Knock signal recognition method and related device

Abstract

The present application relates to the field of signal recognition technology, and in particular to a knock signal recognition method and related devices. The method includes: obtaining an acceleration signal collected by an acceleration sensor; the acceleration sensor is set on the door; determining multiple first valid waveforms in the acceleration signal; if the multiple first valid waveforms meet the waveform distribution conditions, then calculating the energy value of the acceleration signal to obtain an energy signal; determining multiple second valid waveforms in the energy signal; if the multiple second valid waveforms meet the energy value distribution conditions, then determining that the acceleration signal is a signal generated by knocking on the door. The embodiment of the present invention can improve the accuracy of identifying knock signals.

Description

[Technical field]

[0001] The present application relates to the field of signal recognition technology, and in particular to a knock signal recognition method and related devices. [Background technology]

[0002] With the improvement of living standards, people's living environment has improved significantly. If the house is large or the door panels are thick, the sound insulation effect of the house will be better. When someone knocks on the door outside, the people inside may not hear the knock. In order to easily identify the knock, a doorbell can be set outside the door, and the doorbell is connected to the receiving device inside the house. When the doorbell is triggered, the receiving device inside the house will prompt that someone is knocking on the door outside. Although this method can remind residents that someone is knocking on the door, some people are not used to ringing the doorbell and installing a doorbell also affects the aesthetics of the door.

[0003] In the related art, another method of prompting someone to knock on the door is proposed. For example, a vibration sensor can be attached to the door. When the vibration sensor detects an acceleration signal of a certain intensity, it will be triggered, prompting someone to knock on the door. However, this method also has major drawbacks. For example, the vibration sensor is difficult to distinguish between vibrations caused by wind, door movement, or decoration noise, and is more likely to be triggered by mistake. [Summary of the invention]

[0004] The embodiment of the present invention provides a knock signal recognition method and related devices, which can improve the accuracy of recognizing knock signals.

[0005] In a first aspect, an embodiment of the present invention provides a knock signal recognition method, comprising:

[0006] Acquiring an acceleration signal collected by an acceleration sensor; the acceleration sensor is arranged on the door;

[0007] determining a plurality of first valid waveforms in the acceleration signal;

[0008] If the plurality of first effective waveforms satisfy the waveform distribution condition, performing energy value calculation on the acceleration signal to obtain an energy signal;

[0009] determining a plurality of second valid waveforms in the energy signal;

[0010] If the plurality of second valid waveforms satisfy the energy value distribution condition, it is determined that the acceleration signal is a signal generated by knocking on the door.

[0011] In the above scheme, whether the acceleration signal is generated by knocking on the door is determined by performing dual judgments on the waveform distribution and energy distribution of the acceleration signal, thereby improving the accuracy of identifying the knocking signal.

[0012] In one possible implementation, the acceleration signal includes sub-signals of multiple direction axes;

[0013] After acquiring the acceleration signal collected by the acceleration sensor, the method further includes:

[0014] Calculate the variance value of the axon signal in each direction;

[0015] determining a maximum variance value from among the calculated variance values;

[0016] Determine the sub-signal corresponding to the maximum variance value as the original signal;

[0017] Calculating the mean of the original signal;

[0018] Subtract the mean value from the original signal to obtain an absolute value signal;

[0019] Determining a plurality of first valid waveforms in the acceleration signal comprises: determining the plurality of first valid waveforms from the absolute value signal;

[0020] Calculating the energy value of the acceleration signal includes: calculating the energy value of the absolute value signal.

[0021] In one possible implementation manner, determining the plurality of first valid waveforms from the absolute value signal includes:

[0022] Determine a first waveform having a peak value greater than a first threshold from the absolute value signal;

[0023] Taking the first time as the step length, determining the first waveform with the largest peak value within the first time step range;

[0024] The first waveform with the largest peak value is determined as the first effective waveform.

[0025] In one possible implementation, the waveform distribution condition includes a combination of one or more of the following:

[0026] The number of the first valid waveforms is within a preset number range;

[0027] The time interval between adjacent first effective waveforms in the plurality of first effective waveforms is less than a second threshold;

[0028] The peak value of the first effective waveform is less than a third threshold.

[0029] In one possible implementation, determining a plurality of second valid waveforms in the energy signal includes:

[0030] Determine from the energy signal a second waveform having a peak value greater than a fourth threshold;

[0031] Taking the second time as the step length, determining the second waveform with the largest peak value within the second time step range;

[0032] The second waveform with the largest peak value is determined as the second effective waveform.

[0033] In one possible implementation, the energy value distribution condition includes an energy waveform condition; the energy waveform condition includes a combination of one or more of the following:

[0034] The number of the second valid waveforms is within a preset number range;

[0035] A time interval between adjacent second effective waveforms in the plurality of second effective waveforms is less than a fifth threshold.

[0036] In one possible implementation, the knock signal also satisfies a high-frequency vibration condition, wherein determining that the acceleration signal satisfies the high-frequency vibration condition includes:

[0037] Performing frequency domain transformation on the acceleration signal to obtain a frequency domain signal;

[0038] Calculating frequency band energy of a first frequency band and frequency band energy of a second frequency band according to the frequency domain signal; wherein the frequency of the first frequency band is higher than the frequency of the second frequency band;

[0039] If the frequency band energy value of the first frequency band is greater than the frequency band energy value of the second frequency band, it is determined that the acceleration signal meets the high-frequency vibration condition.

[0040] In one possible implementation, the energy value distribution condition includes a first energy value distribution condition; wherein determining that any one of the second effective waveforms satisfies the first energy value distribution condition includes:

[0041] determining a peak energy value of the second effective waveform;

[0042] Determine the noise energy value between two adjacent second effective waveforms;

[0043] determining a first ratio of the peak energy value to an associated noise energy value;

[0044] If the first ratio is greater than a sixth threshold, it is determined that the second effective waveform satisfies a first energy value distribution condition.

