Noise complaint traceability positioning and classification evaluation method

Abstract

The invention discloses a noise complaint traceability positioning and classification evaluation method, relates to the technical field of noise monitoring, and aims to solve the technical problems that a current noise evaluation method is low in evaluation efficiency and is difficult to meet effective traceability and detection of noise sources widely distributed in the society, and the method comprises the following steps: S1, collecting noise complaint data; the method comprises the following steps: S1, carrying out noise large time scale feature analysis according to noise complaint data to obtain a noise complaint frequency number of each grid # imgabs0 #, S2, carrying out time sequence modeling on the noise complaint frequency number of each grid # imgabs1 # to obtain a noise complaint time sequence model of each grid # imgabs2 #, calculating a noise complaint time sequence residual error fluctuation degree of each grid # imgabs3 #, and calculating the noise complaint time sequence residual error fluctuation degree of each grid # imgabs2 #. According to the method, the problems of high cost, low efficiency and low accuracy of the current noise pollution tracing method are solved, the noise complaint management fineness and the tracing accuracy are improved, and the noise management level is further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of noise monitoring, and more specifically to a noise complaint source tracing, positioning and classification evaluation method. Background Art

[0002] With the rapid development of social industrialization and urbanization, environmental pollution has become a serious social problem that cannot be ignored. Noise pollution has become a new form of environmental pollution due to its unique characteristics of uncertainty, difficulty in measurement, and exposure. In recent years, due to the influence of industrial production, transportation, urban expansion, and residents' lives, various noise sources have become more and more numerous, with stronger and stronger intensity, more and more complex nature, and more and more serious harm.

[0003] At present, the main noise evaluation methods include manual analysis and evaluation, automatic night noise monitoring stations, noise analysis software, etc. Among them, the manual analysis and evaluation method mainly relies on professional technicians or monitoring personnel to conduct artificial noise detection and evaluation through detection instruments.

[0004] At present, the method of tracing and locating the classification of noise detection complaints mainly starts from traffic noise detection points, monitoring sites, and monitoring areas, and constructs a rapid evaluation system for traffic noise based on geographic information systems. Using GIS as a platform, traffic noise is evaluated by comparing the actual noise values ​​of monitoring points with the noise values ​​of theoretical models. The evaluation efficiency is low, and it is difficult to effectively trace and detect the noise sources that are widely distributed in society. In view of this, we propose a noise complaint tracing and classification evaluation method. Summary of the invention

[0005] The purpose of the present invention is to provide a noise complaint source tracing and classification evaluation method to solve the technical problem that the current noise evaluation method has low evaluation efficiency and is difficult to meet the effective tracing and detection of noise sources widely distributed in society.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a noise complaint source tracing location and classification evaluation method, comprising the following steps: S1: Collect noise complaint data, analyze the large-scale characteristics of noise based on the noise complaint data, and obtain the characteristics of each grid. Frequency of noise complaints; S2: For each grid The noise complaint frequency is modeled in time series to obtain the Noise complaint time series model; S3: Calculate each grid The degree of volatility of the residuals of the noise complaint time series; S4: Extract features of the residual fluctuation degree of the noise complaint time series to obtain the residual fluctuation degree feature data set of the noise complaint time series ; S5: Collect noise event data, and calculate the impact range of each noise event and the grid of the corresponding position based on the noise event data ; S6: According to each grid The impact of noise events in the area, and the grids affected by each noise event Carry out classification, establish a classification model, and obtain a classification model for the residual fluctuation degree characteristics of each noise complaint time series; S7: Calculate each grid The residual fluctuation degree characteristics of the noise complaint time series of the surrounding grids are used to calculate the residual fluctuation degree of each grid. Merge the surrounding meshes to get the merged mesh Repeat S6 to create the merged grid Classification model of S8: Based on the merged grid The classification model is used to obtain each grid Characteristics of the noise impact level for each noise event; S9: According to each merged grid The average noise complaint time series residual volatility characteristic vector is obtained for each grid Characteristics of the noise impact degree of each noise event .

