A data control system for smart cities based on big data
By integrating multiple data acquisition and analysis modules in the smart city data control system, combined with the influence of multiple factors, the problem of inaccurate traffic flow prediction in the existing technology is solved, more accurate traffic management and control is achieved, and the city is improved Traffic operation efficiency and safety.
Patent Information
- Application Number
- CN202411113469.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-14
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-08-14
AI Technical Summary
The existing smart city data control system fails to fully consider the influence of multiple factors in traffic flow forecasting, resulting in inaccurate prediction of prediction results, difficult to capture abnormal peaks, unable to provide reliable basis for traffic management, and unable to provide timely specific measures to alleviate congestion .
A smart city data control system based on big data was designed, including data acquisition module, road condition monitoring module, weather data acquisition module, special event monitoring module, historical data storage module, data analysis module, comprehensive analysis module, early warning decision-making and control The module and the central general control module use a variety of machine learning algorithms and data mining technologies to collect and analyze traffic data in real time, combine factors such as road construction, large-scale activities and weather to conduct in-depth analysis and modeling to generate traffic guidance decision-making suggestions.
Improve the accuracy of traffic flow forecasting, provide more accurate and reliable decision-making support, effectively optimize traffic flow allocation, alleviate traffic congestion, improve the operation efficiency and safety of urban traffic, and realize the management of smart city road traffic and control.
Smart Images

Figure CN118644990B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of big data technology, and in particular to a data control system for smart cities based on big data. Background Art
[0002] With the acceleration of global urbanization, the scale of cities continues to expand, and the urban population grows rapidly. Cities are facing unprecedented challenges. Traditional urban management models and infrastructure can no longer meet the needs of urban development. Against this background, the concept of smart cities has emerged. Smart cities aim to use advanced information technologies, such as the Internet of Things, big data, cloud computing, artificial intelligence, etc., to achieve intelligent management and sustainable development of cities. By connecting various facilities, equipment and systems in the city, data collection, transmission, analysis and application can be realized, thereby optimizing the city's resource allocation, improving the city's operating efficiency and improving the quality of life of residents.
[0003] The existing data control system for smart cities does not fully consider the impact of multiple factors on traffic flow prediction technology, resulting in inaccurate prediction results, difficulty in capturing abnormal peaks, and failure to provide a reliable basis for traffic management, which often puts traffic management into a passive position. In addition, it is impossible to give effective suggestions based on accurate predictions, it is difficult to judge the level of traffic conditions, and in the face of possible congestion, it is impossible to give specific measures such as adding staff and adjusting traffic lights in a timely manner. For this reason, we propose a data control system for smart cities based on big data. Summary of the invention
[0004] The purpose of the present invention is to provide a data control system for smart cities based on big data.
[0005] In order to solve the problems raised in the above background technology, the present invention provides the following technical solutions: a data control system for smart cities based on big data, the data control system for smart cities based on big data includes a data acquisition module, a road condition monitoring module, a weather data acquisition module, a special event monitoring module, a historical data storage module, a data analysis module, a comprehensive analysis module, an early warning decision-making control module and a central control module;
[0006] Data collection module: responsible for collecting basic data such as traffic flow, speed, vehicle type, vehicle queue length, and lane occupancy in real time through geomagnetic sensors, high-definition cameras, and microwave radar equipment distributed in the urban road network;
[0007] Road condition monitoring module: using deep learning-based video analysis technology and advanced image processing algorithms to monitor and identify road congestion, accident conditions, and road construction conditions, so as to monitor and judge the driving status of vehicles, stagnation time, and the severity of accidents;
[0008] Weather data acquisition module: connects to the data interface of the meteorological department to obtain real-time weather information, including rainfall, temperature, humidity, wind speed, wind direction and visibility data;
[0009] Special event monitoring module: used to obtain information data on large-scale events in the city (including concerts, sports events), road construction, and emergencies (including natural disasters, emergency repairs);
[0010] Historical data storage module: used to store traffic flow data, road condition information, weather data and special event records over a period of time;
[0011] Data analysis module: uses a variety of machine learning algorithms and data mining techniques to clean, preprocess and extract features from the collected data, remove noise, outliers and missing data, and extract valuable features;
[0012] Comprehensive analysis module: responsible for receiving data from various modules and conducting comprehensive analysis on the received data to predict traffic flow in the future;
[0013] Early warning decision-making and control module: responsible for comparing the prediction results obtained by the comprehensive analysis module with the preset threshold range, triggering different levels of early warning mechanisms within different threshold ranges, and generating corresponding traffic diversion decision suggestions;
[0014] Central control module: responsible for coordinating the work between various modules, monitoring the operating status of the system, and allocating computing resources and data transmission tasks.