[0045] In one possible implementation, the energy value distribution condition includes a second energy value distribution condition; wherein determining that any one of the second effective waveforms satisfies the second energy value distribution condition includes:

[0046] Determining a total energy value of the second effective waveform;

[0047] The energy value of the second effective waveform is gradually accumulated with the peak point of the second effective waveform as the base point until the obtained energy accumulation value is equal to or greater than k1 times the total energy value; 0.5<k1<1;

[0048] Determine the first time length corresponding to the second effective waveform when the energy accumulated value is equal to or greater than k1 times the total energy value;

[0049] If the first time length is less than k2 times the total time length of the second effective waveform, it is determined that the second effective waveform meets the second energy value distribution condition; 0<k2<0.6.

[0050] In one possible implementation, the energy value distribution condition includes a third energy value distribution condition; wherein determining that the plurality of second valid waveforms satisfy the third energy value distribution condition includes:

[0051] Determining a maximum peak value and a minimum peak value from the peak values ​​of the plurality of second effective waveforms;

[0052] determining a second ratio of the maximum peak value to the minimum peak value;

[0053] If the second ratio is less than a seventh threshold, it is determined that the plurality of second effective waveforms satisfy a third energy value distribution condition.

[0054] In one possible implementation, the energy value distribution condition includes a fourth energy value distribution condition; wherein determining that the plurality of second valid waveforms satisfy the energy value distribution condition includes:

[0055] respectively determining the time lengths covered by the plurality of second effective waveforms;

[0056] Determine a maximum time length and a minimum time length from the time lengths corresponding to the plurality of second effective waveforms;

[0057] determining a third ratio of the maximum time length to the minimum time length;

[0058] If the third ratio is less than an eighth threshold, it is determined that the plurality of second effective waveforms satisfy a fourth energy value distribution condition.

[0059] In a second aspect, an embodiment of the present invention provides a knock signal recognition device, comprising:

[0060] An acquisition module, used to acquire an acceleration signal collected by an acceleration sensor; the acceleration sensor is arranged on the door;

[0061] A determination module, used for determining a plurality of first valid waveforms in the acceleration signal;

[0062] A calculation module, configured to calculate the energy value of the acceleration signal to obtain an energy signal when the plurality of first effective waveforms meet a waveform distribution condition;

[0063] The determination module is further used to determine a plurality of second valid waveforms in the energy signal; when the plurality of second valid waveforms satisfy an energy value distribution condition, it is determined that the acceleration signal is a signal generated by knocking on the door.

[0064] In a third aspect, an embodiment of the present invention provides a knock signal recognition device, comprising:

[0065] at least one processor; and

[0066] at least one memory in communication with the processor, wherein:

[0067] The memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the method described in the first aspect.

[0068] In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions enable the computer to execute the method provided in the first aspect.

[0069] It should be understood that the second to fourth aspects of the embodiments of the present invention are consistent with the technical solutions of the first aspect of the embodiments of the present invention, and the beneficial effects achieved by each aspect and the corresponding feasible implementation methods are similar and will not be described in detail.

Brief Description of the Drawings

[0070] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0071] Figure 1 A flowchart of a knock signal recognition method provided by an embodiment of the present invention;

[0072] Figure 2 A waveform diagram of an original signal provided by an embodiment of the present invention;

[0073] Figure 3 A waveform diagram of an absolute value signal provided by an embodiment of the present invention;

[0074] Figure 4 A schematic diagram of a first effective waveform provided by an embodiment of the present invention;

[0075] Figure 5 A schematic diagram of an energy signal provided by an embodiment of the present invention;

[0076] Figure 6 A schematic diagram of a second effective waveform provided by an embodiment of the present invention;

[0077] Figure 7 A flowchart of another knock signal recognition method provided by an embodiment of the present invention;

[0078] Figure 8 A schematic diagram of an energy waveform provided by an embodiment of the present invention;

[0079] Fig. 9 Another energy waveform schematic diagram provided by an embodiment of the present invention;

[0080] Fig.10 A schematic diagram of the structure of a knock signal recognition device provided by an embodiment of the present invention;

[0081] Fig.11 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. [Specific implementation method]

[0082] In order to better understand the technical solution of the present invention, the embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0083] In order to accurately identify the knock signal, an embodiment of the present invention provides a knock signal recognition scheme. In this scheme, an acceleration sensor can be set on the door panel, for example, inside the door panel or on the back of the door. When someone knocks on the door or there is wind blowing, the door moves, and decoration noise is generated around, the acceleration sensor can collect vibration signals. Afterwards, the processing module can determine whether the vibration signal collected by the acceleration sensor is generated by knocking on the door based on the vibration characteristics of the knock signal, thereby accurately identifying the knock signal and reducing the occurrence of false triggering. In some embodiments, the processing module can be integrated with the acceleration sensor. In one example, the processing module can be a main control chip. The main control chip and the acceleration sensor are set in the same device. The device can be set inside the door panel or on the back of the door. In some embodiments, the processing module and the acceleration sensor can be set separately and independently. For example, the acceleration sensor is set inside the door panel or on the back of the door, and the processing module is set in the gateway or server.

[0084] Figure 1 The flowchart of a knock signal recognition method provided by an embodiment of the present invention. The execution subject of the method is the above-mentioned processing module. Figure 1 As shown, the processing steps of the method include:

[0085] Step 101: Acquire an acceleration signal collected by an acceleration sensor.

[0086] The acceleration sensor is arranged on the door. Optionally, the acceleration sensor can be installed inside the door panel or on the back side of the door. When someone knocks on the door or the door shakes or moves due to other reasons, the acceleration sensor can collect an acceleration signal. Based on the subsequent steps of the embodiment of the present invention, it can be determined whether the acceleration signal is a signal generated by knocking on the door.

