CN113484416A

CN113484416A - Method and device for detecting hollowing of ceramic tile, storage medium and electronic equipment

Info

Publication number: CN113484416A
Application number: CN202110759750.7A
Authority: CN
Inventors: 李延鹏; 贾忠良; 王旭; 浮颖彬; 李欣悦
Original assignee: Beijing Fangjianghu Technology Co Ltd
Current assignee: Beijing Fangjianghu Technology Co Ltd
Priority date: 2021-07-05
Filing date: 2021-07-05
Publication date: 2021-10-08

Abstract

The embodiment of the disclosure discloses a method and a device for detecting hollowing of a ceramic tile, a storage medium and electronic equipment, wherein the method comprises the following steps: acquiring a first audio signal obtained by knocking a set position on a substrate plane for multiple times to obtain reference frequency spectrum distribution; collecting a second audio signal obtained by knocking the detected point on the substrate plane to obtain the spectrum distribution to be detected; determining whether the detected point has a hollowing phenomenon or not based on the difference between the spectral distribution to be detected and the reference spectral distribution; the embodiment realizes the detection of the hollowing of the ceramic tile based on the difference of the audio frequency spectrum distribution, collects the knocked audio frequencies at different positions of the ceramic tile, can judge whether the hollowing exists between the ceramic tile and the paving surface, and has the advantages of low cost, simple and convenient operation and high real-time property.

Description

Method and device for detecting hollowing of ceramic tile, storage medium and electronic equipment

Technical Field

The disclosure relates to the technical field of hollowing detection, and in particular relates to a method and a device for detecting hollowing of a ceramic tile, a storage medium and electronic equipment.

Background

The ceramic tile is spread and is pasted generally and paste the basement material between ceramic tile and shop's wainscot in current fitment field for firmly paste the ceramic tile on shop's wainscot, because the different influences such as workman's technical merit, pasting material quality, shop's wainscot technology, pasting material solidification back can cause the cavity, leads to ceramic tile and shop's wainscot to have the hollowing phenomenon, if the hollowing area is great cause the ceramic tile to take off from shop's wainscot easily, the influence is used.

Disclosure of Invention

The present disclosure is proposed to solve the above technical problems. The embodiment of the disclosure provides a tile hollowing detection method and device, a storage medium and electronic equipment.

According to an aspect of an embodiment of the present disclosure, there is provided a tile hollowing detection method including:

acquiring a first audio signal obtained by knocking a set position on a substrate plane for multiple times to obtain reference frequency spectrum distribution;

collecting a second audio signal obtained by knocking the detected point on the substrate plane to obtain the spectrum distribution to be detected;

and determining whether the detected point has a hollowing phenomenon or not based on the difference between the spectral distribution to be detected and the reference spectral distribution.

Optionally, the determining whether the detected point has a hollowing phenomenon based on the difference between the spectral distribution to be detected and the reference spectral distribution includes:

calculating the divergence of the to-be-detected frequency spectrum distribution and the reference frequency spectrum distribution to obtain a divergence value;

determining that the detected point has a hollowing phenomenon in response to the divergence value being greater than or equal to a set threshold value;

and determining that the detected point has no empty drum phenomenon in response to the divergence value being smaller than the set threshold value.

Optionally, the obtaining a first audio signal obtained by tapping a set position on a base plane multiple times to obtain a reference spectrum distribution includes:

acquiring a first audio signal obtained by knocking the set position on the base plane for multiple times;

segmenting the first audio signal to obtain a plurality of first audio segments;

determining whether the number of the first audio segments is greater than or equal to a set number, and if so, determining the reference spectral distribution based on the set number of the first audio segments; otherwise, continuously acquiring a first audio signal obtained by knocking the set position on the base plane, and segmenting the first audio signal to obtain at least one first audio segment until a set number of first audio segments are obtained.

Optionally, the segmenting the first audio signal to obtain a plurality of first audio segments includes:

obtaining a plurality of peaks in the first audio signal based on a sliding window;

determining a start position and an end position of each of a plurality of tapping sounds based on each of the plurality of peaks; wherein each time the tapping corresponds to one tapping sound, each tapping sound corresponds to one peak;

and segmenting the first audio signal based on the starting position and the ending position of each knocking sound to obtain a plurality of first audio segments.

Optionally, the determining a start position and an end position of each of a plurality of tapping sounds based on each of the plurality of peaks comprises:

for each peak in the plurality of peaks, forward searching a first position of a first set duration in the first audio signal with the peak as a center point; judging whether at least one peak exists between the central point and the first position, and if so, taking the end position of the peak most adjacent to the peak as the starting position; otherwise, taking the first position as the starting position;

searching a second position with a second set time length backwards in the first audio signal by taking the peak as a central point; judging whether at least one peak exists between the central point and the second position, and if so, taking the position before the peak most adjacent to the peak as the end position; otherwise, taking the second position as the end position.

Optionally, the determining the reference spectral distribution based on the set number of the first audio segments comprises:

respectively carrying out frequency domain conversion on each of the first audio frequency segments in the set number of first audio frequency segments to obtain a set number of first frequency domain signal segments;

respectively carrying out normalization processing on each of the set number of first frequency domain signal segments to obtain a set number of normalized first frequency domain signal segments;

and calculating an average value based on the set number of normalized first frequency domain signal segments to obtain the reference frequency spectrum distribution.

Optionally, each of the normalized first frequency domain signal segments in the set number of normalized first frequency domain signal segments includes the same number of frequency domain values;

the calculating an average value based on the set number of normalized first frequency domain signal segments to obtain the reference frequency spectrum distribution includes:

obtaining a plurality of mean energy values corresponding to the normalized first frequency domain signal segment based on the energy values corresponding to each frequency value in the normalized first frequency domain signal segment in the set number of normalized first frequency domain signal segments; wherein each of the frequency values corresponds to a mean energy value;

and arranging the plurality of average energy values according to the distribution of the normalized first frequency domain signal segments to obtain the reference frequency spectrum distribution.

