Intelligent traffic jam real-time analysis method, system and device based on multi-dimensional spatial geographic features and medium

Abstract

The invention provides an intelligent traffic jam real-time analysis method, system, device and medium based on multi-dimensional spatial geographic features, and belongs to the technical field of intelligent traffic, and the method comprises the following steps: collecting traffic data through combining non-traditional and traditional data collection devices, and transmitting the traffic data to a rear-end data center; the data center adopts a distributed computing framework to clean and integrate data, performs quality control, extracts multi-dimensional spatial features by using a GIS (Geographic Information System), calculates a congestion index and predicts a traffic congestion trend at the same time; and the back-end data center issues real-time congestion conditions and prediction trends through non-traditional and traditional data issuing channels, and pushes personalized congestion planning suggestions according to travel habits of users. According to the invention, a complete intelligent traffic jam real-time analysis solution is formed, the traffic jam problem is effectively relieved, and the intelligent level of traffic management is improved.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent transportation technology, and specifically relates to an intelligent traffic congestion real-time analysis method, system, equipment and medium based on multi-dimensional spatial geographical features. Background Art

[0002] The intelligent transportation system integrates advanced information technology, communication technology, sensor technology and automatic control technology, and is a comprehensive system aimed at improving the efficiency, safety, environmental protection and comfort of transportation.

[0003] Existing intelligent transportation systems mostly rely on traditional sensor detection technology or video image recognition technology. Although these methods can reflect traffic congestion to a certain extent, they have limitations in data dimension, analysis accuracy and real-time performance. The specific manifestations are as follows: First, the data dimension is single. Traditional methods usually only focus on a single traffic parameter, such as vehicle speed or traffic flow, and cannot fully reflect the real situation of traffic congestion. For example, although vehicle speed data can indicate the degree of traffic smoothness, it cannot reflect the specific location, cause and change trend of congestion. Second, the analysis accuracy is insufficient. Due to the limitation of data dimension, traditional methods often have large errors and uncertainties when analyzing traffic congestion. For example, sensor failure or data loss may lead to inaccurate analysis results, affecting the effectiveness of traffic management decisions. Third, the lack of real-time performance. Traditional methods usually have traffic delays when processing and analyzing traffic data, and cannot reflect traffic congestion in real time, which makes it difficult for traffic management departments to take effective measures to alleviate congestion in a timely manner, and drivers cannot obtain the latest traffic information to plan the best driving route.

[0004] In summary, in the complex and ever-changing urban traffic environment, single-dimensional data is difficult to fully reflect the real situation of traffic congestion. Summary of the invention

[0005] In a first aspect, an embodiment of the present application provides a method for real-time analysis of intelligent traffic congestion based on multi-dimensional spatial geographic features, comprising the following steps: S1. Introduce non-traditional data collection equipment and collect traffic data simultaneously with traditional data collection equipment, and build a transmission communication network to transmit the collected traffic data to the back-end data center; S2. The back-end data center uses a distributed computing framework to clean the traffic data and then integrate the multi-source data, and performs quality control on the integrated data to obtain processed data; S3. The back-end data center uses the GIS system to extract multidimensional spatial features from the processed data, calculates the congestion index based on the extracted multidimensional spatial features and uses the pre-built congestion index calculation model, and uses the big data analysis algorithm to analyze the traffic data and predict traffic congestion trends; S4. The back-end data center introduces non-traditional data release channels, and publishes the congestion index that represents the real-time congestion situation and the predicted traffic congestion trend on non-traditional data release channels and traditional data release channels simultaneously, and generates congestion planning suggestions for each user based on the user's travel habits and pushes them to the user.

[0006] Furthermore, the specific steps of step S1 are as follows: S11. Introducing user mobile terminals and social media servers as non-traditional data collection devices; S12. Collecting user location change information in mobile signaling data through the user's mobile terminal; S13. Obtaining traffic information in social media data through a social media server; S14. Collecting vehicle real-time operation data, driver operation behavior data and CAN bus data through the vehicle terminal as a traditional data acquisition device; S15. Collect vehicle count data, vehicle speed data and vehicle position data through roadside sensors as traditional data collection equipment; S16. Collecting traffic flow information, single vehicle tracking data, and traffic incident detection data within a set area through drones as traditional data collection equipment; S17. Using the optical fiber network as the backbone network and the wireless network as the auxiliary network, non-traditional data acquisition equipment and traditional data acquisition equipment are connected to the backbone network through the Ethernet interface as needed, or connected to the auxiliary network through the wireless communication interface; S18. Use the backbone network and auxiliary network to build a transmission communication network to transmit the collected traffic data to the back-end data center.

