Background noise recognition method, device, electronic device and storage medium

Abstract

The embodiment of the present application discloses a background noise identification method, device, electronic device and storage medium, which relates to the technical field of radio environment monitoring. The method includes the following steps: collecting the environmental signal to be measured; obtaining the envelope spectrum of the environmental signal to be measured; distinguishing whether the environmental signal to be measured is in the high frequency band or the low frequency band according to the set frequency threshold; selecting the corresponding optimization strategy to process the envelope spectrum according to the distinguished high and low frequency bands to obtain the final background noise. The present application utilizes the spectral characteristics of the environmental signal to be measured to distinguish the high and low frequency bands of the environmental signal to be measured, and then uses different optimization strategies to differentiate and process the envelope spectrum to obtain the background noise for determination, thereby ensuring and improving the stability and accuracy of the noise curve, making the signal identification result more accurate.

Description

Technical Field

[0001] The present application relates to the technical field of radio environment monitoring, and in particular to a background noise recognition method, device, electronic device and storage medium. Background Art

[0002] In the daily maintenance work of radio, monitoring stations are often used to obtain electromagnetic signals in the environment to complete the monitoring and management of abnormal signals. However, how to distinguish daily signals, background noise and abnormal signals is relatively complicated in the increasingly complex electromagnetic environment.

[0003] In the related art, the environmental spectrum monitoring data obtained by the monitoring station is averaged and a mean curve is generated, and the mean curve is raised as background noise, wherein the raised value is dynamically processed according to the current environment. However, for some very unusual signals, given the low frequency of the signal, the signal strength of the frequency band where the signal is located after averaging will not increase too much, and thus false alarms will occur in conventional monitoring; and if special signals such as frequency hopping signals appear, the background noise curve will not be able to reflect them, and it is easy for normal signals to be reported as abnormal signals.

[0004] It can be seen that how to effectively identify abnormal signals in background noise is one of the technical problems that urgently need to be solved in this field. Summary of the invention

[0005] In view of this, embodiments of the present application provide a background noise recognition method, device, electronic device and storage medium to solve at least one problem existing in the background technology.

[0006] In a first aspect, an embodiment of the present application provides a method for identifying background noise, comprising the following steps:

[0007] Collect the environmental signal to be tested;

[0008] Acquire the envelope spectrum of the environmental signal to be measured;

[0009] Distinguish whether the environmental signal to be measured is in the high frequency band or the low frequency band according to the set frequency threshold;

[0010] According to the distinguished high and low frequency bands, a corresponding optimization strategy is selected to process the envelope spectrum to obtain the final background noise.

[0011] In conjunction with the first aspect of the present application, in an optional implementation manner, the step of selecting a corresponding optimization strategy to process the envelope spectrum according to the distinguished high and low frequency bands specifically includes:

[0012] If the frequency band of the environmental signal to be measured is a low frequency band, the time domain envelope value in the envelope spectrum is processed by segment smoothing in the frequency domain to obtain a frequency domain smoothing result, and the result is raised as the final background noise; or

[0013] If the frequency band of the measured environmental signal is a high frequency band, the minimum value of the time domain envelope value of each frequency point in the envelope spectrum is selected as the background noise value of the measured environmental signal, and the background noise value is raised as the final background noise.

[0014] In conjunction with the first aspect of the present application, in an optional implementation manner, the step of piecewise smoothing the time domain envelope value in the envelope spectrum in the frequency domain specifically includes:

[0015] The frequency domain is segmented according to the set bandwidth, and all the time domain envelope values ​​in each segment are averaged to obtain the first mean value;

[0016] Then, all time domain envelope values ​​in the segment that are lower than the first mean value are averaged to obtain a second mean value, and the second mean value is used as the frequency domain smoothing result of the segment.

[0017] In conjunction with the first aspect of the present application, in an optional implementation manner, after obtaining the second mean, the method further includes the following steps:

[0018] If the difference between the second mean and the true background noise value of the segment exceeds the set threshold, the mean of the time domain envelope values ​​of the first two frequency points of the segment is used as the frequency domain smoothing result of the segment; otherwise, the second mean is used as the frequency domain smoothing result of the segment.

[0019] In conjunction with the first aspect of the present application, in an optional implementation manner, after obtaining the frequency domain smoothing result and before lifting the result, the method further includes the following steps:

[0020] If a frequency point has a sudden change, the value of the frequency point is corrected to the average of the two frequency points before and after the frequency point.