Optionally, before the segmenting the first audio signal to obtain a plurality of first audio segments, the method further includes:

filtering the first audio signal to obtain a filtered first audio signal;

the segmenting the first audio signal to obtain a plurality of first audio segments includes:

and segmenting the filtered first audio signal to obtain a plurality of first audio segments.

Optionally, the acquiring a second audio signal obtained by tapping the detected point on the substrate plane to obtain a spectrum distribution to be detected includes:

acquiring a second audio signal obtained by knocking the detected point on the substrate plane;

segmenting the second audio signal to obtain a second audio segment;

and determining the spectrum distribution to be detected based on the second audio frequency segment.

Optionally, the segmenting the second audio signal to obtain a second audio segment includes:

obtaining peaks in the second audio signal based on a sliding window;

determining a start position and an end position of the tapping sound based on the peak;

and segmenting the second audio signal based on the starting position and the ending position of the knocking sound to obtain the second audio segment.

Optionally, the determining a start position and an end position of the tapping sound based on the peak includes:

for each peak in the at least one peak, forward searching a third position with a third set duration in the second audio signal by taking the peak as a central point to serve as the starting position;

and with the peak as a central point, searching a fourth position of a fourth set time length backwards in the second audio signal as the end position.

Optionally, determining the spectral distribution to be detected based on the second audio segment includes:

performing frequency domain conversion on the second audio frequency segment to obtain a second frequency domain signal segment;

and performing normalization processing on the second frequency domain signal segment to obtain the to-be-detected frequency spectrum distribution.

Optionally, before the slicing is performed on the second audio signal to obtain a second audio segment, the method further includes:

filtering the second audio signal to obtain a filtered second audio signal;

the segmenting the second audio signal to obtain a second audio segment includes:

and segmenting the filtered second audio signal to obtain a plurality of second audio segments.

According to another aspect of the disclosed embodiments, there is provided a tile hollowing detection device, comprising:

the reference distribution determining module is used for acquiring a first audio signal obtained by knocking a set position on a substrate plane for multiple times to obtain reference frequency spectrum distribution;

the distribution determining module to be detected is used for acquiring a second audio signal obtained by knocking the detected point on the substrate plane to obtain the distribution of the frequency spectrum to be detected;

and the empty drum detection module is used for determining whether the detected point has an empty drum phenomenon or not based on the difference between the spectral distribution to be detected and the reference spectral distribution.

Optionally, the hollowing detection module is specifically configured to perform divergence calculation on the to-be-detected spectrum distribution and the reference spectrum distribution to obtain a divergence value; determining that the detected point has a hollowing phenomenon in response to the divergence value being greater than or equal to a set threshold value; and determining that the detected point has no empty drum phenomenon in response to the divergence value being smaller than the set threshold value.

Optionally, the reference distribution determining module includes:

the first signal acquisition unit is used for acquiring a first audio signal obtained by knocking the set position on the substrate plane for multiple times;

the first segmentation unit is used for segmenting the first audio signal to obtain a plurality of first audio segments;

a reference spectrum unit for determining whether the number of the first audio segments is greater than or equal to a set number, and if so, determining the reference spectrum distribution based on the set number of the first audio segments; otherwise, continuously acquiring a first audio signal obtained by knocking the set position on the base plane, and segmenting the first audio signal to obtain at least one first audio segment until a set number of first audio segments are obtained.

Optionally, the first dividing unit is specifically configured to obtain a plurality of peaks in the first audio signal based on a sliding window; determining a start position and an end position of each of a plurality of tapping sounds based on each of the plurality of peaks; wherein each time the tapping corresponds to one tapping sound, each tapping sound corresponds to one peak; and segmenting the first audio signal based on the starting position and the ending position of each knocking sound to obtain a plurality of first audio segments.

Optionally, the first dividing unit, when determining the start position and the end position of each of a plurality of tapping sounds based on each of the plurality of peaks, is configured to, for each of the plurality of peaks, find a first position of a first set duration forward in the first audio signal with the peak as a center point; judging whether at least one peak exists between the central point and the first position, and if so, taking the end position of the peak most adjacent to the peak as the starting position; otherwise, taking the first position as the starting position; searching a second position with a second set time length backwards in the first audio signal by taking the peak as a central point; judging whether at least one peak exists between the central point and the second position, and if so, taking the position before the peak most adjacent to the peak as the end position; otherwise, taking the second position as the end position.

Optionally, the reference spectrum unit is configured to, when determining the reference spectrum distribution based on a set number of the first audio segments, perform frequency domain conversion on each of the first audio segments of the set number of first audio segments, respectively, to obtain a set number of first frequency-domain signal segments; respectively carrying out normalization processing on each of the set number of first frequency domain signal segments to obtain a set number of normalized first frequency domain signal segments; and calculating an average value based on the set number of normalized first frequency domain signal segments to obtain the reference frequency spectrum distribution.

the reference spectrum unit is used for calculating an average value based on the set number of normalized first frequency domain signal segments to obtain a plurality of average value energy values corresponding to the normalized first frequency domain signal segments based on the energy value corresponding to each frequency value in the set number of normalized first frequency domain signal segments in the normalized first frequency domain signal segments when obtaining the reference spectrum distribution; wherein each of the frequency values corresponds to a mean energy value; and arranging the plurality of average energy values according to the distribution of the normalized first frequency domain signal segments to obtain the reference frequency spectrum distribution.

Optionally, the reference distribution determining module further includes:

the first filtering unit is used for filtering the first audio signal to obtain a filtered first audio signal;

the first segmentation unit is specifically configured to segment the filtered first audio signal to obtain a plurality of first audio segments.

Optionally, the distribution determining module to be detected includes:

the second signal acquisition unit is used for acquiring a second audio signal obtained by knocking the detected point on the substrate plane;

the second segmentation unit is used for segmenting the second audio signal to obtain a second audio segment;

and the spectrum unit to be detected is used for determining the spectrum distribution to be detected based on the second audio frequency segment.

