Method and device for identifying and positioning noise source in complex environment and computer equipment
By acquiring and analyzing the noise data of multiple measurement locations, identifying noise types and distributions, combining noise recognition models and triangular positioning algorithms, the problem of low noise source positioning accuracy in complex environments is solved, and higher noise source positioning accuracy is achieved sex.
Patent Information
- Application Number
- CN202411075794.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-07
- Publication Date
- 2024-11-29
AI Technical Summary
In complex environments, traditional noise source positioning methods are difficult to accurately identify and locate noise sources, especially when multiple types of noise interfere with and mix with each other, resulting in low positioning accuracy.
By obtaining noise data of multiple measurement locations, extracting noise characteristic information, identifying noise type and distribution information, using the noise identification model to identify noise structure information, and combining the triangular positioning algorithm to determine the noise source position to generate noise positioning information.
It improves the comprehensiveness and accuracy of noise type analysis in complex noise environments, improves the accuracy of noise source positioning, and avoids the problem of only estimating slightly rough noise orientation and type.
Smart Images

Figure CN119044888A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of artificial intelligence and sound source localization, and in particular to a method, device and computer equipment for identifying and localizing noise sources in complex environments. Background Art
[0002] With the rapid development of the economy and society, as electricity consumption increases, the number of substations in urban areas has gradually increased. The power facilities and ventilation noise reduction facilities in the substations will generate a large amount of external noise, causing noise pollution, which has a certain impact on sensitive areas such as surrounding residential areas, hospitals, and schools, resulting in an increase in complaints and disputes caused by substation noise. In actual production and life, the source of noise is relatively complex, especially in downtown areas. There is not only noise generated by power transmission and transformation facilities, but also noise generated by urban vehicles and human activities. Multiple types of noise are transmitted through a complex urban environment, interfering and mixing with each other, which increases the difficulty of distinguishing noise types and locating noise sources. Therefore, how to accurately identify and locate noise sources is the current research focus.
[0003] The traditional technical solution is to collect field data mainly by relying on fixed monitoring stations and mobile monitoring equipment. The methods include handheld noise detectors, vehicle-mounted noise sensors, etc., and carry out fixed-point measurements of some sensitive areas / sensitive points within the substation boundary. Noise data is collected during the day and night, and combined with urban vehicles and human activities around the sensitive points of residents, the measured data results are used to analyze the substation boundary noise, so as to determine the main source of noise affecting the residents and the nature of the noise. However, this method can only estimate the approximate noise direction and possible noise type, and the deviation and range are large, resulting in low accuracy in locating noise sources under complex environmental conditions. Summary of the invention
[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for identifying and locating noise sources in a complex environment in order to address the above technical problems.
[0005] In a first aspect, the present application provides a method for identifying and locating noise sources in a complex environment. The method comprises:
[0006] Acquire noise data of a plurality of measurement positions in a target area, and extract noise characteristic information of the noise based on the noise data;
[0007] Based on the noise feature information, identifying noise information of each noise type contained in the target area, and based on the noise information of each noise type, identifying noise distribution information of the target area;
[0008] Based on the noise information of each noise type, identifying the noise structure information of each noise information through a noise identification model, and based on the noise distribution information of the target area, identifying the noise source position of the noise information of each noise type;
[0009] The noise location information of the target area is generated based on the noise source position of each piece of noise information and the noise structure information of each piece of noise information.
[0010] Optionally, extracting noise characteristic information of the noise based on the noise data includes:
[0011] Based on the noise data, identifying a noise soundprint of the noise and a noise audio frequency of the noise, and based on the noise soundprint of the noise and the noise audio frequency of the noise, splitting the noise into sub-noise soundprints of different sub-noises and sub-noise audio frequencies of each of the sub-noises;
[0012] For each sub-noise, based on the sub-noise voiceprint of the sub-noise, a sub-voiceprint feature of the sub-noise is identified by a voiceprint feature identification strategy, and a sub-audio feature of the sub-noise is identified by an audio feature identification strategy;
[0013] The sub-voiceprint features of each of the sub-noises and the sub-audio frequency features of each of the sub-noises are used as noise feature information of the noise.
[0014] Optionally, the identifying noise information of each noise type contained in the target area based on the noise feature information includes:
[0015] For each sub-noise, based on the sub-voiceprint feature of the sub-noise, identifying the noise type of the sub-noise through a voiceprint recognition network;
[0016] In the database, the feature range corresponding to each noise feature type of the noise type is queried, and based on the feature range corresponding to each noise feature type of the noise type and the sub-audio feature of the sub-noise, the noise information of the sub-noise in the noise type is identified.
[0017] Optionally, the identifying the noise distribution information of the target area based on the noise information of each noise type includes:
[0018] For each sub-noise, based on the noise data at each measurement position, the sub-voiceprint feature of the sub-noise, and the audio frequency feature of the sub-noise, identifying the noise intensity information of the sub-noise at each measurement position;
[0019] Based on the position information of each of the measurement positions in the target area and the noise intensity information of each of the measurement positions, identifying the sound decreasing distribution range of the sub-noise through a sound wave decreasing strategy;
[0020] The sound decreasing distribution ranges of all sub-noises are projected into the same geographical space to obtain the noise distribution information of the target area.
[0021] Optionally, the step of identifying noise structure information of each noise information based on the noise information of each noise type by using a noise recognition model includes:
[0022] For each sub-noise, based on the noise information of the sub-noise in the noise type, identifying each noise parameter information of the sub-noise;
[0023] The noise parameter information of each sub-noise is input into the noise recognition model to recognize the noise structure information corresponding to the noise information.
