Urban noise map generation method, system and device and storage medium

Abstract

The invention discloses a city noise map generation method, system and device and a storage medium, and relates to the technical field of environment monitoring, and the method comprises the steps: collecting the noise data of each region of a city through a fixed sensor and a mobile sensor, extracting the spatial-temporal characteristics related to the noise intensity in the noise data, and carrying out the integration, the method comprises the following steps: acquiring noise intensity and noise source positions of different types of noise sources, performing noise level classification according to the noise intensity, acquiring noise levels, integrating the noise source positions, the noise levels and acquisition time of the different types of noise sources, placing an integration result in a map, and generating a noise distribution map with different noise levels. According to the method, the change of noise pollution and the region with high noise level are found and dealt with, the noise distribution condition of each region of a city is accurately described through data integration of the data, and a scientific basis is provided for city planning, environmental protection and public health management.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental monitoring, and in particular to a method, system, device and storage medium for generating an urban noise map. Background Art

[0002] With the continuous acceleration of global urbanization, environmental noise pollution has become an important issue affecting the quality of life of residents and the sustainable development of cities.

[0003] Urban noise comes from a wide range of sources, including traffic noise, industrial noise, construction noise, commercial activity noise, and life noise, etc. These noises not only have a negative impact on the health and life of residents, but also pose a threat to the urban ecological environment and economic development.

[0004] Traditional noise monitoring methods often set up noise sensors at specific points for monitoring. This method is difficult to fully grasp the overall situation of urban noise. The existing technology only collects noise intensity to realize the noise pollution situation in a certain area. Because the distribution of urban noise is relatively complex, it is difficult to timely and comprehensively grasp the changing trend of regional noise pollution, and it cannot meet the noise monitoring needs of the rapidly changing urban environment. Summary of the invention

[0005] The purpose of the present invention is to address the deficiencies of the above-mentioned prior art and provide a method, system, device and storage medium for generating an urban noise map, so as to solve the problems in the prior art that it is difficult to fully grasp the overall situation of urban noise, cannot timely discover and respond to the changing trend of noise pollution, lacks flexibility and real-time performance, and cannot meet the needs of noise monitoring in the rapidly changing urban environment.

[0006] The present invention specifically provides the following technical solutions: A method for generating an urban noise map, comprising: Collect noise data from various areas of the city through fixed and mobile sensors; Extracting the spatiotemporal characteristics of noise intensity from the noise data, and integrating the spatiotemporal characteristics to obtain the noise intensity changes and noise source locations of different types of noise sources in the corresponding time period, and classifying the noise levels according to the noise intensity changes to obtain the noise levels; the spatiotemporal characteristics include the change pattern, spatial distribution, time change trend and periodicity of the noise intensity; The noise source locations, noise levels and acquisition times of different types of noise sources are integrated, and the integration results are placed in a map to generate an urban noise distribution map with different types of noise sources.

[0007] Preferably, before collecting noise data of various areas of the city by fixed sensors and mobile sensors, the method further includes: Collect real-time noise data through existing sensor networks; Modeling the real-time noise data to identify noise hotspots and sensitive areas; wherein the noise hotspots are areas in the city where the noise intensity is higher than a threshold, and the sensitive areas are areas that are sensitive to noise changes; Adjust the position of fixed sensors based on real-time noise data and environmental changes in noise hotspots and sensitive areas.

[0008] Preferably, extracting the spatiotemporal characteristics of noise intensity in the noise data includes: Adjust the feature extraction parameters of the feature extraction model according to the change of the noise data to obtain the feature extraction model after the parameters are adjusted; The feature extraction model with adjusted parameters is used to extract the spatiotemporal characteristics of noise intensity of different categories of noise sources in the noise data, and the different categories of noise sources are labeled.

[0009] Preferably, placing the integration result in a map to generate a noise distribution map with different noise levels includes: Use geographic information system to set up a dynamic map interface, using different colors and icons to display the noise level of the integration results; The integration results are placed on the map interface using three-dimensional modeling technology to construct the distribution of noise at different heights and locations, generate noise distribution maps with different noise levels, and display the noise change trend through heat maps and time series.

[0010] Preferably, after collecting noise data of various areas of the city through fixed sensors and mobile sensors, the method further includes: Performing noise filtering on the noise data to remove irrelevant background noise and erroneous data points, and obtaining noise data after data cleaning; Formatting the noise data after data cleaning to obtain noise data with a unified format; The noise data in a unified format are integrated with geographic information, meteorological data and traffic flow data to obtain noise data with quality above the threshold.