Optionally, the second slicing unit is specifically configured to obtain a peak in the second audio signal based on a sliding window; determining a start position and an end position of the tapping sound based on the peak; and segmenting the second audio signal based on the starting position and the ending position of the knocking sound to obtain the second audio segment.

Optionally, the second slicing unit, when determining the start position and the end position of the tapping sound based on the peaks, is configured to, for each peak in the at least one peak, look forward a third position of a third set duration in the second audio signal with the peak as a center point as the start position; and with the peak as a central point, searching a fourth position of a fourth set time length backwards in the second audio signal as the end position.

Optionally, the frequency spectrum unit to be measured is specifically configured to perform frequency domain conversion on the second audio frequency segment to obtain a second frequency domain signal segment; and performing normalization processing on the second frequency domain signal segment to obtain the to-be-detected frequency spectrum distribution.

Optionally, the distribution determining module to be detected further includes:

the second filtering unit is used for filtering the second audio signal to obtain a filtered second audio signal;

the second segmentation unit is specifically configured to segment the filtered second audio signal to obtain a plurality of second audio segments.

According to yet another aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium storing a computer program for executing the tile empty drum detection method according to any one of the above embodiments.

According to still another aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including:

a processor;

a memory for storing the processor-executable instructions;

a knocking device;

the processor is used for reading the executable instructions from the memory and executing the instructions to realize the tile hollowing detection method of any one of the embodiments;

the knocking device is configured to knock a set position and a detected point on the substrate plane.

The tile hollowing detection method and device, the storage medium and the electronic device provided based on the above embodiments of the present disclosure include: acquiring a first audio signal obtained by knocking a set position on a substrate plane for multiple times to obtain reference frequency spectrum distribution; collecting a second audio signal obtained by knocking the detected point on the substrate plane to obtain the spectrum distribution to be detected; determining whether the detected point has a hollowing phenomenon or not based on the difference between the spectral distribution to be detected and the reference spectral distribution; the embodiment realizes the detection of the hollowing of the ceramic tiles based on the difference of the audio frequency spectrum distribution, collects the audio frequency of the knocked ceramic tiles at different positions, can judge whether the hollowing exists between the ceramic tiles and the paving and pasting surface, has low cost, simple and convenient operation and high real-time performance, and can be suitable for the judgment of the hollowing of the ceramic tiles of any brands and batches of any materials due to the fact that the set position and the detected position are the positions of the ceramic tiles on the same substrate plane.

The technical solution of the present disclosure is further described in detail by the accompanying drawings and examples.

Drawings

The above and other objects, features and advantages of the present disclosure will become more apparent by describing in more detail embodiments of the present disclosure with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the principles of the disclosure and not to limit the disclosure. In the drawings, like reference numbers generally represent like parts or steps.

Fig. 1 is a schematic flow chart of a tile hollowing detection method according to an exemplary embodiment of the present disclosure.

Fig. 2a is a waveform diagram comparing differences between a spectral distribution to be detected and a reference spectral distribution in an alternative example of a tile hollowing detection method according to an exemplary embodiment of the disclosure.

Fig. 2b is a waveform diagram comparing differences between a spectral distribution to be detected and a reference spectral distribution in another alternative example of the tile hollowing detection method according to an exemplary embodiment of the disclosure.

FIG. 3 is a schematic flow chart of step 102 in the embodiment shown in FIG. 1 of the present disclosure.

Fig. 4a is a schematic flow chart of step 1022 in the embodiment shown in fig. 3 of the present disclosure.

Fig. 4b is a waveform diagram of a first audio signal in an alternative example of a tile empty drum detection method according to an exemplary embodiment of the disclosure.

Fig. 4c is a waveform schematic diagram of a first audio piece resulting from a slicing of the waveform schematic diagram of fig. 4 b.

Fig. 5a is a schematic flowchart of step 1024 in the embodiment shown in fig. 3 of the present disclosure.

Fig. 5b is a schematic frequency spectrum diagram of normalization and mean calculation for a first frequency-domain signal segment in an alternative example of the tile empty-drum detection method according to an exemplary embodiment of the present disclosure.

Fig. 6 is a schematic flow chart of step 104 in the embodiment shown in fig. 1 of the present disclosure.

Fig. 7 is a schematic structural diagram of a tile hollowing detection device provided by an exemplary embodiment of the present disclosure.

Fig. 8 is a block diagram of an electronic device provided in an exemplary embodiment of the present disclosure.

Detailed Description

Hereinafter, example embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. It is to be understood that the described embodiments are merely a subset of the embodiments of the present disclosure and not all embodiments of the present disclosure, with the understanding that the present disclosure is not limited to the example embodiments described herein.

It should be noted that: the relative arrangement of the components and steps, the numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.

It will be understood by those of skill in the art that the terms "first," "second," and the like in the embodiments of the present disclosure are used merely to distinguish one element from another, and are not intended to imply any particular technical meaning, nor is the necessary logical order between them.

It is also understood that in embodiments of the present disclosure, "a plurality" may refer to two or more and "at least one" may refer to one, two or more.

It is also to be understood that any reference to any component, data, or structure in the embodiments of the disclosure, may be generally understood as one or more, unless explicitly defined otherwise or stated otherwise.

In addition, the term "and/or" in the present disclosure is only one kind of association relationship describing an associated object, and means that three kinds of relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" in the present disclosure generally indicates that the former and latter associated objects are in an "or" relationship.

It should also be understood that the description of the various embodiments of the present disclosure emphasizes the differences between the various embodiments, and the same or similar parts may be referred to each other, so that the descriptions thereof are omitted for brevity.

Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.

The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses.

Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.

