Waveform recognition method and apparatus

Abstract

The embodiment of the application provides a waveform identification method and device, the method comprises sampling the pressing depth of the pressing machine at a preset frequency to obtain a first waveform graph; the abscissa of the first waveform graph is sampling time, and the ordinate is the pressing depth; the first waveform graph is differentiated to obtain a plurality of first feature points in the first waveform graph; the first derivative value corresponding to the first feature point is less than a first preset threshold; a plurality of target sampling points are determined from the plurality of first feature points, and the target sampling point is a wave peak vertex or a wave valley vertex; the plurality of target sampling points are sorted according to the order of the sampling time corresponding to the target sampling points, if the peak valley order corresponding to the plurality of target sampling points is consistent with the first order, the first waveform graph is determined as a target waveform graph, and the first order corresponds to the peak valley order of the wave peak vertex and the wave valley vertex in the target waveform graph. The method provided by the application can identify the target waveform based on the order of the waveform vertex, and then the performance of the pressing machine can be evaluated, and the evaluation is more standard.

Description

Technical Field

[0001] This application relates to the field of signal processing, and more particularly to a waveform recognition method and apparatus. Background Technology

[0002] A chest compression machine, also known as a cardiopulmonary resuscitation (CPR) machine, is a device that uses a preset waveform for pressing up and down. The actual compression pattern of the chest compression machine will affect its effectiveness. Therefore, in practical applications, it is necessary to analyze the actual compression pattern of the chest compression machine to determine whether its performance meets the standards.

[0003] Generally, the method used to analyze the pressing state of a press machine is to monitor the deepest pressing depth that the press machine can reach with each press, and then use the difference between the deepest pressing depth and the standard depth to determine whether the working performance of the press machine meets the standard.

[0004] However, the deepest pressing depth is only one aspect of the press machine's performance. This method only evaluates the press machine's performance from the perspective of the deepest pressing depth. The analysis method is singular and cannot determine whether the press machine works according to the preset waveform, which can easily lead to evaluation errors and thus result in defective press machines. Summary of the Invention

[0005] This application provides a waveform recognition method and apparatus to evaluate a press machine from the perspective of whether the pressing waveform is standard.

[0006] In a first aspect, embodiments of this application provide a waveform recognition method, comprising: sampling the pressing depth of a presser at a preset frequency to obtain a first waveform; the horizontal axis of the first waveform is the sampling time, and the vertical axis is the pressing depth; taking the derivative of the first waveform to obtain a plurality of first feature points in the first waveform; the first derivative value corresponding to the first feature point is less than a first preset threshold; determining a plurality of target sampling points from the plurality of first feature points, wherein the target sampling points are peaks or troughs; sorting the plurality of target sampling points according to the order of their corresponding sampling times, wherein if the peak-to-trough order of the plurality of target sampling points conforms to the first order, the first waveform is determined as the target waveform, wherein the first order corresponds to the peak-to-trough order of the peaks and troughs in the target waveform.

[0007] Secondly, embodiments of this application provide a waveform recognition device, comprising: a sampling module for sampling the pressing depth of a presser at a preset frequency to obtain a first waveform; the horizontal axis of the first waveform is the sampling time, and the vertical axis is the pressing depth; a derivative module for calculating the derivative of the first waveform to obtain multiple first feature points in the first waveform; the first derivative value corresponding to the first feature point is less than a first preset threshold; a first determination module for determining multiple target sampling points from the multiple first feature points, wherein the target sampling points are peaks or troughs; and a second determination module for sorting the multiple target sampling points according to the order of their corresponding sampling times, wherein if the peak-to-trough order of the multiple target sampling points conforms to the first order, the first waveform is determined as the target waveform, and the first order corresponds to the peak-to-trough order of the peaks and troughs in the target waveform.