[0011] Preferably, the step of fusing the noise data in a unified format with geographic information, meteorological data and traffic flow data to obtain noise data with a quality higher than a threshold value comprises: Perform timestamp difference processing on noise data, geographic information, meteorological data and traffic flow data in a unified format to obtain data to be fused that is consistent in the time dimension; Perform mixed interpolation on the data to be fused that are consistent in the time dimension to obtain the data to be fused that are aligned in the spatial dimension; Cleaning the data to be fused that are aligned in the time dimension and the space dimension, removing duplicate and conflicting data, and integrating the cleaned data to be fused in multiple dimensions; Error correction is performed on the data to be fused after multi-dimensional integration, and the data to be fused after error correction is unified in format using heterogeneous data integration technology. The data to be fused in the unified format are layered and merged to obtain noise data with a quality higher than a threshold.

[0012] Preferably, after generating the urban noise distribution map with different types of noise sources, the method further comprises: Setting an interactive user interface, providing browsing, querying and analyzing operations through the interactive user interface; Map data for a specific area, time period, or noise type is provided through the interactive user interface.

[0013] The present invention provides a system for generating an urban noise map, comprising: The data collection module is used to collect noise data from various areas of the city through fixed sensors and mobile sensors; An analysis module is used to extract the spatiotemporal characteristics of noise intensity in the noise data, and integrate the spatiotemporal characteristics to obtain the noise intensity changes and noise source locations of different types of noise sources in the corresponding time period, and classify the noise level according to the noise intensity changes to obtain the noise level; the spatiotemporal characteristics include the change pattern, spatial distribution, time change trend and periodicity of the noise intensity; The map generation module is used to integrate the noise source locations, noise levels and acquisition times of different types of noise sources, and place the integration results in a map to generate an urban noise distribution map with different types of noise sources.

[0014] The present invention provides a computer device, comprising a memory and a processor, wherein a program is stored in the memory, and when the program is executed by the processor, the processor executes the steps of the above-mentioned method for generating a city noise map.

[0015] The present invention provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for generating a city noise map are implemented.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The present invention uses multiple fixed sensors and mobile sensors to comprehensively collect and process noise data in a city in real time, thereby improving the overall monitoring effect of urban noise and the accuracy of noise data. At the same time, the temporal and spatial characteristics of noise data are extracted to obtain the noise intensity and location of noise sources, and noise levels are classified according to noise intensity. Noise data is analyzed in space and time, so that the temporal and spatial changes of noise pollution and areas with high noise levels can be discovered and predicted in time, and displayed through maps. In a rapidly changing urban environment, the monitoring ability of noise pollution distribution and noise levels is improved, providing a scientific basis for urban planning, environmental protection and public health management. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is an overall flow chart of a method for generating an urban noise map provided by the present invention. DETAILED DESCRIPTION

[0018] The following is a clear and complete description of the technical solutions of the embodiments of the present invention in conjunction with the drawings in the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0019] The purpose of the present invention is to provide a method, system, device and storage medium for generating a city noise map. On the basis of traditional noise monitoring technology, it combines advanced sensor technology, Internet of Things technology and machine learning algorithms, and a city noise map generation system comes into being. This system can realize the comprehensive collection and real-time processing of noise data within the city, and accurately depict the noise distribution in various areas of the city through intelligent analysis and algorithm recognition, providing a scientific basis for urban planning, environmental protection and public health management. By combining advanced technology with environmental monitoring, the city noise map generation system provides an innovative solution to the problem of urban noise pollution and makes an important contribution to building a livable, healthy and intelligent urban environment.

[0020] The present invention proposes a method for generating an urban noise map, which specifically comprises the following steps: Data Collection and Sensor Adjustment: Step S1: Collect noise data from various areas of the city through fixed sensors and mobile sensors.

[0021] Multiple fixed sensors are set up in multiple key areas of the city, and the positions of the fixed sensors are automatically adjusted according to real-time noise data and environmental changes. Multiple mobile sensors covering noise monitoring blind spots are set up in the city, and real-time noise data are collected through fixed sensors and mobile sensors.

[0022] Before collecting noise data from various areas of the city through fixed sensors and mobile sensors, the positions of fixed sensors are automatically adjusted according to real-time noise data and environmental changes, including the following steps: Collect real-time noise data through existing sensor networks.