[0087] Step 102, determining multiple first valid waveforms in the acceleration signal. The first valid waveform may be a waveform in the acceleration signal whose peak value is greater than a certain threshold or satisfies a certain waveform condition. Optionally, before identifying the first valid waveform from the acceleration signal, the acceleration signal may be preprocessed, and then the first valid waveform may be identified from the preprocessed signal.

[0088] In some embodiments, the acceleration signal contains sub-signals of multiple directional axes. For example, the acceleration signal contains sub-signals of three directional axes (X, Y, Z). Then, preprocessing the acceleration signal may include: calculating the variance value of each directional axis sub-signal; determining the maximum variance value from the calculated variance values; and determining the sub-signal corresponding to the maximum variance value as the original signal. Afterwards, the absolute value of the original signal is obtained to obtain an absolute value signal. A specific example of determining an absolute value signal is also provided in an embodiment of the present invention, in which it is assumed that the acceleration signal collected by the acceleration sensor contains sub-signals of three directional axes (X, Y, Z). Among the three directional axes, if the variance value of the Y-axis sub-signal is the largest, the Y-axis sub-signal is determined as the original signal. Similarly, if the variance value of the sub-signal of another directional axis is the largest, the sub-signal of the corresponding directional axis is determined as the original signal. Figure 2 A specific schematic diagram of an original signal is shown. Optionally, Figure 2 The original signal shown is a directional axis sub-signal of the acceleration signal. For example, among the three directional axes (X, Y, Z), the variance value of the Y-axis sub-signal is the largest, then Figure 2 The original signal shown is the Y-axis sub-signal. Figure 2 The following is a partial signal intercepted from the Y-axis sub-signal. Figure 2 The horizontal axis of the original signal shown in FIG. 1 represents the sampling time, and the vertical axis represents the acceleration. After determining the original signal, the DC baseline in the original signal is removed. The DC baseline in the original signal may include: calculating the mean of the original signal, Figure 2 Subtract the mean from the original signal shown in the figure to obtain the original signal after removing the DC baseline. Then, take the absolute value of the original signal after removing the DC baseline to obtain the absolute value signal. Figure 3 A schematic diagram of an absolute value signal is shown. Figure 3 The absolute value signal shown is based on Figure 2 The original signal shown is obtained.

[0089] In an embodiment of the present invention, after determining the absolute value signal according to the original signal, a first valid waveform is further determined from the absolute value signal. Determining the first valid waveform from the absolute value signal may include: determining a first waveform having a peak value greater than a first threshold value from the absolute value signal; determining a first waveform having a maximum peak value within the first time step range with a first time as a step length; and determining the first waveform having the maximum peak value as the first valid waveform.

[0090] Optionally, the first threshold can be set according to actual needs. Figure 3 In the absolute value signal shown, the first waveform greater than the first threshold value can be, for example, Figure 3 The waveforms No. 199, 200, 201, 202, 203, 204, 205, 207, 208, 209, 210, 211, 212, 213 and 214 identified in are the first waveform.

[0091] In some embodiments, after determining the first waveform from the absolute value signal, the first valid waveform is further determined. Optionally, determining the first valid waveform from the first waveform may include: determining a first time step. The first time step may be set according to actual needs, for example, 50 sampling unit times may be determined as the first time step. Afterwards, the abscissa of the absolute value signal may be divided into multiple intervals with the first time as the step. The first waveform with the largest peak value is determined in each interval, and the first waveform with the largest peak value in each interval is determined as the first valid waveform.

[0092] In some embodiments, determining the first valid waveform from the first waveform may further include: performing the following iterative determination on the first waveform according to the order of sampling time:

[0093] Determine whether the peak value of the current first waveform is greater than the peak value of the candidate first valid waveform. The candidate first valid waveform is a first waveform whose sampling time is before the current first waveform. Optionally, if one or more first waveforms are included between the candidate first valid waveform and the current first waveform, the peak value of the candidate first valid waveform is greater than the peak value of the one or more first waveforms.

[0094] If the peak value of the current first waveform is greater than the peak value of the candidate first effective waveform, the current first waveform is determined as the candidate first effective waveform, and starting from the sampling time of the candidate first effective waveform, a search is performed within the first time step to find whether there is a first waveform greater than the candidate first effective waveform.

[0095] If the peak value of the current first waveform is less than the peak value of the candidate first effective waveform, determine whether the sampling time difference between the current first waveform and the candidate first effective waveform is greater than the first time step. If the sampling time difference between the current first waveform and the candidate first effective waveform is greater than or equal to the first time step, determine the candidate first effective waveform as the first effective waveform. If the sampling time difference between the current first waveform and the candidate first effective waveform is less than the first time step, compare the next first waveform with the candidate first effective waveform as the current first waveform. In this way, each first effective waveform is determined from the first waveform by iterative judgment with the first time as the step.

[0096] In one example, if Figure 3 As shown, the first time step is set to 50 sampling units. In this example, each first valid waveform can be determined in an iterative manner. Figure 3 As shown, waveform No. 199 (with a horizontal coordinate of 7760) is determined as the candidate first valid waveform. Afterwards, it is determined in turn whether each first waveform with a horizontal coordinate in the range of 7760-7810 is greater than the candidate first valid waveform. When waveform No. 200 (with a horizontal coordinate of 7772) is searched, it is determined that waveform No. 200 is greater than the peak value of waveform No. 199, and waveform No. 200 is determined as the candidate first valid waveform. After waveform No. 200 is determined as the candidate first valid waveform, it is determined in turn whether each first waveform with a horizontal coordinate in the range of 7772-7822 is greater than the candidate first valid waveform. Among them, the peak values ​​of waveforms No. 201 to 205 are all smaller than the peak value of waveform No. 200. When waveform No. 206 (with a horizontal coordinate of 7863) is searched, the horizontal coordinate of waveform No. 206 has exceeded the search area. Therefore, waveform No. 200 can be determined as the first valid waveform. According to the above method, Figure 3 Each first valid waveform is identified in the waveforms shown.