[0015] As a further solution of the present invention: in the data acquisition module, the geomagnetic sensor detects vehicles by using changes in the geomagnetic field, determines the presence and driving direction of the vehicle by changes in the magnetic field strength, and samples data at a high frequency to ensure the timeliness of the data. The camera uses an optical character recognition (OCR) algorithm to automatically identify the type and license plate information of the vehicle. The microwave radar measures the speed and distance of the vehicle by emitting electromagnetic waves and receiving reflected waves. The collected data is preliminarily screened and filtered to remove obvious outliers and erroneous data, and then transmitted to the data analysis module through the 5G network.
[0016] As a further solution of the present invention: the road condition monitoring module sets high-definition cameras on each traffic section to obtain real-time road video images, and then uses a deep learning algorithm to analyze the video images frame by frame to identify the vehicle's driving status, congested areas and possible accident signs. For the judgment of the vehicle's driving status, whether there is congestion is determined by detecting the vehicle's speed, spacing and driving trajectory. In congestion detection, the road is divided into different areas using image segmentation technology, and the density and residence time of vehicles in each area are calculated. For the identification of accident signs, the abnormal behavior of the vehicle, including sudden braking and collision, is identified through training models. The road condition monitoring module updates the monitored road condition information in real time, and the road condition monitoring module transmits the monitored traffic road condition data to the data analysis module.
[0017] As a further solution of the present invention: the weather data acquisition module is implemented by establishing a stable data interface with the meteorological department, and uses the HTTP network communication protocol to send a request to the server of the meteorological department to obtain real-time weather data of the specified area. After receiving the real-time weather data of the specified area, the weather data acquisition module will convert and parse the data format, and extract key information related to traffic flow forecasting, including rainfall, temperature, humidity, wind speed, wind direction and visibility information data. The weather data acquisition module adopts a data verification and error correction mechanism, which can check the rationality of the received data to ensure the accuracy and completeness of the data. At the same time, in order to cope with the update of meteorological data, the module sets a scheduled task to automatically obtain the latest weather information every 30 minutes.
[0018] As a further solution of the present invention: the special event monitoring module is provided with a web crawler technology and a natural language processing algorithm. By setting keywords and rules, the crawler program searches the Internet for web pages, news and social media information related to special events in the city. For the acquired text data, natural language processing technology is used to perform semantic analysis and keyword extraction to determine key information such as the type, time, location and scale of the event. The special event monitoring module also screens and filters in combination with geographic location information and time information to ensure that the acquired special events are related to the traffic conditions of the city.
[0019] As a further solution of the present invention: the historical data storage module stores traffic flow data, road condition information, weather data, and special event record data over a period of time in the past. The historical data storage module adopts a distributed storage architecture and data compression technology, and uses the Hadoop HDFS distributed database system to store a large amount of historical traffic data in multiple nodes in a dispersed manner, so as to improve the storage capacity and access performance of the data. For data compression, the Gzip lossless compression algorithm is adopted to reduce the data storage space without losing data accuracy. At the same time, in order to facilitate data query and analysis, a hash index structure is established, which can quickly locate and retrieve the required data. The historical data storage module interacts with the comprehensive analysis module in real time.
[0020] As a further solution of the present invention: the data analysis module is provided with a machine learning algorithm and data mining technology for data processing. First, data cleaning technology is used to remove noise and missing values to ensure the quality of data. Then, feature engineering technology is used to extract features from the collected raw data, including converting time series data into frequency domain features. For model training, a long short-term memory network (LSTM) deep learning model is used to capture the time dependency in the data. For the LSTM model, the predicted value of its output can be calculated by the following formula:
[0021] ;
[0022] in: represents the predicted value of the output, Represents LSTM at time The hidden state of represents the weight matrix, represents the bias term, represents the Sigmoid activation function, Represents input features The weight of represents the overall bias;
[0023] The data analysis module combines cluster analysis and classification algorithms to classify and identify traffic flow patterns in different road sections and time periods. In the LSTM model evaluation stage, cross-validation and mean square error (MSE) indicator evaluation techniques are used to help select the optimal model parameters and algorithms. The data analysis module will transmit the extracted feature data to the comprehensive analysis module.
[0024] As a further solution of the present invention: the comprehensive analysis module can receive data transmitted by the data analysis module and interact with the historical data storage module in real time. The comprehensive analysis module constructs a mathematical model. When the comprehensive analysis module is ready to train the mathematical model, it will extract the required data from the historical data storage module. The data include multi-dimensional information such as traffic flow values arranged in chronological order, corresponding weather conditions, types and occurrence times of special events, and the degree of road congestion. The mathematical model comprehensively considers the impact of multiple factors on traffic flow. The input of the mathematical model includes data from the data acquisition module, the road condition monitoring module, the weather data acquisition module, and the special event monitoring module. The mathematical model adopts a multivariate nonlinear regression method, and the specific form of its function is as follows:
[0025] ;
[0026] in: represents the traffic flow value, represents different input variables, including current traffic flow, weather conditions, An input variable representing a particular event type, represents the total number of input variables, , , and Represents the model parameters, which are obtained through training with a large amount of historical data. To represent the error term, the traffic flow value can be calculated through the above function formula;
[0027] During the analysis process, the comprehensive analysis module first standardizes the input data so that it has the same dimension and distribution. Then, the standardized data is substituted into the model for calculation to obtain the predicted traffic flow value. Next, the prediction result is corrected and optimized by comparing it with historical data of the same period and empirical data under similar conditions. Finally, the optimized prediction result is output to the early warning decision-making and control module.