[0024] Optionally, the identifying the noise source position of the noise information of each noise type based on the noise distribution information of the target area includes:
[0025] For each sub-noise, based on the sound decreasing distribution range of the sub-noise, using a triangulation positioning algorithm, locate the initial noise source position of the sub-noise in the sound decreasing distribution range;
[0026] Identify each target measurement position within a preset spacing range of the initial noise source position, and re-collect new noise data of each target measurement position;
[0027] Replacing the noise data of each measurement position with the new noise data of each target measurement position, and returning to the step of extracting noise characteristic information of the noise based on the noise data to obtain a new initial noise source position of the sub-noise;
[0028] In the case where the distance between the new initial noise source position and the initial noise source position is greater than a preset distance threshold, the new initial noise source position replaces the initial noise source position, and the step of identifying each target measurement position within the preset distance range of the initial noise source position is returned to be executed until the distance between the new initial noise source position and the initial noise source position is no greater than the preset distance threshold, and the new initial noise source position obtained in the last iteration is used as the noise source position of the sub-noise.
[0029] Optionally, the generating the noise location information of the target area based on the noise source position of each piece of noise information and the noise structure information of each piece of noise information includes:
[0030] Acquire regional map data including the target area, and mark the noise source position of each of the sub-noises in the regional map data;
[0031] The noise structure information of each of the sub-noises is added to the noise source position of each of the sub-noises to obtain the noise location information of the target area.
[0032] In a second aspect, the present application also provides a noise source identification and positioning device in a complex environment. The device comprises:
[0033] An acquisition module, used to acquire noise data of multiple measurement positions in a target area, and extract noise characteristic information of the noise based on the noise data;
[0034] an identification module, configured to identify noise information of each noise type contained in the target area based on the noise feature information, and to identify noise distribution information of the target area based on the noise information of each noise type;
[0035] A positioning module, used to identify the noise structure information of each noise information based on the noise information of each noise type through a noise recognition model, and identify the noise source position of the noise information of each noise type based on the noise distribution information of the target area;
[0036] A generating module is used to generate noise location information of the target area based on the noise source position of each piece of noise information and the noise structure information of each piece of noise information.
[0037] Optionally, the acquisition module is specifically used to:
[0038] Based on the noise data, identifying a noise soundprint of the noise and a noise audio frequency of the noise, and based on the noise soundprint of the noise and the noise audio frequency of the noise, splitting the noise into sub-noise soundprints of different sub-noises and sub-noise audio frequencies of each of the sub-noises;
[0039] For each sub-noise, based on the sub-noise voiceprint of the sub-noise, a sub-voiceprint feature of the sub-noise is identified by a voiceprint feature identification strategy, and a sub-audio feature of the sub-noise is identified by an audio feature identification strategy;
[0040] The sub-voiceprint features of each of the sub-noises and the sub-audio frequency features of each of the sub-noises are used as noise feature information of the noise.
[0041] Optionally, the identification module is specifically used to:
[0042] For each sub-noise, based on the sub-voiceprint feature of the sub-noise, identifying the noise type of the sub-noise through a voiceprint recognition network;
[0043] In the database, the feature range corresponding to each noise feature type of the noise type is queried, and based on the feature range corresponding to each noise feature type of the noise type and the sub-audio feature of the sub-noise, the noise information of the sub-noise in the noise type is identified.
[0044] Optionally, the identification module is specifically used to:
[0045] For each sub-noise, based on the noise data at each measurement position, the sub-voiceprint feature of the sub-noise, and the audio frequency feature of the sub-noise, identifying the noise intensity information of the sub-noise at each measurement position;
[0046] Based on the position information of each of the measurement positions in the target area and the noise intensity information of each of the measurement positions, identifying the sound decreasing distribution range of the sub-noise through a sound wave decreasing strategy;
[0047] The sound decreasing distribution ranges of all sub-noises are projected into the same geographical space to obtain the noise distribution information of the target area.
[0048] Optionally, the positioning module is specifically used to:
[0049] For each sub-noise, based on the noise information of the sub-noise in the noise type, identifying each noise parameter information of the sub-noise;
[0050] The noise parameter information of each sub-noise is input into the noise recognition model to recognize the noise structure information corresponding to the noise information.
[0051] Optionally, the positioning module is specifically used to:
[0052] For each sub-noise, based on the sound decreasing distribution range of the sub-noise, using a triangulation positioning algorithm, locate the initial noise source position of the sub-noise in the sound decreasing distribution range;
[0053] Identify each target measurement position within a preset spacing range of the initial noise source position, and re-collect new noise data of each target measurement position;
[0054] Replacing the noise data of each measurement position with the new noise data of each target measurement position, and returning to the step of extracting noise characteristic information of the noise based on the noise data to obtain a new initial noise source position of the sub-noise;
[0055] In the case where the distance between the new initial noise source position and the initial noise source position is greater than a preset distance threshold, the new initial noise source position replaces the initial noise source position, and the step of identifying each target measurement position within the preset distance range of the initial noise source position is returned to be executed until the distance between the new initial noise source position and the initial noise source position is no greater than the preset distance threshold, and the new initial noise source position obtained in the last iteration is used as the noise source position of the sub-noise.
[0056] Optionally, the generating module is specifically used for:
[0057] Acquire regional map data including the target area, and mark the noise source position of each of the sub-noises in the regional map data;
[0058] The noise structure information of each of the sub-noises is added to the noise source position of each of the sub-noises to obtain the noise location information of the target area.
[0059] In a third aspect, the present application provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.
[0060] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.
[0061] In a fifth aspect, the present application provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.