[0023] Statistical models and machine learning models are used to model real-time noise data and identify noise hotspots and sensitive areas. Noise hotspots refer to areas in the city with high noise intensity, such as busy traffic intersections, industrial areas, construction sites, etc. These areas are subject to serious noise pollution. Noise sensitive areas refer to areas that are more sensitive to noise changes, such as schools, hospitals, residential areas, and nature reserves. Even if the noise intensity in these areas is not particularly high, they still require special attention and protection.

[0024] Through the dynamic sensor placement algorithm, dynamic adjustment and optimization of urban noise monitoring is achieved. The positions of fixed sensors are adjusted according to real-time noise data and environmental changes in noise hotspots and sensitive areas (including weather conditions, traffic flow, construction activities, and changes in crowd activities) to ensure the comprehensiveness and real-time nature of monitoring, thereby improving the accuracy and coverage of noise data.

[0025] Specific algorithms include data collection and initialization, data analysis and modeling, dynamic optimization models, automatic adjustment strategies, and real-time feedback and improvement. Mobile sensor platforms are built through mobile sensors, such as drones and autonomous vehicles. These mobile platforms can perform precise monitoring at a specific time or in a specific area, especially in areas that fixed sensors cannot cover. Mobile sensors can fill in monitoring blind spots and provide more detailed noise data.

[0026] In the embodiment, the first task is to select and arrange noise sensors to ensure that the system can accurately monitor the noise level in the city. In key areas within the city, such as busy traffic intersections, industrial areas, residential areas, etc., appropriate sensors are selected according to the noise monitoring needs. These sensors must be able to monitor the sound pressure level within a specific frequency range to capture various noise sources in the urban environment. The arrangement of sensors should take into account the urban geographical characteristics, building layout, and expected noise distribution to maximize coverage of the target area and ensure representativeness of the data.

[0027] After receiving the noisy data collected from the sensor network, a series of advanced data cleaning and preprocessing technologies, such as outlier detection and noise filtering, are used to ensure the accuracy and integrity of the data. At the same time, the data preprocessing module uses innovative data fusion technology to improve the quality and analysis accuracy of the data, providing a reliable foundation for subsequent analysis.

[0028] That is, after collecting noise data from various areas of the city through fixed sensors and mobile sensors, it also includes: Noise removal: By using regular expressions or specific text processing algorithms, noise data is filtered to remove irrelevant background noise and erroneous data points, and the cleaned noise data is obtained. This algorithm can adaptively adjust the filtering parameters according to real-time environmental changes, ensuring that the accuracy and efficiency of data cleaning are greatly improved in complex urban noise environments.

[0029] Data formatting: Format the noise data after data cleaning to obtain noise data with a unified format. For example, convert the data into a unified time series format, remove extra spaces and line breaks, etc., to ensure data consistency and comparability. When processing complex multi-source data, this technology can simultaneously retain multi-dimensional information such as time, space, and frequency, supporting more complex spatiotemporal analysis.

[0030] Data fusion: The noise data in a unified format are integrated with geographic information, meteorological data and traffic flow data to obtain noise data with quality above the threshold.

[0031] Among them, noise data with unified format are integrated with geographic information, meteorological data and traffic flow data to obtain noise data with quality higher than the threshold, including: 1. Time alignment: Unify the timestamps of different data sources into a standard time format, such as UTC time. Perform timestamp difference processing on noise data, geographic information, meteorological data, and traffic flow data in a unified format to obtain consistent data to be fused in the time dimension. That is, through an innovative multi-level time synchronization algorithm, timestamp differences are processed to ensure data consistency in the time dimension. This algorithm is not only applicable to conventional data, but also can handle data delay and time difference issues.

[0032] 2. Spatial alignment: Unify geographic location data into a standard coordinate system, such as WGS 84. Mix and interpolate the data to be fused that are consistent in the time dimension to obtain data to be fused that are aligned in the spatial dimension. It can not only process data of different spatial scales, but also consider the influence of factors such as terrain and buildings to ensure accurate alignment of data in the spatial dimension. This technology can improve the spatial accuracy and consistency of data.

[0033] 3. Data cleaning: Clean the data to be fused that are aligned in the time and space dimensions, remove duplicate and conflicting data, and perform multi-dimensional integration on the cleaned data to be fused. Including:

[0034] Redundant information cleaning: Clean up duplicate or redundant information in different data sources, use deduplication algorithms, such as data screening based on unique identifiers (such as a combination of timestamp and location), and retain the most representative and high-quality data.