[0028] As a further solution of the present invention: the early warning decision control module can receive the prediction result data provided by the comprehensive analysis module, and the early warning decision control module sets multiple threshold ranges. The specific analysis and comparison categories are as follows:
[0029] when When , no warning is triggered;
[0030] when When the traffic volume is too high, a mild warning is triggered and the system recommends adding more traffic diversion personnel;
[0031] when When the traffic light is on the road, a moderate warning is triggered and the system recommends adjusting the traffic light timing and activating some backup roads.
[0032] when When the vehicle is moving at a high speed, a severe warning is triggered and the system recommends implementing traffic control and vehicle diversion measures;
[0033] in: It represents the normal traffic flow value input by the management personnel;
[0034] The warning decision-making and control module selects corresponding response measures from a pre-established strategy library according to the warning level. During the implementation of the measures, it monitors changes in traffic conditions in real time and evaluates the effectiveness of the measures. When the results are not ideal, the strategy will be adjusted in real time.
[0035] As a further solution of the present invention: the central master control module enjoys the highest control authority of the system, which is equivalent to the computer end of the smart city management personnel. The central master control module can control and edit the data collection frequency of the data collection module, the central master control module can control and edit the frequency of the weather data acquisition module acquiring weather information, the central master control module can edit the parameters of the calculation formula of the data analysis module, the central master control module can edit the function parameters of the comprehensive analysis module, and the central master control module can edit the normal traffic flow value in the early warning decision-making and control module.
[0036] By adopting the above technical solution, compared with the prior art, the beneficial effects of the present invention are:
[0037] 1. The present invention comprehensively considers the complex impact of various factors such as road construction, large-scale events and special weather on traffic flow, thereby greatly improving the accuracy of traffic flow prediction. Through the coordinated work of the data acquisition module, the road condition monitoring module, the weather data acquisition module and the special event monitoring module, the system can obtain various relevant information in real time and accurately. For example, in special circumstances such as large-scale sports events or concerts, it can accurately capture the abnormal peak of traffic flow on surrounding roads, avoiding the problem that traditional algorithms cannot accurately predict. Advanced data analysis and comprehensive analysis modules are used, combined with algorithms such as multivariate nonlinear regression, to conduct in-depth analysis and modeling of these complex factors, thereby providing more accurate and reliable decision support for urban traffic management, effectively optimizing traffic flow distribution, alleviating traffic congestion, and improving the overall operating efficiency and safety of urban traffic, and also realizing the management and control of smart city road traffic;
[0038] 2. The present invention can provide different types of urban traffic management suggestions according to the traffic flow prediction results through the cooperation between the early warning decision-making control module and the comprehensive analysis module. The comprehensive analysis module integrates various data and uses advanced analysis algorithms to accurately predict the changing trend of traffic flow. The early warning decision-making control module compares these prediction results with the preset thresholds to judge the level of traffic conditions. When it is predicted that a certain area may experience traffic congestion in a specific time period, the system will give corresponding governance suggestions according to the degree of congestion and the scope of impact, such as increasing traffic diversion personnel, adjusting the timing of traffic lights, and starting alternate roads. These accurate suggestions help urban managers take effective measures in a timely manner to prevent and alleviate traffic congestion in advance and improve the operating efficiency of urban traffic.
[0039] 3. The present invention adopts a distributed storage architecture and data compression technology through the historical data storage module, thereby improving the data storage capacity and access performance, facilitating the system to store and process large amounts of data. The central control module can control and edit the relevant parameters of each module, such as data collection frequency, data analysis and comprehensive analysis model parameters, etc., so that the system can be flexibly adjusted and optimized according to actual needs and changes in urban development. This scalability and flexibility help the system better adapt to the traffic conditions and development needs of different cities, and provide strong support for the construction of smart cities. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] Figure 1 Schematic diagram of the system flow in an embodiment of the present invention. DETAILED DESCRIPTION
[0041] The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.
[0042] In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.
