A method and system for processing urban and rural planning data

Abstract

The present invention relates to the field of data processing, and in particular to a method and system for processing urban and rural planning data. The method and system are provided with a plurality of noise monitoring devices arranged in groups, including: a receiving module for collecting sounds in a traffic line at an urban-rural junction and generating corresponding sound data; a filtering module for filtering the sound data and generating a corresponding noise learning model; a processing module for preprocessing the filtered data, selecting a plurality of index features to learn the preprocessed data and generating a corresponding noise distribution map; an adjustment module for receiving the noise distribution map, calculating the overlap of the sound data, and making adjustment measures for the noise source and the filtering module. While effectively improving the accuracy of noise identification, the accuracy of identifying the noise pollution position of the traffic line at the urban-rural junction is improved, and the noise of the traffic line at the urban-rural junction is visualized by using the learning model, thereby effectively improving the accuracy of identifying the noise pollution position of the traffic line at the urban-rural junction.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a method and system for processing urban and rural planning data. Background Art

[0002] Urban and rural planning is a comprehensive deployment of the study of the future development of the city, the reasonable layout of the city and the comprehensive arrangement of various urban engineering construction projects. It is a blueprint for urban development in a certain period of time and an important part of urban management. Now that the urban population is increasing, the noise of life and industry such as vehicles and construction has always troubled people. However, there are great differences between cities and villages, and the measurement and collection of noise cannot be fully covered, which makes it difficult to carry out the cleaning of noise pollution.

[0003] China Patent Authorization Announcement No.: CN116819446B discloses an online monitoring system for environmental noise based on noise source positioning, which relates to the field of noise source positioning monitoring technology, including a sound collection module and a noise judgment module, a noise source positioning module and a remote monitoring center, wherein the sound collection module includes a bracket, a first sound receiving device, a second sound receiving device and a third sound receiving device, and the first sound receiving device, the second sound receiving device and the third sound receiving device are arranged on the bracket at equal intervals from top to bottom. The noise collection of the invention adopts three sound receiving devices from top to bottom to realize the accurate collection of audible and inaudible sound sources of different frequency ranges at the same time, solves the defect of the existing sound imaging instrument to analyze all sounds in general, increases the judgment of noise, identifies the noise in the traditional sense based on the decibel threshold, realizes the monitoring of inaudible low-frequency or high-frequency noise, and avoids the impact of inaudible noise such as low-frequency or high-frequency on human production and life.

[0004] Chinese Patent Authorization Announcement No.: CN111121953B discloses a method, device and equipment for dynamic visualization monitoring of noise, including: obtaining the user's location information in the real environment and the noise data collected by the user at the location in real time; constructing a virtual geographic environment including the user's avatar, synchronizing the location information of the user's avatar in the virtual geographic environment with the location information of the user in the real environment, and synchronizing the noise data corresponding to the location information of the user's avatar in the virtual geographic environment with the noise data collected by the user at the location in the real environment; according to the location information of the user's avatar in the virtual geographic environment, using the intensity of the noise data corresponding to the location information as a display attribute, constructing a three-dimensional structure image in the virtual geographic environment; and displaying the virtual geographic environment including the three-dimensional structure image to the user. Compared with the prior art, this invention realizes dynamic visualization monitoring of noise data.

[0005] However, the above method has the following problems: it is impossible to intelligently control the system in real time and the operation efficiency is low. Summary of the invention

[0006] To this end, the present invention provides a method and system for processing urban and rural planning data to overcome the problems in the prior art of being unable to intelligently control the system in real time and having low operating efficiency.

[0007] To achieve the above object, the present invention provides an urban and rural planning data processing system, wherein the system is provided with a plurality of noise monitoring devices arranged in groups along the traffic routes at the junction of urban and rural areas, and a single noise monitoring device comprises:

[0008] A receiving module, which is used to collect sounds in traffic routes at the junction of urban and rural areas and generate corresponding sound data;

[0009] A filtering module, connected to the receiving module, for filtering the sound data and generating corresponding filtering data and a corresponding noise learning model;

[0010] A processing module, which is connected to the filtering module, is used to pre-process the filtered data, generate corresponding pre-processed data, select several indicator features of the pre-processed data, learn the pre-processed data according to the indicator features, and generate a corresponding noise distribution map;

[0011] An adjustment module, connected to the filtering module and the processing module, for receiving the noise distribution map, calculating the overlap of the sound data, and making adjustment measures for the noise source and the filtering module;

[0012] Wherein, the sound data includes vehicle noise and resonance noise;