[0021] In conjunction with the first aspect of the present application, in an optional implementation manner, the step of acquiring the envelope spectrum of the environmental signal to be measured specifically includes:

[0022] Acquire the time domain signals of each frequency point of the environmental signal to be measured, and correct the burst signals in the time domain signals;

[0023] Perform maximum value stroke on the corrected time domain signal to obtain the time domain envelope of each frequency point;

[0024] Each of the time domain envelopes is transformed from time domain to frequency domain to obtain an envelope spectrum.

[0025] In conjunction with the first aspect of the present application, in an optional implementation manner, the step of correcting the burst signal in the time domain signal specifically includes:

[0026] The value of the burst signal is corrected to be the average value of two time domain signals before and after the burst signal.

[0027] In a second aspect, an embodiment of the present application provides a background noise recognition device, including:

[0028] A signal acquisition module, which is configured to acquire an environmental signal to be tested;

[0029] A spectrum acquisition module, configured to acquire an envelope spectrum of the environmental signal to be measured;

[0030] A frequency band distinguishing module, configured to distinguish whether the environmental signal to be measured is in a high frequency band or a low frequency band according to a set frequency threshold;

[0031] The background noise optimization module is configured to select a corresponding optimization strategy to process the envelope spectrum according to the distinguished high and low frequency bands to obtain the final background noise.

[0032] In a third aspect, an embodiment of the present application further provides an electronic device, including a processor and a memory;

[0033] The memory is used to store computer executable instructions;

[0034] The processor is used to execute the computer executable instructions to implement the background noise recognition method as described in any one of the first aspects above.

[0035] In a fourth aspect, an embodiment of the present application further provides a storage medium on which a computer program is stored, and when the computer program is executed by a processor, the method for identifying background noise as described in any one of the above-mentioned first aspects is implemented.

[0036] The beneficial effects brought about by the technical solution provided in the embodiment of the present application include: utilizing the spectral characteristics of the environmental signal to be measured, using the set frequency threshold as the dividing point to distinguish whether the frequency band in which the environmental signal to be measured is located is a high frequency band or a low frequency band, and then using different optimization strategies to differentiate the envelope spectrum of the environmental signal to be measured according to the high and low frequency bands to obtain the background noise used for judgment, thereby ensuring and improving the stability and accuracy of the noise curve, making the signal recognition result more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0038] Figure 1 A flowchart of a method for identifying background noise provided in an embodiment of the present application;

[0039] Figure 2 It is the spectrum diagram of the real-time value and background noise value of the low-frequency signal in the frequency domain;

[0040] Figure 3 It is the spectrum diagram of the real-time value and background noise value of the high-frequency signal in the frequency domain;

[0041] Figure 4 A spectrum diagram of the real-time value, noise floor value and threshold value of another low-frequency signal in the frequency domain;

[0042] Figure 5 A flowchart of a method for identifying background noise provided in a specific example of the present application;

[0043] Figure 6 It is the spectrum diagram in the time domain of three frequency points selected in the broadcast frequency band;

[0044] Figure 7 A schematic diagram of the structure of a background noise recognition device provided in one embodiment of the present application;

[0045] Figure 8 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application.

[0046] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0047] In order to make the technical solutions and beneficial effects of the present invention more clearly understandable, the following is a detailed description by listing specific embodiments. The drawings are not necessarily drawn to scale, and local features may be enlarged or reduced to more clearly show the details of the local features; unless otherwise defined, the technical and scientific terms used herein have the same meanings as those in the technical field to which this application belongs.

[0048] like Figure 1 As shown, the embodiment of the present application provides a method for identifying background noise, comprising the following steps:

[0049] S101, collecting the environmental signal to be tested;

[0050] S102, obtaining the envelope spectrum of the environmental signal to be measured;

[0051] S103, distinguishing whether the environmental signal to be measured is in a high frequency band or a low frequency band according to a set frequency threshold;

[0052] S104, selecting a corresponding optimization strategy according to the distinguished high and low frequency bands to process the envelope spectrum to obtain a final background noise.

[0053] In environmental monitoring, when an environmental signal to be measured is collected, it can be determined whether the real frequency of the environmental signal to be measured is above or below the frequency domain threshold, and then the environmental signal to be measured can be distinguished into a high frequency band and a low frequency band.