The disclosed embodiments may be applied to electronic devices such as terminal devices, computer systems, servers, etc., which are operational with numerous other general purpose or special purpose computing system environments or configurations. Examples of well known terminal devices, computing systems, environments, and/or configurations that may be suitable for use with electronic devices, such as terminal devices, computer systems, servers, and the like, include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, hand-held or laptop devices, microprocessor-based systems, set top boxes, programmable consumer electronics, network pcs, minicomputer systems, mainframe computer systems, distributed cloud computing environments that include any of the above systems, and the like.

Electronic devices such as terminal devices, computer systems, servers, etc. may be described in the general context of computer system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, etc. that perform particular tasks or implement particular abstract data types. The computer system/server may be practiced in distributed cloud computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules may be located in both local and remote computer system storage media including memory storage devices.

Summary of the application

In the process of implementing the present disclosure, the inventor finds that, in the existing decoration process, a common method for detecting hollowing of a tile generally depends on abnormal judgment of knocking sound by human ears, but the prior art at least has the following problems: the method is extremely dependent on the experience of inspectors, and if the experience of the inspectors is insufficient, the hollow part is judged by mistake if the inspection is missed, or the hollow part needs to be knocked repeatedly to deepen the judgment of different ceramic tile parts, so that the efficiency is low.

Exemplary method

Fig. 1 is a schematic flow chart of a tile hollowing detection method according to an exemplary embodiment of the present disclosure. The embodiment can be applied to an electronic device, as shown in fig. 1, and includes the following steps:

step 102, obtaining a first audio signal obtained by knocking a set position on a substrate plane for multiple times, and obtaining a reference frequency spectrum distribution.

In general, it is generally considered that no hollowing occurs in the central part of the tile, and this embodiment may set the central part of the tile as a set position, or other determinable positions where no hollowing exists, as the set position; tapping the set position several times is used to generate a reference audio distribution of the non-empty drum portion.

And 104, acquiring a second audio signal obtained by knocking the detected point on the substrate plane to obtain the spectrum distribution to be detected.

In this embodiment, the set position and the measured point are located on the same base plane, for example, the same wall, the ground in a room, etc., the same base plane at least has the same base material and is located in the same space, and the distance between the set position and the measured point does not exceed the set range (for example, 5 meters, etc.); so as to ensure the accuracy of the measured result.

And 106, determining whether the detected point has a hollowing phenomenon or not based on the difference between the spectral distribution to be detected and the reference spectral distribution.

In an embodiment, if the hollowing phenomenon does not exist in the tiles on the same substrate plane, the spectral distribution difference obtained through knocking is within a certain range, and the spectral distribution to be detected is obtained through knocking the measured point on the same substrate plane with the set position so as to identify whether the hollowing phenomenon exists in the measured point.

According to the tile hollowing detection method provided by the embodiment of the disclosure, a first audio signal obtained by knocking a set position on a substrate plane for multiple times is obtained, and reference frequency spectrum distribution is obtained; collecting a second audio signal obtained by knocking the detected point on the substrate plane to obtain the spectrum distribution to be detected; determining whether the detected point has a hollowing phenomenon or not based on the difference between the spectral distribution to be detected and the reference spectral distribution; the embodiment realizes the detection of the hollowing of the ceramic tiles based on the difference of the audio frequency spectrum distribution, collects the audio frequency of the knocked ceramic tiles at different positions, can judge whether the hollowing exists between the ceramic tiles and the paving and pasting surface, has low cost, simple and convenient operation and high real-time performance, and can be suitable for the judgment of the hollowing of the ceramic tiles of any brands and batches of any materials due to the fact that the set position and the detected position are the positions of the ceramic tiles on the same substrate plane.

In some alternative embodiments, step 106 in the embodiment provided in fig. 1 above may include:

performing divergence calculation on the frequency spectrum distribution to be detected and the reference frequency spectrum distribution to obtain a divergence value;

determining that the detected point has a hollowing phenomenon in response to the divergence value being greater than or equal to the set threshold value;

In this embodiment, the divergence value calculation can be realized by JS divergence calculation, the difference of comparing two distributions is generally measured by using the JS divergence value, the JS divergence value can measure the similarity of two probability distributions, the JS divergence values of the two are obtained by sequentially traversing and calculating the frequencies in the to-be-detected spectrum distribution and the reference spectrum distribution in sequence, the difference of the obtained divergence values and the set threshold value is judged, the larger the JS divergence value is, the larger the spectrum distribution difference is, the difference degree of the two-time knocking sound is further judged, the result of whether the detected point has the empty drum or not can be obtained, and the detected point with the empty drum can be subjected to alarm prompt.

The difference degree between the frequency spectrum distribution to be detected and the reference frequency spectrum distribution can be obtained through calculation of the JS divergence value, the larger the difference is, the higher the possibility of hollowing is, and whether the hollowing phenomenon of the sound signal to be detected can be judged through setting a threshold value. For example, in an alternative example, fig. 2a and fig. 2b respectively show a comparison waveform diagram of the difference between the to-be-detected spectrum distribution (202, 204) corresponding to two different to-be-detected points and the reference spectrum distribution (201, 203) (in the figure, the abscissa represents a frequency value, and the ordinate represents an energy value), in this example, the set threshold value is set to be 0.4, at this time, the JS divergence value calculated by the to-be-detected spectrum distribution and the reference spectrum distribution shown in fig. 2a is 0.19, which is smaller than the set threshold value, and it indicates that the to-be-detected points have no empty drum; and the JS divergence value calculated by the spectrum distribution to be detected and the reference spectrum distribution shown in fig. 2b is 0.78, which is greater than the set threshold, indicating that the point to be detected is empty.

As shown in fig. 3, based on the embodiment shown in fig. 1, step 102 may include the following steps:

step 1021, acquiring a first audio signal obtained by tapping a set position on the substrate plane for multiple times.