[0062] The above-mentioned noise source identification and positioning method, device and computer equipment for complex environment obtains noise data of multiple measurement positions of the target area, and extracts noise feature information of the noise based on the noise data; identifies noise information of each noise type contained in the target area based on the noise feature information, and identifies noise distribution information of the target area based on the noise information of each noise type; identifies noise structure information of each noise information through a noise identification model based on the noise information of each noise type, and identifies the noise source position of each noise type of noise information based on the noise distribution information of the target area; generates noise positioning information of the target area based on the noise source position of each noise information and the noise structure information of each noise information. This scheme can avoid the discontinuity and collection deviation of data collection by manual hand-holding by obtaining each noise data at multiple preset measurement positions. Then, this scheme identifies the noise type and noise structure information of each noise existing in the target area by noise feature recognition, thereby improving the comprehensiveness of analyzing each noise contained in the environment in a complex noise environment, and performing noise analysis from each sub-noise as a granularity, thereby improving the accuracy of analyzing noise types and identifying noise positioning. Then, this solution trains an optimized noise recognition model to identify the noise structure information of each noise information, improves the comprehensiveness and accuracy of the recognition of each noise, and also provides data technology support for the subsequent effective reduction of this type of noise. Finally, after identifying the noise distribution information of the target area, this solution analyzes the location of the noise source of each noise, improves the positioning accuracy of each noise in the environment, avoids the problem of only being able to estimate the approximate noise direction and possible noise type, and thus comprehensively improves the accuracy of locating the noise source under complex environmental conditions. BRIEF DESCRIPTION OF THE DRAWINGS
[0063] Figure 1 A diagram of an application environment of a noise source identification and positioning method in a complex environment in one embodiment;
[0064] Figure 2 A schematic diagram of a flow chart of a method for identifying and locating a noise source in a complex environment in one embodiment;
[0065] Figure 3 A schematic diagram of a process flow of an example of noise source identification and positioning in a complex environment in one embodiment;
[0066] Figure 4 A structural block diagram of a noise source identification and positioning device in a complex environment in one embodiment;
[0067] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0068] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0069] The noise source identification and positioning method in a complex environment provided by the embodiment of the present application can be applied to Figure 1 In the application environment of the substation noise dispute area shown. Among them, number 1# to number 16# are simulation diagrams of monitoring layout points corresponding to the noise monitoring instruments set at each preset position point at the edge of the substation noise dispute area, wherein each preset position point is preset by the staff in the identification and positioning module, and can change with the adjustment of the staff, wherein the dispute area can also be other location ranges that need to measure noise sources. The control module can be a terminal, a server, or a system combining a terminal and a server. When the control module is a terminal, the terminal can avoid the discontinuity and collection deviation of data collection by manual hand-held by obtaining each noise data at multiple preset measurement positions. Then, this scheme identifies the noise type and noise structure information of each noise existing in the target area by means of noise feature recognition, thereby improving the comprehensiveness of the analysis of each noise contained in the analysis environment in a complex noise environment, and performing noise analysis from each sub-noise as a granularity, thereby improving the accuracy of analyzing noise types and identifying noise positioning. Then, this solution trains an optimized noise recognition model to identify the noise structure information of each noise information, improves the comprehensiveness and accuracy of the recognition of each noise, and also provides data technology support for the subsequent effective reduction of this type of noise. Finally, after identifying the noise distribution information of the target area, this solution analyzes the location of the noise source of each noise, improves the positioning accuracy of each noise in the environment, avoids the problem of only being able to estimate the approximate noise direction and possible noise type, and thus comprehensively improves the accuracy of locating the noise source under complex environmental conditions.
[0070] In one embodiment, Figure 2 As shown, a noise source identification and positioning method for a complex environment is provided. Figure 1 The terminal in is used as an example to illustrate, including the following steps:
[0071] Step S201: acquiring noise data of a plurality of measurement positions in a target area, and extracting noise characteristic information of the noise based on the noise data.
[0072] In this embodiment, the terminal collects noise data of each preset time period through noise monitors at each measurement position preset at the edge of the target area. The noise data is sound pitch / decibel, which is greater than the preset pitch / decibel threshold. That is, the noise monitor only collects sound data greater than the preset pitch / decibel threshold. The target area is the area range preset by the staff, and the interval distance between each adjacent measurement position is equal. The noise data that can be collected by the noise monitor at each measurement position includes the noise soundprint data of all noises within the preset time period, and the noise sound spectrum data of all noises. The soundprint data is the sound wave spectrum of the noise, and the noise audio frequency data is the audio frequency frequency, tone size, sound amplitude range, and sound interval duration of the noise. Then, based on the noise data, the terminal extracts the noise feature information of the noise, wherein the noise feature information includes the sub-voiceprint feature of each sub-noise, and the sub-audio frequency feature of each sub-noise. The specific extraction process will be described in detail later. The terminal splits the noise audio data into sub-noise audio data of each sub-noise, and splits the noise voiceprint data into sub-noise voiceprint data of each sub-noise, and then identifies each sub-voiceprint feature and each sub-audio feature. The specific splitting process will be described in detail later.
[0073] Step S202: based on the noise feature information, identifying noise information of each noise type contained in the target area, and based on the noise information of each noise type, identifying noise distribution information of the target area.
[0074] In this embodiment, the terminal identifies the noise information of each noise type contained in the target area based on the noise feature information, and identifies the noise distribution information of the target area based on the noise information of each noise type. The noise information is based on the sub-audio characteristics of each sub-noise, and the noise parameters of the sub-noise are identified. The noise parameters include noise frequency, noise pitch, noise decibel, noise amplitude and other parameters. The noise parameters collected in this step are parameters corresponding to a parameter range, that is, each noise parameter corresponds to a parameter value range. The specific identification process will be described in detail later.