[0043] Please see attached Figure 1 The present invention provides a data control system for smart cities based on big data. The data control system for smart cities based on big data includes a data acquisition module, a road condition monitoring module, a weather data acquisition module, a special event monitoring module, a historical data storage module, a data analysis module, a comprehensive analysis module, an early warning decision-making control module and a central control module;
[0044] Data collection module: responsible for collecting basic data such as traffic flow, speed, vehicle type, vehicle queue length, and lane occupancy in real time through geomagnetic sensors, high-definition cameras, and microwave radar equipment distributed in the urban road network;
[0045] Road condition monitoring module: using deep learning-based video analysis technology and advanced image processing algorithms to monitor and identify road congestion, accident conditions, and road construction conditions, so as to monitor and judge the driving status of vehicles, stagnation time, and the severity of accidents;
[0046] Weather data acquisition module: connects to the data interface of the meteorological department to obtain real-time weather information, including rainfall, temperature, humidity, wind speed, wind direction and visibility data;
[0047] Special event monitoring module: used to obtain information data on large-scale events in the city (including concerts, sports events), road construction, and emergencies (including natural disasters, emergency repairs);
[0048] Historical data storage module: used to store traffic flow data, road condition information, weather data and special event records over a period of time;
[0049] Data analysis module: uses a variety of machine learning algorithms and data mining techniques to clean, preprocess and extract features from the collected data, remove noise, outliers and missing data, and extract valuable features;
[0050] Comprehensive analysis module: responsible for receiving data from various modules and conducting comprehensive analysis on the received data to predict traffic flow in the future;
[0051] Early warning decision-making and control module: responsible for comparing the prediction results obtained by the comprehensive analysis module with the preset threshold range, triggering different levels of early warning mechanisms within different threshold ranges, and generating corresponding traffic diversion decision suggestions;
[0052] Central control module: responsible for coordinating the work between various modules, monitoring the operating status of the system, and allocating computing resources and data transmission tasks.
[0053] In one embodiment of the present invention: In the data acquisition module, the geomagnetic sensor uses the change of the geomagnetic field to detect the vehicle, and determines the existence and driving direction of the vehicle by the change of the magnetic field strength, and samples the data at a high frequency to ensure the timeliness of the data. The camera uses an optical character recognition (OCR) algorithm to automatically identify the type and license plate information of the vehicle. The microwave radar measures the speed and distance of the vehicle by emitting electromagnetic waves and receiving reflected waves. The collected data is preliminarily screened and filtered to remove obvious outliers and erroneous data, and then transmitted to the data analysis module through the 5G network.
[0054] In one embodiment of the present invention: the road condition monitoring module sets high-definition cameras on each traffic section to obtain real-time road video images, and then uses a deep learning algorithm to analyze the video images frame by frame to identify the vehicle's driving status, congestion areas and possible accident signs. For the judgment of the vehicle's driving status, whether there is congestion is determined by detecting the vehicle's speed, spacing and driving trajectory. In congestion detection, the road is divided into different areas using image segmentation technology, and the density and residence time of vehicles in each area are calculated. For the identification of accident signs, the abnormal behavior of the vehicle, including sudden braking and collision, is identified through training models. The road condition monitoring module updates the monitored road condition information in real time, and the road condition monitoring module transmits the monitored traffic road condition data to the data analysis module.
[0055] In one embodiment of the present invention: the weather data acquisition module is implemented by establishing a stable data interface with the meteorological department, and uses the HTTP network communication protocol to send a request to the server of the meteorological department to obtain real-time weather data of the specified area. After receiving the real-time weather data of the specified area, the weather data acquisition module will convert and parse the data format, and extract key information related to traffic flow forecasting, including rainfall, temperature, humidity, wind speed, wind direction and visibility information data. The weather data acquisition module adopts a data verification and error correction mechanism, which can perform a rationality check on the received data to ensure the accuracy and completeness of the data. At the same time, in order to cope with the update of meteorological data, the module sets a scheduled task to automatically obtain the latest weather information every 30 minutes.
[0056] In one embodiment of the present invention: the special event monitoring module is provided with a web crawler technology and a natural language processing algorithm. By setting keywords and rules, the crawler program searches the Internet for web pages, news and social media information related to special events in the city. For the acquired text data, natural language processing technology is used to perform semantic analysis and keyword extraction to determine key information such as the type, time, location and scale of the event. The special event monitoring module also screens and filters in combination with geographic location information and time information to ensure that the acquired special events are related to the traffic conditions of the city.
[0057] In one embodiment of the present invention: the historical data storage module stores traffic flow data, road condition information, weather data, and special event record data for a period of time in the past. The historical data storage module adopts a distributed storage architecture and data compression technology, and uses the Hadoop HDFS distributed database system to store a large amount of historical traffic data in multiple nodes in a dispersed manner, so as to improve the storage capacity and access performance of the data. For data compression, the Gzip lossless compression algorithm is adopted to reduce the data storage space without losing data accuracy. At the same time, in order to facilitate data query and analysis, a hash index structure is established, which can quickly locate and retrieve the required data. The historical data storage module interacts with the comprehensive analysis module in real time.