[0097] In some embodiments, in addition to determining the first effective waveform from the absolute value signal, the method further includes deleting side lobe peaks outside the first effective waveform. Figure 3 The 199th, 201st, 202nd, 203rd, 204th and 205th peaks are all side lobe peaks of the 200th peak. Figure 4 As shown, Figure 4 It is the absolute value signal containing the first effective waveform obtained after deleting the sidelobe peak. Figure 4 The 49th, 50th and 51st waveforms in the above are the first valid waveforms. Deleting the side lobe peaks can prevent the side lobe peaks from affecting subsequent calculations, making the judgment results more accurate.

[0098] Step 103, determining whether the plurality of first valid waveforms satisfy a waveform distribution condition. If the plurality of first valid waveforms satisfy the waveform distribution condition, executing step 104; if not, determining that the acceleration signal is not a signal generated by knocking on the door.

[0099] Among them, the waveform distribution condition can be determined according to the vibration characteristics of the knock signal. In some embodiments, the waveform distribution condition may include one or more of the following combinations: the number of first valid waveforms is within a preset number range; the time interval between adjacent first valid waveforms in the multiple first valid waveforms is less than the second threshold; the peak value of the first valid waveform is less than the third threshold. For example, in the acceleration signal, the number of first valid waveforms is three, the interval between adjacent first valid waveforms does not exceed 1 second, and the value of the peak value of each first valid waveform does not exceed 500, then it can be determined that the acceleration signal meets the waveform distribution condition. The main purpose of the above steps is to preliminarily screen the acceleration signal and determine whether the acceleration signal roughly meets the characteristics and requirements of the knock signal. If it is satisfied, continue to execute step 104 to further determine whether the signal is a knock signal. If it is not satisfied, it can be determined that the acceleration signal is not a signal generated by knocking.

[0100] Step 104: Calculate the energy value of the acceleration signal to obtain an energy signal. Generally, the energy value of the acceleration signal is calculated by squaring the acceleration signal to obtain the energy signal.

[0101] Step 105, determining multiple second valid waveforms in the energy signal. The second valid waveform may be a waveform in the energy signal whose peak value is greater than a certain threshold or satisfies a certain waveform condition. Optionally, before identifying the second valid waveform from the energy signal, the energy signal may be preprocessed, and then the second valid waveform may be identified from the preprocessed energy signal.

[0102] In some embodiments, the energy signal obtained based on the absolute value signal usually contains some interference factors such as interference signals. Therefore, preprocessing the energy signal may include: low-pass filtering the energy signal using a finite impulse response (FIR) filter to reduce interference factors in the energy signal. Afterwards, the second valid waveform can be identified from the filtered energy signal.

[0103] In some embodiments, determining the second effective waveform from the energy signal may include: determining a second waveform having a peak value greater than a fourth threshold value from the energy signal; determining a second waveform having a maximum peak value within a second time step range with a second time as a step size; and determining the second waveform having the maximum peak value as the second effective waveform. In embodiments of the present invention, the method for determining the second waveform from the energy signal and determining the second effective waveform from the second waveform may refer to the above-mentioned process of determining the first waveform and the first effective waveform, which will not be described in detail here. In some embodiments, after determining the second effective waveform from the absolute value signal, the method further includes deleting sidelobe peaks outside the second effective waveform.

[0104] In some embodiments, the fourth threshold may be determined based on the first threshold. In some embodiments, the second time can be set according to actual needs. For example, in one example, the second time can be set to 50 sampling units. Figure 5 As shown in FIG. 1 , the second waveforms whose peak values ​​are greater than the fourth threshold value include waveforms No. 67, 68, 69 and 70. Figure 6 As shown, the second effective waveform determined from the second waveform includes the 8th, 9th and 10th waveforms.

[0105] Step 106, determining whether the plurality of second valid waveforms satisfy an energy value distribution condition, if so, determining that the acceleration signal is a signal generated by knocking on the door; if not, determining that the energy signal is not a signal generated by knocking on the door.

[0106] In some embodiments, the energy value distribution condition can be determined based on the vibration characteristics of the knock signal. Optionally, the energy value distribution condition can include an energy waveform condition. Optionally, the energy waveform condition includes a combination of one or more of the following: the number of second valid waveforms is within a preset number range; the time interval between adjacent second valid waveforms in multiple second valid waveforms is less than a fifth threshold. For example, in the energy signal, the number of second valid waveforms is 3, and the time interval between adjacent second valid waveforms does not exceed 1 second, then it can be determined that the energy signal meets the energy waveform condition.

[0107] In some embodiments, in order to make the signal recognition result more accurate, in addition to judging the above waveform distribution conditions and energy value distribution conditions of the acceleration signal, the high-frequency vibration condition of the acceleration signal can also be judged. Among them, when the acceleration signal is a signal generated by knocking on the door, the high-frequency energy in the acceleration signal must be greater than the low-frequency energy. Figure 7 As shown, the processing steps for determining whether the high-frequency energy of the acceleration signal is greater than the low-frequency energy include:

[0108] Step 201, frequency domain transform the acceleration signal to obtain a frequency domain signal. Optionally, frequency domain transform can be performed on the original signal with the DC baseline removed in step 102. Optionally, Fast Fourier Transform (FFT) can be performed on the acceleration signal to obtain a frequency domain signal.

[0109] Step 202, calculate the frequency band energy of the first frequency band and the frequency band energy of the second frequency band according to the frequency domain signal; wherein the frequency of the first frequency band is higher than the frequency of the second frequency band. In an example, the first frequency band can be set to 50HZ-200HZ, for example, and the second frequency band can be set to 0HZ-50HZ, for example. The energy of each frequency band can be obtained by squaring the frequency domain signal. Then, the maximum x1 energy values ​​in 0HZ-50HZ are selected, and the average value of the x1 energy values ​​is calculated to obtain the frequency band energy value of the second frequency band. Similarly, the maximum x2 energy values ​​in 50HZ-200HZ are selected, and the average value of the x2 energy values ​​is calculated to obtain the frequency band energy value of the first frequency band.