[0054] In the embodiment of the present application, preferably, the range of the frequency threshold is set to 850±20MHz. In a preferred embodiment, the frequency threshold is approximately 850MHz. The low frequency band in the embodiment of the present application is approximately below 850MHz, which is mostly a frequency band not used by operators, and the curve characteristics of its envelope spectrum have the following characteristics:

[0055] (1) The noise floor value is unstable, and the local frequency band is generally raised or lowered;

[0056] (2) There are large fluctuations in the level of the entire frequency band.

[0057] The high frequency band in the embodiment of the present application is approximately above 850 MHz, which is mostly a frequency band used by operators or a dedicated frequency band. The curve characteristics of its envelope spectrum have the following characteristics:

[0058] (1) The noise floor value is stable, and there is no overall increase or decrease in the local frequency band;

[0059] (2) A broadband and stable signal.

[0060] It can be seen that there are obvious differences in the curve characteristics of the envelope spectrum between the high and low frequency bands, such as Figure 2 and Figure 3 As shown, compared with the related art that directly averages the spectrum data, the embodiment of the present application utilizes the curve characteristics of the envelope spectrum of the environmental signal to be measured to distinguish the high and low frequency bands of the environmental signal to be measured, and then uses different optimization strategies to differentiate the envelope spectrum to obtain the background noise used for judgment, thereby ensuring and improving the stability and accuracy of the noise curve, making the signal recognition result more accurate, and accurately realizing the monitoring of abnormal signals.

[0061] Among them, step 102 and step 103 can also be replaced in sequence or performed simultaneously.

[0062] As an optional specific solution of the embodiment of the present application, the step of obtaining the envelope spectrum of the environmental signal to be measured specifically includes:

[0063] Acquire the time domain signals of each frequency point of the environmental signal to be measured, and correct the burst signals in the time domain signals;

[0064] Perform maximum value stroke on the corrected time domain signal to obtain the time domain envelope of each frequency point;

[0065] Each of the time domain envelopes is transformed from time domain to frequency domain to obtain an envelope spectrum.

[0066] Specifically, the specific steps of correcting the burst signal in the time domain signal include:

[0067] The value of the burst signal is corrected to be the average value of two time domain signals before and after the burst signal.

[0068] The embodiment of the present application processes the time domain signals of each frequency point in the time domain. Compared with the traditional mean calculation, the present application filters out abnormal time domain signals, avoids misjudgment or omission of some abnormal signals with low signal strength, and reduces the interference effect on the noise curve.

[0069] Optionally, the step of selecting a corresponding optimization strategy to process the envelope spectrum according to the distinguished high and low frequency bands specifically includes:

[0070] If the frequency band of the environmental signal to be measured is a low frequency band, the time domain envelope value in the envelope spectrum is processed by segment smoothing in the frequency domain to obtain a frequency domain smoothing result, and the result is raised as the final background noise; or

[0071] If the frequency band of the measured environmental signal is a high frequency band, the minimum value of the time domain envelope value of each frequency point in the envelope spectrum is selected as the background noise value of the measured environmental signal, and the background noise value is raised as the final background noise.

[0072] For different high and low frequency bands, the background noise value in the low frequency band is relatively unstable locally, that is, the time domain envelope value is unstable in the frequency domain, so segmentation processing is performed in the frequency domain to obtain a more accurate background noise for judgment, which can be compared with the actual background noise to effectively distinguish between background noise and abnormal noise; while the background noise value in the high frequency band is stable, so a lower value is found in the wide frequency domain as the background noise value for comparison with the actual background noise.

[0073] The time domain envelope value is the mean value of the time domain envelope of the frequency point.

[0074] For high frequency bands, when the frequency range is appropriate, the minimum value of the time domain stroke value is taken as the noise floor value of the entire frequency band. In addition, in order to ensure that the signal recognition result is more accurate, after determining the noise floor value, it is necessary to appropriately increase the margin value of the noise floor value, that is, to raise the noise floor curve, and the raised noise floor value is the threshold value.

[0075] As for the low frequency band, it also needs to be processed segmentally in the frequency domain.

[0076] It can be seen from this that in the differential processing of high-frequency and low-frequency signals, high-frequency signals are relatively stable and can be processed in the time domain alone; while low-frequency signals have many jumps, so a combination of time domain and frequency domain processing can be used to effectively improve the accuracy of the background noise used for judgment obtained from the low-frequency signals.