[0007] Furthermore, the specific steps of step S2 are as follows: S21. The central processing node of the backend data center divides the traffic data by type and assigns a distributed processing node to each type of traffic data for cleaning; S22. The central processing node standardizes the traffic data cleaned by each distributed processing node, and uses a unique identifier to match and associate, and establishes a logical relationship between traffic data of different types; S23. The central processing node fuses the associated traffic data of various types using a weighted average algorithm, and performs a data range check during the fusion process; If a certain type of traffic data exceeds the preset data range, proceed to step S24; If all types of traffic data are within the preset data range, proceed to step S3; S24. The central processing node corrects the traffic data of this type and then integrates it.

[0008] Furthermore, the specific steps of step S3 are as follows: S31. The back-end data center uses the GIS system to combine traffic flow information, changes in vehicle speed data, and vehicle location data to extract multi-dimensional spatial features involving the spatial topological structure of the road network, vehicle density distribution, and speed change patterns; S32. The back-end data center constructs a congestion index calculation model in advance based on the change parameters of road capacity, traffic flow information, and vehicle speed data in the existing road network spatial topology structure, and optimizes it using the historical data of the extracted multi-dimensional spatial features; S33. The backend data center inputs the multi-dimensional spatial features extracted in real time into the optimized congestion index calculation model, calculates the real-time congestion index, and quantifies the traffic congestion status; S34. The back-end data center uses machine learning algorithm models to analyze real-time traffic data and predict traffic congestion trends.

[0009] Furthermore, the specific steps of step S32 are as follows: S321. Pre-construct the traffic congestion index calculation model as follows: CI= α × (Q / C) + β × (1 / V) + γ × D Among them, CI is the traffic congestion index, Q is the actual traffic flow, C is the road capacity, V is the vehicle speed, D is the vehicle density, α, β, γ are the preset weight coefficients; S322. Input the historical multi-dimensional spatial feature data into the constructed traffic congestion index calculation model to verify the matching degree between the actual congestion situation and the traffic congestion index; If they match, go to step S33; If not matched, go to step S323; S323. According to the difference in matching degree between the actual congestion situation and the traffic congestion index, adjust the preset weight coefficients α, β, γ, and return to step S322.

[0010] Furthermore, the specific steps of step S34 are as follows: S341. Pre-select a feature whose correlation with the congestion index is greater than a threshold from the multidimensional space features as an input feature x; S342. Use the support vector regression model to construct a traffic congestion prediction model in advance as follows: The objective function is:

[0011] Among them, w is the mass vector, C is the regularization parameter, and is a slack variable that allows users to handle situations where data points deviate from the regression line; The constraints are as follows:

[0012] in, is the congestion index, is a multidimensional space feature, is the parameter of the insensitive loss function, and b is the bias term; The prediction formula is as follows:

[0013] in, It is the predicted congestion index; S343. Divide the historical multidimensional spatial feature data into a training set and a test set; S344. Use the training set to train the support vector regression model and adjust the regularization parameter C and the insensitive loss function parameter during the training process Perform support vector regression model optimization on the model; S345. Use cross-validation to evaluate the performance of the support vector regression model on the test set, obtain the optimal model parameters, and then determine the traffic congestion prediction model; S346. Input the multi-dimensional spatial features in the real-time traffic data into the traffic congestion prediction model to predict the traffic congestion index.

[0014] Furthermore, the specific steps of step S4 are as follows: S41. Introduce social media servers and smart speakers as non-traditional data distribution channels; S42. The backend data center publishes the real-time congestion index and the predicted congestion index on the vehicle terminal, user mobile terminal APP, traffic guidance screen and non-traditional data release channels as traditional data release channels; S43. The backend data center obtains the historical data of user travel, extracts the user's travel frequency, travel time distribution, and route preference to generate user preferences; S44. The back-end data center compares the user's deviation with the real-time congestion index, identifies the target travel scenario that may be affected by congestion, generates congestion planning suggestions for the target travel scenario, and pushes the congestion planning suggestions to the user.