In this embodiment, an intelligent device may be used to collect audio, an audio collection function in the intelligent device is used, and an audio collection interface is called, for example, AudioRecord class in an android system, and the device that strikes a set position of a tile may be an air drum hammer in the prior art, and this embodiment does not limit striking strength, angle, and the like, and only needs to obtain a signal of a required amplitude through amplitude filtering after collection; in this embodiment, in order to obtain relatively accurate reference spectrum distribution, the number of taps may be increased appropriately, and the duration of collecting audio may be increased, for example, the duration of the adopted first audio signal (time domain signal) may be not less than 5s-10s, and the sound signal is encoded and stored in the memory; where optionally the audio sampling rate is too low resulting in incomplete information, it is generally considered that the larger the audio sampling rate, the more complete the information, but the too high the audio sampling rate resulting in computational inefficiency, in an optional example the audio sampling rate may be set to 44100Hz or 48000 Hz.

Step 1022, the first audio signal is segmented to obtain a plurality of first audio segments.

In the embodiment, the complete first audio signal is divided into the plurality of first audio segments through segmentation, each audio segment corresponds to one tap, and the audio corresponding to the multiple taps is separated, so that the accuracy of the reference spectrum distribution is improved.

1023, determining whether the number of the first audio segments is larger than or equal to a set number, if so, executing step 1024; otherwise, return to step 1021.

A reference spectral distribution is determined based on a set number of first audio segments, step 1024.

In this embodiment, the reference frequency distribution is determined based on the average value of the set number of frequency distributions corresponding to the set number of first audio segments, and the accuracy of the reference frequency distribution is improved by averaging for multiple times, where the set number in this embodiment may be more than 5 times, and when the number of the first audio segments does not reach the set number, the ceramic tiles at the set positions are repeatedly tapped to collect audio signals until the number of the first audio segments reaches the set number.

As shown in fig. 4a, based on the embodiment shown in fig. 3, step 1022 may include the following steps:

a plurality of peaks in the first audio signal is obtained based on the sliding window, step 401.

In this embodiment, a sliding window is adopted to traverse a first audio signal, and whether a signal value with a vibration amplitude exceeding a certain threshold value exists in the window is detected, the threshold value can be adjusted according to the equipment condition, for example, the threshold value is set to 10000-; if a signal value exceeding a threshold is detected, a tapping tone is considered to be detected.

Step 402, determining a start position and an end position of each of a plurality of tapping sounds based on each of the plurality of peaks.

Each tapping corresponds to one tapping sound, and each tapping sound corresponds to one peak.

Optionally, for each peak in the plurality of peaks, with the peak as a central point, a first position of a first set duration is searched forward in the first audio signal; judging whether at least one peak exists between the central point and the first position, and if so, taking the end position of the peak most adjacent to the peak as a starting position; otherwise, taking the first position as the initial position;

searching a second position with a second set time length backwards in the first audio signal by taking the wave crest as a central point; judging whether at least one peak exists between the central point and the second position, and if so, taking the position before the peak most adjacent to the peak as an end position; otherwise, the second position is taken as the end position.

Optionally, after determining a plurality of peaks in the first audio signal, it is necessary to determine a start time and an end time of a tapping sound corresponding to each peak, which are embodied in the audio signal as a start position and an end position, in this embodiment, by searching forward a first position of a first set duration at each peak position, identifying whether there are other peaks between the peak and the first position, if there are other peaks, taking an end position of the other peak nearest to the peak as the start position, if there are no other peaks, taking the first position as the start position, and if the peak is the first peak, directly taking the first position as the start position of the first peak; the backward determination process is similar to the forward process, wherein the second set duration may be the same as or different from the first set duration, and the first set duration and the second set duration are set according to the actual scene in this embodiment.

In step 403, the first audio signal is segmented based on the start position and the end position of each tapping sound to obtain a plurality of first audio segments.

In this embodiment, for a tapping sound corresponding to multiple taps contained in a first audio signal, a peak position of the tapping sound corresponding to each tap needs to be found to be convenient for segmentation of a subsequent audio signal, for example, a first audio signal traversed by a sliding window with a length of about (1/sampling rate) × 2000s (where the sampling rate is determined by the sampling rate of a sampling device) is used, if a signal value exceeding a threshold value is detected, it is considered that a tapping sound is detected, a start position and an end position of the tapping sound can be respectively marked in a certain length forward and backward from the peak position, and the sliding window is slid backward to the end position of the mark to perform a new round of detection until the first audio signal is detected, and the start positions and the end positions of all the tapping sounds are output; segmenting the first audio signal according to the initial position and the end position of each knocking sound to obtain all first audio segments comprising the knocking sound, and recognizing and obtaining all the knocking sounds exceeding a certain amplitude value at a set position; for example, for a first audio signal as shown in fig. 4b (abscissa represents time and ordinate represents amplitude), the first audio signal is detected using a sliding window, a main energy peak is found for each tap, and sound segmentation is performed to obtain a first audio segment corresponding to one tap as shown in fig. 4c (abscissa represents time and ordinate represents amplitude).

As shown in fig. 5a, based on the embodiment shown in fig. 3, step 1024 may include the following steps:

step 501, respectively executing frequency domain conversion on each of the set number of first audio segments to obtain a set number of first frequency domain signal segments.

Optionally, the frequency domain conversion in this embodiment may be implemented by fast fourier transform (FFT conversion), and optionally, when the lengths of the set number of first audio segments are the same, the lengths of the first frequency domain signal segments after frequency domain conversion are also the same.

Step 502, respectively executing normalization processing on each of the set number of first frequency domain signal segments to obtain a set number of normalized first frequency domain signal segments.

Step 503, calculating an average value based on the set number of normalized first frequency domain signal segments, and obtaining a reference spectrum distribution.