[0077] Specifically, the step of smoothing the time domain envelope value in the envelope spectrum in the frequency domain in sections specifically includes:

[0078] The frequency domain is segmented according to the set bandwidth, and all the time domain envelope values ​​in each segment are averaged to obtain the first mean value;

[0079] Then, all time domain envelope values ​​in the segment that are lower than the first mean value are averaged to obtain a second mean value, and the second mean value is used as the frequency domain smoothing result of the segment.

[0080] In this embodiment, the service channel is segmented with a bandwidth of 0.01MHz, and each segment is subjected to frequency domain smoothing processing, that is, the average value of the time domain envelope value of each frequency point in each segment is obtained, which is defined as the first mean value, and then all values ​​in the segment lower than the first mean value are taken out to obtain a new average value based on the first mean value, which is defined as the second mean value. Under normal circumstances, the second mean value will not differ too much from the real background noise value of the segment, so the second mean value is used as the frequency domain smoothing result of the segment, that is, the background noise value of the segment.

[0081] If an abnormal situation occurs, optionally, after obtaining the second mean value, the method further includes the following steps:

[0082] If the difference between the second mean and the true background noise value of the segment exceeds the set threshold, the mean of the time domain envelope values ​​of the first two frequency points of the segment is used as the frequency domain smoothing result of the segment; otherwise, the second mean is used as the frequency domain smoothing result of the segment.

[0083] In this embodiment, the threshold is set based on actual experience. If the actual noise floor value differs greatly from the calculated noise floor value, the average value of the first two frequency points is used instead, so that each narrow signal of the flat domain stroke value can be smoothed out.

[0084] In order to ensure the accuracy of the frequency domain smoothing result, optionally, after obtaining the frequency domain smoothing result and before lifting the result, the following steps are further included:

[0085] If a frequency point has a sudden change, the value of the frequency point is corrected to the average of the two frequency points before and after the frequency point.

[0086] In this embodiment, the concept of frequency domain averaging is proposed to address the instability of low-frequency signals. At the same time, abnormal situations that may occur at certain frequency points are filtered out to ensure the stability and accuracy of the final noise curve.

[0087] like Figure 4 As shown in the figure, taking the low-frequency signal as an example, there are two smoother curves above the real background noise; the lower one is the processed noise curve, that is, the curve corresponding to the result of frequency domain smoothing; the upper one is the final noise curve obtained after raising the noise curve by 5dB, and the final noise curve is used as the background noise discrimination curve.

[0088] As an application of the embodiment of the present application in electromagnetic environment monitoring, in the actual monitoring noise, the final background noise is obtained, that is, the noise floor curve is obtained, and the real-time signal is compared with the noise floor curve. If there is a frequency point that continuously exceeds the noise floor, it is considered that the frequency point is an abnormal frequency point and an alarm signal needs to be issued.

[0089] The background noise recognition method provided in the present application is further explained below with reference to a specific example.

[0090] Figure 5 The flowchart of this specific example is shown; as shown in the figure, first, the external monitoring device starts to perform monitoring and obtain monitoring data. In practical applications, for example, the frequency band and area to be monitored are specified, and the spectrum data of the surrounding area for a period of time is obtained through the external monitoring device.

[0091] Next, perform time domain stroke. Time domain stroke can be called time domain maximum stroke. Regardless of high or low frequency bands, the characteristics of a single frequency point in the time domain are quasi-sine waves with peaks and troughs. First, the trough data must be removed from the time domain. Figure 6 The time domain spectrum diagram of the three frequency points 95.7MHz, 96.5MHz and 91.1MHz selected in the broadcast frequency band is shown. The actual value is the irregularly jumping curve in the figure. The curve is continuously outlined according to the maximum value to form an envelope. In addition, it is necessary to eliminate the interference of burst signals and set a limit value. If the signal strength of a certain frequency point has a sudden change compared with the signal strength of the same frequency point twice before and after it, and the sudden change value exceeds the limit value, then the frequency point is considered to be a burst signal and it is corrected to the average of the two previous and next signals. Finally, the corrected time domain signal is outlined, specifically by sampling and taking the maximum value, and averaging all the points to obtain the mean of a certain frequency point. Each frequency point is outlined in the time domain and the average is taken. The resulting spectrum diagram is as follows: Figure 2 and Figure 3 As shown, the curve in the figure is the background noise value that has not been processed in the frequency domain, which is called "time domain stroke value" or "time domain envelope value" here.

