured to perform the signal recognition step, the signal recognition step including: calculating the variance of the latest P second intervals to obtain the interval variance, and determining the proportion of the second state value based on the latest P target states, if the interval variance is less than the second variance threshold and the proportion is lower than the proportion threshold, then determining that the peak point signal in the latest P second intervals is a non-target signal, otherwise it is a target signal.

[0014] A third aspect of this disclosure provides an electronic device comprising: a memory storing execution instructions; and a processor executing the execution instructions stored in the memory, causing the processor to perform the signal recognition method described in any of the above embodiments.

[0015] The fourth aspect of this disclosure provides a readable storage medium storing executable instructions, which, when executed by a processor, are used to implement the signal recognition method described in any of the above embodiments. Attached Figure Description

[0016] The accompanying drawings illustrate exemplary embodiments of the present disclosure and, together with the description thereof, serve to explain the principles of the present disclosure. These drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification.

[0017] Figure 1 This is a schematic flowchart of a signal recognition method according to one embodiment of the present disclosure.

[0018] Figure 2 This is a schematic diagram of the signal characteristics of a high-frequency interference signal according to one embodiment of the present disclosure.

[0019] Figure 3 This is a schematic diagram of the signal characteristics of a real walking signal according to one embodiment of the present disclosure.

[0020] Figure 4 This is a schematic diagram of a signal recognition device employing a hardware implementation of a processing system according to one embodiment of the present disclosure. Detailed Implementation

[0021] The present disclosure will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the disclosure. Furthermore, it should be noted that, for ease of description, only the parts relevant to the present disclosure are shown in the accompanying drawings.

[0022] It should be noted that, where there is no conflict, the embodiments and features described in this disclosure can be combined with each other. The technical solutions of this disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0023] Unless otherwise stated, the exemplary implementations / embodiments shown are to be understood as providing exemplary features of various details that provide ways in which the technical concepts of this disclosure can be implemented in practice. Therefore, unless otherwise stated, the features of various implementations / embodiments may be additionally combined, separated, interchanged and / or rearranged without departing from the technical concepts of this disclosure.

[0024] The terminology used herein is for the purpose of describing particular embodiments and is not restrictive. As used herein, unless the context clearly indicates otherwise, the singular forms “a” and “the” are intended to include the plural forms as well. Furthermore, when the terms “comprising” and / or “including” and variations thereof are used in this specification, it indicates the presence of the stated features, integrals, steps, operations, parts, components, and / or groups thereof, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, parts, components, and / or groups thereof. It should also be noted that, as used herein, the terms “substantially,” “about,” and other similar terms are used as approximate terms rather than as terms of degree, thus explaining the inherent biases in measurements, calculated values, and / or provided values ​​that would be recognized by one of ordinary skill in the art.

[0025] The following description, using a pedometer device for step counting as an example, illustrates the signal recognition method, apparatus, electronic device, and readable storage medium of this disclosure with reference to the accompanying drawings.

[0026] Figure 1 This is a schematic flowchart of a signal recognition method according to one embodiment of the present disclosure. (See attached diagram) Figure 1 The signal recognition method M10 of this embodiment may include the following steps S100, S200, S300, S400, S500 and S600.

[0027] S100: Process the acquired raw signal to obtain the first vector signal, and add the first vector signal to the signal sequence.

[0028] S200, calculate the variance of the N most recently added first vector signals in the signal sequence to obtain the first signal variance magVar.

[0029] S300, if the first vector signal is a peak point in the signal sequence, then the interval between the peak point and the previous candidate peak point is the first interval stepInterval. Based on the signal amplitude of the peak point, the first signal variance magVar, the recognition result of the previous signal recognition, and the first interval stepInterval, it is determined whether the peak point is a candidate peak point.

[0030] S400, if the peak point is a candidate peak point, calculate the variance of the signal amplitude of the latest M candidate peak points to obtain the second signal variance, and when the second signal variance is less than the first variance threshold varThr, set the target state peakState to the first state value True and execute the signal recognition step.