[0015] In a second aspect, the embodiment of the present application further provides an intelligent real-time traffic congestion analysis system based on multi-dimensional spatial geographic features, including: Data collection module, used to introduce non-traditional data collection equipment and collect traffic data simultaneously with traditional data collection equipment, and build a transmission communication network to transmit the collected traffic data to the back-end data center; The data processing module is used to clean the traffic data using a distributed computing framework in the back-end data center and then integrate the multi-source data, and perform quality control on the integrated data to obtain processed data; The analysis and decision-making module is used to extract multi-dimensional spatial features of the processed data using the GIS system in the back-end data center, calculate the congestion index based on the extracted multi-dimensional spatial features and using the pre-built congestion index calculation model, and use the big data analysis algorithm to analyze the traffic data and predict the traffic congestion trend; The information release module is used to introduce non-traditional data release channels in the back-end data center, and publish the congestion index that represents the real-time congestion situation and the predicted traffic congestion trend on the non-traditional data release channel and the traditional data release channel at the same time, and generate congestion planning suggestions for each user based on the user's travel habits and push them to the user.

[0016] In a third aspect, an embodiment of the present application further provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the program, the steps of the real-time analysis method for intelligent traffic congestion based on multi-dimensional spatial geographic features as described in the first aspect are implemented.

[0017] In a fourth aspect, an embodiment of the present application further provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the real-time analysis method for intelligent traffic congestion based on multi-dimensional spatial geographic features as described in the first aspect.

[0018] It can be seen from the above technical solutions that the present invention has the following advantages: In the intelligent traffic congestion real-time analysis method, system, device and medium based on multi-dimensional spatial geographic features provided by the present application, by introducing non-traditional data acquisition equipment and combining it with traditional equipment, diversified and real-time collection of traffic data is realized, providing a reliable data basis for subsequent data processing and analysis; the distributed computing framework and quality control process are adopted to effectively improve the efficiency and accuracy of data processing, and provide high-quality data input for subsequent multi-dimensional spatial feature extraction and congestion index calculation; the GIS system and big data analysis algorithm are used to realize real-time quantification and trend prediction of traffic congestion, providing scientific decision-making basis for traffic management departments and drivers, and helping to alleviate traffic congestion problems; through non-traditional data release channels and personalized congestion planning suggestions, the timeliness and pertinence of information release are improved, and the user experience is effectively improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solution of the present invention, the accompanying drawings required for use in the description will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0020] Figure 1 The invention provides a process for the intelligent real-time analysis method of traffic congestion based on multi-dimensional spatial geographic features.

[0021] Figure 2 It is a schematic diagram of the intelligent traffic congestion real-time analysis system based on multi-dimensional spatial geographical features of the present invention. DETAILED DESCRIPTION

[0022] In the specific steps of the intelligent traffic congestion real-time analysis method based on multi-dimensional spatial geographic features, which will be described in detail below, various embodiments of the present disclosure will be described more comprehensively. The present disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present disclosure to the specific embodiments disclosed herein, but the present disclosure should be understood to cover all adjustments, equivalents and / or alternatives that fall within the spirit and scope of the various embodiments of the present disclosure.

[0023] For example, the intelligent transportation system is a comprehensive system that integrates cutting-edge information technology, communication technology, sensor technology and automatic control technology. Its core goal is to improve the efficiency, safety, environmental protection performance and riding comfort of the transportation system.

[0024] At present, intelligent transportation systems mainly rely on traditional sensor detection technology and video image recognition technology. Although these technologies can reveal the situation of traffic congestion to a certain extent, they still show obvious limitations in terms of data richness, analysis accuracy and real-time information. Specifically: First, the dimension of the data is relatively single. Traditional monitoring methods often focus on a single traffic indicator such as vehicle speed or traffic flow, which makes it difficult for them to fully and accurately depict the overall picture of traffic congestion. For example, although vehicle speed data can reflect the smoothness of traffic, it cannot accurately point out the specific location, cause and future development trend of congestion. Secondly, the accuracy of analysis needs to be improved. Due to the limitations of data dimensions, traditional analysis methods are often accompanied by large errors and uncertainties when interpreting traffic congestion. For example, sensor failure or data loss may cause deviations in analysis results, thereby weakening the effectiveness and accuracy of traffic management decisions. Finally, the real-time nature of information is also insufficient. When processing and analyzing traffic data, traditional methods often have a certain lag, which makes them unable to reflect the current traffic congestion situation in a timely manner. This lag not only makes it difficult for traffic management departments to take effective measures to alleviate congestion in a timely manner, but also prevents drivers from obtaining the latest traffic information to plan the best driving route. In summary, in the complex and changing urban traffic environment, it is obviously far from enough to rely solely on single-dimensional data to reveal the true situation of traffic congestion.