[0092] From this, we can see that the level value of this frequency point is mostly smaller than this value. By observing the envelope, we can find the following characteristics: the lower value (real background noise) is unstable in the low frequency band and stable in the high frequency band; the frequency point value of the signal will be very large; broadband signals will lead to continuous high values.

[0093] For high frequency bands, when the frequency band range is appropriately large, the minimum value of the time domain stroke value is taken as the noise floor of the entire frequency band. In a large number of observations, the applicant found that after taking the noise floor value for the high frequency band, it is necessary to appropriately increase the margin value, which will make the signal recognition result more accurate.

[0094] For the low frequency band, it is also necessary to process it segmentally in the frequency domain.

[0095] Next, it is determined whether it is a high-frequency signal. If the result of the determination is no, the frequency domain smoothing step is performed. Specifically, the time domain edge value obtained in the low-frequency band is smoothed to the background noise in two steps by using the adjacent frequency situation.

[0096] The first step is to perform segment processing. Divide the service channel into segments with a certain bandwidth (such as 0.1MHz) and process each segment separately. In each segment, take the average value 1, and then take the average value 1 as the standard to take out all values ​​lower than the average value 1 and calculate the average value 2. It can be understood that the actual noise floor value of the frequency band should not differ too much from the average value 2. For frequency bands with too large a difference, use the average value of the first two frequency points instead, so that the narrower signals in each segment of the flat domain stroke value can be smoothed out.

[0097] The second step is to perform comprehensive processing. Correct the frequency point that has undergone a sudden change to the average of the two frequency points on its left and right. And add a value to the final noise curve as the final background noise. Figure 4 As shown, there are two smoother curves above the background noise, of which the lower one is the processed noise curve, and the upper one is the noise curve with 5dB added, which serves as the final background noise discrimination curve.

[0098] In practical applications, the background noise is calculated through the background noise algorithm and applied to monitoring. The real-time signal is compared with the background noise curve. If there is a frequency point that continuously exceeds the background noise, it is considered to be an abnormal frequency point and an immediate alarm is required.

[0099] The noise floor calculation method in this specific example processes high and low frequencies differently. Since the low-frequency signal has too many jumps, a comprehensive processing of the time domain and the frequency domain is adopted. The high-frequency signal is relatively stable and can be processed in the time domain. Differentiating between high- and low-frequency signals can be optimized differently for different characteristics of the signal, and the accuracy of the results is also improved. For the traditional mean calculation method, the idea of ​​filtering outliers is proposed. For some sudden signals in daily life, if they are not eliminated, it will affect the noise curve and will misjudge or miss some abnormal signals with low signal strength. In addition, in view of the instability of low-frequency signals, this specific example proposes frequency domain averaging processing to filter out abnormal situations that may occur at certain frequency points, and ensure the stability and accuracy of the noise curve.

[0100] On this basis, the embodiment of the present application further provides a background noise recognition device. Figure 7 The structure of the background noise recognition device is shown; as shown in the figure, the background noise recognition device 700 includes:

[0101] A signal acquisition module 701 is configured to acquire a signal of an environment to be tested;

[0102] A spectrum acquisition module 702, configured to acquire an envelope spectrum of the environmental signal to be measured;

[0103] A frequency band distinguishing module 703, which is configured to distinguish whether the environmental signal to be measured is in a high frequency band or a low frequency band according to a set frequency threshold;

[0104] The background noise optimization module 704 is configured to select a corresponding optimization strategy to process the envelope spectrum according to the distinguished high and low frequency bands to obtain the final background noise.

[0105] Optionally, the background noise optimization module 704 is specifically configured as follows: if the frequency band of the environmental signal to be measured is a low frequency band, then the time domain envelope value in the envelope spectrum is smoothed in the frequency domain in sections to obtain a frequency domain smoothing result, and the result is raised as the final background noise; or if the frequency band of the environmental signal to be measured is a high frequency band, then the minimum value of the time domain envelope value of each frequency point in the envelope spectrum is selected as the background noise value of the environmental signal to be measured, and the background noise value is raised as the final background noise.