[0035] Conflicting data processing: The system uses a new type of weighted consensus algorithm to solve the problem of conflicting data between different data sources. For example, when the data from different sensors at the same time and place are inconsistent, the data weight is calculated to select the most credible data source to ensure the reliability and consistency of the data. This algorithm can dynamically adjust the weight of the data source to improve the accuracy of the data.

[0036] 4. Data integration, including: Information integration: Integrate noise data with other relevant information (such as geographic location, weather conditions and traffic flow) in multiple dimensions. For example, the noise intensity data can be associated with its collection location, collection time, weather conditions (temperature, humidity, wind speed) and traffic flow data to form a comprehensive data record containing this information.

[0037] Information supplementation: For missing data points, data can be supplemented through interpolation of adjacent data points or prediction algorithms. For example, for missing meteorological data, it can be supplemented based on historical meteorological data and current trends.

[0038] 5. Data calibration, including: Measurement error correction: Correct the measurement errors of different data sources. For example, use standard sensor data or reference data sets to calibrate sensor data, correct the systematic and random errors of the sensor, and ensure the consistency and accuracy of the data.

[0039] Data standardization: Standardize different types of data, such as converting noise data into standardized dB (decibel) units, converting meteorological data into standard temperature (Celsius) and humidity (percentage), etc., to ensure the comparability of data between different sources.

[0040] 6. Data consolidation, including: Unified format conversion: The system uses a novel heterogeneous data integration technology to unify the format (such as CSV or JSON) of the data to be fused after error correction, and merges the data to be fused in layers after the unified format to obtain noise data with quality higher than the threshold. This technology can effectively process data from different sources and formats, and ensure the integrity and consistency of the data during the merging process.

[0041] Data storage: Store the merged data in a centralized database to ensure easy access and management of the data. Use a relational database or a NoSQL database and choose a suitable data storage solution based on the data type and purpose.

[0042] That is, error correction is performed on the data to be fused after multi-dimensional integration, and the data to be fused after error correction is unified in format using heterogeneous data integration technology, and the data to be fused in the unified format are layered and merged to obtain the merged data.

[0043] Noise Data Analysis and Classification: Step S2: Extract the spatiotemporal characteristics of noise intensity from the noise data, and integrate the spatiotemporal characteristics to obtain the noise intensity changes and noise source locations of different types of noise sources in the corresponding time periods, and classify the noise levels according to the noise intensity changes to obtain the noise levels; the spatiotemporal characteristics include the noise intensity change pattern, spatial distribution, time change trend and periodicity.

[0044] Conduct in-depth analysis and mining of pre-processed noise data. The system applies a variety of advanced machine learning models (such as neural networks, random forests, and support vector machines) for integrated analysis to enhance the accuracy and robustness of noise source identification. Use machine learning models to analyze noise data to obtain identified noise sources and classified noise levels, that is, apply a variety of machine learning models (such as neural networks, random forests, support vector machines, etc.) to conduct integrated and in-depth analysis of noise data, including noise source identification and noise level classification, to enhance the accuracy and robustness of noise source identification. Includes the following steps:

[0045] Feature extraction: Adjust the feature extraction parameters of the feature extraction model according to the changes in the noise data to obtain the feature extraction model after adjusting the parameters.

[0046] The feature extraction model with adjusted parameters is used to extract the spatiotemporal characteristics of noise intensity of different categories of noise sources in the noise data, and the different categories of noise sources are labeled.

[0047] That is, key features are extracted from the preprocessed data, including time domain features, frequency domain features, and Mel frequency cepstral coefficients (MFCC). An adaptive feature selection algorithm is introduced, which can dynamically adjust the parameters and methods of feature extraction according to the changes in data features. For example, the system automatically selects the most important features for noise source identification through recursive feature elimination and tree-based feature selection methods, improving the accuracy and efficiency of feature extraction. This adaptive algorithm can better adapt to the dynamic changes of the noise environment and ensure that the extracted features are highly representative and discriminative.

[0048] Model selection and training: Annotate different noise sources and noise levels in features.

[0049] According to the characteristics of the data, the system selects the appropriate machine learning model for training, which includes different types of models such as classification, clustering and regression. The system adopts an integration method of deep learning models (such as convolutional neural networks and recurrent neural networks) and traditional machine learning models (such as random forests and support vector machines). By using multi-layer neural networks for preliminary training to capture complex nonlinear features, and then combining random forests to further optimize the model, the system can show higher robustness and accuracy on large-scale and complex data sets. In addition, the system also uses transfer learning technology to retrain by migrating trained models, reducing dependence on large-scale labeled data and improving the generalization ability and applicability of the model.