[0031] S500, if the peak point is not a candidate peak point, the target state peakState is set to the second state value False, the interval between the peak point and the previous selectable peak point is the second interval peakInterval, and the peak point is determined as a selectable peak point based on the signal amplitude of the peak point and the second interval peakInterval. When the peak point is a selectable peak point, the signal identification step is performed, wherein the candidate peak point belongs to the selectable peak point.

[0032] In signal identification step S600, if the peak point is a candidate peak point or an optional peak point, the variance of the latest P second intervals peakInterval is calculated to obtain the interval variance fakeVar, and the proportion fakePnt of the second state value is determined based on the latest P target states peakState. If the interval variance fakeVar is less than the second variance threshold and the proportion fakePnt is lower than the proportion threshold, then the peak point signal in the latest P second intervals peakInterval is determined to be a non-target signal; otherwise, it is a target signal.

[0033] The signal recognition method proposed according to the embodiments of this disclosure detects possible peak points of real step counting while detecting possible false peak points of leg shaking based on the high-frequency and regular characteristics of signals such as leg shaking, using low interval thresholds and amplitude thresholds. It analyzes the variance of peak points to determine whether the signal is regular, and analyzes the ratio of false peak points of leg shaking to real peak points of step counting to determine whether the current signal is dominated by high-frequency components. Thus, it can identify high-frequency interference signals such as leg shaking in walking signals without adding new sensors or using complex algorithms. It achieves efficient, accurate and low-power recognition of interference signals, solving the problem of false step counting caused by high-frequency interference signals.

[0034] The original signal can be a triaxial acceleration signal. Triaxial acceleration signals include ax, ay, and az. When acquiring triaxial acceleration signals, the time difference (deltaTime) between the current sampling time point and the previous sampling time point can also be obtained. Sampling of the triaxial acceleration signal can be performed periodically; therefore, deltaTime can be a fixed value.

[0035] Figure 2 This is a schematic flowchart illustrating the processing of a triaxial acceleration signal according to one embodiment of this disclosure. (See attached diagram.) Figure 2 In step S100, the method of processing the acquired raw signal to obtain the first vector signal may include the following steps S110 and S120.

[0036] S110 performs vector synthesis on the acquired raw signal to obtain the vector synthesized signal mag.

[0037] S120, smooth the newly obtained K vector composite signals mag to obtain the first vector signal.

[0038] The formula for calculating the vector synthesized signal *mag* is: *mag* = sqrt(ax*ax + ay*ay + az*az). Smoothing can be performed using a 9-point smoothing method, where K = 9. The smoothing method for the newly obtained 9 vector synthesized signals *mag* can be as follows: average the 9 newly obtained vector synthesized signals, use the average value as the latest first vector signal, and add it to the signal sequence. Subsequent analysis of the signal sequence can then identify high-frequency interference signals (such as leg shaking) and normal walking signals.

[0039] Whenever a new first vector signal is added to the signal sequence, the first signal variance magVar corresponding to that first vector signal can be calculated immediately. N can be set to 50, in which case the latest 50 first vector signals in the signal sequence are calculated, and among these 50 first vector signals, the first vector signal that was added to the signal sequence latest in time is selected.

[0040] After obtaining the first signal variance magVar, the corresponding first variance threshold varThr can be determined. Specifically, the amplitude of the triaxial acceleration signal can be used to set the first variance threshold varThr. The first variance threshold varThr is determined based on the amplitude of the first signal variance magVar. The amplitude range of the first signal variance magVar is set with multiple segmented intervals, each segmented interval corresponding to a first variance threshold varThr. The first variance threshold varThr increases as the position of the segmented interval changes positively.

[0041] Specifically, the correspondence between the first signal variance magVar and the first variance threshold varThr can be as follows: if the first signal variance magVar < 0.4, then the first variance threshold varThr = 0.025; if the first signal variance 0.4 ≤ magVar < 1.5, then the first variance threshold varThr = 0.03; if the first signal variance 1.5 ≤ magVar < 30, then the first variance threshold varThr = 0.4; if the first signal variance 30 ≤ magVar, then the first variance threshold varThr = 1.