[0008] As can be seen from the above technical solutions, the embodiments of this application provide a waveform recognition method and apparatus. The method includes acquiring a first waveform graph; the first waveform graph is a curve showing the change of the pressing depth of a presser at each first sampling point, and each first sampling point in the first waveform graph corresponds to a sampling sequence number; the derivative of the first waveform graph is calculated to obtain a plurality of sequentially arranged first derivative values, and the first derivative values ​​are less than a first preset threshold.

[0009] The second waveform is determined based on the first derivative value, and the second waveform is a fitting relationship diagram between the order of the first derivative values ​​and their corresponding sampling numbers;

[0010] The derivative of the second waveform is calculated to obtain multiple sequentially arranged second derivative values, and the second derivative values ​​are greater than a second preset threshold.

[0011] Multiple target sampling points are determined based on the second derivative value. These target sampling points are either peaks or troughs. If the peak-to-trough order of the multiple target sampling points conforms to the first order, the first waveform is determined as the target waveform. The first order corresponds to the peak-to-trough order of the peaks and troughs in the target waveform. The method provided in this application can identify target waveforms based on the order of waveform vertices, thereby enabling the evaluation of the press machine's performance, resulting in a more standardized evaluation. Attached Figure Description

[0012] Figure 1 A flowchart of the waveform recognition method provided in the embodiments of this application;

[0013] Figure 2 A schematic diagram of the first waveform provided in an embodiment of this application;

[0014] Figure 3 A schematic diagram of the target sampling points provided in the embodiments of this application;

[0015] Figure 4 A schematic flowchart illustrating the process of finding the derivative of the first waveform diagram provided in an embodiment of this application;

[0016] Figure 5 This is a schematic diagram of a first process for determining target sampling points provided in an embodiment of this application;

[0017] Figure 6 A schematic diagram of the third waveform provided in the embodiments of this application;

[0018] Figure 7 This is a schematic diagram of the fourth waveform provided in an embodiment of this application;

[0019] Figure 8 This is a schematic diagram of a second process for determining target sampling points provided in an embodiment of this application;

[0020] Figure 9 A disassembly diagram of the first waveform provided in the embodiments of this application;

[0021] Figure 10 This is a schematic diagram of a waveform recognition device provided in an embodiment of this application. Detailed Implementation

[0022] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of this application.

[0023] Figure 1 A flowchart illustrating the waveform recognition method provided in this application embodiment. Figure 1 As shown in the figure, this application provides a waveform recognition method, including the following steps:

[0024] S100: The pressing depth of the presser is sampled at a preset frequency to obtain a first waveform; the horizontal axis of the first waveform is the sampling time, and the vertical axis is the pressing depth.

[0025] Figure 2This is a schematic diagram of the first waveform provided in an embodiment of this application. The presser can press up and down according to a preset waveform, which limits the curve of the presser's pressing depth changing over time. The preset waveform may include a trapezoidal wave, a triangular wave, or a square wave, etc. To evaluate the working performance of the presser, this embodiment of the application can sample the pressing depth of the presser to obtain a first waveform, and then determine whether the first waveform conforms to the preset waveform, thereby evaluating whether the pressing quality of the presser meets the standard. In this embodiment of the application, the preset frequency may be, for example, sampling the pressing depth once every 1.5 milliseconds, or once every 5 milliseconds, or once every 10 milliseconds; this embodiment of the application does not specifically limit this. Figure 2 As shown in (a), the first waveform diagram may include a waveform that approximates a triangular wave or a waveform that approximates a trapezoidal wave.

[0026] In the first waveform diagram, the horizontal axis represents the sampling time, which increases sequentially as sampling continues. The vertical axis represents the pressing depth (amplitude). In some implementations, each sampling time corresponds to a first sequence number, which indicates the number of samplings. For example, the sampling time for the first sample is 0.00, and the first sequence number corresponding to this sampling time is equal to 1.

[0027] During the sampling process, a distance sensor can be installed on the presser to detect the pressing depth. In the actual formation of the first waveform, the vertical axis can be, for example, 60.0 corresponding to the maximum pressing depth of the presser. This can prevent the waveform from crossing zero. This can be designed based on the actual situation, and this application does not impose any specific limitations.