[0050] A machine learning model is selected according to the characteristics of the noise data. The labeled different noise sources and noise levels are integrated through the machine learning model to identify different categories of noise sources, and the noise levels are classified according to the noise intensity of the noise sources.

[0051] Specific models include convolutional neural networks (CNN) and long short-term memory networks (LSTM). CNN is good at processing spatial data, can capture the impact of geographic location and environment on noise data, and extract spatial features such as the change pattern and spatial distribution of noise intensity. LSTM is good at processing time series data, and can extract time features such as the time change trend and periodicity of noise intensity.

[0052] Data integration and modeling are as follows: the extracted spatial features and temporal features are integrated to generate a multi-dimensional feature vector. This ensures that the model takes into account both the temporal and spatial variations of the noise data. A combined model is used for modeling, where LSTM processes time series data and CNN processes spatial data.

[0053] Real-time prediction and noise level generation: After the model is trained, new noise data can be received in real time for prediction. After the data is input, the LSTM module is responsible for predicting the future noise time trend, and the CNN module is responsible for predicting the spatial distribution of noise. The model integrates the results of time prediction and spatial prediction to generate noise change trends and spatial distribution predictions within a certain period of time in the future. By analyzing these prediction results, the system can generate classified noise levels. The generation of noise levels is based on a comprehensive evaluation of noise intensity and distribution, usually expressed in standard decibel (dB) units, and classified according to preset noise level standards (such as low noise, medium noise, high noise, etc.).

[0054] Noise classification method: Noise classification uses a supervised learning method and is trained based on annotated noise data sets. The noise data sets are annotated according to different noise sources (such as traffic noise, industrial noise, construction noise, etc.) and noise levels. By training the machine learning model, the system can automatically identify different types of noise sources and classify them according to noise intensity. The classification standards can refer to the environmental noise standards recommended by the World Health Organization (WHO). According to these standards, the system divides the noise data into different levels and annotates them with corresponding colors and icons on the noise map to intuitively display the noise distribution.

[0055] The noise distribution map is generated as follows: Step S3: Integrate the noise source locations, noise levels and acquisition times of different types of noise sources, and place the integration results in a map to generate an urban noise distribution map with different types of noise sources.

[0056] Based on the data analysis results, a high-precision noise map is generated. Using high-precision geographic information system (GIS) technology and three-dimensional modeling technology, a three-dimensional noise distribution map is generated to show the noise distribution at different heights and locations. At the same time, a spatiotemporal dynamic analysis function is added to show the noise change trend through heat maps and time series, supporting the prediction and analysis of historical and future noise conditions. Specifically:

[0057] Based on the data analysis results, a high-precision noise map is dynamically generated. Using high-precision geographic information system (GIS) technology and three-dimensional modeling technology, a three-dimensional noise distribution map is generated to show the noise distribution at different heights and locations. In addition, a spatiotemporal dynamic analysis function is added to show the noise change trend through heat maps and time series, and support the prediction and analysis of historical and future noise conditions. Specifically:

[0058] The integrated results were placed in a map using GIS and 3D modeling techniques to generate noise distribution maps with different noise levels, including: Data reception and integration: The map generation module first receives the processed noise data from the data analysis module, obtains the location, noise level and time information of the noise source, and integrates the location, noise level and time information of the noise source.

[0059] Map design and development: Use GIS to set up a dynamic map interface, using different colors and icons to display the noise level of the integrated results. It can display the corresponding noise information according to the user's query. Different noise levels are displayed on the map with different colors and icons, for example, red may indicate high noise levels, while green indicates low noise levels.

[0060] Dynamic update function: The map generation module needs to develop a dynamic update function for the map to ensure that the map can reflect changes in noise data in real time. When the data analysis module identifies a new noise event or a change in noise level, the map should be able to automatically update to ensure that users obtain the latest noise information.

[0061] 3D modeling: Use 3D modeling technology to place the integrated results on the map interface, construct the distribution of noise at different heights and locations, generate noise distribution maps with different noise levels, and display the noise change trend through heat maps and time series. This enables users to more intuitively understand the spatial distribution characteristics of noise and supports the prediction and analysis of historical and future noise conditions.

[0062] The user interface is: After generating a city noise distribution map with different types of noise sources, it also includes: An interactive user interface is provided to provide browsing, query and analysis operations through the interactive user interface; map data of specific areas, time periods or noise types are provided through the interactive user interface.