[0025] In response to the above problems, this embodiment provides an intelligent real-time analysis method for traffic congestion based on multi-dimensional spatial geographic features. The method can realize comprehensive, real-time and accurate monitoring and analysis of traffic congestion status, provide scientific decision-making support and real-time traffic information for traffic management departments and drivers, help improve traffic efficiency, alleviate traffic congestion problems, and enhance users' travel experience.

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 are within the scope of protection of the present invention.

[0027] See also Figure 1 FIG. 1 is a flow chart of a method for real-time intelligent traffic congestion analysis based on multi-dimensional spatial geographic features in a specific embodiment, the method comprising: S1. Introduce non-traditional data collection equipment and collect traffic data simultaneously with traditional data collection equipment, and build a transmission communication network to transmit the collected traffic data to the back-end data center; It should be noted that more traffic behavior information can be obtained by introducing non-traditional data collection equipment, and the transmission communication network can quickly transmit traffic data to the back-end data center to ensure the timeliness and integrity of the data; S2. The back-end data center uses a distributed computing framework to clean the traffic data and then integrate the multi-source data, and performs quality control on the integrated data to obtain processed data; It should be noted that the distributed computing framework enables rapid processing of massive traffic data; S3. The back-end data center uses the GIS system to extract multidimensional spatial features from the processed data, calculates the congestion index based on the extracted multidimensional spatial features and uses the pre-built congestion index calculation model, and uses the big data analysis algorithm to analyze the traffic data and predict traffic congestion trends; S4. The backend data center introduces non-traditional data release channels, and publishes the congestion index and predicted traffic congestion trend that represent the real-time congestion situation on non-traditional data release channels and traditional data release channels at the same time, and generates congestion planning suggestions for each user based on the user's travel habits and pushes them to the user; It should be noted that the introduction of non-traditional data release channels ensures new coverage and dissemination speed.

[0028] This embodiment improves the diversity and comprehensiveness of data collection by introducing non-traditional data collection equipment and combining it with traditional equipment, builds a real-time and efficient data transmission network, and provides a rich and accurate data foundation for back-end analysis.