[0007] The present invention collects noise complaint data and noise event data, combines grid processing to calculate the impact range of each noise event and the grid of the corresponding position, and cooperates with the classification model to obtain the noise impact degree characteristics of each grid, thereby solving the problems of high cost, low efficiency and low accuracy of the current noise pollution tracing method. The present invention not only improves the precision of noise complaint management and the accuracy of tracing, but also greatly improves work efficiency, saves manpower and material resources, and further improves the level of noise management.

[0008] Preferably, the step S1 further comprises the following steps: S101: Collect noise complaint data, grid the location of each complaint event, obtain the grid location, and represent each grid according to the grid complaint frequency vector. The noise complaint frequency is For Grid The noise complaint frequency vector of For Grid The frequency of noise complaints For a continuous period of time Inner Grid Number of noise complaints received in the area, is the total number of grids, and the relationship is: , where Indicated in Continuous time period Inner Grid Number of noise complaints received in the area, is the grid of the location where the noise event occurred; S102: Build each mesh The noise complaint frequency vector sequence; S103: Select each grid The maximum value of the noise complaint frequency vector is obtained for each grid The maximum value vector sequence of noise complaints is constructed into a large time scale grid feature dataset : Among them, the maximum value in the noise complaint frequency vector represents: ; but, Represented in vector The noise complaint large time scale grid feature dataset is constructed by taking the maximum complaint frequency in each continuous time period .

[0009] Preferably, step S2 further includes the following steps: S201: For each grid Time series modeling of noise complaint frequency; An autoregressive moving average model is established for the noise complaint frequency time series: , where is the frequency of noise complaints in the large time scale grid characteristics of noise complaints, Is a grid In the past moment The frequency of noise complaints is the time series model coefficient vector Medium Grid The time series model coefficients of is the model error vector, is the autoregressive order; S202: Large time scale grid feature dataset based on noise complaints And each grid The time series model coefficient vector is obtained for each grid Noise complaint time series model: , where Representation Grid At the moment The predicted value of the noise complaint frequency, is the coefficient of the moving average part, It's time The model error vector The elements in .

[0010] Preferably, the step S3 further comprises the following steps: S301: According to each grid The noise complaint time series model and noise complaint frequency vector are obtained for each grid The time series residual vector is expressed as: , where is the time series residual vector, is the noise complaint frequency vector predicted by the time series model; Each grid The mean of the variance vector is: , where yes The first elements, is the vector dimension; S302: According to each grid The variance vector of each grid is obtained The degree of volatility of the noise complaint time series residuals: ; In the formula, For each grid The degree of volatility of the noise complaint time series residuals.

[0011] Preferably, the step S4 further comprises the following steps: S401: For each grid The noise complaint time series residual fluctuation degree is used to extract features, and each grid is obtained The residual volatility characteristics of the noise complaint time series are: , where Representation Grid The residual volatility characteristics of the noise complaint time series are is the feature extraction function; S402: According to each grid The noise complaint time series residual volatility characteristics are obtained by using the noise complaint time series residual volatility characteristics dataset. .

[0012] Preferably, the step S5 further comprises the following steps: S501: Collect noise event data, obtain noise event data and noise event attribute data, and calculate the impact range of each noise event according to the noise event attribute data; S502: Obtaining the grid coordinates of each noise event occurrence location according to the longitude and latitude coordinates of each noise event occurrence location; S503: Calculate the grid coordinates of the corresponding position according to the grid coordinates of each noise event occurrence location .

[0013] Preferably, step S6 further includes the following steps: S601: Grid based on the location of each noise event , and a grid of locations affected by each noise event , for each noise event affecting the grid Classify the noise event to get the grid of each noise complaint The classification results are used to construct a classification training set for the residual fluctuation characteristics of the noise complaint time series. ; The classification results are divided into those affected by the noise event and those not affected by the event; S602: Classification training set based on the residual fluctuation characteristics of noise complaint time series , create each grid SVM classification model , obtain the classification model of the impact characteristics of each noise complaint event; Among them, the classification model The establishment process is as follows: Using the radial basis kernel function: , where is the radial basis kernel function, and is the grid of the noise event location, is the width parameter of the kernel function, is the Euclidean distance or block distance between two grids; ; In the formula, For Grid A collection of For Grid The number of , Symbolic functions; ; In the formula, For each noise complaint grid for noise events If the classification result is affected by the noise event, then ,on the contrary, , For each grid The residual of is the coefficient, Threshold parameter.

