A method and system for delineating concentrated areas of noise-sensitive buildings

Abstract

This invention relates to the field of noise management technology, specifically including a method and system for delineating concentrated areas of noise-sensitive buildings. The method includes: identifying noise-sensitive and non-sensitive buildings and marking their sensitivity; clustering sensitive buildings; analyzing non-sensitive buildings to delineate candidate areas and buffer zones; optimizing boundaries after overlay; and classifying control levels and setting control periods according to sensitivity. This addresses the technical problems of relying on simple spatial overlay for concentrated area delineation, resulting in blurred boundaries of concentrated areas of noise-sensitive buildings, and failing to consider the blocking and transmission effects of the spatial density of non-noise-sensitive buildings on noise propagation, thus limiting the accuracy of noise control. The method achieves the technical effect of generating buffer zones based on the spatial density of non-noise-sensitive buildings and the noise source attenuation gradient; and using the overlay of buffer zones and candidate concentrated areas and spatial consistency analysis to dynamically classify control levels and differentiate time periods based on noise sensitivity marking and usage time patterns, thereby improving the accuracy of noise control.

Description

Technical Field

[0001] This invention relates to the field of noise management technology, specifically to a method and system for delineating concentrated areas of noise-sensitive buildings. Background Technology

[0002] With the acceleration of urbanization and the continuous expansion of urban built-up areas, various buildings are densely distributed, and noise pollution has become a prominent issue affecting the quality of the living environment and public health. Noise-sensitive buildings (such as schools, hospitals, and residences) are core spaces for long-term human activities, and their acoustic environment quality is directly related to the comfort of residents, the learning efficiency of students, and the rehabilitation effect of patients. Scientifically delineating the concentrated areas of noise-sensitive buildings is the foundation for implementing precise noise control and optimizing the urban spatial layout.

[0003] The current delineation of noise-sensitive areas has significant technical limitations. Conventional methods often rely on simple spatial overlay without taking into account the differences in noise sensitivity of buildings for refined classification. This leads to blurred boundaries of concentrated areas, such as schools and ordinary residences often being lumped together into the same area, resulting in insufficient targeted control. In addition, existing schemes lack deep integration with urban planning, causing the delineation results to be out of touch with the current land use situation, making it difficult to implement noise control measures.

[0004] In summary, existing technologies suffer from several technical problems: the delineation of concentrated areas relies solely on simple spatial superposition; the boundaries of concentrated areas of noise-sensitive buildings are blurred; the spatial density of non-noise-sensitive buildings does not consider the blocking and transmission effects on noise propagation; and the accuracy of noise control is limited. Summary of the Invention

[0005] This application provides a method and system for delineating concentrated areas of noise-sensitive buildings, aiming to solve the technical problems in the prior art where the delineation of concentrated areas relies solely on simple spatial superposition, the boundaries of concentrated areas of noise-sensitive buildings are blurred, the spatial density of non-noise-sensitive buildings does not consider the blocking and transmission effects on noise propagation, and the accuracy of noise control is limited.

[0006] In view of the above problems, the technical solution to achieve the present application is as follows:

[0007] In a first aspect, this application provides a method for delineating concentrated areas of noise-sensitive buildings. The method includes: identifying noise-sensitive and non-noise-sensitive buildings based on planned buildings corresponding to urban space, wherein the noise-sensitive buildings have noise sensitivity markers; performing cluster analysis on the noise-sensitive buildings and, in conjunction with noise sound pressure level distribution data, delineating M candidate concentrated areas; performing spatial density analysis on the non-noise-sensitive buildings and, in conjunction with noise source attenuation gradient data, generating N noise buffer zones; superimposing the N noise buffer zones onto the M candidate concentrated areas, and performing spatial conformity analysis based on urban spatial planning and current land use data to optimize and expand the boundaries of the concentrated areas of the noise-sensitive buildings; simultaneously, based on the noise sensitivity markers of the noise-sensitive buildings and the building usage time patterns, classifying the area into dynamic control levels and setting differentiated noise prevention and control time periods.

[0008] Preferably, based on a building use database, noise sensitivity characteristics of school buildings and residential buildings are set; basic sensitivity markers are configured according to environmental noise limits and in combination with the noise sensitivity characteristics of school buildings and residential buildings; and the basic sensitivity markers are weighted and corrected by the usage frequency of school buildings and residential buildings to generate noise sensitivity markers.

[0009] Preferably, the criteria for determining noise-sensitive buildings include building usage information and daytime and nighttime noise limits; by matching building usage information with the building usage database, and combining functional zoning attributes and building volume parameters in urban spatial planning, a determination matrix is ​​established, which is used to quantitatively distinguish between noise-sensitive buildings and non-noise-sensitive buildings.

[0010] Preferably, the spatial coordinates of the building's center point are used as the input feature, and a clustering cutoff distance is set; noise-sensitive buildings with spatial distances less than the clustering cutoff distance and the same noise sensitivity label level are divided into the same initial cluster.

[0011] Preferably, the noise source in the noise buffer zone is identified, and the sound pressure level and distance attenuation index of the noise source are established; based on the noise source intensity level, combined with the sound pressure level and distance attenuation index of the noise source, and using the spatial density of the non-noise-sensitive building as a correction coefficient, a dynamic noise buffer distance is set.

[0012] Preferably, after detecting a temporary noise event, traffic noise sensor data is accessed; based on the traffic noise sensor data, the noise sound pressure level distribution data is updated, and the boundary of the concentrated area of ​​the noise-sensitive building is flexibly adjusted.

[0013] Preferably, a noise tolerance threshold is configured based on the noise sensitivity marker; noise contour lines are drawn according to the updated noise sound pressure level distribution data, and the intersection of the noise contour lines and the noise tolerance threshold is taken as the expansion critical point corresponding to the temporary noise event; at the same time, the noise propagation path is corrected according to real-time meteorological data.

[0014] Preferably, the N noise buffer regions and the M candidate concentrated regions are superimposed to identify spatial topological relationships, including overlapping regions, adjacent regions, and separated regions; in the adjacent regions corresponding to the spatial topological relationships, a buffer fusion configuration transition zone is adopted, and the transition zone is an elastic range for the optimized expansion of the concentrated region boundary of the noise-sensitive building.

[0015] Preferably, in the overlapping region corresponding to the spatial topology, the noise contour weights of the overlapping region are dynamically adjusted based on a spatiotemporal graph convolutional network. When a conflict in noise sensitivity markers is detected in the overlapping region, the buffer distance is reallocated to improve the matching degree between the noise contours and noise sensitivity markers in the overlapping region. In the separated region corresponding to the spatial topology, edge computing nodes are deployed to monitor the noise propagation path. When the deviation between the boundary of the separated region and the noise source attenuation gradient data exceeds the deviation threshold, buffer distance calibration is triggered. Based on the noise propagation path, a noise diffusion path after digital twin pre-simulation calibration is configured, and topology compatibility is verified in conjunction with urban spatial planning data. The buffer distance threshold is dynamically adjusted using real-time noise intensity and meteorological parameters as the state space and boundary matching degree as the reward function.