[0063] That is, an interface is provided for users (including government managers and the public) to view real-time noise maps to assist urban planning and noise control decision-making. The interface design is flexible and can be customized according to the user's role and authority. Users can choose to display map data for a specific area, a specific time period, or a specific noise type according to their needs, and can easily perform interactive operations and data queries. In addition, the user interface also provides noise data download and report generation functions to meet users' flexible application and management needs for data.

[0064] In user interface design, the system does the following: Interface design: Design a clear, intuitive, and responsive user interface to ensure that all users (regardless of their skill level) can easily access and understand noise data. Considering the adaptability of different devices, the interface design should be well responsive and display correctly on various screen sizes.

[0065] Information display: Ensure that the interface can clearly display key information such as noise level maps, historical data comparisons, detailed information on noise sources, etc. Use tools such as charts, color-coded legends, and dynamic filters to enable users to intuitively understand and compare noise levels in different regions and time periods.

[0066] Interactive functions: Develop a variety of interactive functions, such as map zooming, area selection, time range selection, etc., so that users can view specific noise information according to their needs. In addition, provide a search function so that users can quickly locate specific locations or noise events, improving the accessibility and efficiency of data use.

[0067] Data access and download: Provide users with data download options, allowing them to download noise data reports and maps for offline analysis and record keeping. At the same time, ensure real-time data updates to maintain the accuracy and timeliness of displayed information and meet users' needs for real-time data.

[0068] User feedback and support: Set up a user feedback mechanism to allow users to report problems or make suggestions for improvement. At the same time, provide help documents and FAQ sections to provide users with support and assistance in solving problems encountered during use and improve user experience.

[0069] Data storage and alarm system: A complete data storage module is built in for long-term storage of historical noise data. These data can not only support real-time environmental monitoring, but also perform trend analysis and pattern recognition, helping city managers to gain an in-depth understanding of the changing trends and laws of noise pollution, so as to take targeted management and control measures. At the same time, the system is also equipped with an efficient and reliable alarm system. When the monitored noise exceeds the preset threshold, the system can immediately issue an alarm and automatically notify relevant managers so that they can take timely countermeasures to ensure the quality of life and health and safety of urban residents. Compared with the existing technology, this application has made innovative improvements in data security and data traceability, and introduced blockchain technology.

[0070] In the data storage and alert system, the system does the following: Data Storage: The system's built-in data storage module is used to store historical noise data for a long time. These data can not only support real-time environmental monitoring, but also perform trend analysis and pattern recognition, helping city managers to gain a deeper understanding of the changing trends and laws of noise pollution, so as to take targeted management and control measures. Blockchain technology is introduced to store and manage noise data. Through the distributed ledger technology of blockchain, each piece of noise data will be recorded on the blockchain to ensure the transparency and immutability of the data. This can prevent the data from being maliciously modified or deleted, and ensure the integrity and credibility of the data.

[0071] Specific operations: Data on-chain: Each time noise data is collected, the system will package the data into blocks and verify and reach consensus through the blockchain network. The verified data blocks will be added to the blockchain chain, forming an unchangeable historical record.

[0072] Before the data is uploaded to the chain, the system will hash the noise data to generate a unique hash value to ensure that the data is not tampered with during transmission and storage.

[0073] Data verification: The system uses the consensus mechanism of blockchain (such as PoW or PoS) to ensure that the data in each block is credible data verified by the majority of nodes. This mechanism can effectively prevent data tampering by a single node.

[0074] During the data verification process, the system will record the verification results of each node and generate an unalterable verification record to ensure the transparency and security of the data.

[0075] Data query: Taking advantage of the distributed characteristics of blockchain, users can query historical noise data of any time period through the system interface, and the traceability information of all data (such as the generation time and source of the data) can be traced back to specific blocks and recording nodes.

[0076] When users query data, the system will provide a hash value verification tool, which allows users to verify the authenticity of the data and ensure that the queried data has not been tampered with.

[0077] Data Protection: Data encryption: All data uploaded to the chain will be encrypted and stored. The system uses advanced encryption algorithms (such as AES-256) to encrypt data to ensure that data cannot be accessed by unauthorized users during storage and transmission.

[0078] Specific operation: Before uploading the data to the blockchain, it will be encrypted and a unique encryption key will be generated. Only authorized users can decrypt and access the data, ensuring the privacy and security of the data.