[0028] S200: Calculate the derivative of the first waveform to obtain multiple first feature points in the first waveform; the first derivative value corresponding to the first feature point is less than the first preset threshold.

[0029] Because the press-type device involves up-and-down pressing motions during operation, the corresponding first waveform diagram always includes peaks and troughs, regardless of whether the press follows a preset waveform. In this embodiment, the intersection of peaks and troughs is collectively referred to as an "inflection point." Furthermore, for example, when the curve in the first waveform diagram approximates a trapezoidal wave, the intersection between the rising wave and the rising platform can also be called the peak apex, and the intersection between the rising platform and the falling wave can also be called the peak apex. The intersection between the falling wave and the falling platform can be called the trough apex, and the intersection between the falling platform and the rising wave can also be called the trough apex. When the curve in the first waveform diagram approximates a triangular wave, the intersection between the rising and falling waves can be called the peak apex, the intersection between the falling wave and the platform portion can be called the trough apex, and the intersection between the platform portion and the rising wave can also be called the trough apex.

[0030] In this embodiment, to identify the peaks or troughs in the first waveform, the derivative of the first waveform is calculated. Furthermore, points where the derivative value is close to zero are considered "inflection points" in the first waveform. Therefore, this embodiment calculates the derivative of the first waveform to obtain first feature points whose first derivative value is less than a first preset threshold. The first preset threshold can be, for example, equal to 1. In some implementations, to accurately distinguish between different peaks and troughs, different first preset thresholds can be set for each type of peak. For example, a first preset threshold of 1 can be set for troughs, and a first preset threshold of 10 can be set for peaks. The first preset threshold can be adjusted based on actual application processes, and this embodiment does not specifically limit this adjustment.

[0031] S300: Determine multiple target sampling points from multiple first feature points, where the target sampling points are either peak vertices or trough vertices.

[0032] Due to the susceptibility to noise during actual sampling, and considering that the derivatives of the first waveform (approximately trapezoidal) and the second waveform (approximately triangular) are both zero or approximately zero after taking the derivative of the third waveform (approximately triangular), and the data fluctuations are complex, it is necessary to further determine the target sampling point from multiple first feature points. This target sampling point is either the peak or trough of the wave. The specific determination method will be detailed below and will not be repeated here.

[0033] S400: Sort multiple target sampling points according to the order of their corresponding sampling times. If the peak-valley order of multiple target sampling points matches the first order, the first waveform is determined as the target waveform. The first order corresponds to the peak-valley order of the peak vertices and trough vertices in the target waveform.

[0034] Figure 3 This is a schematic diagram of the target sampling points provided in an embodiment of this application. Figure 3 As shown, multiple target sampling points are sorted according to the order of their corresponding sampling times, so that multiple sampling points can be arranged according to the order of sampling.

[0035] The target waveform can be, for example, a trapezoidal wave, with the first sequence being, for example, the peak-valley sequence corresponding to the trapezoidal wave, specifically "valley-peak-peak-valley-valley". Alternatively, the target waveform can be a triangular wave, with the first sequence being, for example, the peak-valley sequence corresponding to the triangular wave, specifically "valley-peak-valley-valley".

[0036] Figure 3 (a) is a schematic diagram of the peak-valley sequence of the trapezoidal wave, where 1-5 represent the order of the target sampling points. Figure 3Figure (b) shows a schematic diagram of the peak-valley sequence of a triangular wave, where 1-4 represent the order of the target sampling points. Next, the peak-valley sequence of multiple target sampling points is determined. For example, if the peak-valley sequence of multiple target sampling points conforms to the order of "valley-peak-peak-valley-valley," then the corresponding first waveform diagram includes a trapezoidal wave, which is the target waveform diagram. Similarly, if the peak-valley sequence of multiple target sampling points conforms to the order of "valley-peak-valley-valley," then the corresponding first waveform diagram includes a triangular wave, which is the target waveform diagram.