[0013] The filtered data is the corresponding vehicle noise data and resonance noise data generated after filtering the sound data;

[0014] The noise learning model is generated by training the vehicle noise data and the resonance noise data according to the filtered data set;

[0015] The filtered data set includes the vehicle noise data and the resonance noise data of the traffic line at the urban-rural junction at different periods;

[0016] The vehicle noise is the noise generated in the air by vehicles along the traffic routes at the junction of urban and rural areas;

[0017] The resonance noise is the noise generated by vehicles on the ground along the traffic routes at the junction of urban and rural areas;

[0018] The pre-processed data is to fit the corresponding waveform according to the filtered data and generate a number of audio data with a sampling rate of a standard sampling rate, and the processing module generates a corresponding indicator feature according to each audio data;

[0019] The standard sampling rate is a sampling rate that can be recognized by the processing module, and for a single sampling, the corresponding standard sampling rate is a single sampling rate.

[0020] Furthermore, the receiving module includes:

[0021] A noise sensor group is arranged at corresponding ground and underground locations to respectively collect the vibration frequencies of the air and the ground of the traffic line at the urban-rural junction;

[0022] A converter is connected to the noise sensor group and is used for converting the vibration frequency of the air and the ground into the vehicle noise and the resonance noise.

[0023] Furthermore, the filtering module includes:

[0024] A collector, configured to receive the vehicle noise and the resonance noise;

[0025] A filter connected to the collector, for filtering the vehicle noise and the resonance noise, and generating corresponding vehicle noise data and resonance noise data;

[0026] A generator is connected to the filter and is used to store the vehicle noise data and the resonance noise data, and train the vehicle noise data and the resonance noise data according to the filtered data set to generate a corresponding noise learning model.

[0027] Furthermore, the processing module includes:

[0028] A preprocessor, which is used to preprocess the vehicle noise data and the resonance noise data to generate corresponding preprocessed data;

[0029] a receiver connected to the generator and configured to receive the noise learning model;

[0030] A learner is connected to the receiver and the preprocessor, and is used to select several indicator features of the preprocessed data, learn the preprocessed data according to the noise learning model, and generate corresponding vehicle noise distribution maps and resonance noise distribution maps.

[0031] Furthermore, the noise sensor groups located at the ground and underground positions respectively collect the vibration frequencies of the air and the ground of the traffic lines at the urban-rural junction, and convert them into the corresponding sound data through the converter. The collector receives the sound data, and a monitoring volume threshold is set in the filter. For a single sound data, when it reaches the monitoring volume threshold, the filter collects the sound data corresponding to the preset filtering time before reaching the monitoring volume threshold, and forms corresponding vehicle noise data and resonance noise data.

[0032] Furthermore, the preprocessor preprocesses the vehicle noise data and the resonance noise data to generate corresponding preprocessed data, and the preprocessing further includes:

[0033] Based on the data collection characteristics of the filtered data set, data cleaning is performed to obtain cleaned data of the filtered data set, and the cleaned data is standardized;

[0034] The data cleaning is to remove the sound data below the monitoring volume threshold in the filtered data;

[0035] The standardization process is to segment the filtered data according to a standard sampling rate.

[0036] Furthermore, the receiver receives a corresponding noise learning model, and the noise learning model learns the preprocessed data according to the indicator characteristics to generate a corresponding noise distribution map.

[0037] Wherein, the indicator characteristics include the decibel and generation location of the noise;

[0038] The learning is to convert the preprocessed data into a spectrogram, extract the index feature in the spectrogram, and annotate the spectrogram based on the index feature;

[0039] The noise distribution map includes a vehicle noise distribution map and a resonance noise distribution map.

[0040] Furthermore, the adjustment module receives the noise distribution map, and calculates the time difference between the propagation of the vehicle noise and the resonance noise based on the difference in the propagation speed of sound in the solid medium and the gas medium, and translates the vehicle noise distribution map by the time difference in the noise distribution map to obtain a corresponding parallel propagation map.

[0041] Furthermore, the degree of overlap between the vehicle noise distribution map and the resonance noise distribution map in the parallel propagation map is calculated, and an overlap threshold is provided in the adjustment module. When the overlap is less than the overlap threshold, the adjustment module does not make adjustments along the traffic route. When the overlap is greater than the overlap threshold, the adjustment module adjusts the monitoring volume threshold and the preset filtering time, and sets a sound insulation belt along the traffic route.