[0079] Data permission management: The system uses smart contract technology to achieve fine management of data access rights. Different user roles (such as city managers and ordinary citizens) can access different data according to their permissions.

[0080] Specific operation: Smart contracts will verify and authorize each data access according to the preset permission rules. Unauthorized access requests will be rejected and recorded on the blockchain to ensure the security and compliance of data access.

[0081] Data backup and recovery: The system supports data backup and recovery functions to ensure data security and integrity. Through regular backup, the system can quickly restore data when data is lost or damaged, ensuring the normal operation of the system.

[0082] Specific operation: The system will regularly back up data to multiple nodes of the blockchain to ensure distributed storage and high availability of data. When data is damaged or lost, the system can restore data by reading data backups on other nodes to ensure data integrity and recoverability.

[0083] Alarm system: The system is equipped with an efficient and reliable alarm system. When the monitored noise exceeds the preset threshold, the system can immediately sound an alarm and automatically notify relevant managers so that they can take timely countermeasures to ensure the quality of life and health and safety of urban residents. Using blockchain technology, the alarm data will also be recorded on the blockchain to form an unalterable record. This not only ensures the authenticity of the alarm data, but also provides accurate historical records for subsequent analysis.

[0084] Specific operation: Whenever the system issues an alarm, the alarm information (such as alarm time, alarm content, response measures, etc.) will be packaged into blocks and added to the blockchain to form a complete alarm record. Managers can query the blockchain to view the detailed information of each alarm and ensure the authenticity and integrity of all alarm records.

[0085] Based on the above method, the present invention provides a system for generating an urban noise map, comprising: a data collection module, an analysis module and a map generation module.

[0086] Among them, the data collection module is used to collect noise data from various areas of the city through fixed sensors and mobile sensors; the analysis module is used to extract the spatiotemporal characteristics of noise intensity in the noise data, and integrate the spatiotemporal characteristics to obtain the noise intensity changes and noise source locations of different types of noise sources in the corresponding time period, and classify the noise level according to the noise intensity changes to obtain the noise level; the spatiotemporal characteristics include the change pattern, spatial distribution, time change trend and periodicity of noise intensity; the map generation module is used to integrate the noise source location, noise level and acquisition time of different types of noise sources, and place the integration results in the map to generate an urban noise distribution map with different types of noise sources.

[0087] The present invention also provides a computer device, including a memory and a processor. The memory stores a program. When the program is executed by the processor, the processor executes the steps of a method for generating a city noise map.

[0088] According to the disclosed embodiments, a computing device may communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth communications, etc.), or with any device (e.g., routers, modems, etc.) that enables a computing device to communicate with one or more other computing devices.

[0089] The present invention also provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, a method for generating an urban noise map is implemented.

[0090] According to the disclosed embodiments, the storage medium may be a non-volatile computer-readable storage medium, such as but not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, the storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0091] Application scenarios: 1. Urban Planning and Management: The system can provide detailed noise data and analysis results to urban planners and managers, helping them to formulate more scientific and reasonable urban development plans. For example, when planning new residential or commercial areas, managers can refer to the noise map and select areas with lower noise for development to improve the quality of life of residents.

[0092] 2. Environmental protection and public health: The system can help environmental protection departments and public health agencies monitor and evaluate urban noise pollution in real time, providing a scientific basis for noise pollution control and public health protection. Through the noise map, relevant departments can quickly identify the source of noise pollution and take targeted control measures to reduce the impact of noise on residents' health.

[0093] 3. Community Engagement and Public Education: The user interface module of the system can be open to the public, allowing citizens to understand and participate in urban noise monitoring and management. Citizens can use the system to view the noise situation in their communities, make suggestions for improvement, and participate in noise pollution control. The system can also be used for public education, to raise people's awareness of the hazards of noise pollution and to promote public participation in noise pollution prevention and control.

[0094] 4. Intelligent Traffic Management: The system can be combined with the intelligent traffic management system to provide reference data for traffic management departments through real-time monitoring of urban traffic noise, optimize traffic flow and road design, and reduce the impact of traffic noise on the urban environment. The system can also be used to evaluate the effectiveness of traffic improvement measures and help managers develop more effective traffic management strategies.

[0095] The various embodiments of the present invention are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to in detail.