[0106] Optionally, the background noise optimization module 704 is configured to perform segmented smoothing processing on the time domain envelope values ​​in the envelope spectrum in the frequency domain, specifically including: segmenting the frequency domain according to a set bandwidth, and averaging all the time domain envelope values ​​in each segment to obtain a first mean; then averaging all the time domain envelope values ​​in the segment that are lower than the first mean to obtain a second mean, and using the second mean as the frequency domain smoothing result of the segment.

[0107] Optionally, after obtaining the second mean, the background noise optimization module 704 is further configured as follows: if the difference between the second mean and the true background noise value of the segment exceeds a set threshold, then the mean of the time domain envelope values ​​of the first two frequency points of the segment is used as the frequency domain smoothing result of the segment; otherwise, the second mean is used as the frequency domain smoothing result of the segment.

[0108] Optionally, after obtaining the frequency domain smoothing result and before raising the result, the noise floor optimization module 704 is further configured to: if a frequency point has a sudden change, correct the value of the frequency point to the average of the two frequency points before and after the frequency point.

[0109] Optionally, the spectrum acquisition module 702 is specifically configured to: obtain the time domain signal of each frequency point of the environmental signal to be measured, and correct the burst signal in the time domain signal; perform maximum value outlining on the corrected time domain signal to obtain the time domain envelope of each frequency point; perform time domain to frequency domain transformation on each of the time domain envelopes to obtain an envelope spectrum.

[0110] Optionally, the spectrum acquisition module 702 is configured to correct the burst signal in the time domain signal, specifically including: correcting the value of the burst signal to an average value of two time domain signals before and after the burst signal.

[0111] It is worth noting that the device embodiments provided in the present application have been described in detail in the above method embodiments and will not be repeated here.

[0112] The embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the background noise recognition method as described in any of the above embodiments are implemented.

[0113] The present application embodiment can be a system, method and / or computer program product. The computer program product may include a computer-readable storage medium, which is loaded with a computer-readable program instruction for making a processor realize various aspects of the present application. The computer program product can be written in any combination of one or more programming languages ​​to perform the program code for performing the operation of the present application embodiment, and the programming language includes an object-oriented programming language, such as Java, C++, etc., and also includes a conventional procedural programming language, such as "C" language or similar programming language. The program code can be executed completely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device, partially on the remote computing device, or completely on the remote computing device or server. In the case of a remote computer, the remote computer can be connected to the user computer through any type of network-including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet). In some embodiments, by utilizing the state information of computer-readable program instructions to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer-readable program instructions to implement various aspects of the present application.

[0114] Computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. Computer readable storage medium is a tangible device that can keep and store instructions used by an instruction execution device. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage medium include: portable computer disk, hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanical encoding device, such as a punch card or a convex structure in a groove on which instructions are stored, and any suitable combination of the above. The computer readable storage medium used here is not interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated by a waveguide or other transmission medium (for example, a light pulse by an optical fiber cable), or an electrical signal transmitted by a wire.

[0115] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0116] Various aspects of the present application are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0117] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0118] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0119] An embodiment of the present application also provides an electronic device. Figure 8 The structure diagram of an electronic device provided by an embodiment of the present application is shown. As shown in the figure, the electronic device 800 includes: one or more processors 801 and a memory 802; the memory 802 stores computer executable instructions; the processor 801 is used to execute the computer executable instructions to implement the steps in the background noise recognition method of any of the above embodiments.

[0120] The processor 801 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0121] The memory 802 may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. 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 the processor 801 may execute the program instructions to implement the steps in the text recognition method of each embodiment of the present application described above and / or other desired functions.

[0122] In one example, the electronic device 800 may further include: an input device and an output device, and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown in the figure).

[0123] In addition, the input device may also include, for example, a keyboard, a mouse, a microphone, etc. The output device may output various information to the outside, and may include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0124] Of course, to simplify, Figure 8 Only a part of the components related to the present application in the electronic device 800 is shown, and components such as a bus, an input device / output interface, etc. are omitted. In addition, according to specific application conditions, the electronic device 800 may also include any other appropriate components.

[0125] It should be noted that the background noise recognition method embodiment, background noise recognition device embodiment, computer-readable storage medium embodiment and electronic device embodiment provided in the embodiments of the present application belong to the same concept; the technical features in the technical solutions recorded in each embodiment can be arbitrarily combined without conflict.