[0110] Step 203, determine whether the frequency band energy value of the first frequency band is greater than the frequency band energy value of the second frequency band. If greater, it is determined that the acceleration signal meets the high-frequency vibration condition. If the frequency band energy value of the first frequency band is less than or equal to the frequency band energy value of the second frequency band, the acceleration signal does not meet the high-frequency vibration condition, and it can be determined that the acceleration signal is not generated by knocking on the door.

[0111] In some embodiments, when determining whether the acceleration signal is a signal generated by knocking on the door, the acceleration signal can also be determined based on the energy concentration principle. The energy concentration principle verifies whether the energy of the acceleration signal is concentrated near the peak value. Optionally, the first energy value distribution condition can be used to determine whether the energy of the acceleration signal is concentrated near the peak value. In some embodiments, the first energy value distribution condition includes: the peak energy is greater than the noise energy.

[0112] Optionally, determining whether any one of the second effective waveforms satisfies the first energy value distribution condition includes: determining the peak energy value of the second effective waveform; determining the noise energy value between two adjacent second effective waveforms; determining a first ratio of the peak energy value to the associated noise energy value; if the first ratio is greater than a sixth threshold, determining that the second effective waveform satisfies the first energy value distribution condition.

[0113] Optionally, determining the peak energy value of the second effective waveform may include: determining the peak value of the second effective waveform as the peak energy value of the waveform.

[0114] Optionally, determining the peak energy value of the second effective waveform may further include: determining a peak interval according to the peak value of the second effective waveform; and accumulating and averaging the second effective waveform within the peak interval to obtain the peak energy value of the second effective waveform.

[0115] like Figure 8 As shown in FIG. 1 , the horizontal coordinate corresponding to the peak value of the second effective waveform is taken as the center point, and the 20 sampling units of time around the center point are determined as the peak interval. The second effective waveform within the peak interval is accumulated and averaged to obtain the peak energy value, that is, Figure 8 In this way, the peak energy value of each second effective waveform can be determined.

[0116] Optionally, determining the noise energy value between two adjacent second effective waveforms includes: determining a noise interval between two adjacent second effective waveforms, and accumulating and averaging noise waveforms within the noise interval to obtain a noise energy value.

[0117] In some embodiments, the noise interval is determined according to the horizontal coordinates of the peak values ​​of two adjacent second effective waveforms. Figure 8 As shown, the horizontal coordinates of the peaks of two adjacent second effective waveforms are PEAK1 and PEAK2 respectively. The distance between PEAK1 and PEAK2 is DIS. According to DIS, the noise interval is determined to be PEAK1+DIS / 3 to PEAK1+DIS*2 / 3. Then, the noise energy mean of the noise interval is obtained, that is, Figure 8 The EngergyNoiseMean in .

[0118] Determine a first ratio of the peak energy value of the second effective waveform to the associated noise energy value. If the first ratio is greater than the sixth threshold, it can be determined that the second effective waveform meets the first energy value distribution condition. If the first ratio is less than or equal to the sixth threshold, it is determined that the signal does not meet the first energy value distribution condition, and it is determined that the signal is not a signal generated by knocking on the door. In some specific examples, if the peak energy mean (EnergyPeakMean) is more than 3 times the noise energy mean (EngergyNoiseMean), it is determined that the signal meets the first energy value distribution condition.

[0119] In some embodiments, the energy concentration principle may also include a second energy value distribution condition. In some embodiments, the second energy value distribution condition includes: the energy of the acceleration signal is concentrated around the peak value. Optionally, determining that any second effective waveform satisfies the second energy value distribution condition includes: determining the total energy value of the second effective waveform; gradually accumulating the energy value of the second effective waveform based on the peak point of the second effective waveform until the obtained energy accumulation value is equal to or greater than k1 times the total energy value; wherein 0.5<k1<1. Determine the first time length corresponding to the second effective waveform when the energy accumulation value is equal to or greater than k1 times the total energy value; if the first time length is less than k2 times the total time length of the second effective waveform, then determine that the second effective waveform satisfies the second energy value distribution condition; wherein 0<k2<0.6.

[0120] Optionally, determining the total energy value of the second effective waveform may include: determining the starting position and the ending position of the abscissa of the second effective waveform, and accumulating the values ​​of the second effective waveform within the interval between the starting position and the ending position to obtain the total energy value of the second effective waveform.

[0121] In some embodiments, determining the starting position of the abscissa of the second effective waveform includes: determining the peak abscissa of the second effective waveform preceding the current second effective waveform (referred to as the first abscissa) according to the order of sampling time; determining the starting position of the current second effective waveform according to the peak abscissa of the current second effective waveform (referred to as the second abscissa) and the first abscissa. For example, (first abscissa+second abscissa) / 2 is determined as the starting position of the current second effective waveform.

[0122] like Fig. 9 As shown, the horizontal coordinate corresponding to the peak value of waveform No. 8 is marked as PEAK_X1 (for example, 7782). Wherein, there is no other second valid waveform before the sampling time of waveform No. 8, then the horizontal coordinate starting position of waveform No. 8 can be: Start = (0 + PEAK_X1) / 2. Optionally, the horizontal coordinate corresponding to the peak value of waveform No. 9 is marked as PEAK_X2 (for example, 7873). The second valid waveform before waveform No. 9 is waveform No. 8. Then the horizontal coordinate starting position of waveform No. 9 can be Start = (PEAK_X1 + PEAK_X2) / 2.

[0123] In some embodiments, determining the end position of the abscissa of the second effective waveform includes: determining the peak abscissa of the second effective waveform after the current second effective waveform (called the third abscissa) according to the order of sampling time; determining the end position of the current second effective waveform according to the peak abscissa of the current second effective waveform (called the second abscissa) and the third abscissa. For example, (the second abscissa + the third abscissa) / 2 is determined as the end position of the current second effective waveform.