[0014] Preferably, the step S8 further includes the following steps: S801: According to each merged grid The classification model is used to obtain each merged grid The average classification result of each noise event is The merged grid The average classification result of The merged grid The classification results corresponding to each original grid contained in , The merged grid The number of original grids included, ; S802: According to each merged grid The average classification result of each merged grid is obtained The average noise complaint time series residual volatility characteristic vector, if the merged grid Affected by the noise event, the merged grid The average classification result is 1, then the merged grid The average noise complaint time series residual volatility characteristic vector is selected corresponding to the grid The eigenvalues ​​are integrated, otherwise the merged grid The average classification result is -1, which is represented by the merged grid Not affected by noise events.

[0015] Preferably, the noise event attribute data includes the noise event type and the maximum noise volume in the noise event, and the noise event data includes the impact range of the noise event, the geographical coordinates and occurrence time of the noise event, the event type, and the maximum sound level of the noise event.

[0016] A noise complaint source tracing and classification evaluation system, comprising a noise complaint frequency analysis unit, a noise complaint model calculation unit, a residual fluctuation degree feature calculation unit, a residual fluctuation degree feature extraction unit, a noise event data collection unit, and a noise event data classification unit; The noise complaint frequency analysis unit is used to collect noise complaint data, perform large-time-scale noise feature analysis based on the noise complaint data, and obtain the noise complaint frequency of each grid. The noise complaint model calculation unit is connected to the noise complaint frequency analysis unit and is used to perform time series modeling on the noise complaint frequency of each grid to obtain a noise complaint time series model for each grid. The residual fluctuation degree characteristic calculation unit is connected to the noise complaint model calculation unit, and is used to calculate the residual fluctuation degree of the noise complaint time series of each grid; The residual fluctuation degree feature extraction unit is connected to the residual fluctuation degree feature calculation unit, and is used to extract features of the residual fluctuation degree of the noise complaint time series of each grid to obtain the residual fluctuation degree features of the noise complaint time series of each grid; The noise event data collection unit is used to collect noise event data, and calculate the impact range of each noise event and the grid at the corresponding position based on the noise event data. The noise event data classification unit is connected to the residual fluctuation degree feature extraction unit and the noise event data collection unit, and is used to classify the grids affected by each noise event according to the impact of the noise event on the area where each grid is located, establish a classification model, and obtain the noise impact degree characteristics of each grid.

[0017] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention collects noise complaint data and noise event data, combines grid processing to calculate the impact range of each noise event and the grid of the corresponding position, and cooperates with the classification model to obtain the noise impact degree characteristics of each grid, thereby solving the problems of high cost, low efficiency and low accuracy of the current noise pollution tracing method. The present invention not only improves the precision of noise complaint management and the accuracy of tracing, but also greatly improves work efficiency, saves manpower and material resources, and further improves the level of noise management.

[0018] 2. The present invention can also perform large-scale feature extraction on the noise complaints of each grid, thereby obtaining the frequency of noise complaints, and extract the fluctuation characteristics of the noise complaint time series of each grid through comparative analysis to improve the analysis efficiency, effectively combine the noise event data, and extract the predictive classification model of the impact range of each noise event to effectively evaluate the impact of the noise event.

[0019] 3. The present invention also calculates and extracts the residual fluctuation degree characteristics of the noise complaint time series of each grid with the help of the residual fluctuation degree characteristic calculation unit and the residual fluctuation degree characteristic extraction unit, which can deeply understand the fluctuation characteristics of the noise complaint situation of each grid. At the same time, combined with the noise event data collection unit and the noise event data collection classification unit, the noise event data is collected, the impact range is calculated, the affected grids are classified and the noise impact degree characteristics are obtained, so that the actual impact characteristics of noise on the surrounding environment and residents in different grid areas can be comprehensively and deeply obtained, which is conducive to a more scientific and reasonable assessment of the degree of noise hazard. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 Schematic diagram of the method of the present invention. DETAILED DESCRIPTION