[0042] After adding the first vector signal to the signal sequence in step S100, it can be determined whether the first vector signal is a peak signal. The condition for determining that the first vector signal is a peak point (maximum point) can be: the signal amplitude of the peak point is greater than the signal amplitudes of the adjacent signals on both sides. Assume the first vector signal to be identified is sig. n , where n is the order of the first vector signal in the signal sequence, if sig n The signal amplitude is greater than that in the signal sequence in sig n The first vector signal added before sign-1 The signal amplitude is greater than that in the signal sequence at sig n The first vector signal sig added after the last one n+1 The signal amplitude, then sig n This is the peak point. It should be noted that, regarding the first vector signal sig... n When determining whether a point is a peak, a value greater than sig needs to be obtained. n The first vector signal sig added later to the signal sequence n+1 That is, for the same original signal, the corresponding peak point detection will lag behind the generation of the corresponding first vector signal, and at least until a new first vector signal is added to the signal sequence, but the period of peak point detection and the generation of the first vector signal can be the same.

[0043] If the first vector signal to be identified is sig n If the peak point is reached, then sig can be determined in step 300. n Whether it is a candidate peak point can then be determined in step S500, sig. n Is it an optional peak point? If sig n If it is a candidate peak point, then sig is considered n It is also an optional peak point. If sig n If it is not a candidate peak point, then sig n It can be an optional peak point, or sig n It is neither a candidate peak point nor an optional peak point.

[0044] The conditions for determining a peak point as a candidate peak point can be that the candidate peak point must simultaneously meet the following four requirements.

[0045] 1. The signal amplitude of the candidate peak point is greater than the first amplitude threshold, which can be set to 1.1.

[0046] 2. With the first vector signal sig n The corresponding first signal variance magVar n The difference is greater than the third-party difference threshold, which can be set to 0.15.

[0047] 3. The result of the previous signal recognition was: the original signal was identified as the target signal. The target signal can be a non-high-frequency interference signal, such as a walking signal, while a high-frequency interference signal is a non-target signal, such as a signal generated when the user shakes their leg. It can be understood that the previous signal recognition was the result of recognizing the previous selectable peak point, which may or may not be a candidate peak point.

[0048] 4. First Interval (stepInterval) n Located within the interval, which can be (240ms, 1400ms), it can be understood that if the current peak point sig n The original signal acquisition time is t n The previous peak point identified as a candidate peak point, sig m The original signal acquisition time is t m Then the first interval stepInterval at this time n =t n -t m .

[0049] If the peak point sig n The signal amplitude is >1.1, sig n The corresponding first signal variance magVar n >0.15, the identification result of the previous optional signal is a non-high-frequency interference signal, and 240 <stepInterval n If the value is less than 1400, then the peak point sig is determined. n This is a candidate peak point. If the peak point sig n If any of the above requirements 1 to 4 are not met, then the peak point sig is determined. n It does not belong to the candidate peak point.

[0050] If the peak point sig is determined n If the M candidate peak points are identified, the signal amplitudes of the newly determined M candidate peak points are obtained, the variance of these M signal amplitudes is calculated, and the calculated second signal variance is compared with the previously determined sig corresponding to the peak point. n First variance threshold varThr n Compare. If sig n <varThr n Then, set the target state peakState to the first state value, and set the first interval stepInterval. n Reset to zero. At this point, the peak value is sig. n Once a peak in step counting is identified, the step count can be incremented by 1, confirming that the original signal indicates the user took a step rather than simply shook their leg. This is achieved through stepInterval. n Resetting the value to zero allows for the identification of whether subsequent peak points are candidate peak points, with stepInterval being zeroed out. n It can accumulate from zero.

[0051] `peakState` represents the peak step count state. `peakState` has only two possible values: a first state value and a second state value. Specifically, `peakState` can be a Boolean variable, where the first state value can be `True` and the second state value can be `False`. The value of `peakState` is one of the bases for subsequent signal recognition. If `sig`... n <varThr n If so, then set the value of peakState to True.

[0052] Understandably, a first buffer array, `peakArr`, can be used to store the signal amplitudes of candidate peak points. The length of `peakArr` is M, meaning it can store M values. Whenever a new value is added from the array's entry point, all values ​​in `peakArr` are shifted to the next position, and the value at the array's exit point is discarded. When calculating the second signal variance, the variance can be directly calculated from the M values ​​currently stored in `peakArr`.