[0042] In another aspect, the present invention provides a method for processing urban and rural planning data, comprising:

[0043] The generator iteratively optimizes the noise learning model according to the filtered data set until the loss value converges to a preset value;

[0044] Testing the current noise learning model using the filtered data set;

[0045] When the test results meet the preset test results, the noise learning model parameters are saved.

[0046] Compared with the prior art, the present invention is provided with a plurality of noise monitoring devices arranged in groups, including: a receiving module for collecting sounds in traffic lines at urban and rural borders and generating corresponding sound data, a filtering module for filtering the sound data and generating a corresponding noise learning model, a processing module for preprocessing the filtered data, selecting a plurality of index features to learn the preprocessed data and generating a corresponding noise distribution map, an adjustment module for receiving the noise distribution map, calculating the overlap of the sound data, and making adjustment measures for the noise source and the filtering module, thereby effectively improving the accuracy of noise identification and the accuracy of noise pollution position identification of traffic lines at urban and rural borders, and using the learning model to visualize the noise of traffic lines at urban and rural borders, thereby effectively improving the accuracy of noise pollution position identification of traffic lines at urban and rural borders.

[0047] Furthermore, by providing a converter in the receiving module to convert the surrounding sound into vehicle noise and resonance noise, it is easier for the noise learning model to learn the noise data, thereby improving the efficiency of regulating the noise data.

[0048] Furthermore, by filtering the vehicle noise and resonance noise in the filtering module, the corresponding vehicle noise data and resonance noise data are obtained, thereby eliminating the error in the learning result caused by the error in filtering data processing during the learning process, and making the learning result more accurate.

[0049] Furthermore, by setting a monitoring volume threshold in the filter, noise screening is achieved, which facilitates real-time adjustment of noise and effectively improves the accuracy of noise recognition.

[0050] Furthermore, by preprocessing the filtered data, corresponding preprocessed data is obtained to improve the recognition efficiency of noise, so that effective features of the preprocessed data can be quickly selected, thereby further improving the accuracy of identifying the location of noise pollution in traffic routes at urban and rural boundaries.

[0051] Furthermore, by setting the overlap threshold and adjusting the noise source and filtering module, the accuracy of identifying the location of noise pollution in traffic routes at urban and rural boundaries is improved, and the complexity of urban and rural planning data processing is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a structural schematic diagram of a single noise monitoring device in an urban and rural planning data processing system of the present invention;

[0053] Figure 2 It is a structural schematic diagram of the filtering module of the present invention;

[0054] Figure 3 It is a structural schematic diagram of the processing module of the present invention;

[0055] Figure 4 The present invention is a flow chart of a method for processing urban and rural planning data. DETAILED DESCRIPTION

[0056] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0057] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0058] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0059] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0060] See also Figure 1 As shown, it is a structural schematic diagram of a single noise monitoring device in an urban and rural planning data processing system of the present invention, including:

[0061] A receiving module, which is used to collect sounds in traffic routes at the junction of urban and rural areas and generate corresponding sound data;

[0062] A filtering module, which is connected to the receiving module, is used to filter the sound data and generate corresponding filtered data and a corresponding noise learning model;

[0063] A processing module, which is connected to the filtering module, is used to pre-process the filtered data, generate corresponding pre-processed data, select several indicator features of the pre-processed data, learn the pre-processed data according to the indicator features, and generate a corresponding noise distribution map;

[0064] An adjustment module, which is connected to the filtering module and the processing module, is used to receive the noise distribution map, calculate the overlap of the sound data, and make adjustment measures for the noise source and the filtering module;

[0065] Among them, the sound data includes vehicle noise and resonance noise;

[0066] The filtered data is the corresponding vehicle noise data and resonance noise data generated after the sound data is filtered;

[0067] The noise learning model is trained and generated based on the filtered data set for the vehicle noise data and the resonance noise data;

[0068] The filtered data set includes vehicle noise data and resonance noise data at different periods of traffic routes at the urban-rural junction;

[0069] Vehicle noise is the noise generated in the air by vehicles along traffic routes at the junction of urban and rural areas;

[0070] Resonance noise is the noise generated by vehicles on the ground along traffic routes at the junction of urban and rural areas;

[0071] The preprocessing data is to fit the corresponding waveform according to the filtered data and generate a number of audio data with a standard sampling rate. The processing module generates corresponding indicator features according to each audio data;

[0072] The standard sampling rate is a sampling rate that can be recognized by the processing module, and for a single sampling, the corresponding standard sampling rate is a single sampling rate.