[0021] Embodiment 1: Figure 1 As shown, the present invention relates to a noise complaint source tracing location and classification evaluation method, comprising the following steps: S1: Collect noise complaint data, analyze the large-scale characteristics of noise based on the noise complaint data, and obtain the characteristics of each grid. Frequency of noise complaints; S101: Collect noise complaint data, grid the location of each complaint event, obtain the grid location, and represent each grid according to the grid complaint frequency vector. The noise complaint frequency is For Grid The noise complaint frequency vector of For Grid The frequency of noise complaints For a continuous period of time Inner Grid Number of noise complaints received in the area, is the total number of grids, and the relationship is: , where Indicated in Continuous time period Inner Grid Number of noise complaints received in the area, is the grid of the location where the noise event occurred; S102: Build each mesh The noise complaint frequency vector sequence; S103: Select each grid The maximum value of the noise complaint frequency vector is obtained for each grid The maximum value vector sequence of noise complaints is constructed into a large time scale grid feature dataset : Among them, the maximum value in the noise complaint frequency vector represents: ,but Represented in vector The noise complaint large time scale grid feature dataset is constructed by taking the maximum complaint frequency in each continuous time period ; S2: For each grid The noise complaint frequency is modeled in time series to obtain the Noise complaint time series model; S201: For each grid Time series modeling of noise complaint frequency; An autoregressive moving average model is established for the noise complaint frequency time series: , where is the frequency of noise complaints in the large time scale grid characteristics of noise complaints, Is a grid In the past moment The frequency of noise complaints is the time series model coefficient vector Medium Grid The time series model coefficients of is the model error vector, is the autoregressive order; S202: Large time scale grid feature dataset based on noise complaints And each grid The time series model coefficient vector is obtained for each grid Noise complaint time series model: , where Representation Grid At the moment The predicted value of the noise complaint frequency, is the coefficient of the moving average part, It's time The model error vector Elements in S3: Calculate each grid The degree of volatility of the residuals of the noise complaint time series; S301: According to each grid The noise complaint time series model and noise complaint frequency vector are obtained for each grid The time series residual vector is expressed as: , where is the time series residual vector, is the noise complaint frequency vector predicted by the time series model; Each grid The mean of the variance vector is: , where yes The first elements, is the vector dimension; S302: According to each grid The variance vector of each grid is obtained The degree of volatility of the noise complaint time series residuals: ; In the formula, For each grid The degree of volatility of the residuals of the noise complaint time series; S4: Extract features of the residual fluctuation degree of the noise complaint time series to obtain the residual fluctuation degree feature data set of the noise complaint time series ; S401: For each grid The noise complaint time series residual fluctuation degree is used to extract features, and each grid is obtained The residual volatility characteristics of the noise complaint time series are: , where Representation Grid The residual volatility characteristics of the noise complaint time series are is the feature extraction function; S402: According to each grid The noise complaint time series residual volatility characteristics are obtained by using the noise complaint time series residual volatility characteristics dataset. ; S5: Collect noise event data, and calculate the impact range of each noise event and the grid of the corresponding position based on the noise event data ; S501: Collect noise event data, obtain noise event data and noise event attribute data, and calculate the impact range of each noise event according to the noise event attribute data; In an embodiment of the present invention, the noise event attribute data includes the noise event type and the maximum noise volume in the noise event, and the noise event data includes the impact range of the noise event and the geographical coordinates and occurrence time of the noise event, the event type, and the maximum sound level of the noise event; S502: Obtaining the grid coordinates of each noise event occurrence location according to the longitude and latitude coordinates of each noise event occurrence location; S503: Calculate the grid coordinates of the corresponding position according to the grid coordinates of each noise event occurrence location ; S6: According to each grid The impact of noise events in the area, and the grids affected by each noise event Carry out classification, establish a classification model, and obtain a classification model for the residual fluctuation degree characteristics of each noise complaint time series; S601: Grid based on the location of each noise event , and a grid of locations affected by each noise event , for each noise event affecting the grid Classify the noise event to get the grid of each noise complaint The classification results are used to construct a classification training set for the residual fluctuation characteristics of the noise complaint time series. ; The classification results are divided into those affected by the noise event and those not affected by the event; S602: Classification training set based on the residual fluctuation characteristics of noise complaint time series , create each grid SVM classification model , obtain the classification model of the impact characteristics of each noise complaint event; Among them, the classification model The establishment process is as follows: Using the radial basis kernel function: , where is the radial basis kernel function, and is the grid of the noise event location, is the width parameter of the kernel function, is the Euclidean distance or block distance between two grids; ; In the formula, For Grid A collection of For Grid The number of , Symbolic functions; ; In the formula, For each noise complaint grid for noise events If the classification result is affected by the noise event, then ,on the contrary, , For each grid The residual of is the coefficient, Threshold parameter; S7: Calculate each grid The residual fluctuation degree characteristics of the noise complaint time series of the surrounding grids are used to calculate the residual fluctuation degree of each grid. Merge the surrounding meshes to get the merged mesh , repeat sub-step S602 in step S6 to create a merged grid Classification model of S8: Based on the merged grid The classification model is used to obtain each grid Characteristics of the noise impact level for each noise event; S801: According to each merged grid The classification model is used to obtain each merged grid The average classification result of each noise event is The merged grid The average classification result of The merged grid The classification results corresponding to each original grid contained in , The merged grid The number of original grids included, ; S802: According to each merged grid The average classification result of each merged grid is obtained The average noise complaint time series residual volatility characteristic vector, if the merged grid Affected by the noise event, the merged grid The average classification result is 1, then the merged grid The average noise complaint time series residual volatility characteristic vector is selected corresponding to the grid The eigenvalues ​​are integrated, otherwise the merged grid The average classification result is -1, which is represented by the merged grid Not affected by noise events; S9: According to each merged grid The average noise complaint time series residual volatility characteristic vector is obtained for each grid Characteristics of the noise impact degree of each noise event .