[0037] As can be seen from the above technical solutions, the embodiments of this application provide a waveform recognition method. The method includes sampling the pressing depth of a presser at a preset frequency to obtain a first waveform diagram; the horizontal axis of the first waveform diagram is the sampling time, and the vertical axis is the pressing depth; the derivative of the first waveform diagram is calculated to obtain multiple first feature points in the first waveform diagram; the first derivative value corresponding to the first feature point is less than a first preset threshold; multiple target sampling points are determined from the multiple first feature points, where the target sampling points are peaks or troughs; the multiple target sampling points are sorted according to the order of their corresponding sampling times, and if the peak-to-trough order of the multiple target sampling points conforms to the first order, the first waveform diagram is determined as the target waveform diagram, where the first order corresponds to the peak-to-trough order of the peaks and troughs in the target waveform diagram. The method provided by this application can identify target waveforms based on the order of waveform vertices, thereby enabling the evaluation of the presser's performance, resulting in a more standardized evaluation.

[0038] Figure 4 This is a flowchart illustrating the process of finding the derivative of the first waveform diagram according to an embodiment of this application, as shown below. Figure 4 As shown, step S200 includes the following steps S201-S203:

[0039] S201: Filter the first waveform based on the preset filter to obtain the filtered first waveform.

[0040] The preset filter can be, for example, a median filter or a Chebyshev filter. A median filter can remove noise from an image or its signal, examine the sampled input signal, and determine whether it represents the signal. Since the sampling process of the press-button press is easily affected by noise, leading to inaccurate pressing depth measurements, this embodiment of the application can utilize a preset filter to remove noise and obtain a filtered first waveform.

[0041] In some implementations, the horizontal axis (sampling time) of the first waveform after filtering is equal to the horizontal axis (sampling time) of the first waveform before filtering, while the vertical axis may be equal or not due to the filtering effect of the filter.

[0042] S202: Remove the starting part of the filtered first waveform to obtain the second waveform; the starting part corresponds to the sampling time of the first duration.

[0043] In some implementations, to improve the user experience, the pressing depth of the press device may not reach the preset depth at initial startup. For example, if the preset depth corresponding to the preset waveform is 50mm, the pressing depth within the first 5 seconds of startup may be 30mm or 40mm, gradually increasing to 50mm, and then pressing according to the preset waveform. Therefore, in this embodiment, a portion of the waveform can be removed to obtain a second waveform. In practical applications, the first duration can be, for example, equal to 10 seconds. Removing the pressing waveform corresponding to the sampling time of 0 seconds to 10 seconds can ensure the accuracy of image recognition.

[0044] S203: Calculate the derivative of the second waveform.

[0045] In this embodiment, the first feature points can be arranged in ascending order of their corresponding first serial numbers, and each first feature point corresponds to a second serial number, with the second serial numbers increasing sequentially. It can be understood that in the first waveform diagram, each point corresponds to an abscissa (sampling time) and a total ordinate (press depth), and each sampling time corresponds to a first serial number. Therefore, the first feature points determined from the first waveform diagram can be arranged in ascending order of their corresponding first serial numbers. The second serial number corresponding to the first first feature point is 1, the second first feature point is 2, the third first feature point is 3, and so on.

[0046] Figure 5 This is a schematic diagram of a first process for determining target sampling points provided in an embodiment of this application. Figure 5 As shown, in this embodiment of the application, step S300 includes the following steps S301-S303:

[0047] S301: Determine the third waveform based on multiple first feature points. The horizontal axis of the third waveform is the second index corresponding to the first feature point, and the vertical axis is the first index corresponding to the first feature point.

[0048] Figure 6 This is a schematic diagram of the third waveform provided in an embodiment of this application. For example... Figure 6 As shown, based on the first and second indices corresponding to the first feature point, a third waveform can be obtained. The third waveform has a rhythmic step shape, including a "small slope portion" and a "large slope portion." The "small slope portion" corresponds to... Figure 6 The stepped platform in the middle.