In this embodiment, after sound is converted into a frequency domain signal, when there is a tap on a spectrogram, the frequency of the main energy concentration of the sound is the main frequency band of the tap, an empty drum and a non-empty drum can be judged by the difference of the main frequency, the amplitudes of the frequencies on the spectrogram are different, the energy amplitudes of the same frequency band obtained by tapping the same position are also different, the difference of the frequency distribution of the two spectrograms needs to be compared, and the frequency spectrum needs to be unified to the same amplitude interval in a normalization manner and then is compared; therefore, in this embodiment, first, normalization processing is performed on each first frequency domain signal segment to generate normalized first frequency domain signal segments, and an average value is sequentially calculated according to a signal value in a sequence corresponding to each first frequency domain signal segment, so as to generate normalized average value spectrum distribution, which is the reference spectrum distribution during the detection of the tap; for example, in an alternative example, as shown in fig. 5b, wherein the abscissa represents the frequency value and the ordinate represents the energy value, the spectrum in the line is normalized and averaged to obtain the spectrum distribution shown in the curve in fig. 5 b.

Optionally, each normalized first frequency domain signal segment in the set number of normalized first frequency domain signal segments includes the same number of frequency domain values;

optionally, step 503 may include:

obtaining a plurality of mean energy values corresponding to the normalized first frequency domain signal segment based on the energy values corresponding to each frequency value in the normalized first frequency domain signal segment in the set number of normalized first frequency domain signal segments; wherein each frequency value corresponds to a mean energy value;

As shown in fig. 5b, the average calculation in this embodiment may be performed by averaging the ordinate values of the set number corresponding to the distribution of each abscissa point in the set number of first frequency domain signal segments, to obtain an average ordinate value corresponding to each abscissa point, so as to obtain the frequency spectrum distribution shown by the curve in fig. 5 b.

Optionally, before the slicing the first audio signal to obtain the plurality of first audio segments, the method may further include:

filtering the first audio signal to obtain a filtered first audio signal;

segmenting the first audio signal to obtain a plurality of first audio segments, comprising:

In this embodiment, a band-pass filter may be used to filter the first audio signal, filter out low-frequency and high-frequency interference signals, and output the filtered first audio signal. In this embodiment, the band pass filter is used to filter out environmental noise and low frequency interference, so that the main sound frequency can enter the subsequent processing flow. Because the subsequent process mainly uses the sound frequency information for calculation, due to the interference of the sound receiving equipment and the influence of environmental noise, when high-frequency and low-frequency sound signals enter the subsequent processing process, the frequency spectrum distribution of main knocking sound is influenced, and the calculation accuracy is influenced, so that the low-frequency and high-frequency noise needs to be filtered firstly. The input of high-frequency and low-frequency signals can be blocked by setting low-frequency and high-frequency cut-off frequencies of a band-pass filter.

As shown in fig. 6, based on the embodiment shown in fig. 1, step 104 may include the following steps:

step 1041, collecting a second audio signal obtained by knocking the detected point on the substrate plane.

In this embodiment, the second audio signal detected is collected similarly to the first audio signal, except that the collection time of the second audio signal only needs to ensure that there is a peak (i.e. the second audio signal includes a tapping sound), for example, the collection time is 200ms to 500 ms.

Step 1042, the second audio signal is segmented to obtain a second audio segment.

Alternatively, for the detected point, there is no need to calculate the mean spectral distribution of the position, and therefore, during the slicing process, only the second audio segment including one peak may be obtained.

Step 1043, determining the spectral distribution to be detected based on the second audio segment.

Optionally, performing frequency domain conversion on the second audio segment to obtain a second frequency domain signal segment; and performing normalization processing on the second frequency domain signal segment to obtain the frequency spectrum distribution to be detected.

The essence of sound is vibration, a sound time domain signal is embodied by the strength of vibration in a time dimension, only the strength of the sound vibration cannot judge the difference characteristic of different knocking sounds, the difference between the knocking of ceramic tile hollowing and non-hollowing is embodied by the difference of sound frequency, therefore, the sound time domain signal needs to be subjected to frequency domain conversion (for example, Fourier transform and the like) to obtain a frequency domain signal (in the embodiment, a plurality of first frequency domain signal sections are obtained at set positions, and a second frequency domain signal section is obtained at a detected point), the sound energy peak values of different types of knocking are embodied on different frequency bands of a frequency spectrum, and whether hollowing exists or not can be judged by comparing the difference between the two; after sound is converted into a frequency domain signal, the frequency of the sound with the concentrated main energy when a knock is made on a spectrogram is the main frequency band of the knock, hollowing and non-hollowing can be judged through different main frequencies, the amplitudes of the frequencies on the spectrogram are different, the amplitudes of energy in the same frequency band obtained by knocking at the same position are also different, the difference of frequency distribution of the two spectrograms needs to be compared, and the frequency spectrum needs to be unified to the same amplitude interval in a normalization mode and then is compared.

Optionally, step 1042 in the above embodiment may include:

obtaining peaks in the second audio signal based on the sliding window;

determining a start position and an end position of the tapping sound based on the wave crest;

and segmenting the second audio signal based on the starting position and the ending position of the knocking sound to obtain a second audio segment.

In this embodiment, a peak in the second audio signal is obtained, a start position and an end position of the tapping sound are determined based on the peak, and a process of segmenting the second audio signal based on the start position and the end position of the tapping sound is the same as that of segmenting the first audio signal, except that only one playing is included in the second audio signal, so as to obtain a second audio segment; optionally, determining the start position and the end position of the tapping sound based on the peak comprises:

for each peak in the at least one peak, forward searching a third position with a third set time length in the second audio signal by taking the peak as a central point to serve as an initial position;

and with the wave crest as a central point, backward searching a fourth position with a fourth set time length in the second audio signal as an end position.

Optionally, in this embodiment, the process of determining the starting position and the ending position is also the same as the slicing process of the first audio signal, and the difference is only that the durations searched forward and backward are different, optionally, the fourth set duration may be the same as or different from the third set duration, and the third set duration and the fourth set duration are set according to the actual scene.