[0075] Step S203 , based on the noise information of each noise type, the noise structure information of each noise information is identified through a noise identification model, and based on the noise distribution information of the target area, the noise source position of the noise information of each noise type is identified.
[0076] In this embodiment, the terminal identifies the noise structure information of each noise information based on the noise information of each noise type through a noise recognition model, and identifies the noise source position of the noise information of each noise type based on the noise distribution information of the target area. Among them, the noise structure information is the true parameter value of each noise parameter corresponding to the noise information described above. Since the noise parameter identified when identifying the noise information is a parameter range, this solution identifies the specific parameter value of each noise parameter through a noise recognition model. The noise recognition network is a convolutional neural network (CNN) based on reinforcement learning. The convolutional neural network can extract the characteristic value of each noise feature information, and then the parameter values of each noise parameter corresponding to different characteristic values are stored in the noise database. The terminal characteristic value corresponds to the query method to identify the true parameter value of each noise parameter. The noise source position identification process will be described in detail later.
[0077] Step S204: generating noise location information of the target area based on the noise source position of each noise information and the noise structure information of each noise information.
[0078] In this embodiment, the terminal generates noise location information of the target area based on the noise source location of each noise information and the noise structure information of each noise information, wherein the noise location information is the location of each noise source in the target area and the indication identification information of the noise structure information of each noise source.
[0079] Based on the above scheme, by obtaining each noise data at multiple preset measurement positions, the discontinuity and collection deviation of data collection by hand can be avoided. Then, this scheme identifies the noise type and noise structure information of each noise existing in the target area by noise feature recognition, which improves the comprehensiveness of the analysis of each noise contained in the environment in a complex noise environment, and analyzes the noise from each sub-noise as a granularity, which improves the accuracy of analyzing the noise type and identifying the noise location. After that, this scheme identifies the noise structure information of each noise information by training an optimized noise recognition model, improves the comprehensiveness and accuracy of the recognition of each noise, and also provides data technology support for the subsequent effective reduction of this type of noise. Finally, this scheme analyzes the noise source position of each noise after identifying the noise distribution information of the target area, improves the positioning accuracy of each noise existing in the environment, avoids the problem of only being able to estimate the approximate noise direction and possible noise type, and thus comprehensively improves the accuracy of locating the noise source under complex environmental conditions.
[0080] Optionally, based on the noise data, noise characteristic information of the noise is extracted, including: based on the noise data, identifying the noise voiceprint and the noise audio frequency of the noise, and splitting the noise into sub-noise soundprints of different sub-noises and sub-noise audio frequencies of each sub-noise based on the noise voiceprint of the noise and the noise audio frequency of the noise; for each sub-noise, based on the sub-noise voiceprint of the sub-noise, identifying the sub-voiceprint feature of the sub-noise through a voiceprint feature recognition strategy, and identifying the sub-audio frequency feature of the sub-noise through an audio feature recognition strategy; using the sub-voiceprint features of each sub-noise and the sub-audio frequency features of each sub-noise as the noise characteristic information of the noise.
[0081] In this embodiment, the terminal identifies the noise voiceprint and the noise audio frequency of the noise based on the noise data, and splits the noise into sub-noise voiceprints of different sub-noises and sub-noise audio frequencies of each sub-noise based on the noise voiceprint and the noise audio frequency of the noise.
[0082] The specific splitting process is that the terminal identifies a single noise voiceprint containing a single sub-noise in the noise voiceprint, and removes each of the single sub-noise voiceprints in the noise voiceprint through a noise removal program to obtain a new noise voiceprint, and then the terminal replaces the noise voiceprint with the new noise voiceprint, and returns to the step of identifying a single noise voiceprint containing a single sub-noise in the noise voiceprint to obtain the sub-noise voiceprints of each sub-noise split out. Similarly, the terminal also splits the noise audio frequency of each noise one by one through the above-mentioned single noise splitting method. Among them, the noise removal program is to perform noise removal operations through the noise removal program of MATLAB.
[0083] For each sub-noise, based on the sub-noise voiceprint of the sub-noise, a sub-voiceprint feature of the sub-noise is identified through a voiceprint feature identification strategy.
[0084] The recognition process of the sub-voiceprint feature is to split each sub-noise voiceprint into several single-frame voiceprints, and then perform fast Fourier transform (FFT) on each frame to obtain the noise spectrum. After that, the terminal converts the spectrum into a Mel frequency scale and calculates the Mel spectrum coefficients. Finally, the Mel frequency cepstral feature vector (Mel-frequency cepstral coefficients, MFCC) is obtained by performing discrete cosine transform (DCT for Discrete Cosine Transform, DCT) on the Mel spectrum coefficients. Among them, the feature vector is the sub-voiceprint feature of the sub-noise.
[0085] Then, the terminal identifies the sub-audio features of the sub-noise through an audio feature recognition strategy.
[0086] The database stores the corresponding relationship of the characteristic values corresponding to each audio data, for example, the frequency characteristic value corresponding to the audio frequency, the tone characteristic value corresponding to the tone size, the sound amplitude characteristic value corresponding to the sound amplitude range, and the sound interval characteristic value corresponding to the sound interval duration. Then, the terminal identifies the sub-audio characteristics of each sub-noise based on the above corresponding relationship.
[0087] Finally, the terminal uses the sub-voiceprint features of each sub-noise and the sub-audio frequency features of each sub-noise as noise feature information of the noise.
[0088] Based on the above solution, by splitting the noise into sub-noises, the sub-voiceprint features of each sub-noise and the sub-audio frequency features of each sub-noise are identified respectively, thereby improving the fineness and accuracy of the analysis.