[0058] In one embodiment of the present invention: the data analysis module is provided with a machine learning algorithm and data mining technology for data processing. First, data cleaning technology is used to remove noise and missing values to ensure the quality of data. Then, feature engineering technology is used to extract features from the collected raw data, including converting time series data into frequency domain features. For model training, a long short-term memory network (LSTM) deep learning model is used to capture the time dependency in the data. For the LSTM model, the predicted value of its output can be calculated by the following formula:
[0059] ;
[0060] in: represents the predicted value of the output, Represents LSTM at time The hidden state of represents the weight matrix, represents the bias term, represents the Sigmoid activation function, Represents input features The weight of represents the overall bias;
[0061] The data analysis module combines cluster analysis and classification algorithms to classify and identify traffic flow patterns in different road sections and time periods. In the LSTM model evaluation stage, cross-validation and mean square error (MSE) indicator evaluation techniques are used to help select the optimal model parameters and algorithms. The data analysis module will transmit the extracted feature data to the comprehensive analysis module.
[0062] In one embodiment of the present invention: the comprehensive analysis module can receive data transmitted by the data analysis module and interact with the historical data storage module in real time. The comprehensive analysis module constructs a mathematical model. When the comprehensive analysis module is ready to train the mathematical model, it will extract the required data from the historical data storage module. These data include multi-dimensional information such as traffic flow values arranged in chronological order, corresponding weather conditions, types and occurrence times of special events, and the degree of road congestion. The mathematical model comprehensively considers the impact of multiple factors on traffic flow. The input of the mathematical model includes data from the data acquisition module, the road condition monitoring module, the weather data acquisition module, and the special event monitoring module. The mathematical model adopts a multivariate nonlinear regression method, and the specific form of its function is as follows:
[0063] ;
[0064] in: represents the traffic flow value, represents different input variables, including current traffic flow, weather conditions, An input variable representing a particular event type, represents the total number of input variables, , , and Represents the model parameters, which are obtained through training with a large amount of historical data. To represent the error term, the traffic flow value can be calculated through the above function formula;
[0065] During the analysis process, the comprehensive analysis module first standardizes the input data to make it have the same dimension and distribution. Then, the standardized data is substituted into the model for calculation to obtain the predicted traffic flow value. Next, the prediction results are corrected and optimized by comparing with historical data of the same period and empirical data under similar conditions. Finally, the optimized prediction results are output to the early warning decision-making and control module.
[0066] In one embodiment of the present invention: the early warning decision control module can receive the prediction result data provided by the comprehensive analysis module, and the early warning decision control module sets multiple threshold ranges. The specific analysis and comparison categories are as follows:
[0067] when When , no warning is triggered;
[0068] when When the traffic volume is too high, a mild warning is triggered and the system recommends adding more traffic diversion personnel;
[0069] when When the traffic light is on the road, a moderate warning is triggered and the system recommends adjusting the traffic light timing and activating some backup roads.
[0070] when When the vehicle is moving at a high speed, a severe warning is triggered and the system recommends implementing traffic control and vehicle diversion measures;
[0071] in: It represents the normal traffic flow value input by the management personnel;
[0072] The early warning decision-making and control module selects corresponding response measures from the pre-established strategy library according to the early warning level. In the process of implementing the measures, it monitors the changes in traffic conditions in real time and evaluates the effectiveness of the measures. When the results are not ideal, it will adjust the strategy in real time.
[0073] In one embodiment of the present invention: the central master control module enjoys the highest control authority of the system, which is equivalent to the computer end of the smart city manager. The central master control module can control and edit the data collection frequency of the data collection module, the central master control module can control and edit the frequency of the weather data acquisition module acquiring weather information, the central master control module can edit the parameters of the calculation formula of the data analysis module, the central master control module can edit the function parameters of the comprehensive analysis module, and the central master control module can edit the normal traffic flow value in the early warning decision-making and control module.
[0074] Example 1, please refer to the attached Figure 1 In the actual application of the road condition monitoring module, the high-definition camera has high resolution and wide-angle shooting capabilities, can cover a wider road area, and obtain more detailed road video images. The deep learning algorithm is constantly optimized. In addition to being able to identify vehicle driving status, congested areas and accident signs, it can also predict potential traffic congestion points. In congestion detection, the image segmentation technology is more sophisticated and can divide the road into smaller areas. The density and residence time of vehicles in each area can be accurately calculated. For the identification of accident signs, the training model can analyze the vehicle's driving behavior in real time, and warn of possible accidents in advance, providing more timely decision support for traffic management.
[0075] Example 2, please refer to the attached Figure 1 The historical data storage module adopts a more advanced distributed storage architecture to ensure the security and non-tamperability of data. The data compression technology adopts a more efficient algorithm to further reduce the data storage space while improving the data decompression speed. The hash index structure is optimized and upgraded to locate and retrieve the required data faster. The module adds a data backup and recovery mechanism to back up data regularly to prevent data loss. At the same time, the data storage module is combined with the cloud computing platform to achieve elastic expansion of storage resources to meet the growing data storage needs.