[0053] If a peak point is a candidate peak point, then it is also a selectable peak point. If a peak point is a selectable peak point, then it may or may not be a candidate peak point. If the peak point sig is determined... n If a peak point is not a candidate peak point, set the value of peakState to False and further determine the peak point's sig. n Whether it belongs to the optional peak point.

[0054] The condition for determining a peak point as an optional peak point is that the optional peak point must simultaneously meet the following two requirements.

[0055] 1. The signal amplitude at the selectable peak point is greater than the second amplitude threshold, and the second amplitude threshold is less than the first amplitude threshold. For example, the second amplitude threshold can be set to 1.05.

[0056] 2. The second peak interval n The interval threshold is greater than the interval value, and the interval threshold is less than the smaller of the two endpoints of the interval interval. For example, when the interval interval is (240ms, 1400ms), the interval threshold can be set to 120ms. It is understandable that if the current peak point sig n The original signal acquisition time is t n The previous peak point identified as an optional peak point, sig k The original signal acquisition time is t k Then the second peak interval at this time n =t n -t k .

[0057] If the peak point sig n It is not a candidate peak point, but the peak point sig n The signal amplitude is greater than 1.05, and the peak interval is... n >120ms, then the peak point sig n This is an optional peak point. If the peak point sig n It is not a candidate peak point, but the peak point sig n The signal amplitude is ≤1.05 or peakInterval n ≤120ms, peak point sig n It is neither a candidate peak point nor an optional peak point, but only a normal peak point.

[0058] When the peak point sig is determined n When a candidate peak point is identified and step S400 has been completed, or when the peak point sig is determined... n If a peak point is not a candidate peak point but is a selectable peak point and step S500 has been completed, the signal identification step S600 begins. In the signal identification step, the newly determined P second intervals (peakInterval) are obtained, and the variance (interval variance) of these P second intervals (peakInterval) is calculated. The target state (peakState) of the newly determined P peak points that belong to either candidate or selectable peak points is obtained, and the proportion of peakStates with a value of False (fakePnt) is calculated. For the second interval (peakInterval)... n To clear it, use peakInterval. n Resetting the peak value to zero allows for the identification of whether subsequent peak points are selectable peak points, thus reducing the peakInterval value. n It can accumulate from zero.

[0059] Understandably, a second cache array `intervalArr` can be used to store the values ​​of the second interval `peakInterval`, and a third cache array `stateArr` can be used to store the values ​​of `peakState`. Both `intervalArr` and `stateArr` have a length of `P`, meaning each can store `P` values; `P` can be set to 8. Whenever a new value is stored at the array entry point, all values ​​in `intervalArr` and `stateArr` are shifted forward, and the value at the array exit point is discarded. When calculating the interval variance `fakeVar`, the variance is directly calculated on the P values ​​currently stored in `intervalArr`. When determining the proportion of false values ​​`fakePnt`, all values ​​in `stateArr` are directly analyzed.

[0060] The second variance threshold can be set to 500, and the proportion threshold can be set to 0.5. If the interval variance fakeVar < 500, and the proportion of false values ​​fakePnt > 0.5, it indicates that the original signal occurred frequently within the interval of the most recent P peak points, and most of them were non-walking signals. Therefore, the signal within the interval of the most recent P peak points is considered to be a high-frequency interference signal (such as a high-frequency signal collected by the pedometer by the user shaking their leg). If the interval variance fakeVar ≥ 500, or the proportion of false values ​​fakePnt ≤ 0.5, then the signal within the interval of the most recent P peak points is considered to be a normal walking signal.

[0061] It should be noted that in step S300, if the first vector signal is not a peak point in the signal sequence, the values ​​of the first interval stepInterval and the second interval peakInterval can be directly increased by the time difference deltaTime, that is, stepInterval = stepInterval + deltaTime and peakInterval = peakInterval + deltaTime, thereby updating the interval values. If the first vector signal is a peak point but not a candidate peak point or an optional peak point, the values ​​of the first interval stepInterval and the second interval peakInterval can be directly increased by the time difference deltaTime. If the first vector signal is a peak point and belongs to an optional peak point or a candidate peak point, then after completing the signal identification step, the values ​​of the first interval stepInterval and the second interval peakInterval are increased by the time difference deltaTime.