[0124] Still Fig. 9 For example, the second valid waveform after the waveform No. 8 is the waveform No. 9. Then the end position of the horizontal coordinate of the waveform No. 8 can be end=(PEAK_X1+PEAK_X2) / 2.

[0125] Still Fig. 9 For example, after determining the starting position and the ending position of the 8th waveform, the values ​​of the 8th waveform within the starting position and the ending position are accumulated to obtain the total energy value of the 8th waveform.

[0126] In some embodiments, the energy value of the second effective waveform is gradually accumulated with the peak point of the second effective waveform as the base point until the obtained energy accumulation value is equal to or greater than k1 times the total energy value, including: determining the peak value of the current second effective waveform; selecting a larger value from the waveform values ​​on the left and right sides of the peak value for accumulation until the obtained energy accumulation value is equal to or greater than k1 times the total energy value. Among them, k1 can be set according to actual needs. For example, k1 can be set to 0.6, 0.7, 0.8 or 0.9, etc.

[0127] In one example, for example, calculating Fig. 9The energy accumulation value of the 8th waveform includes: determining the horizontal coordinate of the peak value of the 8th waveform as PEAK_X1, and the peak value of the 8th waveform is SINGAL(PEAK_X1). Then, taking PEAK_X1 as the base point, determine the size of the waveform values ​​at two positions on both sides of the peak. For example, determine the size of SINGAL(PEAK_X1-1) and SINGAL(PEAK_X1+1). If SINGAL(PEAK_X1-1) is greater than SINGAL(PEAK_X1+1), then add the energy of SINGAL(PEAK_X1-1) to the energy accumulation value (ENERGY), and update the energy accumulation value to: ENERGY=ENERGY+SINGAL(PEAK_X1-1). Then, determine the position PEAK_X1-2 again on the side of PEAK_X1-1. Compare the size of SINGAL(PEAK_X1-2) and SINGAL(PEAK_X1+1). If SINGAL(PEAK_X1-2) is greater, the energy value of SINGAL(PEAK_X1-2) is added to the energy accumulation value, that is, ENERGY=ENERGY+SINGAL(PEAK_X1-2). In this way, the energy accumulation value is equal to or greater than k1 times the total energy value of the 8th waveform.

[0128] In a specific example, k1 can be set to 0.8 and k2 can be set to 0.5. That is, when the energy accumulation value reaches 80% of the total value of the peak energy value (EnergyPeakSum1), the accumulated horizontal coordinate length (i.e., the first time length) of the second effective waveform is determined. If the first time length is less than 50% of the total horizontal coordinate length covered by the second effective waveform, it is determined that the second effective waveform meets the second energy value distribution condition.

[0129] In some embodiments, the acceleration signal collected by the acceleration sensor satisfies both the first energy value distribution condition and the second energy value distribution condition.

[0130] In some embodiments, the acceleration signal generated by knocking on the door further satisfies the energy similarity principle. The energy similarity principle verifies whether the shapes of multiple second valid waveforms in the acceleration signal are similar. Optionally, whether the multiple second valid waveforms are similar can be determined by determining whether the second valid waveforms satisfy a third energy value distribution condition. In some embodiments, the third energy value distribution condition includes: the peak energies of the multiple second valid waveforms are similar.

[0131] Optionally, determining whether any one of the second effective waveforms satisfies the third energy value distribution condition includes: determining a maximum peak and a minimum peak from the peaks of the multiple second effective waveforms; determining a second ratio of the maximum peak to the minimum peak; if the second ratio is less than a seventh threshold, determining that the multiple second effective waveforms satisfy the third energy value distribution condition.

[0132] For example, Fig. 9 The peak values ​​of the 8th, 9th and 10th waveforms can be recorded as EngeryPeakHigh1, EngeryPeakHigh2 and EngeryPeakHigh3 respectively. The maximum peak value is EngeryPeakHigh3 and the minimum peak value is EngeryPeakHigh2. Then, the second ratio is EngeryPeakHigh3 / EngeryPeakHigh2. According to this method, it can be determined whether the second ratio is less than the seventh threshold.

[0133] In a specific example, the seventh threshold may be set to 3, that is, the maximum value / minimum value is less than 3. For example, if the above-mentioned EnergyPeakHigh3 / EgeryPeakHigh2<3, it is determined that the second effective waveform meets the third energy value distribution condition.

[0134] In some embodiments, the energy similarity principle may further include a fourth energy value distribution condition. The fourth energy value distribution condition includes: the widths of the plurality of second effective waveforms are similar. Wherein, determining whether the second effective waveform satisfies the fourth energy value distribution condition includes: respectively determining the time lengths covered by the plurality of second effective waveforms; determining the maximum time length and the minimum time length from the time lengths corresponding to the plurality of second effective waveforms; determining a third ratio of the maximum time length to the minimum time length; if the third ratio is less than the eighth threshold value, determining that the plurality of second effective waveforms satisfy the fourth energy value distribution condition.

[0135] In some embodiments, determining the time length covered by the second effective waveform may be: Fig. 9 The starting position and the ending position of the second effective waveform are determined in the manner of determining the starting position and the ending position of the second effective waveform, and the difference between the starting position and the ending position of the second effective waveform is determined as the time length covered by the second effective waveform.

[0136] In other embodiments, determining the time length covered by the second effective waveform includes: setting an edge threshold; determining the intersection point A1 of the edge threshold with the rising edge of each second effective waveform, and the intersection point A2 with the falling edge; and obtaining the time length covered by the second effective waveform through A2-A1.