[0076] Example 3, please refer to the attached Figure 1,During the data extraction process, the comprehensive analysis module uses real-time ,data collection technology to ensure the timeliness of the data. ,The factors considered by the model are more comprehensive, including the ,impact of road construction progress, holidays and other factors on traffic flow. ,During the analysis process, big data visualization technology is used to ,display the analysis results in the form of intuitive charts, ,which is convenient for managers to make decisions.
[0077] Specifically, the present invention comprehensively considers the complex impacts of many factors such as road construction, large-scale events and special weather on traffic flow, greatly improving the accuracy of traffic flow prediction. With the coordinated operation of the data acquisition module, the road condition monitoring module, the weather data acquisition module and the special event monitoring module, the system can obtain various relevant information in real time and accurately. For example, in special circumstances such as large-scale sports events or concerts, it can accurately capture abnormal peaks in traffic flow on surrounding roads, avoiding the problem that traditional algorithms are difficult to accurately predict. It uses cutting-edge data analysis and comprehensive analysis modules, combined with algorithms such as multivariate nonlinear regression, to conduct in-depth analysis and modeling of these complex factors, thereby providing more accurate and reliable decision-making support for urban traffic management, effectively optimizing traffic flow distribution, alleviating traffic congestion, and improving the overall operating efficiency and safety of urban traffic.
[0078] Specifically, the present invention can give different types of urban traffic management suggestions based on traffic flow prediction results through the mutual cooperation of the early warning decision-making and control module and the comprehensive analysis module. The comprehensive analysis module integrates multi-dimensional data and uses advanced analysis algorithms to accurately predict the changing trend of traffic flow. The early warning decision-making and control module compares these prediction results with preset thresholds to determine the level of traffic conditions. When it is predicted that traffic congestion may occur in a certain area during a specific period of time, the system will give corresponding management suggestions according to the degree of congestion and the scope of impact, such as increasing traffic diversion personnel, adjusting traffic light timing, and activating alternate roads. These accurate suggestions are conducive to urban managers to implement effective measures in a timely manner, prevent and alleviate traffic congestion in advance, and improve the operating efficiency of urban traffic.
[0079] Specifically, the present invention adopts a distributed storage architecture and data compression technology through the historical data storage module, thereby enhancing the data storage capacity and access performance, which is beneficial for the system to store and process large amounts of data. The central control module can control and edit the relevant parameters of each module, such as data collection frequency, data analysis and comprehensive analysis model parameters, etc., so that the system can be flexibly adjusted and optimized according to actual needs and changes in urban development. This scalability and flexibility helps the system to better adapt to the traffic conditions and development needs of different cities, and provide strong guarantees for the construction of smart cities.
[0080] Working principle:
[0081] First, the data acquisition module uses geomagnetic sensors, high-definition cameras, and microwave radar equipment to collect basic traffic-related data in real time. The road condition monitoring module uses video analysis technology and image processing algorithms to monitor road conditions. The weather data acquisition module connects with the meteorological department to obtain real-time weather information. The special event monitoring module obtains information on large-scale activities, road construction, and emergencies in the city. The historical data storage module stores past related data to help the comprehensive analysis module train mathematical models. These four modules will aggregate and transmit the data to the data analysis module. Then, the data analysis module uses machine learning algorithms and data mining techniques to process the collected data, and uses the long short-term memory network (LSTM) deep learning model to capture the feature data in the acquired data. Output the predicted value of the acquired data, and transmit the acquired data to the comprehensive analysis module. Then, the comprehensive analysis module predicts the traffic flow through the mathematical module according to the received data and the data recorded by the historical data storage module. Then, the predicted traffic flow value data is transmitted to the early warning decision-making and control module. Then, an excess threshold is set in the early warning decision-making and control module. The early warning decision-making and control module will compare the threshold with the calculated traffic flow value. According to different comparison ranges, the early warning decision-making and control module triggers different levels of early warning mechanisms and generates corresponding traffic diversion decision suggestions. Through the cooperation between various modules, it can keenly analyze and predict the current urban traffic situation based on the current urban traffic data, avoid the problem that traditional algorithms cannot accurately predict, and give reasonable governance suggestions based on the current urban traffic status, effectively alleviate traffic congestion, improve the overall operation efficiency and safety of urban traffic, and also realize the management and control of smart city road traffic. At this point, the entire workflow ends.
[0082] At the same time, the present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.
[0083] Some aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". The processor may be one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DAPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, or combinations thereof. In addition, various aspects of the present application may be represented as computer products located in one or more computer-readable media, which include computer-readable program codes. For example, computer-readable media may include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, tapes ...), optical disks (e.g., compact disks CDs, digital versatile disks DVDs ...), smart cards, and flash memory devices (e.g., cards, sticks, key drives ...).