[0029] Further, as a refinement and extension of the specific implementation of the above embodiment, in order to fully illustrate the specific implementation process in this embodiment, another intelligent traffic congestion real-time analysis method based on multi-dimensional spatial geographic features is provided, and the method includes the following steps: S1. Introduce non-traditional data collection equipment and collect traffic data simultaneously with traditional data collection equipment, build a transmission communication network to transmit the collected traffic data to the back-end data center; the specific steps of step S1 are as follows: S11. Introducing user mobile terminals and social media servers as non-traditional data collection devices; S12. Collecting user location change information in mobile signaling data through the user's mobile terminal; Specifically, mobile phone signaling data records the user's location change information, reflecting the user's approximate movement trajectory in the urban space; through the continuous tracking and processing of massive mobile phone signaling data, the user's starting and ending locations at different time periods can be calculated, and then the starting and ending point matrix of the trip can be constructed, revealing the key information such as the flow patterns, travel habits and transportation needs of large-scale people; S13. Obtaining traffic information in social media data through a social media server; S14. Collecting vehicle real-time operation data, driver operation behavior data and CAN bus data through the vehicle terminal as a traditional data acquisition device; Specifically, the real-time vehicle operation data may include latitude and longitude, speed, direction, and instrument information, which can provide the vehicle's driving status and trajectory; the driving source operation behavior data may include braking, acceleration, door opening and other driving operations, which can be used to evaluate the driver's driving behavior and safety; CAN bus data is the data of the vehicle engine, instrument, brake and other systems collected through the CAN bus interface of the vehicle terminal; S15. Collect vehicle count data, vehicle speed data and vehicle position data through roadside sensors as traditional data collection equipment; S16. Collecting traffic flow information, single vehicle tracking data, and traffic incident detection data within a set area through drones as traditional data collection equipment; Specifically, the traffic flow information within the set area may include traffic density, traffic volume, and traffic speed; when detecting traffic time data, the high-definition camera and computer vision technology carried by the drone can be used to conduct real-time monitoring and identify traffic accidents, congestion and other traffic events, providing timely and accurate warning information for the traffic management department; S17. Using the optical fiber network as the backbone network and the wireless network as the auxiliary network, non-traditional data acquisition equipment and traditional data acquisition equipment are connected to the backbone network through the Ethernet interface as needed, or connected to the auxiliary network through the wireless communication interface; S18. Use the backbone network and auxiliary network to build a transmission communication network to transmit the collected traffic data to the back-end data center; It should be noted that through traditional and non-traditional data acquisition equipment, the diversity and real-time nature of the data are ensured, providing a reliable data source for subsequent data processing and analysis; S2. The back-end data center uses a distributed computing framework to clean the traffic data and then integrate the multi-source data, and performs quality control on the integrated data to obtain processed data; the specific steps of step S2 are as follows: S21. The central processing node of the backend data center divides the traffic data by type and assigns a distributed processing node to each type of traffic data for cleaning; S22. The central processing node standardizes the traffic data cleaned by each distributed processing node, and uses a unique identifier to match and associate, and establishes a logical relationship between traffic data of different types; Specifically, standardization processing includes data format, timestamp alignment, unit unification, etc., to ensure the logical consistency of data; the unique identifier can be a vehicle ID or geographic location coordinates; S23. The central processing node fuses the associated traffic data of various types using a weighted average algorithm, and performs a data range check during the fusion process; Specifically, the data fusion algorithm may also be a Kalman filter method or a Bayesian network algorithm; If a certain type of traffic data exceeds the preset data range, proceed to step S24; If all types of traffic data are within the preset data range, proceed to step S3; S24. The central processing node corrects the traffic data of this type and then fuses it; Specifically, data correction can be difference or smoothing processing; It should be noted that the distributed computing framework and quality control process effectively improve the efficiency and accuracy of data processing, providing high-quality data input for subsequent multi-dimensional spatial feature extraction and congestion index calculation; S3. The back-end data center uses the GIS system to extract multidimensional spatial features from the processed data, calculates the congestion index based on the extracted multidimensional spatial features and using the pre-built congestion index calculation model, and uses the big data analysis algorithm to analyze the traffic data and predict the traffic congestion trend; the specific steps of step S3 are as follows: S31. The back-end data center uses the GIS system to combine traffic flow information, changes in vehicle speed data, and vehicle location data to extract multi-dimensional spatial features involving the spatial topological structure of the road network, vehicle density distribution, and speed change patterns; S32. The back-end data center constructs a congestion index calculation model in advance based on the change parameters of road capacity, traffic flow information, and vehicle speed data in the existing road network spatial topology structure, and optimizes it using the historical data of the extracted multi-dimensional spatial features; S33. The backend data center inputs the multi-dimensional spatial features extracted in real time into the optimized congestion index calculation model, calculates the real-time congestion index, and quantifies the traffic congestion status; S34. The backend data center uses machine learning algorithm models to analyze real-time traffic data and predict traffic congestion trends; It should be noted that the use of GIS system and big data analysis algorithms has achieved real-time quantification and trend prediction of traffic congestion, providing a scientific basis for decision-making for traffic management departments and drivers; S4. The backend data center introduces a non-traditional data release channel, and releases the congestion index representing the real-time congestion situation and the predicted traffic congestion trend on the non-traditional data release channel and the traditional data release channel at the same time, and generates congestion planning suggestions for each user based on the user's travel habits and pushes them to the user; the specific steps of step S4 are as follows: S41. Introduce social media servers and smart speakers as non-traditional data distribution channels; S42. The backend data center publishes the real-time congestion index and the predicted congestion index on the vehicle terminal, user mobile terminal APP, traffic guidance screen and non-traditional data release channels as traditional data release channels; S43. The backend data center obtains the historical data of user travel, extracts the user's travel frequency, travel time distribution, and route preference to generate user preferences; S44. The backend data center compares the user's deviation with the real-time congestion index, identifies the target travel scenario that may be affected by congestion, generates congestion planning suggestions for the target travel scenario, and pushes the congestion planning suggestions to the user; It should be noted that the use of non-traditional data release channels and personalized congestion planning suggestions has improved the timeliness and pertinence of information release, effectively alleviated traffic congestion problems, and improved user experience.