[0022] The present invention collects noise complaint data and noise event data, combines grid processing to calculate the impact range of each noise event and the grid of the corresponding position, and cooperates with the classification model to obtain the noise impact degree characteristics of each grid, thereby solving the problems of high cost, low efficiency and low accuracy of the current noise pollution tracing method. The present invention not only improves the precision of noise complaint management and the accuracy of tracing, but also greatly improves work efficiency, saves manpower and material resources, and further improves the level of noise management.

[0023] Embodiment 2: As another embodiment of the present invention, a noise complaint source tracing location and classification evaluation system includes: The noise complaint frequency analysis unit is used to collect noise complaint data, perform large-time-scale noise feature analysis based on the noise complaint data, and obtain the noise complaint frequency of each grid; A noise complaint model calculation unit, which is connected to the noise complaint frequency analysis unit and is used to perform time series modeling on the noise complaint frequency of each grid to obtain a noise complaint time series model for each grid; A residual fluctuation degree characteristic calculation unit, which is connected to the noise complaint model calculation unit and is used to calculate the residual fluctuation degree of the noise complaint time series of each grid; A residual fluctuation degree feature extraction unit, which is connected to the residual fluctuation degree feature calculation unit and is used to extract features of the residual fluctuation degree of the noise complaint time series of each grid to obtain the residual fluctuation degree features of the noise complaint time series of each grid; A noise event data collection unit is used to collect noise event data and calculate the impact range of each noise event and the grid of the corresponding position according to the noise event data; A noise event data classification unit is connected to the residual fluctuation degree feature extraction unit and the noise event data acquisition unit, and is used to classify the grids affected by each noise event according to the impact of the noise event on the area where each grid is located, establish a classification model, and obtain the noise impact degree characteristics of each grid.

[0024] The present invention can also extract the characteristics of noise complaints of each grid on a large time scale, thereby obtaining the frequency of noise complaints, and extract the characteristics of the fluctuation degree of the noise complaint time series of each grid through comparative analysis to improve the analysis efficiency, effectively combine the noise event data, and extract the prediction classification model of the impact range of each noise event to effectively evaluate the impact degree of the noise event; With the help of the residual fluctuation degree characteristic calculation unit and the residual fluctuation degree characteristic extraction unit, the residual fluctuation degree characteristics of the noise complaint time series of each grid are calculated and extracted, which can deeply understand the fluctuation characteristics of the noise complaints in each grid. At the same time, combined with the noise event data collection unit and the noise event data collection classification unit, the noise event data is collected, the impact range is calculated, the affected grids are classified and the noise impact degree characteristics are obtained, so that the actual impact characteristics of noise on the surrounding environment and residents in different grid areas can be comprehensively and deeply obtained, which is conducive to a more scientific and reasonable assessment of the degree of noise hazard.