[0084] A computer-readable medium may include a propagated data signal containing computer program code, such as in baseband or as part of a carrier wave. The propagated signal may have a variety of manifestations, including electromagnetic, optical, etc., or a suitable combination. A computer-readable medium may be any computer-readable medium other than a computer-readable storage medium, which may be connected to an instruction execution system, device or apparatus to communicate, propagate or transmit a program for use. The program code on the computer-readable medium may be propagated through any suitable medium, including radio, cable, fiber optic cable, radio frequency signal, or similar medium, or a combination of any of the above mediums.
[0085] Similarly, it should be noted that in order to simplify the description disclosed in this application, so as to help understand one or more embodiments of the invention, in the above description of the embodiments of the present application, sometimes multiple features are merged into one embodiment, drawings or descriptions thereof. However, this disclosure method does not mean that the features required by the object of the present application are more than the features mentioned in the claims. In fact, the features of the embodiment are less than all the features of the single embodiment disclosed above. In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "approximately", "approximately" or "substantially" in some examples. Unless otherwise specified, "approximately", "approximately" or "substantially" indicate that the number allows a variation of ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the characteristics required by individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining the digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of the present application are approximate values, in specific embodiments, such numerical settings are as accurate as possible within the feasible range.
[0086] Although the present invention is disclosed as above in terms of preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art may make possible changes and modifications without departing from the spirit and scope of the present invention. Therefore, any modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention shall fall within the scope of protection defined by the claims of the present invention.
Claims
1. A data control system for smart cities based on big data, characterized in that: The data control system for smart cities based on big data includes a data acquisition module, a road condition monitoring module, a weather data acquisition module, a special event monitoring module, a historical data storage module, a data analysis module, a comprehensive analysis module, an early warning decision-making and control module, and a central control module; The data acquisition module is used to obtain basic data of vehicles in the urban road network, including vehicle flow, vehicle type, vehicle queue length, and lane occupancy rate; the road condition monitoring module is used to monitor road and traffic information in real time; the weather data acquisition module is used to obtain real-time weather data of the current urban area; and the special event monitoring module is used to obtain special event information data related to traffic conditions in the city; The data analysis module is used to process and mine the acquired data and extract valuable feature data. The historical data storage module can provide a search function to find the urban traffic related data in the past period of time based on the urban traffic data stored for a period of time. The comprehensive analysis module receives the data from the data analysis module and interacts with the historical data storage module in real time, and uses the function of the multivariate nonlinear regression method in the mathematical model according to the received data. Calculate traffic flow values, where: represents the traffic flow value, represents different input variables, including current traffic flow, weather conditions, represents the input variable of a special event type, n represents the total number of input variables, , , and Represents the model parameters, which are obtained through training with a large amount of historical data. To represent the error term, a redundant threshold is set in the early warning decision control module, and the threshold is compared with the calculated traffic flow value. According to different comparison ranges, the early warning decision control module triggers different levels of early warning mechanisms and generates corresponding traffic diversion decision suggestions; The data analysis module is provided with machine learning algorithms and data mining techniques for data processing. First, data cleaning techniques are used to remove noise and missing values to ensure data quality. Then, feature engineering techniques are used to extract features from the collected raw data, including converting time series data into frequency domain features. For model training, a long short-term memory network (LSTM) deep learning model is used to capture the time dependency in the data. For the LSTM model, the output prediction value is calculated by the following formula: in: represents the predicted value of the output, represents the hidden state of LSTM at time t, represents the weight matrix, represents the bias term, represents the Sigmoid activation function, Represents input features The weight of represents the overall bias; The data analysis module combines cluster analysis and classification algorithms to classify and identify traffic flow patterns in different sections and time periods. In the LSTM model evaluation stage, cross-validation and mean square error (MSE) indicator evaluation techniques are used to help select the optimal model parameters and algorithms. The data analysis module will transmit the extracted feature data to the comprehensive analysis module; The special event monitoring module is provided with web crawler technology and natural language processing algorithm. By setting keywords and rules, the crawler program searches the Internet for web pages, news and social media information related to special events in the city. For the acquired text data, the natural language processing technology is used to perform semantic analysis and keyword extraction to determine the key information of the type, time, location and scale of the event. The special event monitoring module also screens and filters in combination with geographic location information and time information to ensure that the acquired special events are related to the traffic conditions of the city. The historical data storage module stores traffic flow data, road condition information, weather data, and special event record data for a period of time in the past. The historical data storage module adopts a distributed storage architecture and data compression technology, and uses the Hadoop HDFS distributed database system to store a large amount of historical traffic data in multiple nodes in a dispersed manner, thereby improving the storage capacity and access performance of the data. For data compression, the Gzip lossless compression algorithm is used to reduce the data storage space without losing data accuracy. At the same time, in order to facilitate data query and analysis, a hash