Optionally, on the basis of the foregoing embodiment, before step 1042, the method may further include:

filtering the second audio signal to obtain a filtered second audio signal;

step 1042 may include:

In this embodiment, the band pass filter is used to filter out environmental noise and low frequency interference, so that the main sound frequency can enter the subsequent processing flow. Because the subsequent process mainly uses the sound frequency information for calculation, due to the interference of the sound receiving equipment and the influence of environmental noise, when high-frequency and low-frequency sound signals enter the subsequent processing process, the frequency spectrum distribution of main knocking sound is influenced, and the calculation accuracy is influenced, so that the low-frequency and high-frequency noise needs to be filtered firstly. The input of high-frequency and low-frequency signals can be blocked by setting low-frequency and high-frequency cut-off frequencies of a band-pass filter.

Any of the tile hollowing detection methods provided by the embodiments of the present disclosure may be performed by any suitable device having data processing capabilities, including but not limited to: terminal equipment, a server and the like. Alternatively, any of the tile empty drum detection methods provided by the embodiments of the present disclosure may be executed by a processor, such as the processor executing any of the tile empty drum detection methods mentioned by the embodiments of the present disclosure by calling corresponding instructions stored in a memory. And will not be described in detail below.

Exemplary devices

Fig. 7 is a schematic structural diagram of a tile hollowing detection device provided by an exemplary embodiment of the present disclosure. As shown in fig. 7, the apparatus provided in this embodiment includes:

the reference distribution determining module 71 is configured to obtain a first audio signal obtained by tapping a set position on a base plane multiple times, and obtain a reference spectrum distribution.

And the distribution determining module 72 to be detected is used for acquiring a second audio signal obtained by knocking the detected point on the substrate plane to obtain the spectrum distribution to be detected.

And the empty-drum detection module 73 is configured to determine whether an empty-drum phenomenon exists at the detected point based on a difference between the spectral distribution to be detected and the reference spectral distribution.

According to the tile hollowing detection device provided by the embodiment of the disclosure, a first audio signal obtained by knocking a set position on a substrate plane for multiple times is obtained, and reference frequency spectrum distribution is obtained; collecting a second audio signal obtained by knocking the detected point on the substrate plane to obtain the spectrum distribution to be detected; determining whether the detected point has a hollowing phenomenon or not based on the difference between the spectral distribution to be detected and the reference spectral distribution; the embodiment realizes the detection of the hollowing of the ceramic tile based on the difference of the audio frequency spectrum distribution, collects the knocked audio frequencies at different positions of the ceramic tile, can judge whether the hollowing exists between the ceramic tile and the paving surface, and has the advantages of low cost, simple and convenient operation and high real-time property.

Optionally, the hollowing detection module 73 is specifically configured to perform divergence calculation on the to-be-detected spectrum distribution and the reference spectrum distribution to obtain a divergence value; determining that the detected point has a hollowing phenomenon in response to the divergence value being greater than or equal to the set threshold value; and determining that the detected point has no empty drum phenomenon in response to the divergence value being smaller than the set threshold value.

Optionally, the reference distribution determining module 71 includes:

the first signal acquisition unit is used for acquiring a first audio signal obtained by knocking a set position on a substrate plane for multiple times;

a reference spectrum unit for determining whether the number of the first audio segments is greater than or equal to a set number, and if so, determining a reference spectrum distribution based on the set number of the first audio segments; otherwise, continuously acquiring a first audio signal obtained by knocking the set position on the substrate plane, and segmenting the first audio signal to obtain at least one first audio segment until a set number of first audio segments are obtained.

Optionally, the first dividing unit is specifically configured to obtain a plurality of peaks in the first audio signal based on the sliding window; determining a start position and an end position of each of a plurality of tapping sounds based on each of the plurality of peaks; each tapping corresponds to a tapping sound, and each tapping sound corresponds to a peak; the first audio signal is segmented based on the start position and the end position of each tapping sound to obtain a plurality of first audio segments.

Optionally, the first dividing unit, when determining the start position and the end position of each of the plurality of tapping sounds based on each of the plurality of peaks, is configured to, for each of the plurality of peaks, find a first position of a first set duration forward in the first audio signal with the peak as a center point; judging whether at least one peak exists between the central point and the first position, and if so, taking the end position of the peak most adjacent to the peak as a starting position; otherwise, taking the first position as the initial position; searching a second position with a second set time length backwards in the first audio signal by taking the wave crest as a central point; judging whether at least one peak exists between the central point and the second position, and if so, taking the position before the peak most adjacent to the peak as an end position; otherwise, the second position is taken as the end position.

Optionally, the reference spectrum unit is configured to, when determining the reference spectrum distribution based on a set number of the first audio segments, perform frequency domain conversion on each of the first audio segments in the set number of first audio segments, respectively, to obtain a set number of first frequency domain signal segments; respectively carrying out normalization processing on each of the set number of first frequency domain signal segments to obtain a set number of normalized first frequency domain signal segments; and calculating an average value based on the set number of normalized first frequency domain signal segments to obtain the reference frequency spectrum distribution.

the reference frequency spectrum unit is used for calculating an average value based on the set number of normalized first frequency domain signal segments to obtain a plurality of average value energy values corresponding to the normalized first frequency domain signal segments based on the energy values corresponding to each frequency value in the set number of normalized first frequency domain signal segments in the normalized first frequency domain signal segments when obtaining reference frequency spectrum distribution; wherein each frequency value corresponds to a mean energy value; and arranging the plurality of average energy values according to the distribution of the normalized first frequency domain signal segments to obtain the reference frequency spectrum distribution.

Optionally, the reference distribution determining module 71 further includes:

Optionally, the distribution to be detected determining module 72 includes:

Optionally, the second slicing unit is specifically configured to obtain a peak in the second audio signal based on the sliding window; determining a start position and an end position of the tapping sound based on the wave crest; and segmenting the second audio signal based on the starting position and the ending position of the knocking sound to obtain a second audio segment.