[0089] Optionally, based on the noise feature information, noise information of each noise type contained in the target area is identified, including: for each sub-noise, based on the sub-voiceprint feature of the sub-noise, identifying the noise type of the sub-noise through a voiceprint recognition network; in a database, querying the feature range corresponding to each noise feature type of the noise type, and identifying the noise information of the sub-noise in the noise type based on the feature range corresponding to each noise feature type of the noise type and the sub-audio feature of the sub-noise.
[0090] In this embodiment, the terminal identifies the noise type of each sub-noise based on the sub-voiceprint feature of the sub-noise through the voiceprint recognition network. The noise types include but are not limited to transformer noise, high-voltage line noise in the station, ventilation noise reduction fan noise, vehicle noise on surrounding roads, human activity noise (sound, gathering activities) and other noise types. Each noise type corresponds to a voiceprint feature range, and the terminal determines the noise type of the sub-noise by matching the voiceprint feature range to which the sub-voiceprint feature of the sub-noise belongs.
[0091] In the database, the terminal queries the feature range corresponding to each noise feature type of the noise type, and identifies the noise information of the sub-noise in the noise type based on the feature range corresponding to each noise feature type of the noise type and the sub-audio feature of the sub-noise. The noise feature type is the parameter feature type of each noise parameter, such as the frequency feature type, the pitch feature type, the decibel feature type, and the amplitude feature type. Based on each feature value, the terminal queries the sub-noise information of each sub-audio feature in the database to obtain the noise information of the sub-noise. For example, the feature value of the decibel feature type is from 1-10, and the feature value corresponding to 180 decibels is 9, where 1-5 is low decibels, 6-8 is medium decibels, and 10 is high decibels, then the sub-noise information corresponding to the feature value is high decibels.
[0092] Based on the above scheme, the sub-noise information corresponding to each sub-audio frequency feature is identified by database query, thereby obtaining noise information, and identifying the noise type corresponding to the sub-voiceprint feature, thereby improving the accuracy of identifying noise information and noise type.
[0093] Optionally, based on the noise information of each noise type, the noise distribution information of the target area is identified, including: for each sub-noise, based on the noise data of each measurement location, the sub-voiceprint characteristics of the sub-noise, and the audio frequency characteristics of the sub-noise, identifying the noise intensity information of the sub-noise at each measurement location; based on the position information of each measurement location in the target area and the noise intensity information of each measurement location, identifying the sound decreasing distribution range of the sub-noise through a sound wave decreasing strategy; and projecting the sound decreasing distribution ranges of all sub-noises into the same geographic space to obtain the noise distribution information of the target area.
[0094] In this embodiment, for each sub-noise, the terminal identifies the noise intensity information of the sub-noise at each measurement position based on the noise data at each measurement position, the sub-voiceprint feature of the sub-noise, and the audio frequency feature of the sub-noise. Then, based on the position information of each measurement position in the target area and the noise intensity information at each measurement position, the terminal identifies the sound decreasing distribution range of the sub-noise through the sound wave decreasing strategy.
[0095] Specifically, the terminal identifies the decreasing direction of the sound wave intensity of the sub-noise based on the noise intensity information of the sub-noise at each measurement position, and then connects two measurement positions with the same noise intensity information through an arc to obtain the noise gradient range of the sub-noise in the target area, and then the terminal deletes the range area with noise intensity lower than the preset intensity threshold in each noise gradient to obtain the target noise gradient range of the sub-noise in the target area.
[0096] Finally, the terminal projects the decreasing distribution ranges of all sub-noises into the same geographic space to obtain the noise distribution information of the target area.
[0097] Based on the above scheme, the noise source and decreasing range of each sub-noise are identified through the intensity gradient analysis strategy, so as to determine the noise gradient range of each sub-noise to construct the noise distribution information of the target area, thereby improving the comprehensiveness of the accuracy of identifying the noise distribution information.
[0098] Optionally, based on the noise information of each noise type, noise structure information of each noise information is identified through a noise recognition model, including: for each sub-noise, based on the noise information of the sub-noise in the noise type, identifying each noise parameter information of the sub-noise; inputting each noise parameter information of the sub-noise into the noise recognition model to identify the noise structure information corresponding to the noise information.
[0099] In this embodiment, the terminal identifies each noise parameter information of each sub-noise based on the noise information of the noise type of the sub-noise.
[0100] Specifically, the terminal obtains the correspondence between each parameter range and the sub-noise information contained in each parameter feature type, and the correspondence between each parameter value and the characteristic value in each parameter range. Then, the terminal identifies the target parameter range corresponding to the sub-noise information of each parameter feature type of each sub-noise, and in the target parameter range, through the correspondence between each parameter value and the characteristic value in each parameter range, queries the parameter value corresponding to the characteristic value of the parameter feature type, and obtains the noise parameter information of the sub-noise.
[0101] For example, if the characteristic value of the decibel characteristic type is 9 and the sub-noise information is high decibel, the parameter range corresponding to the sub-noise information of the decibel characteristic type is (90, 100), where each characteristic value corresponds to a parameter value. When the characteristic value is 9, the noise parameter information of the sub-noise is 90. Finally, the terminal obtains the noise parameter information of each sub-noise through the above scheme.
[0102] The terminal inputs each noise parameter information of the sub-noise into the noise recognition model, and identifies the noise structure information corresponding to the noise information. The noise recognition model is a classifier model, and the terminal inputs the noise type of the sub-noise into the initial classifier model in advance to obtain a classifier suitable for the sub-noise. Then, after the terminal inputs each noise parameter information into the classifier model, the terminal identifies the noise structure information of the sub-noise. The noise structure information is the noise generation method of the sub-noise. The classifier is trained by each sample noise information of multiple different noise types and the sample noise generation method corresponding to each sample noise information to obtain a classifier.