[0073] In a specific implementation, the indicator features of the preprocessed data can be selected as the decibel and generation location of the noise.

[0074] Preferably, setting the sampling rate to 7000 Hz has a better learning effect on the preprocessed data, and for the system described in this application, the corresponding analysis effect is optimal.

[0075] By providing a number of noise monitoring devices arranged in groups, including: a receiving module, used to collect sounds in traffic lines at urban and rural junctions, and generate corresponding sound data, a filtering module, used to filter the sound data, and generate a corresponding noise learning model, a processing module, used to pre-process the filtered data, select a number of indicator features to learn the pre-processed data, and generate a corresponding noise distribution map, an adjustment module, used to receive the noise distribution map, calculate the overlap of the sound data, and make adjustment measures for the noise source and the filtering module, while effectively improving the accuracy of noise identification, the accuracy of noise pollution position identification of traffic lines at urban and rural junctions is improved, and the noise of traffic lines at urban and rural junctions is visualized by using the learning model, thereby effectively improving the accuracy of noise pollution position identification of traffic lines at urban and rural junctions.

[0076] Specifically, the receiving module includes:

[0077] A noise sensor group is arranged at corresponding ground and underground locations to respectively collect the vibration frequencies of the air and the ground of the traffic routes at the junction of urban and rural areas;

[0078] The converter is connected to the noise sensor group and is used to convert the vibration frequency of the air and the ground into vehicle noise and resonance noise.

[0079] By setting a converter in the receiving module to convert the surrounding sound into vehicle noise and resonance noise, it is easier for the noise learning model to learn the noise data, thereby improving the efficiency of regulating the noise data.

[0080] See also Figure 2 As shown, it is a schematic diagram of the structure of the filtering module of the present invention, comprising:

[0081] A collector for receiving vehicle noise and resonance noise;

[0082] A filter connected to the collector for filtering the vehicle noise and the resonance noise and generating corresponding vehicle noise data and resonance noise data;

[0083] The generator is connected to the filter and is used to store the vehicle noise data and the resonance noise data, and train the vehicle noise data and the resonance noise data according to the filtered data set to generate a corresponding noise learning model.

[0084] By filtering the vehicle noise and resonance noise in the filtering module, the corresponding vehicle noise data and resonance noise data are obtained, which eliminates the errors in the learning results caused by the wrong processing of the filtering data during the learning process, making the learning results more accurate.

[0085] See also Figure 3 As shown, it is a structural schematic diagram of the processing module of the present invention, including:

[0086] A preprocessor, which is used to preprocess the vehicle noise data and the resonance noise data to generate corresponding preprocessed data;

[0087] a receiver, connected to the generator, for receiving the noise learning model;

[0088] The learner is connected to the receiver and the preprocessor, and is used to select several indicator features of the preprocessed data, learn the preprocessed data according to the noise learning model, and generate corresponding vehicle noise distribution maps and resonance noise distribution maps.

[0089] Specifically, the noise sensor groups located on the ground and underground respectively collect the vibration frequencies of the air and the ground of the traffic lines at the urban and rural junctions, and convert them into corresponding sound data through the converter. The collector receives the sound data, and a monitoring volume threshold is set in the filter. For a single sound data, when it reaches the monitoring volume threshold, the filter collects the sound data corresponding to the preset filtering time before reaching the monitoring volume threshold, and forms corresponding vehicle noise data and resonance noise data. Embodiment 1:

[0090] Assume that the monitoring volume threshold is 7000Hz. If the volume of sound data A is 6000Hz, the sound data A will not be collected. Embodiment 2:

[0091] Assume that the monitoring volume threshold is 7000Hz and the preset filtering time is 0.5s. If the volume of sound data B is 8000Hz, the filter collects the sound data corresponding to 0.5s before the sound data B reaches the monitoring volume threshold of 7000Hz and forms the corresponding filtered data.

[0092] By setting the monitoring volume threshold in the filter, noise screening is achieved, which facilitates real-time adjustment of noise and effectively improves the accuracy of noise identification.

[0093] Specifically, the preprocessor preprocesses the vehicle noise data and the resonance noise data to generate corresponding preprocessed data, and the preprocessing also includes:

[0094] Based on the data collection characteristics of the filtered data set, data cleaning is performed to obtain the cleaned data of the filtered data set, and the cleaned data is standardized;

[0095] Among them, data cleaning is to remove the corresponding data of the sound data below the monitoring volume threshold in the filtered data;

[0096] The normalization process is to divide the filtered data into segments according to the standard sampling rate.