[0025] The embodiments of the present invention disclose preferred embodiments, but are not limited thereto. A person skilled in the art can easily understand the spirit of the present invention based on the above embodiments and make different extensions and changes. However, as long as they do not deviate from the spirit of the present invention, they are all within the protection scope of the present invention.

Claims

1. A noise complaint source location and classification evaluation method, characterized in that: The steps include: S1: Collect noise complaint data, analyze the large-scale characteristics of noise based on the noise complaint data, and obtain the characteristics of each grid. Frequency of noise complaints; S2: For each grid The noise complaint frequency is modeled in time series to obtain the Noise complaint time series model; S3: Calculate each grid The degree of volatility of the residuals of the noise complaint time series; S4: Extract features of the residual fluctuation degree of the noise complaint time series to obtain the residual fluctuation degree feature data set of the noise complaint time series ; S5: Collect noise event data, and calculate the impact range of each noise event and the grid of the corresponding position based on the noise event data ; S6: According to each grid The impact of noise events in the area, and the grids affected by each noise event Carry out classification, establish a classification model, and obtain a classification model for the residual fluctuation degree characteristics of each noise complaint time series; S7: Calculate each grid The residual fluctuation degree characteristics of the noise complaint time series of the surrounding grids are used to calculate the residual fluctuation degree of each grid. Merge the surrounding meshes to get the merged mesh Repeat S6 to create the merged grid Classification model of S8: Based on the merged grid The classification model is used to obtain each grid Characteristics of the noise impact level for each noise event; S9: According to each merged grid The average noise complaint time series residual volatility characteristic vector is obtained for each grid Characteristics of the noise impact degree of each noise event .

2. A noise complaint source tracing and classification evaluation method according to claim 1, characterized in that: The step S1 also includes the following steps: S101: Collect noise complaint data, grid the location of each complaint event, obtain the grid location, and represent each grid according to the grid complaint frequency vector. The noise complaint frequency is For Grid The noise complaint frequency vector of For Grid The frequency of noise complaints For a continuous period of time Inner Grid Number of noise complaints received in the area, is the total number of grids, and the relationship is: , where Indicated in Continuous time period Inner Grid Number of noise complaints received in the area, is the grid of the location where the noise event occurred; S102: Build each mesh The noise complaint frequency vector sequence; S103: Select each grid The maximum value of the noise complaint frequency vector is obtained for each grid The maximum value vector sequence of noise complaints is constructed into a large time scale grid feature dataset : Among them, the maximum value in the noise complaint frequency vector represents: ; but, Represented in vector The noise complaint large time scale grid feature dataset is constructed by taking the maximum value of the complaint frequency in each continuous time period .

3. A noise complaint source tracing and classification evaluation method according to claim 2, characterized in that: The step S2 further comprises the following steps: S201: For each grid Time series modeling of noise complaint frequency; An autoregressive moving average model is established for the noise complaint frequency time series: , where is the frequency of noise complaints in the large time scale grid characteristics of noise complaints, Is a grid In the past moment The frequency of noise complaints is the time series model coefficient vector Medium Grid The time series model coefficients of is the model error vector, is the autoregressive order; S202: Large time scale grid feature dataset based on noise complaints And each grid The time series model coefficient vector is obtained for each grid Noise complaint time series model: , where Representation Grid At the moment The predicted value of the noise complaint frequency, is the coefficient of the moving average part, It's time The model error vector The elements in .

4. A noise complaint source tracing and classification evaluation method according to claim 3, characterized in that: The step S3 also includes the following steps: S301: According to each grid The noise complaint time series model and noise complaint frequency vector are obtained for each grid The time series residual vector is expressed as: , where is the time series residual vector, is the noise complaint frequency vector predicted by the time series model; Each grid The mean of the variance vector is: , where yes The first elements, is the vector dimension; S302: According to each grid The variance vector of each grid is obtained The degree of volatility of the noise complaint time series residuals: ； In the formula, For each grid The degree of volatility of the noise complaint time series residuals.