index structure is established, which can quickly locate and retrieve the required data. The historical data storage module interacts with the comprehensive analysis module in real time; The comprehensive analysis module is capable of receiving data transmitted by the data analysis module and interacting with the historical data storage module in real time. The comprehensive analysis module constructs a mathematical model. When the comprehensive analysis module is preparing to train the mathematical model, it extracts the required data from the historical data storage module. The data include multi-dimensional information such as traffic flow values arranged in chronological order, corresponding weather conditions, types and occurrence times of special events, and the degree of road congestion. The mathematical model comprehensively considers the impact of multiple factors on traffic flow. The input of the mathematical model includes data from the data acquisition module, the road condition monitoring module, the weather data acquisition module, and the special event monitoring module. The mathematical model uses a multivariate nonlinear regression method to calculate the traffic flow value data; During the analysis process, the comprehensive analysis module first standardizes the input data to make it have the same dimension and distribution, then substitutes the standardized data into the model for calculation to obtain the predicted traffic flow value, then, by comparing with historical data of the same period and empirical data under similar conditions, the predicted results are corrected and optimized, and finally, the optimized predicted results are output to the early warning decision-making and control module; The early warning decision-making and control module can receive the prediction result data provided by the comprehensive analysis module. The early warning decision-making and control module sets multiple threshold ranges. The specific analysis and comparison categories are as follows: when When , no warning is triggered; when , a mild warning is triggered, and the system recommends adding traffic diversion personnel appropriately; when , a moderate warning is triggered, and the system recommends adjusting the timing of traffic lights and activating some backup roads; when , a severe warning is triggered, and the system recommends implementing traffic control and vehicle diversion measures; in: It represents the normal traffic flow value input by the management personnel; The warning decision-making and control module selects corresponding response measures from a pre-established strategy library according to the warning level. During the implementation of the measures, it monitors changes in traffic conditions in real time and evaluates the effectiveness of the measures. When the results are not ideal, the strategy will be adjusted in real time.
2. According to the big data-based smart city data control system of claim 1, it is characterized by: In the data acquisition module, the geomagnetic sensor uses changes in the geomagnetic field to detect vehicles, and determines the presence and direction of the vehicle by changes in the magnetic field strength. It also samples data at a high frequency to ensure the timeliness of the data. The camera uses an optical character recognition (OCR) algorithm to automatically identify the type and license plate information of the vehicle. The microwave radar measures the speed and distance of the vehicle by emitting electromagnetic waves and receiving reflected waves. The collected data is preliminarily screened and filtered to remove obvious outliers and erroneous data, and then transmitted to the data analysis module via the 5G network.
3. According to the data control system for smart cities based on big data as described in claim 1, it is characterized by: The road condition monitoring module sets high-definition cameras on various traffic sections to obtain real-time road video images, and then uses deep learning algorithms to analyze the video images frame by frame to identify the vehicle's driving status, congestion areas and possible accident signs. For the judgment of the vehicle's driving status, whether there is congestion is determined by detecting the vehicle's speed, spacing and driving trajectory. In congestion detection, the road is divided into different areas using image segmentation technology, and the density and residence time of vehicles in each area are calculated. For the identification of accident signs, the abnormal behavior of the vehicle, including sudden braking and collision, is identified through training models. The road condition monitoring module updates the monitored road condition information in real time, and the road condition monitoring module transmits the monitored traffic road condition data to the data analysis module.
4. According to the data control system for smart cities based on big data as claimed in claim 1, it is characterized by: The weather data acquisition module is implemented by establishing a stable data interface with the meteorological department, and uses the HTTP network communication protocol to send a request to the server of the meteorological department to obtain real-time weather data of the specified area. After receiving the real-time weather data of the specified area, the weather data acquisition module will convert and parse the data format and extract key information related to traffic flow forecasting, including rainfall, temperature, humidity, wind speed, wind direction and visibility information data. The weather data acquisition module adopts a data verification and error correction mechanism, which can check the rationality of the received data to ensure the accuracy and completeness of the data. At the same time, in order to cope with the update of meteorological data, the module sets a scheduled task to automatically obtain the latest weather information every 30 minutes.
5. The data control system for smart cities based on big data according to claim 1, characterized in that: The central control module enjoys the highest control authority of the system, which is equivalent to the computer end of the smart city manager. The central control module can control and edit the data collection frequency of the data collection module, the central control module can control and edit the frequency of the weather data acquisition module acquiring weather information, the central control module can edit the parameters of the calculation formula of the data analysis module, the central control module can edit the function parameters of the comprehensive analysis module, and the central control module can edit the normal traffic flow value in the early warning decision-making and control module.
Citation Information
Patent Citations
Intersection traffic flow prediction system based on automobile electronic signs
CN107038877A
Fault prediction method for adaptive threshold of refrigeration equipment based on multi-algorithm fusion
CN110689075A
Expressway congestion management and control system based on multi-source data
CN113538898A
Internet-of-things traffic monitoring system in intelligent traffic system and use method of Internet-of-things traffic monitoring system
CN114170795A
Intelligent traffic monitoring method and device based on multi-modal data fusion and graph neural network, and electronic equipment
CN118366311A