[0137] For example, Fig. 9The time lengths covered by the 8th, 9th and 10th waveforms are EnergyPeakWidth1, Energy PeakWidth2 and EnergyPeakWidth3 respectively. Assume that the maximum time length is EnergyPeakWidth3 and the minimum time length is EnergyPeakWidth2. Then the third ratio is EnergyPeakWidth3 / EnergyPeakWidth2. Then it is determined whether the ratio is less than the eighth threshold value. If it is less than, it is determined that the second valid waveform meets the fourth energy value distribution condition.

[0138] In a specific example, the eighth threshold may be set to 3. Assuming that the maximum value / minimum value in this example is less than 3, it is determined that the second effective waveform satisfies the fourth energy value distribution condition.

[0139] Optionally, when judging the acceleration signal, the signal may be required to satisfy both the third energy value distribution condition and the fourth energy value distribution condition.

[0140] Fig.10 This is a schematic diagram of the structure of a knock signal recognition device provided in an embodiment of this specification. Fig.10 As shown, the knock signal recognition device may include: an acquisition module 501 , a determination module 502 and a calculation module 503 .

[0141] An acquisition module 501 is used to acquire an acceleration signal collected by an acceleration sensor installed on the door;

[0142] A determination module 502, configured to determine a plurality of first valid waveforms in the acceleration signal;

[0143] A calculation module 503, configured to calculate the energy value of the acceleration signal to obtain an energy signal when the plurality of first valid waveforms meet the waveform distribution condition;

[0144] The determination module 502 is further used to determine a plurality of second valid waveforms in the energy signal; when the plurality of second valid waveforms satisfy an energy value distribution condition, it is determined that the acceleration signal is a signal generated by knocking on the door.

[0145] Optionally, the acquisition module 501 can be implemented as an acceleration sensor. The determination module 502 and the calculation module 503 can be integrated into a processing module. For example, the processing module is a main control chip. The processing module can be integrated with the acceleration sensor. Optionally, the processing module can also be set in other processing devices, such as in a gateway or a server.

[0146] The knock signal recognition device shown in FIG10 can be used to implement the embodiment of the present invention. Figures 1 to 9The technical solution of the method embodiment shown, its implementation principle and technical effects can be further referred to the relevant description in the method embodiment, and will not be repeated here.

[0147] Fig.11 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Fig.11 The electronic device shown is only an example and does not impose any limitation on the functions and scope of use of the embodiments of this specification. Fig.11 As shown, the electronic device is in the form of a general computing device. The components of the electronic device may include, but are not limited to: one or more processors 610, a communication interface 620, a memory 630, and a communication bus 640 connecting different system components (including the memory 630, the communication interface 620 and the processing unit 610).

[0148] The communication bus 640 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnection (PCI) bus.

[0149] Electronic devices typically include a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device, including volatile and non-volatile media, removable and non-removable media.

[0150] The memory 630 may include a computer system readable medium in the form of a volatile memory, such as a random access memory (RAM) and / or a cache memory. The electronic device may further include other removable / non-removable, volatile / non-volatile computer system storage media. The memory 630 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of each embodiment of the present specification.

[0151] A program / utility having a set (at least one) of program modules may be stored in memory 630, such program modules including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules generally perform the functions and / or methods of the embodiments described in this specification.

[0152] The processor 610 executes various functional applications and data processing by running the programs stored in the memory 630, such as implementing the Figures 1 to 9 The embodiment shown provides a knock signal recognition method.

[0153] An embodiment of the present invention provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, wherein the computer instructions enable the computer to execute an embodiment of the present invention. Figures 1 to 9 The embodiment shown provides a knock signal recognition method.

[0154] The above-mentioned non-transitory computer-readable storage medium can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, - but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (Read Only Memory; hereinafter referred to as: ROM), an erasable programmable read-only memory (Erasable Programmable Read Only Memory; hereinafter referred to as: EPROM) or flash memory, optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0155] Computer-readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0156] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0157] The computer program code for performing the operation of the embodiments of the present invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (Local Area Network; hereinafter referred to as: LAN) or a wide area network (Wide Area Network; hereinafter referred to as: WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0158] The above describes specific embodiments of the present invention. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0159] In the description of the embodiments of the present invention, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiments of the present invention. In the embodiments of the present invention, the schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in the embodiments of the present invention and the features of the different embodiments or examples, without contradiction.

[0160] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the embodiments of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0161] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred implementation of the embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0162] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0163] It should be noted that the terminals involved in the embodiments of the present invention may include but are not limited to personal computers (Personal Computer; hereinafter referred to as: PC), personal digital assistants (Personal Digital Assistant; hereinafter referred to as: PDA), wireless handheld devices, tablet computers (Tablet Computer), mobile phones, MP3 players, MP4 players, etc.

[0164] In the several embodiments provided in the embodiments of the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0165] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0166] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (Processor) to perform some steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk and other media that can store program codes.

[0167] The above description is only a preferred embodiment of the embodiment of the present invention and is not intended to limit the embodiment of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiment of the present invention should be included in the scope of protection of the embodiment of the present invention.

Claims

1. A knock signal recognition method, characterized in that: include: Acquire the acceleration signal collected by the acceleration sensor; The acceleration sensor is arranged on the door; Determining a plurality of first valid waveforms in the acceleration signal; The first effective waveform is a waveform in the acceleration signal whose peak value is greater than a first threshold; If the plurality of first effective waveforms satisfy the waveform distribution condition, square calculation is performed on the acceleration signal to obtain an energy signal; The waveform distribution condition is a condition for preliminarily screening the acceleration signal, determined according to the vibration characteristics of the knock signal; Determine a plurality of second valid waveforms in the energy signal; the second valid waveform is a waveform in the energy signal whose peak value is greater than a fourth threshold; If the multiple second valid waveforms meet the energy value distribution condition, it is determined that the acceleration signal is a signal generated by knocking on the door; the energy value distribution condition is a condition for secondary screening of the acceleration signal determined based on the vibration characteristics of the knocking signal.