[0103] Based on the above scheme, after identifying the noise parameter information corresponding to each noise information, the generation mode of each sub-noise is identified through a classifier, thereby improving the comprehensiveness of noise identification.
[0104] Optionally, based on the noise distribution information of the target area, the noise source position of the noise information of each noise type is identified, including: for each sub-noise, based on the sound decreasing distribution range of the sub-noise, using a triangulation positioning algorithm, locating the initial noise source position of the sub-noise in the sound decreasing distribution range; identifying each target measurement position within a preset spacing range of the initial noise source position, and re-collecting new noise data for each target measurement position; replacing the noise data of each measurement position with the new noise data of each target measurement position, and returning to execute the step of extracting noise feature information of the noise based on the noise data to obtain a new initial noise source position of the sub-noise; when the spacing between the new initial noise source position and the initial noise source position is greater than a preset spacing threshold, replacing the initial noise source position with the new initial noise source position, and returning to execute the step of identifying each target measurement position within the preset spacing range of the initial noise source position, until the spacing between the new initial noise source position and the initial noise source position is not greater than the preset spacing threshold, and the new initial noise source position obtained in the last iteration is used as the noise source position of the sub-noise.
[0105] In this embodiment, for each sub-noise, based on the sound decreasing distribution range of the sub-noise, the terminal uses a triangulation positioning algorithm to locate the initial noise source position of the sub-noise in the sound decreasing distribution range.
[0106] Specifically, based on the sound decreasing distribution range corresponding to each sub-noise, the terminal fits the entire distribution range of each noise gradient of the sub-noise in space through a linear fitting algorithm. Then, the terminal identifies the sub-noise source position corresponding to the entire range of each noise gradient through a triangulation positioning algorithm to obtain multiple sub-noise source positions of the sub-noise. Finally, the terminal averages the positions of each sub-noise source to obtain the noise source position of the sub-noise.
[0107] The terminal identifies each target measurement position within the preset spacing range of the initial noise source position, and re-collects new noise data for each target measurement position. The preset spacing range is preset in the terminal, and the preset spacing range can change with the adjustment of the staff. Then the general section replaces the noise data of each measurement position with the new noise data of each target measurement position, and returns to execute the step of extracting noise feature information of the noise based on the noise data to obtain a new initial noise source position of the sub-noise. Then, the terminal determines whether the spacing between the new initial noise source position and the initial noise source position is greater than the preset spacing threshold.
[0108] In the case where the distance between the new initial noise source position and the initial noise source position is greater than the preset distance threshold, the terminal replaces the initial noise source position with the new initial noise source position, and returns to execute the step of identifying each target measurement position within the preset distance range of the initial noise source position, until the distance between the new initial noise source position and the initial noise source position is no greater than the preset distance threshold, and the new initial noise source position obtained in the last iteration is used as the noise source position of the sub-noise.
[0109] Based on the above scheme, the noise source position of each sub-noise is identified through range fitting and triangulation positioning strategy, thereby improving the accuracy of identification. Then, this scheme iteratively identifies the noise source position of each sub-noise by re-measuring the accuracy of the above noise source position, thereby improving the accuracy of identifying the noise source position of each sub-noise.
[0110] Optionally, based on the noise source position of each noise information and the noise structure information of each noise information, noise location information of the target area is generated, including: obtaining regional map data including the target area, and marking the noise source position of each sub-noise in the regional map data; adding the noise structure information of each sub-noise to the noise source position of each sub-noise to obtain the noise location information of the target area.
[0111] In this embodiment, the terminal obtains the regional map data including the target area, and marks the noise source position of each sub-noise in the regional map data. Finally, the terminal adds the noise structure information of each sub-noise to the noise source position of each sub-noise to obtain the noise location information of the target area.
[0112] Based on the above scheme, after marking the location of the noise source, the noise structure information of each sub-noise is marked, which improves the accuracy and intuitiveness of identifying noise location information.
[0113] This application also provides an example of noise source identification and positioning in a complex environment, such as Figure 3 As shown, the specific processing process includes the following steps:
[0114] Step S301, obtaining noise data of multiple measurement positions in a target area.
[0115] Step S302, based on the noise data, identifying the noise voiceprint of the noise and the noise audio frequency of the noise, and based on the noise voiceprint of the noise and the noise audio frequency of the noise, splitting the noise into sub-noise voiceprints of different sub-noises and sub-noise audio frequencies of each sub-noise.
[0116] Step S303, for each sub-noise, based on the sub-noise voiceprint of the sub-noise, a voiceprint feature recognition strategy is used to identify the sub-voiceprint feature of the sub-noise, and a sub-audio feature of the sub-noise is recognized through an audio feature recognition strategy.
[0117] Step S304: taking the sub-voiceprint features of each sub-noise and the sub-audio frequency features of each sub-noise as noise feature information of the noise.
[0118] Step S305: for each sub-noise, based on the sub-voiceprint features of the sub-noise, identify the noise type of the sub-noise through a voiceprint recognition network.
[0119] Step S306, querying the database for the feature range corresponding to each noise feature type of the noise type, and identifying the noise information of the sub-noise in the noise type based on the feature range corresponding to each noise feature type of the noise type and the sub-audio feature of the sub-noise.
[0120] Step S307 : for each sub-noise, based on the noise data at each measurement position, the sub-voiceprint feature of the sub-noise, and the audio frequency feature of the sub-noise, identify the noise intensity information of the sub-noise at each measurement position.
[0121] Step S308 : Based on the position information of each measurement position in the target area and the noise intensity information of each measurement position, a sound decreasing distribution range of the sub-noise is identified through a sound wave decreasing strategy.