[0030] In an embodiment of the present invention, based on S32, a possible embodiment is given below to illustrate its specific implementation scheme in a non-limiting manner.

[0031] The specific steps of step S32 are as follows: S321. Pre-construct the traffic congestion index calculation model as follows: CI= α × (Q / C) + β × (1 / V) + γ × D Among them, CI is the traffic congestion index, Q is the actual traffic flow, C is the road capacity, V is the vehicle speed, D is the vehicle density, α, β, γ are the preset weight coefficients; Specifically, the actual traffic flow Q is a representation of the total number of vehicles passing through the road in a specific time period, the road capacity C is a representation of the maximum number of vehicles that the road can accommodate under specific conditions, the vehicle speed V is the average speed of vehicles traveling on the road, and the lower the vehicle speed, the higher the congestion level; the vehicle density D is a representation of the number of vehicles on a unit length of road, and the higher the vehicle density, the higher the congestion level; S322. Input the historical multi-dimensional spatial feature data into the constructed traffic congestion index calculation model to verify the matching degree between the actual congestion situation and the traffic congestion index; If they match, go to step S33; If not matched, go to step S323; S323. According to the difference in matching degree between the actual congestion situation and the traffic congestion index, adjust the preset weight coefficients α, β, γ, and return to step S322.

[0032] In one embodiment of the present invention, based on S34, a possible embodiment is given below to illustrate its specific implementation scheme in a non-limiting manner; It should be noted that, through the construction and optimization process of a specific congestion index calculation model, the accuracy and reliability of the congestion index are ensured, and the precision of traffic congestion analysis is improved.

[0033] The specific steps of step S34 are as follows: S341. Pre-select a feature whose correlation with the congestion index is greater than a threshold from the multidimensional space features as an input feature x; S342. Use the support vector regression model to construct a traffic congestion prediction model in advance as follows: The objective function is:

[0034] Among them, w is the mass vector, C is the regularization parameter, and is a slack variable that allows users to handle situations where data points deviate from the regression line; The constraints are as follows:

[0035] in, is the congestion index, is a multidimensional space feature, is the parameter of the insensitive loss function, and b is the bias term; The prediction formula is as follows:

[0036] in, It is the predicted congestion index; S343. Divide the historical multidimensional spatial feature data into a training set and a test set; S344. Use the training set to train the support vector regression model and adjust the regularization parameter C and the insensitive loss function parameter during the training process Perform support vector regression model optimization on the model; S345. Use cross-validation to evaluate the performance of the support vector regression model on the test set, obtain the optimal model parameters, and then determine the traffic congestion prediction model; S346. Input the multidimensional spatial features in the real-time traffic data into the traffic congestion prediction model to predict the traffic congestion index; It should be noted that the support vector regression model can be used to accurately predict traffic congestion trends, providing strong technical support for traffic management and planning.

[0037] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0038] like Figure 2 As shown, the following is an embodiment of the intelligent traffic congestion real-time analysis system based on multi-dimensional spatial geographic features provided by the embodiment of the present disclosure. The system and the intelligent traffic congestion real-time analysis method based on multi-dimensional spatial geographic features of the above-mentioned embodiments belong to the same inventive concept. For details not described in detail in the embodiment of the intelligent traffic congestion real-time analysis system based on multi-dimensional spatial geographic features, please refer to the embodiment of the intelligent traffic congestion real-time analysis method based on multi-dimensional spatial geographic features.