2. The method according to claim 1, characterized in that The acceleration signal includes sub-signals of multiple direction axes; After acquiring the acceleration signal collected by the acceleration sensor, the method further includes: Calculate the variance value of the axon signal in each direction; determining a maximum variance value from among the calculated variance values; Determine the sub-signal corresponding to the maximum variance value as the original signal; Calculating the mean of the original signal; Subtract the mean value from the original signal to obtain an absolute value signal; Determining a plurality of first valid waveforms in the acceleration signal comprises: determining the plurality of first valid waveforms from the absolute value signal; Calculating the energy value of the acceleration signal includes: An energy value is calculated for the absolute value signal.

3. The method according to claim 2, characterized in that Determining the plurality of first valid waveforms from the absolute value signal comprises: Determine a first waveform having a peak value greater than a first threshold from the absolute value signal; Taking the first time as the step length, determining the first waveform with the largest peak value within the first time step range; The first waveform with the largest peak value is determined as the first effective waveform.

4. The method according to claim 1, characterized in that: The waveform distribution condition includes a combination of one or more of the following: The number of the first valid waveforms is within a preset number range; The time interval between adjacent first effective waveforms in the plurality of first effective waveforms is less than a second threshold; The peak value of the first effective waveform is less than a third threshold.

5. The method according to claim 1, characterized in that: Determining a plurality of second valid waveforms in the energy signal comprises: Determine from the energy signal a second waveform having a peak value greater than a fourth threshold; Taking the second time as the step length, determining the second waveform with the largest peak value within the second time step range; The second waveform with the largest peak value is determined as the second effective waveform.

6. The method according to claim 1, characterized in that The energy value distribution condition includes an energy waveform condition; the energy waveform condition includes a combination of one or more of the following: The number of the second valid waveforms is within a preset number range; A time interval between adjacent second effective waveforms in the plurality of second effective waveforms is less than a fifth threshold.

7. The method according to claim 1, characterized in that The knock signal also satisfies a high-frequency vibration condition, wherein determining that the acceleration signal satisfies the high-frequency vibration condition includes: Performing frequency domain transformation on the acceleration signal to obtain a frequency domain signal; Calculating frequency band energy of a first frequency band and frequency band energy of a second frequency band according to the frequency domain signal; wherein the frequency of the first frequency band is higher than the frequency of the second frequency band; If the frequency band energy value of the first frequency band is greater than the frequency band energy value of the second frequency band, it is determined that the acceleration signal meets the high-frequency vibration condition.

8. The method according to any one of claims 1 to 7, characterized in that The energy value distribution condition includes a first energy value distribution condition; wherein determining that any one of the second effective waveforms satisfies the first energy value distribution condition includes: determining a peak energy value of the second effective waveform; Determine the noise energy value between two adjacent second effective waveforms; determining a first ratio of the peak energy value to an associated noise energy value; If the first ratio is greater than a sixth threshold, it is determined that the second effective waveform satisfies a first energy value distribution condition.

9. The method according to any one of claims 1 to 7, characterized in that The energy value distribution condition includes a second energy value distribution condition; wherein determining that any one of the second effective waveforms satisfies the second energy value distribution condition includes: Determining a total energy value of the second effective waveform; The energy value of the second effective waveform is gradually accumulated with the peak point of the second effective waveform as the base point until the obtained energy accumulation value is equal to or greater than k1 times the total energy value; 0.5<k1<1; Determine the first time length corresponding to the second effective waveform when the energy accumulated value is equal to or greater than k1 times the total energy value; If the first time length is less than k2 times the total time length of the second effective waveform, it is determined that the second effective waveform meets the second energy value distribution condition; 0<k2<0.

6.

10. The method according to any one of claims 1 to 7, characterized in that The energy value distribution condition includes a third energy value distribution condition; wherein determining that the plurality of second effective waveforms satisfy the third energy value distribution condition includes: Determining a maximum peak value and a minimum peak value from the peak values ​​of the plurality of second effective waveforms; determining a second ratio of the maximum peak value to the minimum peak value; If the second ratio is less than a seventh threshold, it is determined that the plurality of second effective waveforms satisfy a third energy value distribution condition.

11. The method according to any one of claims 1 to 7, characterized in that The energy value distribution condition includes a fourth energy value distribution condition; wherein determining that the plurality of second valid waveforms satisfy the fourth energy value distribution condition includes: respectively determining the time lengths covered by the plurality of second effective waveforms; Determine a maximum time length and a minimum time length from the time lengths corresponding to the plurality of second effective waveforms; determining a third ratio of the maximum time length to the minimum time length; If the third ratio is less than an eighth threshold, it is determined that the plurality of second effective waveforms satisfy a fourth energy value distribution condition.

12. A knock signal recognition device, characterized in that: include: An acquisition module is used to acquire the acceleration signal collected by the acceleration sensor; The acceleration sensor is arranged on the door; A determination module, used to determine a plurality of first valid waveforms in the acceleration signal; the first valid waveform is a waveform in the acceleration signal whose peak value is greater than a first threshold; A calculation module, configured to perform square calculation on the acceleration signal to obtain an energy signal when the plurality of first effective waveforms satisfy a waveform distribution condition; The waveform distribution condition is a condition for preliminarily screening the acceleration signal, determined according to the vibration characteristics of the knock signal; The determination module is further used to determine a plurality of second valid waveforms in the energy signal; the second valid waveform is a waveform in the energy signal whose peak value is greater than a fourth threshold; When the multiple second valid waveforms meet the energy value distribution condition, it is determined that the acceleration signal is a signal generated by knocking on the door; the energy value distribution condition is a condition for secondary screening of the acceleration signal determined based on the vibration characteristics of the knocking signal.

13. A knock signal recognition device, characterized in that: include: at least one processor; as well as at least one memory in communication with the processor, wherein: The memory stores program instructions that can be executed by the processor, and the processor can execute the method according to any one of claims 1 to 11 by calling the program instructions.

14. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer instructions that cause the computer to perform the method of any one of claims 1 to 11.

Images