[0016] In a second aspect, this application provides a system for delineating concentrated areas of noise-sensitive buildings, wherein the system includes: a planning module: determining noise-sensitive buildings and non-noise-sensitive buildings based on planned buildings corresponding to urban space, wherein the noise-sensitive buildings are marked with noise sensitivity indicators; a building analysis module: performing cluster analysis on the noise-sensitive buildings and, in conjunction with noise pressure level distribution data, delineating M candidate concentrated areas; performing spatial density analysis on the non-noise-sensitive buildings and, in conjunction with noise source attenuation gradient data, generating N noise buffer zones; a conformity analysis module: superimposing the N noise buffer zones onto the M candidate concentrated areas, performing spatial conformity analysis in conjunction with urban spatial planning and current land use data, and optimizing and expanding the boundaries of the concentrated areas of the noise-sensitive buildings; and a differentiated setting module: simultaneously, based on the noise sensitivity indicators of the noise-sensitive buildings and the building usage time patterns, classifying the area into dynamic control levels and setting differentiated noise prevention and control time periods.

[0017] In summary, one or more technical solutions provided in this application achieve refined classification by generating noise sensitivity markers. At the same time, buffer zones are generated based on the spatial density of non-noise-sensitive buildings and the noise source attenuation gradient. By overlaying the buffer zones with candidate concentrated areas and analyzing spatial consistency, and by optimizing the boundaries in conjunction with urban planning and current land use, dynamic control levels are classified and time-period differentiated settings are made based on noise sensitivity markers and usage time patterns. This improves the accuracy of noise control and enhances the quality of the urban acoustic environment. Attached Figure Description

[0018] Figure 1 This application provides a flowchart illustrating a method for delineating concentrated areas of noise-sensitive buildings.

[0019] Figure 2 This application provides a structural schematic diagram of a system for delineating concentrated areas of noise-sensitive buildings.

[0020] Explanation of reference numerals in the attached diagram: Planning module M100, Building analysis module M200, Consistency analysis module M300, Differentiation setting module M400. Detailed Implementation

[0021] Example 1: The present application will be described in detail below with reference to the accompanying drawings, as follows... Figure 1 As shown, this application provides a method for delineating concentrated areas of noise-sensitive buildings, wherein the method includes:

[0022] S1: Based on the planned buildings corresponding to the urban space, identify noise-sensitive buildings and non-noise-sensitive buildings, wherein the noise-sensitive buildings are marked with noise sensitivity; S2: Perform cluster analysis on the noise-sensitive buildings, and combine with noise sound pressure level distribution data to delineate M candidate concentration areas; perform spatial density analysis on the non-noise-sensitive buildings, and combine with noise source attenuation gradient data to generate N noise buffer areas.

[0023] Specifically, noise-sensitive buildings refer to buildings that are relatively sensitive to noise, such as schools, hospitals, and residences, where people have a low tolerance for noise and require a quieter environment. Noise sensitivity labels are used to quantify the noise tolerance of noise-sensitive buildings and are usually set based on factors such as the building's purpose and frequency of use. Cluster analysis is used to group data points with similar characteristics into the same group (cluster), specifically, to group buildings with similar noise sensitivity into the same candidate cluster region.

[0024] Noise pressure level distribution data refers to the spatial distribution of noise intensity, usually expressed in decibels (dB); spatial density refers to the density of buildings in a certain area, usually calculated by counting the number of buildings per unit area; noise source attenuation gradient data describes the law that noise emitted by a noise source weakens with increasing distance during propagation, usually expressed as the attenuation rate of sound pressure level with distance.

[0025] Implementation steps: Classify buildings in urban space, distinguish between noise-sensitive and non-noise-sensitive buildings, and assign noise sensitivity labels to noise-sensitive buildings. This is done by querying a building use database and combining information such as environmental noise limits and building usage frequency, ensuring the accuracy of the classification. For example, schools and hospitals are usually more noise-sensitive and therefore will be assigned higher sensitivity labels.

[0026] Cluster analysis was performed on noise-sensitive buildings. Specifically, the spatial coordinates of the building's center point were used as input features. A cluster cutoff distance was set, and buildings with a spatial distance less than the cutoff distance and the same noise sensitivity level were grouped into the same initial cluster. Combined with noise sound pressure level distribution data, M candidate cluster areas were delineated. By utilizing the spatial analysis capabilities of the clustering algorithm, the cluster areas of noise-sensitive buildings could be identified, providing a foundation for subsequent noise control measures.

[0027] Simultaneously, spatial density analysis is performed on non-noise-sensitive buildings, and combined with noise source attenuation gradient data, N noise buffer zones are generated. The spatial distribution of non-noise-sensitive buildings is considered to have the blocking and transmission effects on noise propagation. For example, if the building density in a certain area is high, the noise will be blocked or absorbed by the buildings during propagation, thus forming a noise buffer zone. In this way, the propagation path and intensity changes of noise can be predicted more accurately, providing more effective protection for noise-sensitive buildings.

[0028] In the above steps, a noise-sensitive area delineation framework based on multi-source data was constructed. Through refined classification and multi-dimensional analysis, the concentrated areas of noise-sensitive buildings can be delineated more scientifically. At the same time, the complexity of noise propagation is taken into account, providing a solid foundation for subsequent boundary optimization and dynamic management. Furthermore, through cluster analysis and spatial density analysis, areas where schools and residences are clustered are discovered and noise-sensitive areas are delineated for them. Meanwhile, noise buffer zones are generated in the surrounding areas to effectively reduce the impact of noise on these sensitive areas.

[0029] S3: Overlay the N noise buffer zones onto the M candidate concentrated areas, and perform spatial conformity analysis based on urban spatial planning and current land use data to optimize and expand the concentrated area boundary of the noise-sensitive buildings; S4: Simultaneously, based on the noise sensitivity markings of the noise-sensitive buildings and the building usage time patterns, classify the regional dynamic control levels and set differentiated noise prevention and control time periods.

[0030] Specifically, spatial conformity analysis refers to the overlay analysis of different spatial data layers using technologies such as Geographic Information Systems (GIS) to assess the degree of matching between the layers in spatial distribution, thereby determining their rationality and coordination in spatial layout; optimization and expansion refers to further improving the boundaries of existing designated areas through analysis and adjustment, making them more in line with actual needs and scientific planning; dynamic control level classification refers to dividing noise-sensitive areas into different control levels based on the noise sensitivity markings of noise-sensitive buildings and the usage time patterns of buildings, so as to implement differentiated noise control measures; and differentiated noise control time period settings refer to determining different noise control time periods based on the usage time patterns of buildings, in order to achieve precise noise control.