[0039] The system includes: Data collection module, used to introduce non-traditional data collection equipment and collect traffic data simultaneously with traditional data collection equipment, and build a transmission communication network to transmit the collected traffic data to the back-end data center; The data processing module is used to clean the traffic data using a distributed computing framework in the back-end data center and then integrate the multi-source data, and perform quality control on the integrated data to obtain processed data; The analysis and decision-making module is used to extract multi-dimensional spatial features of the processed data using the GIS system in the back-end data center, calculate the congestion index based on the extracted multi-dimensional spatial features and using the pre-built congestion index calculation model, and use the big data analysis algorithm to analyze the traffic data and predict the traffic congestion trend; The information release module is used to introduce non-traditional data release channels in the back-end data center, and publish the congestion index that represents the real-time congestion situation and the predicted traffic congestion trend on the non-traditional data release channel and the traditional data release channel at the same time, and generate congestion planning suggestions for each user based on the user's travel habits and push them to the user.

[0040] This embodiment improves the diversity and comprehensiveness of data collection by introducing non-traditional data collection equipment and combining it with traditional equipment, builds a real-time and efficient data transmission network, and provides a rich and accurate data foundation for back-end analysis.

[0041] The intelligent traffic congestion real-time analysis method based on multidimensional spatial geographic features provided by the present application can be applied to electronic devices. Those skilled in the art will appreciate that the electronic device structure involved in the embodiment of the present invention does not constitute a limitation on the electronic device, and the electronic device may include more or less components than shown, or combine certain components, or arrange different components. In an embodiment of the present invention, the electronic device includes but is not limited to a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples, and are not intended to limit the implementation of the embodiments of the present application described and / or required herein.

[0042] The electronic device may include a processor, an external memory interface, an internal memory, a universal serial bus (USB) interface, a charging management module, a power management module, a battery, a wireless communication module, an audio module, a speaker, a microphone, a sensor module, buttons, a camera, a display, and a SIM card interface, etc.

[0043] It is to be understood that the structure illustrated in the embodiments of the present application does not constitute a specific limitation on the electronic device. In other embodiments of the present application, the electronic device may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0044] The processor may include one or more processing units, for example, the processor may include a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Among them, different processing units may be independent devices or integrated into one or more processors.

[0045] The processor can be the nerve center and command center of the electronic device. The controller can generate an operation control signal according to the instruction operation code and timing signal to complete the control of fetching and executing instructions.

[0046] A memory may also be provided in the processor for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. The memory may store instructions or data that the processor has just used or is cyclically used. If the processor needs to use the instruction or data again, it may be directly called from the memory. This avoids repeated access, reduces the waiting time of the processor, and thus improves system efficiency.

[0047] The electronic device implements the intelligent real-time analysis method of traffic congestion based on multi-dimensional spatial geographic features of the present application. By combining non-traditional and traditional data collection equipment, the diversified and real-time collection of traffic data is realized. The distributed computing framework and quality control are adopted to improve the efficiency and accuracy of data processing. The use of GIS and big data analysis realizes the real-time quantification and prediction of traffic congestion. Non-traditional data release and personalized suggestions enhance the user experience.

[0048] The storage medium provided in the present application stores a program product that can implement an intelligent real-time analysis method for traffic congestion based on multi-dimensional spatial geographic features.

[0049] The intelligent real-time analysis method of traffic congestion based on multi-dimensional spatial geographic features includes: introducing non-traditional data collection equipment, collecting traffic data simultaneously with traditional data collection equipment, and constructing a transmission communication network to transmit the collected traffic data to a back-end data center; the back-end data center uses a distributed computing framework to clean the traffic data and then integrates multi-source data, and performs quality control on the integrated data to obtain processed data; the back-end data center uses a GIS system to extract multi-dimensional spatial features of the processed data, calculates the congestion index based on the extracted multi-dimensional spatial features and using a pre-built congestion index calculation model, and uses a big data analysis algorithm to analyze the traffic data and predict traffic congestion trends; the back-end data center introduces a non-traditional data release channel, and publishes the congestion index representing the real-time congestion status and the predicted traffic congestion trend on the non-traditional data release channel and the traditional data release channel at the same time, and generates congestion planning suggestions for each user based on the user's travel habits and pushes them to the user.

[0050] In some possible implementations, the intelligent real-time analysis method for traffic congestion based on multi-dimensional spatial geographic features disclosed herein can be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps of various exemplary implementations of the present disclosure described in the above “Exemplary Method” section of this specification.