[0097] By preprocessing the filtered data, the corresponding preprocessed data is obtained to improve the recognition efficiency of noise, so that the effective features of the preprocessed data can be quickly selected, thereby further improving the accuracy of identifying the location of noise pollution in traffic routes at urban and rural boundaries.

[0098] Specifically, the receiver receives the corresponding noise learning model, and the noise learning model learns the preprocessed data according to the indicator characteristics to generate the corresponding noise distribution map.

[0099] Among them, the indicator characteristics include the decibel level and generation location of the noise;

[0100] Learning is to convert the preprocessed data into a spectrogram, extract the index features in the spectrogram, and annotate the spectrogram based on the index features;

[0101] The noise distribution map includes the vehicle noise distribution map and the resonance noise distribution map.

[0102] Specifically, the adjustment module receives the noise distribution map, and calculates the time difference between the propagation of vehicle noise and resonance noise based on the difference in the propagation speed of sound in solid media and gaseous media, and translates the vehicle noise distribution map by the time difference in the noise distribution map to obtain the corresponding parallel propagation map. Embodiment 3:

[0103] The speed of sound propagation in solid media is 5200m / s, and the speed of sound propagation in gas media is 340m / s. Assuming that the noise propagates for 176800m, the time difference between the propagation of vehicle noise and resonance noise is 486s. In the noise distribution diagram, the vehicle noise distribution diagram is translated by 486 units to obtain the corresponding parallel propagation diagram.

[0104] Specifically, the degree of overlap between the vehicle noise distribution map and the resonance noise distribution map in the parallel propagation map is calculated. An overlap threshold is set in the adjustment module. When the overlap is less than the overlap threshold, the adjustment module does not make adjustments along the traffic route. When the overlap is greater than the overlap threshold, the adjustment module adjusts the monitoring volume threshold and the preset filtering time, and sets up sound insulation strips along the traffic route. Embodiment 4:

[0105] The overlap threshold is set to 80%. When the overlap between the vehicle noise distribution map and the resonance noise distribution map in the parallel propagation map is 70%, the adjustment module does not make any adjustments along the traffic route. Embodiment 5:

[0106] Set the overlap threshold to 80%, the monitoring volume threshold to 7000Hz, and the preset filtering time to 0.5s. When the overlap between the vehicle noise distribution map and the resonance noise distribution map in the parallel propagation diagram is 90%, the adjustment module will adjust the monitoring volume threshold to 6500Hz, the preset filtering time to 0.6s, and set up sound insulation strips along the traffic routes.

[0107] By setting the overlap threshold and adjusting the noise source and filtering module, the accuracy of identifying the location of noise pollution in traffic routes at urban and rural boundaries is improved, and the complexity of urban and rural planning data processing is reduced.

[0108] See also Figure 4 As shown, it is a flow chart of a method for processing urban and rural planning data of the present invention, comprising:

[0109] Step S1, the generator iteratively optimizes the noise learning model according to the filtered data set until the loss value converges to a preset value;

[0110] Step S2, testing the current noise learning model by filtering the data set;

[0111] Step S3: When the test result meets the preset test result, the noise learning model parameters are saved.

[0112] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0113] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A system for processing urban and rural planning data, characterized in that: The system is provided with a plurality of noise monitoring devices arranged in groups along the traffic routes at the junction of urban and rural areas. For a single noise monitoring device, it includes: A receiving module, which is used to collect sounds in traffic routes at the junction of urban and rural areas and generate corresponding sound data; A filtering module, connected to the receiving module, for filtering the sound data and generating corresponding filtering data and a corresponding noise learning model; A processing module, connected to the filtering module, for receiving the noise learning model generated by the filtering module, preprocessing the filtered data, generating corresponding preprocessed data, and selecting several index features of the preprocessed data, wherein the noise learning model learns the preprocessed data according to the index features, and generates corresponding vehicle noise distribution maps and resonance noise distribution maps; An adjustment module, connected to the filtering module and the processing module, for receiving the vehicle noise distribution map and the resonance noise distribution map, calculating the overlap between the vehicle noise and the resonance noise, and making adjustment measures for the filtering module; Wherein, the overlap degree of the vehicle noise distribution map and the resonance noise distribution map in the parallel propagation map is calculated, and an overlap threshold is provided in the adjustment module. When the overlap degree is less than the overlap threshold, the adjustment module does not make any adjustment along the traffic route. When the overlap degree is greater than the overlap threshold, the adjustment module adjusts the monitoring volume threshold and the preset filtering time, and sets a sound insulation belt along the traffic route. The sound data includes the vehicle noise and the resonance noise; The filtered data is the corresponding vehicle noise data and resonance noise data generated after filtering the sound data; The noise learning model is generated by training the vehicle noise data and the resonance noise data according to the filtered data set; The filtered data set includes the vehicle noise data and the resonance noise data of the traffic line at the urban-rural junction at different periods; The vehicle noise is the noise generated in the air by vehicles along the traffic routes at the junction of urban and rural areas; The resonance noise is the noise generated by vehicles on the ground along the traffic routes at the junction of urban and rural areas; The pre-processed data is to fit the corresponding waveform according to the filtered data and generate a number of audio data with a sampling rate of a standard sampling rate, and the processing module generates a corresponding indicator feature according to each audio data; The standard sampling rate is a sampling rate that can be recognized by the processing module, and for a single sampling, the corresponding standard sampling rate is a single sampling rate.