[0122] Step S309: Project the sound decreasing distribution ranges of all sub-noises into the same geographical space to obtain noise distribution information of the target area.
[0123] Step S310 : for each sub-noise, based on the noise information of the noise type of the sub-noise, identifying each noise parameter information of the sub-noise.
[0124] Step S311: input each noise parameter information of the sub-noise into the noise recognition model to recognize the noise structure information corresponding to the noise information.
[0125] Step S312: for each sub-noise, based on the sound decreasing distribution range of the sub-noise, locate the initial noise source position of the sub-noise in the sound decreasing distribution range by using a triangulation positioning algorithm.
[0126] Step S313: identifying each target measurement position within a preset spacing range of the initial noise source position, and recollecting new noise data of each target measurement position.
[0127] Step S314: replace the noise data of each measurement position with the new noise data of each target measurement position, and return to the step of extracting noise characteristic information of the noise based on the noise data to obtain a new initial noise source position of the sub-noise.
[0128] Step S315, when the distance between the new initial noise source position and the initial noise source position is greater than the preset distance threshold, the new initial noise source position replaces the initial noise source position, and returns to execute the step of identifying each target measurement position within the preset distance range of the initial noise source position, until the distance between the new initial noise source position and the initial noise source position is not greater than the preset distance threshold, and the new initial noise source position obtained in the last iteration is used as the noise source position of the sub-noise.
[0129] Step S316, obtaining regional map data including the target area, and marking the noise source position of each sub-noise in the regional map data.
[0130] Step S317: adding the noise structure information of each sub-noise to the noise source position of each sub-noise to obtain the noise location information of the target area.
[0131] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0132] Based on the same inventive concept, the embodiment of the present application also provides a device for identifying and locating a noise source in a complex environment for implementing the above-mentioned method for identifying and locating a noise source in a complex environment. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in the embodiments of one or more devices for identifying and locating a noise source in a complex environment provided below can refer to the limitations of the method for identifying and locating a noise source in a complex environment above, and will not be repeated here.
[0133] In one embodiment, Figure 4 As shown, a noise source identification and positioning device in a complex environment is provided, including: an acquisition module 410, an identification module 420, a positioning module 430 and a generation module 440, wherein:
[0134] An acquisition module 410 is used to acquire noise data of multiple measurement positions in a target area, and extract noise characteristic information of the noise based on the noise data;
[0135] An identification module 420, configured to identify noise information of each noise type contained in the target area based on the noise feature information, and identify noise distribution information of the target area based on the noise information of each noise type;
[0136] A positioning module 430 is used to identify noise structure information of each noise information based on the noise information of each noise type through a noise recognition model, and to identify a noise source position of the noise information of each noise type based on the noise distribution information of the target area;
[0137] The generating module 440 is used to generate the noise location information of the target area based on the noise source position of each piece of the noise information and the noise structure information of each piece of the noise information.
[0138] Optionally, the acquisition module 410 is specifically configured to:
[0139] Based on the noise data, identifying a noise soundprint of the noise and a noise audio frequency of the noise, and based on the noise soundprint of the noise and the noise audio frequency of the noise, splitting the noise into sub-noise soundprints of different sub-noises and sub-noise audio frequencies of each of the sub-noises;
[0140] For each sub-noise, based on the sub-noise voiceprint of the sub-noise, a sub-voiceprint feature of the sub-noise is identified by a voiceprint feature identification strategy, and a sub-audio feature of the sub-noise is identified by an audio feature identification strategy;
[0141] The sub-voiceprint features of each of the sub-noises and the sub-audio frequency features of each of the sub-noises are used as noise feature information of the noise.
[0142] Optionally, the identification module 420 is specifically configured to:
[0143] For each sub-noise, based on the sub-voiceprint feature of the sub-noise, identifying the noise type of the sub-noise through a voiceprint recognition network;
[0144] In the database, the feature range corresponding to each noise feature type of the noise type is queried, and based on the feature range corresponding to each noise feature type of the noise type and the sub-audio feature of the sub-noise, the noise information of the sub-noise in the noise type is identified.
[0145] Optionally, the identification module 420 is specifically configured to:
[0146] For each sub-noise, based on the noise data at each measurement position, the sub-voiceprint feature of the sub-noise, and the audio frequency feature of the sub-noise, identifying the noise intensity information of the sub-noise at each measurement position;
[0147] Based on the position information of each of the measurement positions in the target area and the noise intensity information of each of the measurement positions, identifying the sound decreasing distribution range of the sub-noise through a sound wave decreasing strategy;
[0148] The sound decreasing distribution ranges of all sub-noises are projected into the same geographical space to obtain the noise distribution information of the target area.
[0149] Optionally, the positioning module 430 is specifically used to:
[0150] For each sub-noise, based on the noise information of the sub-noise in the noise type, identifying each noise parameter information of the sub-noise;
[0151] The noise parameter information of each sub-noise is input into the noise recognition model to recognize the noise structure information corresponding to the noise information.
[0152] Optionally, the positioning module 430 is specifically used to:
[0153] For each sub-noise, based on the sound decreasing distribution range of the sub-noise, using a triangulation positioning algorithm, locate the initial noise source position of the sub-noise in the sound decreasing distribution range;
[0154] Identify each target measurement position within a preset spacing range of the initial noise source position, and re-collect new noise data of each target measurement position;
[0155] Replacing the noise data of each measurement position with the new noise data of each target measurement position, and returning to the step of extracting noise characteristic information of the noise based on the noise data to obtain a new initial noise source position of the sub-noise;
[0156] In the case where the distance between the new initial noise source position and the initial noise source position is greater than a preset distance threshold, the new initial noise source position replaces the initial noise source position, and the step of identifying each target measurement position within the preset distance range of the initial noise source position is returned to be executed until the distance between the new initial noise source position and the initial noise source position is no greater than the preset distance threshold, and the new initial noise source position obtained in the last iteration is used as the noise source position of the sub-noise.