[0031] Execution steps: The generated N noise buffer zones are superimposed on M candidate concentrated areas. This process utilizes the data overlay function of Geographic Information System (GIS). By performing spatial overlay operations on the noise buffer zones and candidate concentrated areas, the spatial topological relationship between the two is identified, including overlapping areas, adjacent areas, and separated areas. If the noise buffer zone of a certain area overlaps with the candidate concentrated area, then that area has a certain buffering effect during the noise propagation process, and its noise control strategy can be adjusted appropriately.

[0032] Spatial alignment analysis is conducted by combining basic data on urban spatial planning and current land use. Urban spatial planning data includes land use planning and functional zoning, while current land use data covers the actual use of the land. By overlaying and analyzing these data, the degree of matching between the delineation of noise-sensitive areas and urban planning and current land use can be assessed. If the delineated noise-sensitive areas highly match the residential areas in the urban plan, it indicates that the delineation is relatively reasonable. If there are discrepancies, adjustments need to be made based on the planning and current data.

[0033] Based on this, the boundaries of the concentrated areas of noise-sensitive buildings can be optimized and expanded. Furthermore, if a noise buffer zone of a certain area is adjacent to a candidate concentrated area, and the current land use status shows that the area is a green space or a low-density development area, it can be considered to be included in the boundary expansion range of the noise-sensitive area to enhance the noise control effect.

[0034] Meanwhile, based on the noise sensitivity markings of noise-sensitive buildings and the usage patterns of buildings, the area is dynamically classified into control levels and noise control periods are differentiated. Specifically, schools are more sensitive to noise during daytime classes and can be classified as high-level control areas, with stricter noise control measures implemented during class hours. On the other hand, surrounding commercial buildings generate more noise at night, but have less impact on schools, so they can be classified as low-level control areas, with different noise control periods set at night.

[0035] In the above steps, the delineation of noise-sensitive areas is closely integrated with urban spatial planning and current land use. Through spatial conformity analysis and dynamic control measures, the delineation of noise-sensitive areas becomes more scientific and reasonable, thereby improving the accuracy and effectiveness of noise control.

[0036] Furthermore, the noise-sensitive building has a noise sensitivity label, and the method of this application includes:

[0037] Based on a building use database, noise sensitivity characteristics of school buildings and residential buildings are set; according to environmental noise limits, and in combination with the noise sensitivity characteristics of the school buildings and residential buildings, basic sensitivity markers are configured; the basic sensitivity markers are weighted and corrected by the usage frequency of the school buildings and the usage frequency of the residential buildings to generate noise sensitivity markers.

[0038] Specifically, the building use database stores information about the use of buildings, including details such as building type (e.g., school, residence), usage time, and functional zoning; noise sensitivity characteristics refer to a building's tolerance to noise, which is usually related to the building's use and usage scenarios. For example, schools and hospitals are highly sensitive to noise because these places require a quiet environment to ensure the normal operation of teaching and medical activities; basic sensitivity marking refers to a preliminary noise sensitivity label set based on the building's use and environmental noise limits, used to distinguish the degree of noise sensitivity of different buildings; weighted correction involves adjusting the basic sensitivity marking by considering factors such as the building's usage frequency to more accurately reflect the building's actual noise sensitivity.

[0039] Implementation steps: Based on the building use database, set the noise sensitivity characteristics of school buildings and residential buildings. For example, the noise sensitivity characteristics of school buildings are mainly reflected in their high sensitivity to noise during daytime school hours, while residential buildings are more sensitive to noise at night. Based on these characteristics and combined with the environmental noise limit (e.g., 85dB), configure basic sensitivity labels. Specifically, the basic sensitivity label for schools is higher during daytime school hours, while the basic sensitivity label for residences is correspondingly increased at night.

[0040] The basic noise sensitivity markers are weighted and adjusted based on the usage frequency of school and residential buildings. For example, if a school is used frequently each day and has long class hours, its basic noise sensitivity marker will be further increased through weighted adjustment to reflect its high sensitivity to noise. Similarly, for residences, if they are used frequently at night, their noise sensitivity marker will also increase accordingly. Through these steps, a precise noise sensitivity label is provided for noise-sensitive buildings, thus providing a scientific basis for subsequent noise-sensitive area delineation and noise control measures. In this way, noise-sensitive areas requiring key protection can be identified more accurately, improving the targeting and effectiveness of noise control.

[0041] Furthermore, based on the planned buildings corresponding to the urban space, noise-sensitive buildings and non-noise-sensitive buildings are identified. The method in this application includes:

[0042] The criteria for determining noise-sensitive buildings include building usage information and daytime and nighttime noise limits. By matching building usage information with the building usage database and combining functional zoning attributes and building volume parameters in urban spatial planning, a determination matrix is ​​established. The determination matrix is ​​used to quantitatively distinguish between noise-sensitive buildings and non-noise-sensitive buildings.

[0043] Specifically, daytime and nighttime noise limits refer to the standards for limiting noise intensity based on different time periods (day and night). Generally, daytime noise limits are higher, while nighttime limits are lower, to accommodate the need for a quiet environment at different times. A building use database stores information about building uses, including building type (e.g., school, residential, commercial, industrial), usage time, functional zoning, and other detailed information. Functional zoning attributes refer to the functional division of different areas in urban spatial planning, such as residential areas, commercial areas, and industrial areas. These attributes determine the main uses of buildings within a region and the noise environment requirements. Building massing parameters refer to the physical characteristics of a building, such as building area, height, and number of floors; these parameters can affect the building's sensitivity to noise. A decision matrix is ​​a tool used for quantitative analysis, combining multiple factors (such as use, noise limits, functional zoning attributes, massing parameters, etc.) into a matrix to classify and evaluate buildings.

[0044] Implementation steps: Establish a judgment matrix to quantitatively distinguish between noise-sensitive and non-noise-sensitive buildings, and determine the judgment criteria for noise-sensitive buildings, including the building's usage information and daytime and nighttime noise limit requirements. For example, schools and hospitals are usually more sensitive to noise, and their daytime and nighttime noise limit requirements are usually lower (e.g., no more than 45dB at night and no more than 55dB during the day), while buildings in commercial areas have higher noise tolerance.