[0096] The present invention uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only used to help understand the method and core ideas of the present invention. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for generating an urban noise map, characterized in that: include: Collect noise data from various areas of the city through fixed and mobile sensors; Extracting the spatiotemporal characteristics of noise intensity from the noise data, and integrating the spatiotemporal characteristics to obtain the noise intensity changes and noise source locations of different types of noise sources in the corresponding time period, and classifying the noise levels according to the noise intensity changes to obtain the noise levels; the spatiotemporal characteristics include the change pattern, spatial distribution, time change trend and periodicity of the noise intensity; The noise source locations, noise levels and acquisition times of different types of noise sources are integrated, and the integration results are placed in a map to generate an urban noise distribution map with different types of noise sources.

2. A method for generating an urban noise map according to claim 1, characterized in that: Before collecting noise data of various areas of the city by using fixed sensors and mobile sensors, the method further includes: Collect real-time noise data through existing sensor networks; Modeling the real-time noise data to identify noise hotspots and sensitive areas; wherein the noise hotspots are areas in the city where the noise intensity is higher than a threshold, and the sensitive areas are areas that are sensitive to noise changes; Adjust the position of fixed sensors based on real-time noise data and environmental changes in noise hotspots and sensitive areas.

3. A method for generating an urban noise map as claimed in claim 1, characterized in that: Extract the spatiotemporal characteristics of noise intensity from noise data, including: Adjust the feature extraction parameters of the feature extraction model according to the change of the noise data to obtain the feature extraction model after the parameters are adjusted; The feature extraction model with adjusted parameters is used to extract the spatiotemporal characteristics of noise intensity of different categories of noise sources in the noise data, and the different categories of noise sources are labeled.

4. A method for generating an urban noise map as claimed in claim 1, characterized in that: The integration results are placed in a map to generate a noise distribution map with different noise levels, including: Use geographic information system to set up a dynamic map interface, using different colors and icons to display the noise level of the integration results; The integration results are placed on the map interface using three-dimensional modeling technology to construct the distribution of noise at different heights and locations, generate noise distribution maps with different noise levels, and display the noise change trend through heat maps and time series.

5. The method for generating an urban noise map according to claim 1, characterized in that: After collecting noise data from various areas of the city through fixed sensors and mobile sensors, the method further includes: Performing noise filtering on the noise data to remove irrelevant background noise and erroneous data points, and obtaining noise data after data cleaning; Formatting the noise data after data cleaning to obtain noise data with a unified format; The noise data in a unified format are integrated with geographic information, meteorological data and traffic flow data to obtain noise data with quality above the threshold.

6. A method for generating an urban noise map as claimed in claim 5, characterized in that: The noise data in a unified format is integrated with geographic information, meteorological data and traffic flow data to obtain noise data with a quality higher than a threshold, including: Perform timestamp difference processing on noise data, geographic information, meteorological data and traffic flow data in a unified format to obtain data to be fused that is consistent in the time dimension; Perform mixed interpolation on the data to be fused that are consistent in the time dimension to obtain the data to be fused that are aligned in the spatial dimension; Cleaning the data to be fused that are aligned in the time dimension and the space dimension, removing duplicate and conflicting data, and integrating the cleaned data to be fused in multiple dimensions; Error correction is performed on the data to be fused after multi-dimensional integration, and the data to be fused after error correction is unified in format using heterogeneous data integration technology. The data to be fused in the unified format are layered and merged to obtain noise data with a quality higher than a threshold.

7. A method for generating an urban noise map as claimed in claim 1, characterized in that: After generating the urban noise distribution map with different types of noise sources, the method further includes: Setting an interactive user interface, providing browsing, querying and analyzing operations through the interactive user interface; Map data for a specific area, time period, or noise type is provided through the interactive user interface.

8. A system for generating an urban noise map, characterized in that: include: The data collection module is used to collect noise data from various areas of the city through fixed sensors and mobile sensors; An analysis module is used to extract the spatiotemporal characteristics of noise intensity in the noise data, and integrate the spatiotemporal characteristics to obtain the noise intensity changes and noise source locations of different types of noise sources in the corresponding time period, and classify the noise level according to the noise intensity changes to obtain the noise level; the spatiotemporal characteristics include the change pattern, spatial distribution, time change trend and periodicity of the noise intensity; The map generation module is used to integrate the noise source locations, noise levels and acquisition times of different types of noise sources, and place the integration results in a map to generate an urban noise distribution map with different types of noise sources.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein a program is stored in the memory, and when the program is executed by the processor, the processor executes the steps of a method for generating an urban noise map as claimed in any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for generating an urban noise map according to any one of claims 1 to 7 are implemented.

Images