[0157] Optionally, the generating module 440 is specifically configured to:
[0158] Acquire regional map data including the target area, and mark the noise source position of each of the sub-noises in the regional map data;
[0159] The noise structure information of each of the sub-noises is added to the noise source position of each of the sub-noises to obtain the noise location information of the target area.
[0160] Each module in the noise source identification and positioning device for a complex environment can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.
[0161] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a noise source identification and positioning method for a complex environment is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.
[0162] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0163] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.
[0164] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.
[0165] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of any one of the methods in the first aspect.
[0166] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.
[0167] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.
[0168] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0169] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A method for identifying and locating noise sources in a complex environment, characterized in that: The method comprises: Acquire noise data of a plurality of measurement positions in a target area, and extract noise characteristic information of the noise based on the noise data; Based on the noise feature information, identifying noise information of each noise type contained in the target area, and based on the noise information of each noise type, identifying noise distribution information of the target area; Based on the noise information of each noise type, identifying the noise structure information of each noise information through a noise identification model, and based on the noise distribution information of the target area, identifying the noise source position of the noise information of each noise type; The noise location information of the target area is generated based on the noise source position of each piece of noise information and the noise structure information of each piece of noise information.
2. The method according to claim 1, characterized in that The step of extracting noise characteristic information of the noise based on the noise data includes: Based on the noise data, identifying a noise voiceprint of the noise and a noise audio frequency of the noise, and based on the noise voiceprint of the noise and the noise audio frequency of the noise, splitting the noise into sub-noise voiceprints of different sub-noises and sub-noise audio frequencies of each of the sub-noises; For each sub-noise, based on the sub-noise voiceprint of the sub-noise, a sub-voiceprint feature of the sub-noise is identified by a voiceprint feature identification strategy, and a sub-audio feature of the sub-noise is identified by an audio feature identification strategy; The sub-voiceprint features of each of the sub-noises and the sub-audio frequency features of each of the sub-noises are used as noise feature information of the noise.
3. The method according to claim 2, characterized in that The step of identifying noise information of each noise type contained in the target area based on the noise feature information includes: For each sub-noise, based on the sub-voiceprint feature of the sub-noise, identifying the noise type of the sub-noise through a voiceprint recognition network; In the database, the feature range corresponding to each noise feature type of the noise type is queried, and based on the feature range corresponding to each noise feature type of the noise type and the sub-audio feature of the sub-noise, the noise information of the sub-noise in the noise type is identified.
4. The method according to claim 2, characterized in that: The identifying the noise distribution information of the target area based on the noise information of each noise type includes: For each sub-noise, based on the noise data at each of the measurement positions, the sub-voiceprint features of the sub-noise, and the audio frequency features of the sub-noise, identifying the noise intensity information of the sub-noise at each measurement position; Based on the position information of each of the measurement positions in the target area and the noise intensity information of each of the measurement positions, identifying the sound decreasing distribution range of the sub-noise through a sound wave decreasing strategy; The sound decreasing distribution ranges of all sub-noises are projected into the same geographical space to obtain the noise distribution information of the target area.
5. The method according to claim 3, characterized in that: The step of identifying noise structure information of each noise information based on the noise information of each noise type by using a noise identification model includes: For each sub-noise, based on the noise information of the sub-noise in the noise type, identifying each noise parameter information of the sub-noise; The noise parameter information of each sub-noise is input into the noise recognition model to recognize the noise structure information corresponding to the noise information.
6. The method according to claim 4, characterized in that The step of identifying the noise source position of the noise information of each noise type based on the noise distribution information of the target area includes: For each sub-noise, based on the sound decreasing distribution range of the sub-noise, using a triangulation positioning algorithm, locate the initial noise source position of the sub-noise in the sound decreasing distribution range; Identify each target measurement position within a preset spacing range of the initial noise source position, and re-collect new noise data of each target measurement position; Replacing the noise data of each measurement position with the new noise data of each target measurement position, and returning to the step of extracting noise characteristic information of the noise based on the noise data to obtain a new initial noise source position of the sub-noise; In the case where the distance between the new initial noise source position and the initial noise source position is greater than a preset distance threshold, the new initial noise source position replaces the initial noise source position, and the step of identifying each target measurement position within the preset distance range of the initial noise source position is returned to be executed until the distance between the new initial noise source position and the initial noise source position is no greater than the preset distance threshold, and the new initial noise source position obtained in the last iteration is used as the noise source position of the sub-noise.
7. The method according to claim 2, characterized in that The generating the noise location information of the target area based on the noise source position of each piece of noise information and the noise structure information of each piece of noise information comprises: Acquire regional map data including the target area, and mark the noise source position of each of the sub-noises in the regional map data; The noise structure information of each of the sub-noises is added to the noise source position of each of the sub-noises to obtain the noise location information of the target area.
8. A noise source identification and positioning device in a complex environment, characterized in that: The device comprises: An acquisition module, used to acquire noise data of multiple measurement positions in a target area, and extract noise characteristic information of the noise based on the noise data; an identification module, configured to identify noise information of each noise type contained in the target area based on the noise feature information, and to identify noise distribution information of the target area based on the noise information of each noise type; A positioning module, used to identify the noise structure information of each noise information based on the noise information of each noise type through a noise recognition model, and identify the noise source position of the noise information of each noise type based on the noise distribution information of the target area; A generating module is used to generate noise location information of the target area based on the noise source position of each piece of noise information and the noise structure information of each piece of noise information.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