[0045] By matching building usage information with a building use database, specifically, the database records that a certain building is a school, whose main purpose is teaching, and therefore it is more sensitive to noise. At the same time, combined with the functional zoning attributes in urban spatial planning, the functional positioning of the area where the building is located is determined. If the school is located in a residential area, its surrounding environment also has higher requirements for noise, further amplifying its noise sensitivity. In addition, the building's size parameters, such as building area and height, are considered. For example, large school buildings may be more sensitive to noise than small schools because they accommodate more students and have a greater need for a quiet environment. These factors are combined to form a judgment matrix.

[0046] The purpose of the decision matrix is ​​to classify buildings by combining factors such as their use, noise limits, functional zoning attributes, and size parameters through quantitative analysis. Specifically, a large school located in a residential area, whose purpose is teaching, has low daytime and nighttime noise limits and a large size, can be clearly classified as a noise-sensitive building through the decision matrix. On the other hand, a small warehouse located in an industrial area, whose purpose is storage, has high daytime and nighttime noise limits and a small size, may be classified as a non-noise-sensitive building through the decision matrix.

[0047] The above steps provide a scientific and quantitative basis for the identification of noise-sensitive buildings. The judgment matrix can more accurately identify noise-sensitive buildings that need key protection, providing a solid foundation for subsequent noise-sensitive area delineation and noise control measures. The judgment matrix can identify noise-sensitive buildings such as schools, hospitals, and residences, thereby improving the accuracy and effectiveness of noise control.

[0048] Furthermore, cluster analysis is performed on the noise-sensitive buildings, and M candidate concentration areas are delineated based on noise sound pressure level distribution data. The method of this application includes:

[0049] Using the spatial coordinates of the building's center point as the input feature, a cluster cutoff distance is set; noise-sensitive buildings with spatial distances less than the cluster cutoff distance and the same noise sensitivity label level are grouped into the same initial cluster.

[0050] Specifically, spatial coordinates refer to the location information of the building's center point in geographic space, usually expressed in latitude and longitude or planar coordinates (such as projected coordinates); cluster cutoff distance refers to a threshold set in cluster analysis to determine which buildings can be classified into the same cluster. When the spatial distance between two buildings is less than this threshold, they are considered close enough to be classified into the same cluster; initial clusters refer to the clusters formed in the initial stage of cluster analysis, which may be further optimized or adjusted according to other conditions later.

[0051] Execution steps: The initial stage of noise-sensitive building cluster analysis. First, the spatial coordinates of the building center point are used as input features. Assuming that a city has multiple schools and residences, their center point coordinates can be obtained through a geographic information system (GIS). Set the cluster cutoff distance. This distance can be determined based on actual needs and experience. Considering the range of noise propagation and the actual distance between buildings, the cluster cutoff distance can be set to 500 meters.

[0052] Noise-sensitive buildings that are spatially closer than the cluster cutoff distance and have the same noise sensitivity rating are grouped into the same initial cluster. For example, if there are three schools in a certain area, the distance between their center points is less than 500 meters, and their noise sensitivity ratings are the same (e.g., all are high sensitivity), then these three schools will be grouped into the same initial cluster.

[0053] In the above steps, by using both spatial distance and noise sensitivity level criteria, the clustering areas of noise-sensitive buildings are initially identified, effectively identifying concentrated areas of noise-sensitive buildings and providing a basis for subsequent delineation of noise-sensitive areas. Through cluster analysis, densely populated areas of schools and residences can be identified, and these areas may be the key targets for delineation of noise-sensitive areas. In this way, noise-sensitive areas that need to be given priority protection can be identified more scientifically, improving the accuracy and effectiveness of noise control.

[0054] Furthermore, by performing spatial density analysis on the non-noise-sensitive buildings and combining this with noise source attenuation gradient data, N noise buffer zones are generated. The method of this application also includes:

[0055] Identify the noise sources in the noise buffer zone and establish the sound pressure level and distance attenuation index of the noise sources. Based on the noise source intensity level, combined with the sound pressure level and distance attenuation index of the noise sources, and using the spatial density of the non-noise-sensitive buildings as a correction coefficient, set a dynamic noise buffer distance.

[0056] Specifically, a noise source refers to the origin of noise, such as traffic noise, industrial noise, and construction noise; sound pressure level and distance attenuation index are used to describe how the sound pressure level (usually expressed in decibels) emitted by a noise source attenuates with increasing distance, and the attenuation index is used to quantify the degree of noise reduction with distance; noise source intensity level refers to classifying noise sources into different intensity levels based on their sound pressure level, used to assess their impact on the surrounding environment; spatial density refers to the density of buildings in a certain area, usually expressed by calculating the number of buildings per unit area; dynamic noise buffer distance refers to the boundary distance of the noise buffer zone that is dynamically adjusted according to the intensity of the noise source, the attenuation law, and the spatial density of surrounding buildings.

[0057] Execution steps: Identify noise sources within the noise buffer zone. In urban environments, traffic noise is one of the main noise sources. By using noise monitoring equipment or geographic information system (GIS) data, the location and traffic flow of major roads can be determined, thereby identifying traffic noise sources and establishing the sound pressure level and distance attenuation index of the noise source. For example, the attenuation index of traffic noise can be determined by on-site measurement or by referring to existing acoustic models. Assuming that the sound pressure level of traffic noise at a distance of 100 meters from the noise source is 70 decibels and the attenuation index is 6 decibels / times distance, this means that the sound pressure level will drop to 64 decibels at 200 meters.

[0058] Based on the noise source intensity level, combined with the sound pressure level and distance attenuation index, and using the spatial density of non-noise-sensitive buildings as a correction coefficient, a dynamic noise buffer distance is set. Specifically, if the noise source intensity in a certain area is high (such as a busy highway) and the spatial density of non-noise-sensitive buildings (such as factories) in that area is high, then the noise buffer distance will be increased accordingly. This is because high-density buildings can play a certain role in blocking noise propagation, but at the same time, it also means that the noise propagation path is more complex, requiring a larger buffer distance to ensure the acoustic environment quality of noise-sensitive areas.

[0059] In the above steps, by dynamically adjusting the noise buffer distance, the characteristics of the noise source and the complexity of the surrounding environment are considered more scientifically, thereby improving the accuracy and effectiveness of noise buffer zone delineation. By identifying traffic noise sources and combining them with the spatial density of surrounding buildings, the noise buffer distance can be dynamically set, which can more effectively protect noise-sensitive areas (such as schools and hospitals) from noise pollution. This method not only considers the intensity and attenuation law of the noise source, but also incorporates the actual urban spatial layout, making the delineation of noise buffer zones more reasonable and practical.

[0060] Furthermore, by combining urban spatial planning and existing land use data to conduct spatial conformity analysis and optimize the expansion of the concentrated area boundary of the noise-sensitive buildings, the method of this application includes:

[0061] After detecting a temporary noise event, traffic noise sensor data is accessed; based on the traffic noise sensor data, the noise sound pressure level distribution data is updated, and the boundary of the concentrated area of ​​the noise-sensitive building is flexibly adjusted.