[0062] This implementation method utilizes the high frequency characteristic of high-frequency interference signals to cache the detected optional peak points. It analyzes whether the current signal is a high-frequency, regular interference (leg shaking signal) by using the variance of the interval between optional peak points and the proportion of the actual peak points within the window. Compared to using complex algorithms for dynamic recognition in conjunction with gravity sensors to detect actual leg movements and avoid false step counting by high-frequency signals, and compared to using GPS devices for positioning and calculating walking distance and location to avoid false step counting by high-frequency signals, this implementation method has lower computational load and resource consumption, making it suitable for implementation in portable devices with limited battery life.

[0063] The following is an explanation of the identification results of high-frequency interference signals and real walking signals.

[0064] Figure 2 This is a schematic diagram of the signal characteristics of a high-frequency interference signal according to one embodiment of the present disclosure. Figure 3 This is a schematic diagram of the signal characteristics of a real walking signal according to one embodiment of this disclosure. (See also...) Figure 2 and Figure 3 The first row of the graph shows the curve of the vector synthesized signal mag and the detected optional peak points on the curve, indicated by asterisks. The second row shows the curve of the proportion of values ​​of flase (fakePnt) among the P target states peakState. The third row shows the curve of the variance (interval variance fakeVar) of the second interval peakInterval.

[0065] from Figure 2 It can be seen that the value of fakePnt is consistently 1, and the interval variance fakeVar < 500. Based on the judgment condition of non-target signal in the signal recognition step, it can be determined that the current state is leg shaking and non-step counting.

[0066] from Figure 3 It can be seen that the value of fakePnt is basically below 0.5, and the interval variance fakeVar>500. According to the judgment condition of non-target signal in the signal recognition step, it can be determined that the current state is a real walking state.

[0067] Figure 3 This is a schematic diagram of a signal recognition device employing a hardware implementation of a processing system according to one embodiment of the present disclosure. (See also...) Figure 3 The signal recognition device 1000 of this embodiment may include a vector signal acquisition module 1002, a signal variance acquisition module 1004, a candidate peak value determination module 1006, a target state setting module 1008, an optional peak value determination module 1010, and a signal recognition module 1012.

[0068] The vector signal acquisition module 1002 is used to process the acquired raw signal to obtain a first vector signal and add the first vector signal to the signal sequence.

[0069] The signal variance acquisition module 1004 is used to calculate the variance of the N most recently added first vector signals in the signal sequence to obtain the first signal variance.

[0070] The candidate peak determination module 1006 is used to determine whether a peak point is a candidate peak point based on the signal amplitude of the peak point, the first signal variance, the recognition result of the previous signal recognition, and the first interval if the first vector signal is a peak point in the signal sequence.

[0071] The target state setting module 1008 is used to calculate the variance of the signal amplitude of the latest M candidate peak points to obtain the second signal variance if the peak point is a candidate peak point, and set the target state to the first state value when the second signal variance is less than the first variance threshold, and cause the signal recognition module to perform the signal recognition step.

[0072] The optional peak determination module 1010 is used to set the target state to a second state value if the peak point is not a candidate peak point, take the interval between the peak point and the previous optional peak point as the second interval, determine whether the peak point is an optional peak point based on the signal amplitude of the peak point and the second interval, and cause the signal recognition module to perform the signal recognition step when the peak point is an optional peak point, wherein the candidate peak point belongs to the optional peak point.

[0073] The signal recognition module 1012 is used to perform the signal recognition steps, which include: calculating the variance of the latest P second intervals to obtain the interval variance, and determining the proportion of the second state value based on the latest P target states. If the interval variance is less than the second variance threshold and the proportion is lower than the proportion threshold, then the peak point signal in the latest P second intervals is determined to be a non-target signal; otherwise, it is a target signal.

[0074] It should be noted that details not disclosed in the signal recognition device 1000 of this embodiment can be found in the details disclosed in the signal recognition method M10 of the above-described embodiment of this disclosure, and will not be repeated here.