Optionally, the second slicing unit is configured to, when determining the start position and the end position of the tapping sound based on the peaks, find a third position of a third set duration forward in the second audio signal as the start position with the peak as a center point for each peak in the at least one peak; and with the wave crest as a central point, backward searching a fourth position with a fourth set time length in the second audio signal as an end position.

Optionally, the frequency spectrum unit to be measured is specifically configured to perform frequency domain conversion on the second audio frequency segment to obtain a second frequency domain signal segment; and performing normalization processing on the second frequency domain signal segment to obtain the frequency spectrum distribution to be detected.

Optionally, the distribution to be detected determining module 72 further includes:

Exemplary electronic device

Next, an electronic apparatus according to an embodiment of the present disclosure is described with reference to fig. 8. The electronic device may be either or both of the first device 100 and the second device 200, or a stand-alone device separate from them that may communicate with the first device and the second device to receive the collected input signals therefrom.

FIG. 8 illustrates a block diagram of an electronic device in accordance with an embodiment of the disclosure.

As shown in fig. 8, the electronic device 80 includes one or more processors 81 and memory 82.

The processor 81 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 80 to perform desired functions.

Memory 82 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, Random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, Read Only Memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer readable storage medium and executed by the processor 81 to implement the tile hollowing detection method of the various embodiments of the present disclosure described above and/or other desired functions. Various contents such as an input signal, a signal component, a noise component, etc. may also be stored in the computer-readable storage medium.

In one example, the electronic device 80 may further include: and a knocking device (not shown in the figure) configured to knock a set position and a detected point on the plane of the substrate.

In one example, the electronic device 80 may further include: an input device 83 and an output device 84, which are interconnected by a bus system and/or other form of connection mechanism (not shown).

For example, when the electronic device is the first device 100 or the second device 200, the input device 83 may be a microphone or a microphone array as described above for capturing an input signal of a sound source. When the electronic device is a stand-alone device, the input means 83 may be a communication network connector for receiving the acquired input signals from the first device 100 and the second device 200.

The input device 83 may include, for example, a keyboard, a mouse, and the like.

The output device 84 may output various information including the determined distance information, direction information, and the like to the outside. The output devices 84 may include, for example, a display, speakers, a printer, and a communication network and its connected remote output devices, among others.

Of course, for simplicity, only some of the components of the electronic device 80 relevant to the present disclosure are shown in fig. 8, omitting components such as buses, input/output interfaces, and the like. In addition, the electronic device 80 may include any other suitable components depending on the particular application.

Exemplary computer program product and computer-readable storage Medium

In addition to the above-described methods and apparatus, embodiments of the present disclosure may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform the steps in the tile empty-drum detection method according to various embodiments of the present disclosure described in the "exemplary methods" section of this specification above.

The computer program product may write program code for carrying out operations for embodiments of the present disclosure in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.

Furthermore, embodiments of the present disclosure may also be a computer-readable storage medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform the steps in the tile empty drum detection method according to various embodiments of the present disclosure described in the "exemplary methods" section above in this specification.

The computer-readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The foregoing describes the general principles of the present disclosure in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present disclosure are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present disclosure. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the disclosure is not intended to be limited to the specific details so described.

In the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts in the embodiments are referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The block diagrams of devices, apparatuses, systems referred to in this disclosure are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, systems may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. Words such as "including," "comprising," "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".

The methods and apparatus of the present disclosure may be implemented in a number of ways. For example, the methods and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless specifically stated otherwise. Further, in some embodiments, the present disclosure may also be embodied as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

It is also noted that in the devices, apparatuses, and methods of the present disclosure, each component or step can be decomposed and/or recombined. These decompositions and/or recombinations are to be considered equivalents of the present disclosure.

The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit embodiments of the disclosure to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.

Claims

1. A method for detecting hollowing of ceramic tiles, comprising:

2. The method according to claim 1, wherein the determining whether the detected point has a hollowing phenomenon based on the difference between the to-be-detected spectral distribution and the reference spectral distribution comprises:

3. The method of claim 2, wherein obtaining the first audio signal obtained by tapping a set position on a base plane multiple times to obtain a reference spectral distribution comprises:

4. The method of claim 3, wherein said slicing the first audio signal into a plurality of first audio segments comprises:

segmenting the first audio signal based on the starting position and the ending position of each knocking sound to obtain a plurality of first audio segments;

preferably, the determining a start position and an end position of each of a plurality of tapping sounds based on each of the plurality of peaks includes:

5. A method as claimed in claim 3 or 4, wherein the determining the reference spectral distribution based on a set number of the first audio segments comprises:

calculating an average value based on the set number of normalized first frequency domain signal segments to obtain the reference frequency spectrum distribution;

preferably, each of the normalized first frequency domain signal segments in the set number of normalized first frequency domain signal segments includes the same number of frequency domain values;

6. The method according to any one of claims 1 to 5, wherein the acquiring a second audio signal obtained by tapping the detected point on the substrate plane to obtain the spectrum distribution to be detected comprises:

segmenting the second audio signal to obtain a second audio segment;

7. The method of claim 6, wherein said slicing the second audio signal to obtain a second audio segment comprises:

obtaining peaks in the second audio signal based on a sliding window;

segmenting the second audio signal based on the starting position and the ending position of the knocking sound to obtain a second audio segment;

preferably, the determining the start position and the end position of the tapping sound based on the peak comprises:

8. The method according to claim 6 or 7, wherein determining the spectral distribution to be detected based on the second audio segment comprises:

9. A computer-readable storage medium, characterized in that it stores a computer program for executing the tile hollowing detection method according to any one of the preceding claims 1 to 8.

10. An electronic device, characterized in that the electronic device comprises:

a processor;

a memory for storing the processor-executable instructions;

a knocking device;

-said processor for reading said executable instructions from said memory and executing said instructions to implement the tile hollowing detection method of any one of the preceding claims 1-8;