[0062] Specifically, temporary noise events refer to an increase in noise beyond the normal noise level caused by specific activities or sudden events, such as construction or large-scale events; traffic noise sensor data refers to noise data collected in real time by noise sensors installed on urban roads or key locations, including information such as noise sound pressure level and noise frequency distribution; flexible adjustment refers to the dynamic adjustment of the boundary of the concentrated area of ​​noise-sensitive buildings based on real-time monitoring data to adapt to changes in noise levels.

[0063] Execution steps: After detecting a temporary noise event, traffic noise sensor data is accessed, and noise sound pressure level distribution data is updated based on this data. This allows for flexible adjustments to the boundaries of concentrated areas of noise-sensitive buildings. Specifically, traffic noise sensor data is accessed, and further, when a temporary noise event (such as traffic congestion or construction) is detected, noise data is collected in real time through traffic noise sensors. These sensors are typically distributed near major roads, intersections, and noise-sensitive areas in cities, enabling real-time monitoring of noise sound pressure levels. For example, on a main urban road, sensors detect traffic congestion caused by a traffic accident, resulting in a significant increase in noise sound pressure level.

[0064] The noise sound pressure level distribution data is updated by transmitting the collected traffic noise sensor data to the data processing system. This process can be achieved using a Geographic Information System (GIS) and a noise propagation model. By combining real-time monitoring data with a pre-set noise distribution model, a more accurate noise distribution map can be generated. For example, based on sensor data, the updated noise distribution map shows that the noise sound pressure level in the traffic congestion area has increased from 70 decibels to 80 decibels.

[0065] The boundaries of noise-sensitive areas are flexibly adjusted. Further, based on updated noise pressure level distribution data, the boundaries of concentrated noise-sensitive building areas are flexibly adjusted. Specifically, noise tolerance thresholds are configured, and a tolerable noise threshold is set according to the noise sensitivity markers of noise-sensitive buildings. For example, the noise tolerance threshold for a school during the daytime is 55 dB. Noise contour lines are drawn, representing the boundaries of areas with the same noise level, based on the updated noise pressure level distribution data. Expansion thresholds are determined, with the intersection of the noise contour lines and the noise tolerance thresholds serving as the expansion thresholds for temporary noise events. For example, if the noise contour line near a school is 60 dB, and its noise tolerance threshold is 55 dB, then the intersection is the expansion threshold. Noise propagation paths are corrected by combining real-time meteorological data (such as wind direction and speed) to further optimize the adjustment of noise-sensitive area boundaries.

[0066] In the above steps, real-time monitoring and dynamic adjustment ensure that the delineation of noise-sensitive areas can adapt to the impact of temporary noise events, thereby improving the flexibility and effectiveness of noise control. For example, when traffic congestion leads to increased noise, the protection range can be expanded in a timely manner by flexibly adjusting the boundaries of noise-sensitive areas, thereby reducing the impact of noise on sensitive areas such as schools and hospitals.

[0067] Furthermore, the method of this application includes flexibly adjusting the boundary of the concentrated area of ​​the noise-sensitive building:

[0068] Based on the noise sensitivity marker, a noise tolerance threshold is configured; noise contour lines are drawn according to the updated noise sound pressure level distribution data, and the intersection of the noise contour lines and the noise tolerance threshold is taken as the expansion critical point corresponding to the temporary noise event; at the same time, the noise propagation path is corrected according to real-time meteorological data.

[0069] Specifically, the noise tolerance threshold refers to the highest noise level that a noise-sensitive building can withstand, usually expressed in decibels (dB). It is configured according to the building's noise sensitivity rating, with different sensitivity levels of buildings having different tolerance thresholds. Noise contour lines are curves connecting points with the same noise sound pressure level within a certain area. Noise contour maps can be drawn using noise sound pressure level distribution data to visually display the spatial distribution of noise. The expansion critical point is when the noise contour lines intersect with the noise tolerance threshold. At the intersection point, the noise level reaches the building's tolerance limit. This point is the expansion critical point. Beyond this point, the noise-sensitive area needs to be expanded to provide better protection. Real-time meteorological data includes meteorological parameters such as wind direction, wind speed, temperature, and humidity. These data affect the propagation path and intensity of noise. For example, wind direction and wind speed can change the direction and distance of noise propagation.

[0070] Execution steps: Configure noise tolerance thresholds based on noise sensitivity markers, and draft noise contour lines based on updated noise sound pressure level distribution data to determine the expansion critical point. Simultaneously, correct the noise propagation path based on real-time meteorological data. Specifically, the noise tolerance threshold is configured according to the noise sensitivity markers of noise-sensitive buildings. For example, for schools (high sensitivity markers), the noise tolerance threshold is set to 55 dB; while for ordinary residences (medium sensitivity markers), the noise tolerance threshold is set to 60 dB. These thresholds are pre-set based on the building's purpose and usage scenario to ensure the comfort and health of its occupants.

[0071] Noise contour lines are drawn. Specifically, noise contour lines are drawn based on the updated noise sound pressure level distribution data. For example, if the updated noise sound pressure level distribution data for a certain area shows that traffic noise reaches 70 decibels in some areas and 60 decibels in other areas, noise contour lines with different sound pressure levels can be drawn to visually show the spatial distribution of noise.

[0072] To determine the expansion threshold, further compare the noise contour lines with the noise tolerance threshold and find their intersection. For example, if the noise contour line near a school is 60 dB and its noise tolerance threshold is 55 dB, then the noise level at the intersection point is 60 dB. This is the expansion threshold, which means that at this point, the noise level has exceeded the school's tolerance threshold, and the boundary of the noise-sensitive area needs to be expanded to provide better protection.

[0073] Noise propagation paths can be corrected based on real-time meteorological data (such as wind direction, wind speed, and temperature). If real-time meteorological data shows that the wind is blowing from the noise source towards the noise-sensitive area and the wind speed is high, the noise propagation distance may increase and the propagation path may change. By correcting the noise propagation path, the impact range of noise can be predicted more accurately, thereby allowing for a more scientific adjustment of the boundaries of noise-sensitive areas.

[0074] In the steps described above, by dynamically adjusting the boundaries of noise-sensitive areas, effective protection of noise-sensitive buildings is ensured during temporary noise events. By configuring noise tolerance thresholds, defining noise contour lines, determining expansion thresholds, and correcting noise propagation paths, flexible adjustments to the boundaries of noise-sensitive areas can be achieved, improving the flexibility and precision of noise control. For example, in a city center, these measures can be used to promptly address temporary noise events such as traffic congestion or construction work, reducing the impact of noise on sensitive areas such as schools and hospitals.