2. The urban and rural planning data processing system according to claim 1, characterized in that: The receiving module comprises: A noise sensor group is arranged at corresponding ground and underground locations to respectively collect the vibration frequencies of the air and the ground of the traffic line at the urban-rural junction; A converter is connected to the noise sensor group and is used for converting the vibration frequency of the air and the ground into the vehicle noise and the resonance noise.

3. The urban and rural planning data processing system according to claim 2, characterized in that: The filtering module comprises: A collector, configured to receive the vehicle noise and the resonance noise; A filter connected to the collector, for filtering the vehicle noise and the resonance noise, and generating corresponding vehicle noise data and resonance noise data; A generator is connected to the filter and is used to store the vehicle noise data and the resonance noise data, and train the vehicle noise data and the resonance noise data according to the filtered data set to generate a corresponding noise learning model.

4. The urban and rural planning data processing system according to claim 3, characterized in that: The processing module comprises: A preprocessor, which is used to preprocess the vehicle noise data and the resonance noise data to generate corresponding preprocessed data; a receiver connected to the generator and configured to receive the noise learning model; A learner is connected to the receiver and the preprocessor, and is used to select several indicator features of the preprocessed data, learn the preprocessed data according to the noise learning model, and generate the corresponding vehicle noise distribution map and the resonance noise distribution map.

5. The urban and rural planning data processing system according to claim 4, characterized in that: The noise sensor groups located at the ground and underground positions respectively collect the vibration frequencies of the air and the ground of the traffic lines at the urban-rural junction, and convert them into the corresponding sound data through the converter. The collector receives the sound data, and the filter is provided with the monitoring volume threshold. For a single sound data, when it reaches the monitoring volume threshold, the filter collects the sound data corresponding to the preset filtering time before reaching the monitoring volume threshold, and forms corresponding vehicle noise data and resonance noise data.

6. The urban and rural planning data processing system according to claim 5, characterized in that: The preprocessor preprocesses the vehicle noise data and the resonance noise data to generate corresponding preprocessed data, and the preprocessing further includes: Based on the data collection characteristics of the filtered data set, data cleaning is performed to obtain cleaned data of the filtered data set, and the cleaned data is standardized; The data cleaning is to remove the sound data below the monitoring volume threshold in the filtered data; The standardization process is to segment the filtered data according to a standard sampling rate.

7. The urban and rural planning data processing system according to claim 6, characterized in that: The receiver receives a corresponding noise learning model, and the noise learning model learns the pre-processed data according to the indicator characteristics to generate a corresponding vehicle noise distribution map and a resonance noise distribution map. Wherein, the indicator characteristics include the decibel of the noise and the generating location; The learning is to convert the preprocessed data into a spectrogram, extract the index feature in the spectrogram, and annotate the spectrogram based on the index feature.

8. The urban and rural planning data processing system according to claim 7, characterized in that: The adjustment module receives the vehicle noise distribution map and the resonance noise distribution map, and calculates the time difference between the propagation of the vehicle noise and the resonance noise according to the difference in the propagation speed of sound in a solid medium and a gas medium, and translates the vehicle noise distribution map by the time difference in the vehicle noise distribution map and the resonance noise distribution map to obtain a corresponding parallel propagation map.

9. A method for processing urban and rural planning data according to the system of any one of claims 1 to 8, characterized in that: include: The generator iteratively optimizes the noise learning model according to the filtered data set until the loss value converges to a preset value; Testing the current noise learning model using the filtered data set; When the test results meet the preset test results, the noise learning model parameters are saved.

Images