[0049] Specifically, taking a triangular wave as an example, the derivative of its plateau portion is always zero or approximately zero. Since the first index corresponding to the plateau portion gradually increases, the plateau portion corresponds to the "small slope portion" in the third waveform diagram. The derivative of the points at and near the peak of the triangular wave is also zero or approximately zero. Alternatively, in the rising or falling portion of the triangular wave, there may be points where the derivative is zero or approximately zero. Since the first index corresponding to these points changes significantly, these points correspond to the "large slope portion" in the third waveform diagram. This process continues to form a stepped third waveform diagram, with the apex of the step corresponding to the peak or trough of the triangular wave.

[0050] S302: Calculate the derivative of the third waveform to obtain the second derivative value corresponding to each second index in the third waveform.

[0051] For the third waveform of the step shape, take its derivative to obtain the second derivative value. Then, based on the magnitude of the second derivative value, the "small slope part" of the third waveform can be selected, highlighting only the "large slope part" and the apex of the step.

[0052] S303: Determine the fourth waveform. The horizontal axis of the fourth waveform is the second sequence number, and the vertical axis is the second derivative value corresponding to the second sequence number.

[0053] Figure 7 This is a schematic diagram of the fourth waveform provided in an embodiment of this application. Figure 7 As shown, specifically, to highlight the step apex and the "high-slope portion" in the third waveform diagram, a fourth waveform diagram can be formed. The horizontal axis of the fourth waveform diagram can be the same as the second index in the third waveform diagram, increasing sequentially, and the vertical axis can be the second derivative value corresponding to each second index. Thus, the step apex and the "high-slope wavelet component" of the third waveform diagram will appear as convex points in the fourth waveform diagram. This embodiment of the application can further find the first index corresponding to these convex points, thereby determining the peak and trough apexes.

[0054] See also Figure 5 In this embodiment of the application, after step S303, the following steps S304-S306 are also included:

[0055] S304: Determine the second sequence number of multiple targets based on the fourth waveform diagram, and the second derivative value corresponding to the second sequence number of the target is greater than the second preset threshold.

[0056] In this embodiment, a second preset threshold can be set for the second derivative value. The second preset threshold can be, for example, equal to 50000, 60000, or 100000, and can be specifically set based on the numerical distribution of the second derivative value. This embodiment does not impose specific limitations on this. This allows the second derivative value of the convex point to be highlighted.

[0057] S305: Determine the target first number corresponding to the target second number based on the third waveform diagram.

[0058] In this embodiment of the application, since the horizontal coordinate (second sequence number) of the third waveform diagram corresponds to the fourth waveform diagram, and the vertical coordinate of the third waveform diagram is the first sequence number corresponding to the second sequence number, the target first sequence number corresponding to the target second sequence number can be determined based on the third waveform diagram in this embodiment of the application.

[0059] S306: In the second waveform diagram, determine the target points corresponding to the first and second target numbers.

[0060] Since there is a one-to-one correspondence between the horizontal axis (sampling time) of the second waveform and the first sequence number, and a one-to-one correspondence between the first target sequence number and the second target sequence number, the corresponding target points can be determined in the second waveform based on the first target sequence number and the second target sequence number. Subsequently, embodiments of this application can determine whether these target points are target sampling points, and thus determine whether the first waveform is a target waveform.

[0061] Further details can be found by referring to [link / reference]. Figure 5 In this embodiment of the application, after step S306, the following steps S307-S310 are also included:

[0062] S307: Determine the maximum peak value and minimum trough value in the second waveform graph.

[0063] S308: The first range is composed of the maximum peak value, the first interval above the maximum peak value, and the second interval below the maximum peak value; and the second range is composed of the minimum trough value, the third interval above the minimum trough value, and the fourth interval below the minimum trough value.

[0064] The maximum peak value corresponds to the maximum compression depth in the second waveform diagram, and the minimum trough value corresponds to the minimum compression depth in the second waveform diagram. The first range can specifically refer to a range of 10% above and below the maximum peak value, and the second range can specifically refer to a range of 10% above and below the minimum trough value. 10% is an exemplary value provided in this application embodiment, and can be determined based on actual circumstances. Thus, if the compression depth corresponding to the target point is within the first range, then the target point meets the peak condition and is a peak apex. If the compression depth corresponding to the target point is within the second range, then the target point meets the trough condition and is a trough apex.