[0075] Furthermore, the method of this application involves superimposing the N noise buffer regions onto the M candidate set regions, including:

[0076] The N noise buffer regions and the M candidate concentrated regions are superimposed to identify spatial topological relationships, including overlapping regions, adjacent regions, and separated regions. In the adjacent regions corresponding to the spatial topological relationships, a buffer fusion configuration transition zone is adopted. The transition zone is an elastic range for the optimized expansion of the concentrated region boundary of the noise-sensitive building.

[0077] Specifically, overlay operations refer to the process of merging and analyzing multiple spatial data layers in a Geographic Information System (GIS). Through overlay operations, spatial relationships between different layers can be identified. Spatial topological relationships describe the geometric relationships of the relative positions of spatial entities, including overlap, adjacency, and separation. Among these, overlapping areas refer to the parts of two or more spatial regions that cover each other in space, adjacent areas refer to the parts of two spatial regions that touch each other in space but do not overlap, and separated areas refer to the parts of two spatial regions that do not touch each other in space. Buffer fusion refers to merging adjacent buffer areas into a larger buffer area to reduce boundary effects and provide a smoother transition. Transition zones are buffer areas set in adjacent areas to smooth the transition between noise-sensitive and non-sensitive areas and reduce the impact of noise on sensitive areas.

[0078] Execution steps: Overlay operations are performed on the noise buffer regions (N) and the candidate concentrated regions (M) to identify the spatial topological relationships between them, and transition zones are set in adjacent regions. Specifically, the overlay operation is further performed on the N noise buffer regions and the M candidate concentrated regions. Using Geographic Information System (GIS) software, the two layers are merged and analyzed to identify the spatial topological relationships between them. Through the overlay operation, it can be found that some noise buffer regions and candidate concentrated regions have overlapping, adjacent, or separate relationships.

[0079] Identifying spatial topological relationships further categorizes noise buffer zones and candidate concentration zones as follows: Overlapping regions refer to areas where noise buffer zones and candidate concentration zones overlap. Overlapping regions provide some buffering during noise propagation, but further optimization of noise control measures is needed. Adjacent regions refer to areas where noise buffer zones and candidate concentration zones are adjacent, indicating a certain correlation in the noise propagation path, but without overlap. In this case, special attention needs to be paid to the noise propagation path and intensity to prevent noise from affecting the candidate concentration zone. Separated regions refer to areas where noise buffer zones and candidate concentration zones are completely separated, indicating that they are relatively independent during noise propagation, but the noise propagation path still needs to be monitored to ensure that noise does not accidentally affect the candidate concentration zone.

[0080] The buffer fusion configuration transition zone further utilizes the buffer fusion method to configure transition zones in adjacent areas. The transition zone is a flexible interval used to optimize and extend the boundary of the concentrated area of ​​noise-sensitive buildings. For example, if a noise buffer area is adjacent to a candidate concentrated area, the boundary between the two areas can be smoothed through buffer fusion to form a transition zone. The transition zone can serve as an extension of the noise-sensitive area, providing broader protection.

[0081] In the above steps, by identifying spatial topological relationships and setting transition zones, the boundaries of noise-sensitive areas are optimized, reducing the impact of noise on sensitive areas. In this way, noise-sensitive areas are delineated more scientifically, improving the flexibility and effectiveness of noise control. Through superposition operations and buffer fusion, the relationship between noise buffer areas and candidate concentration areas can be identified, and transition zones can be set in adjacent areas to better protect noise-sensitive buildings such as schools and hospitals.

[0082] Furthermore, the method of this application includes:

[0083] In the overlapping regions corresponding to the spatial topology, the weights of noise contour lines in the overlapping regions are dynamically adjusted based on a spatiotemporal graph convolutional network. When a conflict in noise sensitivity markers is detected in the overlapping regions, the buffer distance is reallocated to improve the matching degree between the noise contour lines and the noise sensitivity markers in the overlapping regions. In the separated regions corresponding to the spatial topology, edge computing nodes are deployed to monitor the noise propagation path. When the deviation between the boundary of the separated region and the noise source attenuation gradient data exceeds the deviation threshold, buffer distance calibration is triggered. Based on the noise propagation path, a noise diffusion path after digital twin pre-simulation calibration is configured, and topology compatibility is verified in conjunction with urban spatial planning data. The buffer distance threshold is dynamically adjusted using real-time noise intensity and meteorological parameters as the state space and boundary conformity as the reward function.

[0084] Specifically, Spatiotemporal Graph Convolutional Network (ST-GCN) refers to a graph convolutional network that combines temporal and spatial dimensions to process spatiotemporal data, capturing dynamic changes and spatial relationships in time series; noise sensitivity label conflict refers to the inconsistency in noise sensitivity labels of different noise-sensitive buildings in overlapping areas, making it difficult to determine a unified noise control strategy; digital twins optimize the performance of physical entities by creating virtual models of physical entities and using real-time data for simulation and analysis; edge computing nodes are computing nodes deployed at the network edge for real-time processing and analysis of local data, reducing data transmission latency; buffer distance calibration refers to dynamically adjusting the distance of buffer areas based on real-time monitoring data and model predictions to ensure the effectiveness of noise control.

[0085] Execution steps: In the division of noise-sensitive areas, the handling of overlapping and separated regions is a key step. Specifically, in the handling of overlapping regions, the weights of noise contour lines are dynamically adjusted based on a spatiotemporal graph convolutional network (ST-GCN). ST-GCN can capture the dynamic changes of noise in time and space. By learning the spatiotemporal characteristics of noise propagation, it dynamically adjusts the weights of noise contour lines to more accurately reflect the noise distribution. When a conflict of noise sensitivity markers is detected in the overlapping region, the buffer distance is reallocated to make the noise contour lines in the overlapping region match the noise sensitivity markers more closely. For example, if a school and a hospital are in the same overlapping region but have different noise sensitivity markers, by reallocating the buffer distance, it can be ensured that noise control measures can meet the needs of both schools and hospitals.

[0086] Further, in the separated areas, edge computing nodes are deployed to monitor noise propagation paths. These edge computing nodes can process local noise data in real time, respond quickly to noise changes, and reduce the latency of data transmission to the central server. When the deviation between the boundary of the separated area and the noise source attenuation gradient data exceeds the deviation threshold, buffer distance calibration is triggered. The calibrated noise diffusion path is pre-simulated using digital twin technology, and topological compatibility is verified by combining urban spatial planning data. For example, a digital twin model can be used to simulate the propagation of noise in the urban environment, and the buffer distance threshold can be adjusted according to real-time noise intensity and meteorological parameters to ensure the effectiveness of noise control measures.