[0075] The device 1000 may include corresponding modules that perform one or more steps in the flowchart described above. Therefore, each or more steps in the flowchart can be performed by a corresponding module, and the device may include one or more of these modules. A module may be one or more hardware modules specifically configured to perform a corresponding step, or implemented by a processor configured to perform a corresponding step, or stored in a computer-readable medium for implementation by a processor, or implemented through some combination thereof.

[0076] This hardware architecture can be implemented using a bus architecture. The bus architecture can include any number of interconnect buses and bridges, depending on the specific application and overall design constraints of the hardware. Bus 1100 connects various circuits, including one or more processors 1200, memory 1300, and / or hardware modules. Bus 1100 can also connect various other circuits 1400, such as peripherals, voltage regulators, power management circuits, external antennas, etc.

[0077] Bus 1100 can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Component (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, only one connection line is used in this diagram, but this does not imply that there is only one bus or only one type of bus.

[0078] Any process or method description in the flowcharts or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of this disclosure includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of this disclosure pertain. The processor performs the various methods and processes described above. For example, the method embodiments of this disclosure may be implemented as software programs tangibly contained in a machine-readable medium, such as memory. In some embodiments, part or all of the software program may be loaded and / or installed via memory and / or a communication interface. When the software program is loaded into memory and executed by the processor, one or more steps of the methods described above may be performed. Alternatively, in other embodiments, the processor may be configured to perform one of the methods described above by any other suitable means (e.g., by means of firmware).

[0079] The logic and / or steps represented in the flowchart or otherwise described herein may be specifically implemented in any readable storage medium for use by, or in conjunction with, an instruction execution system, apparatus or device (such as a computer-based system, a processor-included system or other system that can fetch and execute instructions from, an instruction execution system, apparatus or device).

[0080] It should be understood that various parts of this disclosure can be implemented in hardware, software, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0081] Those skilled in the art will understand that all or part of the steps of the methods described above can be implemented by a program instructing related hardware. This program can be stored in a readable storage medium, and when executed, it includes one or a combination of the steps of the method implementation. The storage medium can be volatile or non-volatile.

[0082] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into a single processing module, or each unit can exist physically separately, or two or more units can be integrated into a single module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a readable storage medium. The storage medium can be a read-only memory, a disk, or an optical disk, etc.

[0083] This disclosure also provides an electronic device, including: a memory storing execution instructions; and a processor or other hardware module executing the execution instructions stored in the memory, causing the processor or other hardware module to perform the signal recognition method of the above embodiments.

[0084] This disclosure also provides a readable storage medium storing execution instructions, which, when executed by a processor, are used to implement the signal recognition method of any of the above embodiments.

[0085] For the purposes of this specification, a "readable storage medium" can be any means capable of containing, storing, communicating, propagating, or transmitting a program for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and portable read-only memory (CDROM). Furthermore, a readable storage medium can even be paper or other suitable media on which a program can be printed, since a program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in memory.

[0086] This disclosure also provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the signal recognition method of any of the above embodiments.

[0087] In the description of this specification, the references to terms such as "one embodiment / mode," "some embodiments / modes," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment / mode or example is included in at least one embodiment / mode or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment / mode or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments / modes or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments / modes or examples described in this specification, as well as the features of different embodiments / modes or examples.

[0088] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0089] Those skilled in the art should understand that the above embodiments are merely for illustrating the present disclosure and are not intended to limit the scope of the disclosure. Those skilled in the art can make other changes or modifications based on the above disclosure, and these changes or modifications still fall within the scope of the present disclosure.

Claims

1. A signal recognition method, characterized in that, include: The acquired raw signal is processed to obtain a first vector signal, and the first vector signal is added to the signal sequence; The variance of the first signal is obtained by calculating the variance of the N most recently added first vector signals in the signal sequence; If the first vector signal is a peak point in the signal sequence, the interval between the peak point and the previous candidate peak point is taken as the first interval. Based on the signal amplitude of the peak point, the variance of the first signal, the recognition result of the previous signal recognition, and the first interval, it is determined whether the peak point is a candidate peak point. If the peak point is a candidate peak point, calculate the variance of the signal amplitude of the latest M candidate peak points to obtain the second signal variance, and when the second signal variance is less than the first variance threshold, set the target state to the first state value and execute the signal recognition step. If the peak point is not a candidate peak point, the target state is set to the second state value, the interval between the peak point and the previous optional peak point is taken as the second interval, and the peak point is determined as an optional peak point based on the signal amplitude of the peak point and the second interval. When the peak point is an optional peak point, the signal identification step is performed, wherein the candidate peak point belongs to the optional peak point. as well as The signal identification step involves calculating the variance of the latest P second intervals to obtain the interval variance, and determining the proportion of the second state value based on the latest P target states. If the interval variance is less than the second variance threshold and the proportion is lower than the proportion threshold, then the peak point signal within the latest P second intervals is determined to be a non-target signal; otherwise, it is a target signal.