[0065] S309: Determine the pressing depth corresponding to the first serial number of the target based on the second waveform diagram.

[0066] Understandably, based on the second waveform, the pressing depth corresponding to the first sequence number of any target can be found.

[0067] S310: If the pressing depth is within the first range or the second range, the target point corresponding to the first target number is determined as the target sampling point.

[0068] In this way, target sampling points can be determined from target points, and points corresponding to "large slope parts" in the second waveform diagram can be excluded from the target points.

[0069] Figure 8 This is a schematic diagram of a second process for determining target sampling points provided in an embodiment of this application. For example... Figure 8 As shown, in this embodiment of the application, step S400 includes the following steps S401-S402:

[0070] S401: Arrange multiple target sampling points in ascending order of their corresponding sampling times.

[0071] This ensures that the peak-valley sequence of the target sampling points is accurate.

[0072] S402: If the peak-valley order of the first N target sampling points conforms to the first order, and the peak-valley order of other target sampling points repeats periodically with the first order, the first waveform is determined as the target waveform; N is equal to the number of peak vertices and trough vertices included in the smallest repeating unit of the target waveform.

[0073] In this embodiment, when the first waveform approximates a trapezoidal wave, the value of N can specifically be equal to 5; when the first waveform approximates a triangular wave, the value of N can specifically be equal to 4. The minimum repeating units of peaks and valleys are arranged in the first order, and the peaks and valleys of trapezoidal waves or triangular waves can be continuously and periodically repeated using the minimum repeating units of peaks and valleys.

[0074] Therefore, it is determined that the peak-valley order of the first N target sampling points conforms to the first order, and that the peak-valley order of other sampling points is periodic.

[0075] In some implementations, if the first target sampling point does not correspond to the intersection of the peak-valley platform and the rising wave, then the judgment can be made according to the corresponding first order. For example, when the first target sampling point is the peak of the left side of the trapezoidal wave, the judgment can be made according to the first order of "peak-peak-valley-valley-peak", which will not be elaborated here.

[0076] Furthermore, in this embodiment of the application, step S400 may be followed by step S500:

[0077] S500: Calculate the pressing ratio of the presser based on the first waveform. If the difference between the pressing ratio and the target pressing ratio is less than the third preset threshold, determine that the pressing action of the presser is a valid pressing action. The pressing ratio is the ratio of the first time to the waveform period. The first time is equal to the duration of an upward wave in the first waveform, or the first time is equal to the duration between the start of an upward wave in the first waveform and the start of the adjacent downward wave.

[0078] Figure 9 This is a disassembly diagram of the first waveform provided in an embodiment of this application. Figure 9 (a) is a schematic diagram of the trapezoidal wave. The duration of the rising wave (pressing machine rising) is equal to T1, the duration of the rising platform (pressing machine rising and then remaining stationary) is equal to T2, the duration of the falling wave (pressing machine falling) is equal to T3, the duration of the falling platform (pressing machine falling and then remaining stationary) is equal to T4, and the total time T for a pressing action, including the downward pressing phase and the non-downward pressing phase.

[0079] Figure 9 (b) is a schematic diagram of the triangular wave. The duration of the rising wave (pressing machine rising) is equal to T1, the duration of the falling wave (pressing machine falling) is equal to T3, the duration of the falling platform (pressing machine falling and remaining stationary after pressing) is equal to T4, and the total time T for a pressing action, including the pressing and non-pressing phases, is T.

[0080] Furthermore, the press ratio refers to the ratio of the time spent in the non-pressing phase of the press to the total time spent in both the pressing and non-pressing phases of a pressing action. For example, for Figure 9 In (a), the pressing ratio is equal to (T1+T2) / T. For Figure 9 In (b), the pressing ratio is equal to T1 / T.