[0087] In summary, the beneficial effects of the embodiments of this application are:

[0088] By identifying noise-sensitive and non-noise-sensitive buildings based on planned buildings corresponding to urban space, noise-sensitive buildings are marked with noise sensitivity indicators. Cluster analysis is performed on noise-sensitive buildings, and M candidate concentration areas are delineated based on noise sound pressure level distribution data. Spatial density analysis is performed on non-noise-sensitive buildings, and N noise buffer areas are generated based on noise source attenuation gradient data. The N noise buffer areas are superimposed on the M candidate concentration areas, and spatial conformity analysis is performed based on urban spatial planning and current land use data to optimize and expand the concentration area boundaries of noise-sensitive buildings. At the same time, based on the noise sensitivity indicators of noise-sensitive buildings and the building usage time patterns, the area dynamic control level is classified and noise prevention and control time periods are differentiated. This application provides a method and system for delineating concentrated areas of noise-sensitive buildings. It achieves refined classification by generating noise sensitivity markers, and generates buffer zones based on the spatial density of non-noise-sensitive buildings and the noise source attenuation gradient. By overlaying the buffer zones with candidate concentrated areas and analyzing their spatial fit, and by optimizing the boundaries in conjunction with urban planning and current land use, it dynamically classifies control levels and sets time-period differentiated settings based on noise sensitivity markers and usage time patterns. This improves the accuracy of noise control and ultimately enhances the quality of the urban acoustic environment.

[0089] Example 2, based on the same inventive concept as the method for delineating a concentrated area of ​​noise-sensitive buildings in the foregoing examples, such as... Figure 2 As shown in the figure, this application provides a system for delineating concentrated areas of noise-sensitive buildings, wherein the system includes:

[0090] Planning module M100: Based on the planned buildings corresponding to the urban space, determine noise-sensitive buildings and non-noise-sensitive buildings, wherein the noise-sensitive buildings are marked with noise sensitivity.

[0091] Building Analysis Module M200: Performs cluster analysis on the noise-sensitive buildings and delineates M candidate cluster regions based on noise sound pressure level distribution data; performs spatial density analysis on the non-noise-sensitive buildings and generates N noise buffer regions based on noise source attenuation gradient data.

[0092] The consistency analysis module M300: superimposes the N noise buffer zones onto the M candidate concentrated areas, performs spatial consistency analysis in conjunction with urban spatial planning and current land use data, and optimizes and expands the boundary of the concentrated area of ​​the noise-sensitive buildings.

[0093] Differentiation setting module M400: Simultaneously, based on the noise sensitivity markings of the noise-sensitive buildings and the building usage time patterns, it performs regional dynamic control level classification and noise prevention time period differentiation settings.

[0094] Furthermore, the planning module M100 is used to perform the following method:

[0095] Based on a building use database, noise sensitivity characteristics of school buildings and residential buildings are set; according to environmental noise limits, and in combination with the noise sensitivity characteristics of the school buildings and residential buildings, basic sensitivity markers are configured; the basic sensitivity markers are weighted and corrected by the usage frequency of the school buildings and the usage frequency of the residential buildings to generate noise sensitivity markers.

[0096] Furthermore, the planning module M100 is also used to perform the following methods:

[0097] The criteria for determining noise-sensitive buildings include building usage information and daytime and nighttime noise limits. By matching building usage information with the building usage database and combining functional zoning attributes and building volume parameters in urban spatial planning, a determination matrix is ​​established. The determination matrix is ​​used to quantitatively distinguish between noise-sensitive buildings and non-noise-sensitive buildings.

[0098] Furthermore, the building analysis module M200 is used to perform the following methods:

[0099] Using the spatial coordinates of the building's center point as the input feature, a cluster cutoff distance is set; noise-sensitive buildings with spatial distances less than the cluster cutoff distance and the same noise sensitivity label level are grouped into the same initial cluster.

[0100] Furthermore, the building analysis module M200 is also used to perform the following methods:

[0101] Identify the noise sources in the noise buffer zone and establish the sound pressure level and distance attenuation index of the noise sources. Based on the noise source intensity level, combined with the sound pressure level and distance attenuation index of the noise sources, and using the spatial density of the non-noise-sensitive buildings as a correction coefficient, set a dynamic noise buffer distance.

[0102] Furthermore, the fit analysis module M300 is used to perform the following method:

[0103] After detecting a temporary noise event, traffic noise sensor data is accessed; based on the traffic noise sensor data, the noise sound pressure level distribution data is updated, and the boundary of the concentrated area of ​​the noise-sensitive building is flexibly adjusted.

[0104] Furthermore, the conformity analysis module M300 is also used to perform the following methods:

[0105] Based on the noise sensitivity marker, a noise tolerance threshold is configured; noise contour lines are drawn according to the updated noise sound pressure level distribution data, and the intersection of the noise contour lines and the noise tolerance threshold is taken as the expansion critical point corresponding to the temporary noise event; at the same time, the noise propagation path is corrected according to real-time meteorological data.

[0106] Furthermore, the conformity analysis module M300 is also used to perform the following methods:

[0107] The N noise buffer regions and the M candidate concentrated regions are superimposed to identify spatial topological relationships, including overlapping regions, adjacent regions, and separated regions. In the adjacent regions corresponding to the spatial topological relationships, a buffer fusion configuration transition zone is adopted. The transition zone is an elastic range for the optimized expansion of the concentrated region boundary of the noise-sensitive building.

[0108] Furthermore, the conformity analysis module M300 is also used to perform the following methods:

[0109] In the overlapping regions corresponding to the spatial topology, the weights of noise contour lines in the overlapping regions are dynamically adjusted based on a spatiotemporal graph convolutional network. When a conflict in noise sensitivity markers is detected in the overlapping regions, the buffer distance is reallocated to improve the matching degree between the noise contour lines and the noise sensitivity markers in the overlapping regions. In the separated regions corresponding to the spatial topology, edge computing nodes are deployed to monitor the noise propagation path. When the deviation between the boundary of the separated region and the noise source attenuation gradient data exceeds the deviation threshold, buffer distance calibration is triggered. Based on the noise propagation path, a noise diffusion path after digital twin pre-simulation calibration is configured, and topology compatibility is verified in conjunction with urban spatial planning data. The buffer distance threshold is dynamically adjusted using real-time noise intensity and meteorological parameters as the state space and boundary conformity as the reward function.

[0110] In summary, any step can be stored as a computer instruction or program in an unrestricted computer memory and can be called and recognized by an unrestricted computer processor; no further restrictions are imposed here.