2. The method according to claim 1, characterized in that, The original signal is a triaxial acceleration signal.

3. The method according to claim 1, characterized in that, The acquired raw signal is processed to obtain the first vector signal, including: The acquired raw signals are vector synthesized to obtain a vector synthesized signal; and The first vector signal is obtained by smoothing the newly obtained K vector composite signals.

4. The method according to claim 3, characterized in that, The first vector signal is obtained by smoothing the newly obtained K vector composite signals, including: The average of the newly obtained K vector composite signals is calculated, and the average value is used as the first vector signal.

5. The method according to claim 1, characterized in that, The first variance threshold is determined based on the amplitude of the first signal variance. The amplitude range of the first signal variance is set with multiple segmented intervals, and each segmented interval corresponds to a first variance threshold. The first variance threshold increases as the position of the segmented interval changes positively.

6. The method according to claim 5, characterized in that, The candidate peak point simultaneously meets the following requirements: the signal amplitude of the candidate peak point is greater than the first amplitude threshold, the corresponding first signal variance is greater than the third variance threshold, the recognition result of the previous signal recognition is the target signal, and the first interval is located within the interval range.

7. The method according to claim 6, characterized in that, The optional peak point simultaneously meets the following requirements: the signal amplitude of the optional peak point is greater than the second amplitude threshold, the second interval is greater than the interval threshold, wherein the second amplitude threshold is less than the first amplitude threshold, and the interval threshold is less than the smaller endpoint of the two interval endpoints of the interval interval.

8. A signal recognition device, characterized in that, include: The vector signal acquisition module is used to process the acquired raw signal to obtain a first vector signal and add the first vector signal to the signal sequence. The signal variance acquisition module is used to calculate the variance of the N most recently added first vector signals in the signal sequence to obtain the first signal variance; The candidate peak determination module is used to determine whether the peak point is a candidate peak point if the first vector signal is a peak point in the signal sequence, taking the interval between the peak point and the previous candidate peak point as the first interval, and based on the signal amplitude of the peak point, the variance of the first signal, the recognition result of the previous signal recognition, and the first interval. The target state setting module is used to calculate the variance of the signal amplitude of the latest M candidate peak points to obtain the second signal variance if the peak point is a candidate peak point, and set the target state to the first state value when the second signal variance is less than the first variance threshold, and cause the signal recognition module to perform the signal recognition step. An optional peak determination module is configured to, if the peak point is not a candidate peak point, set the target state to a second state value, take the interval between the peak point and the previous optional peak point as the second interval, determine whether the peak point is an optional peak point based on the signal amplitude of the peak point and the second interval, and, if the peak point is an optional peak point, cause the signal recognition module to perform the signal recognition step, wherein the candidate peak point belongs to the optional peak point; and The signal recognition module is used to perform the signal recognition step, which includes: calculating the variance of the latest P second intervals to obtain the interval variance, and determining the proportion of the second state value based on the latest P target states. If the interval variance is less than the second variance threshold and the proportion is lower than the proportion threshold, then the peak point signal in the latest P second intervals is determined to be a non-target signal; otherwise, it is a target signal.

9. An electronic device, characterized in that, include: The memory stores execution instructions; as well as A processor that executes execution instructions stored in the memory, causing the processor to perform the signal recognition method as described in any one of claims 1 to 7.

10. A readable storage medium, characterized in that, The readable storage medium stores execution instructions, which, when executed by a processor, are used to implement the signal recognition method as described in any one of claims 1 to 7.

Images