[0081] In some implementations, embodiments of this application can also calculate the pressing period and frequency based on the first waveform diagram. The period specifically refers to the value of T. Embodiments of this application can calculate T corresponding to multiple pressing periods, and then calculate the average of the multiple T values ​​as the pressing period of the pressing machine. The frequency specifically refers to the number of presses per minute, which can be determined by calculating how many T values ​​are included in one minute.

[0082] In some implementations, embodiments of this application may also calculate the average amplitude (press depth) of all T2 stages in the first waveform diagram and the average amplitude (press depth) of all T4 stages in the first waveform diagram, and then calculate the difference between the two average values. In this way, the pressing depth of the presser can be obtained without calculating the pressing depth based on a single measurement value of the distance sensor. Instead, a relative value is used for calculation, which can save the step of zeroing the distance sensor.

[0083] In some implementations, embodiments of this application can also calculate the average of multiple first waveforms from the same pressing machine. For example, the pressing machine operates multiple times with the same preset waveform, sampling is performed for each operation to obtain multiple first waveforms, the period is calculated based on each of the multiple first waveforms, and then the average of the periods is taken as the pressing period of the pressing machine. This makes the pressing period calculation more accurate.

[0084] According to the signal recognition method provided in the embodiments of this application, the embodiments of this application also provide a signal recognition device, such as... Figure 10 As shown, the device may include: a sampling module 601, used to sample the pressing depth of the presser at a preset frequency to obtain a first waveform; the horizontal axis of the first waveform is the sampling time, and the vertical axis is the pressing depth; a derivative module 602, used to calculate the derivative of the first waveform to obtain multiple first feature points in the first waveform; the first derivative value corresponding to the first feature point is less than a first preset threshold; a first determination module 603, used to determine multiple target sampling points from the multiple first feature points, the target sampling points being peaks or troughs; and a second determination module 604, used to sort the multiple target sampling points according to the order of their corresponding sampling times, and if the peak-to-trough order of the multiple target sampling points conforms to the first order, the first waveform is determined as the target waveform, the first order corresponding to the peak-to-trough order of the peaks and troughs in the target waveform.

[0085] In a specific implementation, the present invention also provides a computer storage medium, wherein the computer storage medium may store a program, and when the program is executed, it may include some or all of the steps of the network resource reuse area determination method provided by the present invention. The storage medium may be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0086] It is readily understood that, based on the several embodiments provided in this application, those skilled in the art can combine, split, or reorganize the embodiments of this application to obtain other embodiments, none of which exceed the protection scope of this application.

[0087] The above detailed embodiments further illustrate the purpose, technical solution, and beneficial effects of the embodiments of this application. It should be understood that the above are merely specific embodiments of the embodiments of this application and are not intended to limit the protection scope of the embodiments of this application. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solutions of the embodiments of this application should be included within the protection scope of the embodiments of this application.

Claims

1. A waveform recognition method, characterized in that, include: The pressing depth of the presser is sampled at a preset frequency to obtain the first waveform. The horizontal axis of the first waveform graph represents the sampling time, and the vertical axis represents the pressing depth. The derivative of the first waveform is obtained to obtain multiple first feature points in the first waveform; the first derivative value corresponding to the first feature point is less than a first preset threshold. Multiple target sampling points are determined from the plurality of first feature points, wherein the target sampling points are peak vertices or trough vertices; The multiple target sampling points are sorted according to the order of their corresponding sampling times. If the peak-valley order of the multiple target sampling points matches the first order, the first waveform is determined as the target waveform. The first order corresponds to the peak-valley order of the peak vertices and trough vertices in the target waveform.

2. The waveform recognition method according to claim 1, characterized in that, The step of taking the derivative of the first waveform includes: The first waveform is filtered based on a preset filter to obtain the filtered first waveform. The first waveform after filtering is removed to obtain the second waveform; the first portion corresponds to the sampling time of the first duration. The derivative of the second waveform is calculated.

3. The waveform recognition method according to claim 2, characterized in that, The preset filter is a median filter or a Chebyshev filter.