[0126] It should be understood that the above embodiments are exemplary and are not intended to include all possible implementations included in the claims. Various modifications and changes may be made on the basis of the above embodiments without departing from the scope of the present disclosure. Similarly, the various technical features of the above embodiments may be arbitrarily combined to form other embodiments of the present invention that may not be explicitly described. Therefore, the above embodiments only express several implementations of the present invention and do not limit the scope of protection of the patent of the present invention.

Claims

1. A method for identifying background noise, characterized in that: The following steps are involved: Collect the environmental signal to be tested; Acquire the envelope spectrum of the environmental signal to be measured; Distinguish whether the environmental signal to be measured is in the high frequency band or the low frequency band according to the set frequency threshold; Selecting a corresponding optimization strategy to process the envelope spectrum according to the distinguished high and low frequency bands to obtain the final background noise; The step of selecting a corresponding optimization strategy to process the envelope spectrum according to the distinguished high and low frequency bands specifically includes: If the frequency band of the environmental signal to be measured is a low frequency band, the time domain envelope value in the envelope spectrum is processed by segment smoothing in the frequency domain to obtain a frequency domain smoothing result, and the result is raised as the final background noise; or If the frequency band of the measured environmental signal is a high frequency band, the minimum value of the time domain envelope value of each frequency point in the envelope spectrum is selected as the background noise value of the measured environmental signal, and the background noise value is raised as the final background noise.

2. The background noise recognition method according to claim 1, characterized in that: The step of piecewise smoothing the time domain envelope value in the envelope spectrum in the frequency domain specifically comprises: The frequency domain is segmented according to the set bandwidth, and all the time domain envelope values ​​in each segment are averaged to obtain the first mean value; Then, all time domain envelope values ​​in the segment that are lower than the first mean value are averaged to obtain a second mean value, and the second mean value is used as the frequency domain smoothing result of the segment.

3. The background noise recognition method according to claim 2, characterized in that: After obtaining the second mean, the method further comprises the steps of: If the difference between the second mean and the true background noise value of the segment exceeds the set threshold, the mean of the time domain envelope values ​​of the first two frequency points of the segment is used as the frequency domain smoothing result of the segment; otherwise, the second mean is used as the frequency domain smoothing result of the segment.

4. The background noise recognition method according to claim 1, characterized in that: After obtaining the frequency domain smoothing result and before lifting the result, the following steps are also included: If a frequency point has a sudden change, the value of the frequency point is corrected to the average of the two frequency points before and after the frequency point.

5. The background noise recognition method according to claim 1, characterized in that: The step of obtaining the envelope spectrum of the environmental signal to be measured specifically includes: Acquire the time domain signals of each frequency point of the environmental signal to be measured, and correct the burst signals in the time domain signals; Perform maximum value stroke on the corrected time domain signal to obtain the time domain envelope of each frequency point; Each of the time domain envelopes is transformed from time domain to frequency domain to obtain an envelope spectrum.

6. The background noise recognition method according to claim 5, characterized in that: The step of correcting the burst signal in the time domain signal specifically includes: The value of the burst signal is corrected to be the average value of two time domain signals before and after the burst signal.

7. A background noise recognition device, characterized in that: include: A signal acquisition module, which is configured to acquire an environmental signal to be tested; A spectrum acquisition module, configured to acquire an envelope spectrum of the environmental signal to be measured; A frequency band distinguishing module, configured to distinguish whether the environmental signal to be measured is in a high frequency band or a low frequency band according to a set frequency threshold; A background noise optimization module is configured to select a corresponding optimization strategy to process the envelope spectrum according to the distinguished high and low frequency bands to obtain a final background noise; The noise floor optimization module is specifically configured as follows: if the frequency band of the environmental signal to be measured is a low frequency band, the time domain envelope value in the envelope spectrum is smoothed in the frequency domain in sections to obtain a frequency domain smoothing result, and the result is raised as the final background noise; or if the frequency band of the environmental signal to be measured is a high frequency band, the minimum value of the time domain envelope value of each frequency point in the envelope spectrum is selected as the noise floor value of the environmental signal to be measured, and the noise floor value is raised as the final background noise.

8. An electronic device, characterized in that: including a processor and a memory; The memory is used to store computer executable instructions; The processor is used to execute the computer executable instructions to implement the background noise recognition method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the method for identifying background noise as claimed in any one of claims 1 to 6 is implemented.

Images