5. A noise complaint source tracing and classification evaluation method according to claim 4, characterized in that: The step S4 also includes the following steps: S401: For each grid The noise complaint time series residual fluctuation degree is used to extract features, and each grid is obtained The residual volatility characteristics of the noise complaint time series are: , where Representation Grid The residual volatility characteristics of the noise complaint time series are is the feature extraction function; S402: According to each grid The noise complaint time series residual volatility characteristics are obtained by using the noise complaint time series residual volatility characteristics dataset. .

6. A noise complaint source tracing and classification evaluation method according to claim 5, characterized in that: The step S5 further comprises the following steps: S501: Collect noise event data, obtain noise event data and noise event attribute data, and calculate the impact range of each noise event according to the noise event attribute data; S502: Obtaining the grid coordinates of each noise event occurrence location according to the longitude and latitude coordinates of each noise event occurrence location; S503: Calculate the grid coordinates of the corresponding position according to the grid coordinates of each noise event occurrence location .

7. A noise complaint source tracing location and classification evaluation method according to claim 6, characterized in that: The step S6 also includes the following steps: S601: Grid based on the location of each noise event , and a grid of locations affected by each noise event , for each noise event affecting the grid Classify the noise event to get the grid of each noise complaint The classification results are used to construct a classification training set for the residual fluctuation characteristics of the noise complaint time series. ; The classification results are divided into those affected by the noise event and those not affected by the event; S602: Classification training set based on the residual fluctuation characteristics of noise complaint time series , create each grid SVM classification model , obtain the classification model of the impact characteristics of each noise complaint event; Among them, the classification model The establishment process is as follows: Using the radial basis kernel function: , where is the radial basis kernel function, and is the grid of the noise event location, is the width parameter of the kernel function, is the Euclidean distance or block distance between two grids; ； In the formula, For Grid A collection of For Grid The number of , Symbolic functions; ； In the formula, For each noise complaint grid for a noise event If the classification result is affected by the noise event, then ,on the contrary, , For each grid The residual of is the coefficient, Threshold parameter.

8. A noise complaint source tracing location and classification evaluation method according to claim 7, characterized in that: The step S8 also includes the following steps: S801: According to each merged grid The classification model is used to obtain each merged grid The average classification result of each noise event is The merged grid The average classification result of The merged grid The classification results corresponding to each original grid contained in , The merged grid The number of original grids included, ; S802: According to each merged grid The average classification result of each merged grid is obtained The average noise complaint time series residual volatility characteristic vector, if the merged grid Affected by the noise event, the merged grid The average classification result is 1, then the merged grid The average noise complaint time series residual volatility characteristic vector is selected corresponding to the grid The eigenvalues ​​are integrated, otherwise the merged grid The average classification result is -1, which is represented by the merged grid Not affected by noise events.

9. A noise complaint source tracing and classification evaluation method according to claim 6, characterized in that: The noise event attribute data includes the noise event type and the maximum noise volume in the noise event. The noise event data includes the impact range of the noise event, the geographical coordinates and occurrence time of the noise event, the event type, and the maximum sound level of the noise event.

10. A noise complaint source tracing and classification evaluation system, which uses the noise complaint source tracing and classification evaluation method according to any one of claims 1 to 9, characterized in that: include: The noise complaint frequency analysis unit is used to collect noise complaint data, perform large-time-scale noise feature analysis based on the noise complaint data, and obtain the noise complaint frequency of each grid; A noise complaint model calculation unit, which is connected to the noise complaint frequency analysis unit and is used to perform time series modeling on the noise complaint frequency of each grid to obtain a noise complaint time series model for each grid; A residual fluctuation degree characteristic calculation unit, which is connected to the noise complaint model calculation unit and is used to calculate the residual fluctuation degree of the noise complaint time series of each grid; A residual fluctuation degree feature extraction unit, which is connected to the residual fluctuation degree feature calculation unit and is used to extract features of the residual fluctuation degree of the noise complaint time series of each grid to obtain the residual fluctuation degree features of the noise complaint time series of each grid; A noise event data collection unit is used to collect noise event data and calculate the impact range of each noise event and the grid of the corresponding position according to the noise event data; A noise event data classification unit is connected to the residual fluctuation degree feature extraction unit and the noise event data acquisition unit, and is used to classify the grids affected by each noise event according to the impact of the noise event on the area where each grid is located, establish a classification model, and obtain the noise impact degree characteristics of each grid.

Images