4. The waveform recognition method according to claim 2, characterized in that, In the first waveform diagram, each sampling time corresponds to a first sequence number, and the value of the first sequence number is used to represent the number of samplings; the first feature points are arranged in ascending order of their corresponding first sequence numbers, and each first feature point corresponds to a second sequence number, with the second sequence numbers increasing sequentially. The step of determining multiple target sampling points from the plurality of first feature points includes: A third waveform is determined based on the plurality of first feature points, wherein the horizontal axis of the third waveform is the second sequence number corresponding to the first feature point, and the vertical axis is the first sequence number corresponding to the first feature point. By taking the derivative of the third waveform, the second derivative value corresponding to each second index in the third waveform is obtained; A fourth waveform is determined, wherein the horizontal axis of the fourth waveform is the second sequence number, and the vertical axis is the second derivative value corresponding to the second sequence number.

5. The waveform recognition method according to claim 4, characterized in that, After determining the fourth waveform, the method further includes: Based on the fourth waveform, multiple target second serial numbers are determined, and the second derivative value corresponding to the target second serial number is greater than a second preset threshold. Based on the third waveform diagram, determine the target first number corresponding to the target second number; In the second waveform diagram, the target points corresponding to the first target number and the second target number are determined.

6. The waveform recognition method according to claim 5, characterized in that, After determining the target points corresponding to the first target number and the second target number in the second waveform diagram, the method further includes: Determine the maximum peak value and minimum trough value in the second waveform graph; A first range is formed by the maximum peak value, a first interval above the maximum peak value, and a second interval below the maximum peak value; and a second range is formed by the minimum trough value, a third interval above the minimum trough value, and a fourth interval below the minimum trough value. The pressing depth corresponding to the first serial number of the target is determined based on the second waveform diagram; If the pressing depth is within the first range or the second range, the target point corresponding to the first target number is determined as the target sampling point.

7. The waveform recognition method according to claim 1, characterized in that, The step of determining the first waveform as the target waveform if the peak-valley order corresponding to the plurality of target sampling points conforms to the first order includes: The plurality of target sampling points are arranged in ascending order according to their corresponding sampling times; If the peak-valley order of the first N target sampling points conforms to the first order, and the peak-valley order of the other target sampling points repeats periodically with the first order, the first waveform is determined as the target waveform; N is equal to the number of peak vertices and trough vertices included in the minimum repeating unit of the peak-valley of the target waveform.

8. The waveform recognition method according to claim 1, characterized in that, After the step of determining the first waveform as the target waveform if the peak-valley order corresponding to the plurality of target sampling points conforms to the first order, the method further includes: The pressing ratio of the presser is calculated based on the first waveform. If the difference between the pressing ratio and the target pressing ratio is less than a third preset threshold, the pressing action of the presser is determined to be a valid pressing action. The pressing ratio is the ratio of a first time to the waveform period. The first time is equal to the duration of an upward wave in the first waveform, or the first time is equal to the duration between the start of an upward wave in the first waveform and the start of the adjacent downward wave.

9. The waveform recognition method according to claim 1, characterized in that, The first preset threshold is equal to 1.

10. A waveform recognition device, characterized in that, include: The sampling module is used to sample the pressing depth of the presser at a preset frequency to obtain the first waveform. The horizontal axis of the first waveform graph represents the sampling time, and the vertical axis represents the pressing depth. The derivative module is used to calculate the derivative of the first waveform to obtain multiple first feature points in the first waveform; the first derivative value corresponding to the first feature point is less than a first preset threshold. The first determining module is used to determine multiple target sampling points from the plurality of first feature points, wherein the target sampling points are peak vertices or trough vertices; The second determining module is used to sort the plurality of target sampling points according to the order of their corresponding sampling times. If the peak-valley order corresponding to the plurality of target sampling points conforms to the first order, the first waveform diagram is determined as the target waveform diagram. The first order corresponds to the peak-valley order of the peak vertices and trough vertices in the target waveform diagram.

Images