[0111] Furthermore, the above technical solutions only embody the preferred technical solutions of the embodiments of this application. Any changes that those skilled in the art may make to certain parts of these solutions embody the novel principles of the embodiments of this application. Obviously, those skilled in the art can make various modifications and variations to this application without departing from the scope of this application.

Claims

1. A method for delineating concentrated areas of noise-sensitive buildings, characterized in that, The method includes: Based on the planned buildings corresponding to the urban space, noise-sensitive buildings and non-noise-sensitive buildings are identified, and the noise-sensitive buildings are marked with noise sensitivity. Cluster analysis is performed on the noise-sensitive buildings, and M candidate cluster regions are identified by combining noise sound pressure level distribution data; spatial density analysis is performed on the non-noise-sensitive buildings, and N noise buffer regions are generated by combining noise source attenuation gradient data. The N noise buffer zones are superimposed onto the M candidate concentration zones, and spatial conformity analysis is performed in conjunction with urban spatial planning and current land use data to optimize and expand the concentration zone boundary of the noise-sensitive buildings. Meanwhile, based on the noise sensitivity markings of the noise-sensitive buildings and the usage time patterns of the buildings, the regional dynamic control level is divided and the noise prevention and control time periods are set differently. The noise-sensitive building is equipped with a noise sensitivity marker, including: Based on a building use database, noise sensitivity characteristics of school buildings and residential buildings are defined. Based on the environmental noise limits and considering the noise sensitivity characteristics of the school buildings and residential buildings, basic sensitivity markers are configured. The basic sensitivity markers are weighted and corrected based on the usage frequency of the school buildings and residential buildings to generate noise sensitivity markers.

2. The method for delineating concentrated areas of noise-sensitive buildings as described in claim 1, characterized in that, Based on the planned buildings corresponding to the urban space, noise-sensitive buildings and non-noise-sensitive buildings are identified, the method including: The criteria for determining noise-sensitive buildings include information on building use and daytime and nighttime noise limits. By matching building use information with the building use database, and combining the functional zoning attributes and building volume parameters in urban spatial planning, a judgment matrix is ​​established. The judgment matrix is ​​used to quantitatively distinguish between noise-sensitive buildings and non-noise-sensitive buildings.

3. The method for delineating concentrated areas of noise-sensitive buildings as described in claim 1, characterized in that, Cluster analysis is performed on the noise-sensitive buildings, and M candidate cluster regions are identified by combining noise sound pressure level distribution data. The method includes: Using the spatial coordinates of the building's center point as input features, set the cluster cutoff distance; Noise-sensitive buildings that are spatially closer than the cluster cutoff distance and have the same noise sensitivity rating are grouped into the same initial cluster.

4. The method for delineating concentrated areas of noise-sensitive buildings as described in claim 3, characterized in that, The method further includes performing spatial density analysis on the non-noise-sensitive buildings, combining noise source attenuation gradient data, and generating N noise buffer zones. Identify the noise sources in the noise buffer zone and establish the sound pressure level and distance attenuation index of the noise sources; Based on the noise source intensity level, combined with the noise source sound pressure level and distance attenuation index, and using the spatial density of the non-noise-sensitive building as a correction coefficient, a dynamic noise buffer distance is set.

5. The method for delineating concentrated areas of noise-sensitive buildings as described in claim 4, characterized in that, The method involves combining urban spatial planning and current land use data to conduct spatial conformity analysis, and optimizing and expanding the boundary of the concentrated area of ​​noise-sensitive buildings. After detecting a temporary noise event, traffic noise sensor data is accessed; Based on the traffic noise sensor data, the noise sound pressure level distribution data is updated, and the boundary of the concentrated area of ​​the noise-sensitive building is flexibly adjusted.

6. The method for delineating a concentrated area of ​​noise-sensitive buildings as described in claim 5, characterized in that, The method for flexibly adjusting the boundary of the concentrated area of ​​the noise-sensitive building includes: Based on the noise sensitivity marker, configure the noise tolerance threshold; Based on the updated noise sound pressure level distribution data, noise contour lines are proposed, and the intersection of the noise contour lines and the noise tolerance threshold is taken as the expansion critical point corresponding to the temporary noise event. At the same time, the noise propagation path is corrected based on real-time meteorological data.

7. The method for delineating concentrated areas of noise-sensitive buildings as described in claim 6, characterized in that, The method of superimposing the N noise buffer regions onto the M candidate set regions includes: The N noise buffer regions and the M candidate concentrated regions are superimposed to identify spatial topological relationships, including overlapping regions, adjacent regions and separated regions. In adjacent regions corresponding to the spatial topology, a buffer fusion configuration transition zone is adopted, which is an elastic range for optimized expansion of the concentrated area boundary of the noise-sensitive building.

8. The method for delineating a concentrated area of ​​noise-sensitive buildings as described in claim 7, characterized in that, The method includes: In the overlapping region corresponding to the spatial topology, the weights of the noise contour lines in the overlapping region are dynamically adjusted based on the spatiotemporal graph convolutional network. When a conflict of noise sensitivity labels is detected in the overlapping region, the buffer distance is reallocated to improve the matching degree between the noise contour lines in the overlapping region and the noise sensitivity labels. In the separated area corresponding to the spatial topology, edge computing nodes are deployed to monitor the noise propagation path. When the deviation between the boundary of the separated area and the noise source attenuation gradient data exceeds the deviation threshold, buffer distance calibration is triggered. Based on the noise propagation path, the noise diffusion path after digital twin pre-simulation calibration is configured, and the topology compatibility is verified in combination with urban spatial planning data. The buffer distance threshold is dynamically adjusted with real-time noise intensity and meteorological parameters as the state space and boundary conformity as the reward function.

9. A system for delineating concentrated areas of noise-sensitive buildings, characterized in that, The system is used to implement the method for delineating a concentrated area of ​​noise-sensitive buildings according to any one of claims 1-8, wherein the system comprises: Planning module: Based on the planned buildings corresponding to the urban space, identify noise-sensitive buildings and non-noise-sensitive buildings, wherein the noise-sensitive buildings are marked with noise sensitivity. Building analysis module: performs cluster analysis on the noise-sensitive buildings, and delineates M candidate cluster regions based on noise sound pressure level distribution data; performs spatial density analysis on the non-noise-sensitive buildings, and generates N noise buffer regions based on noise source attenuation gradient data; The conformity analysis module superimposes the N noise buffer zones onto the M candidate concentration zones, and performs spatial conformity analysis in conjunction with urban spatial planning and current land use data to optimize and expand the boundary of the concentration zone of the noise-sensitive buildings. Differentiated settings module: Simultaneously, based on the noise sensitivity markings of the noise-sensitive buildings and the building usage time patterns, the module performs regional dynamic control level classification and differentiated settings for noise prevention and control time periods.

Images