[0051] The storage medium of the present disclosure can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0052] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A real-time intelligent traffic congestion analysis method based on multi-dimensional spatial geographic features, characterized in that: The steps include: S1. Introduce non-traditional data collection equipment and collect traffic data simultaneously with traditional data collection equipment, and build a transmission communication network to transmit the collected traffic data to the back-end data center; S2. The back-end data center uses a distributed computing framework to clean the traffic data and then integrate the multi-source data, and performs quality control on the integrated data to obtain processed data; S3. The back-end data center uses the GIS system to extract multidimensional spatial features from the processed data, calculates the congestion index based on the extracted multidimensional spatial features and uses the pre-built congestion index calculation model, and uses the big data analysis algorithm to analyze the traffic data and predict traffic congestion trends; S4. The back-end data center introduces non-traditional data release channels, and publishes the congestion index that represents the real-time congestion situation and the predicted traffic congestion trend on non-traditional data release channels and traditional data release channels simultaneously, and generates congestion planning suggestions for each user based on the user's travel habits and pushes them to the user.

2. The intelligent real-time analysis method for traffic congestion based on multi-dimensional spatial geographic features as claimed in claim 1, characterized in that: The specific steps of step S1 are as follows: S11. Introducing user mobile terminals and social media servers as non-traditional data collection devices; S12. Collecting user location change information in mobile signaling data through the user's mobile terminal; S13. Obtaining traffic information in social media data through a social media server; S14. Collecting vehicle real-time operation data, driver operation behavior data and CAN bus data through the vehicle terminal as a traditional data acquisition device; S15. Collect vehicle count data, vehicle speed data and vehicle position data through roadside sensors as traditional data collection equipment; S16. Collecting traffic flow information, single vehicle tracking data, and traffic incident detection data within a set area through drones as traditional data collection equipment; S17. Using the optical fiber network as the backbone network and the wireless network as the auxiliary network, non-traditional data acquisition equipment and traditional data acquisition equipment are connected to the backbone network through the Ethernet interface as needed, or connected to the auxiliary network through the wireless communication interface; S18. Use the backbone network and auxiliary network to build a transmission communication network to transmit the collected traffic data to the back-end data center.

3. The intelligent real-time traffic congestion analysis method based on multi-dimensional spatial geographic features as claimed in claim 1, characterized in that: The specific steps of step S2 are as follows: S21. The central processing node of the backend data center divides the traffic data by type and assigns a distributed processing node to each type of traffic data for cleaning; S22. The central processing node standardizes the traffic data cleaned by each distributed processing node, and uses a unique identifier to match and associate, and establishes a logical relationship between traffic data of different types; S23. The central processing node fuses the associated traffic data of various types using a weighted average algorithm, and performs a data range check during the fusion process; If a certain type of traffic data exceeds the preset data range, proceed to step S24; If all types of traffic data are within the preset data range, proceed to step S3; S24. The central processing node corrects the traffic data of this type and then integrates it.

4. The intelligent real-time analysis method for traffic congestion based on multi-dimensional spatial geographic features as claimed in claim 3, characterized in that: The specific steps of step S3 are as follows: S31. The back-end data center uses the GIS system to combine traffic flow information, changes in vehicle speed data, and vehicle location data to extract multi-dimensional spatial features involving the spatial topological structure of the road network, vehicle density distribution, and speed change patterns; S32. The back-end data center constructs a congestion index calculation model in advance based on the change parameters of road capacity, traffic flow information, and vehicle speed data in the existing road network spatial topology structure, and optimizes it using the historical data of the extracted multi-dimensional spatial features; S33. The backend data center inputs the multi-dimensional spatial features extracted in real time into the optimized congestion index calculation model, calculates the real-time congestion index, and quantifies the traffic congestion status; S34. The back-end data center uses machine learning algorithm models to analyze real-time traffic data and predict traffic congestion trends.

5. The intelligent real-time analysis method for traffic congestion based on multi-dimensional spatial geographic features as claimed in claim 4, characterized in that: The specific steps of step S32 are as follows: S321. Pre-construct the traffic congestion index calculation model as follows: CI= α × (Q / C) + β × (1 / V) + γ × D Among them, CI is the traffic congestion index, Q is the actual traffic flow, C is the road capacity, V is the vehicle speed, D is the vehicle density, α, β, γ are the preset weight coefficients; S322. Input the historical multi-dimensional spatial feature data into the constructed traffic congestion index calculation model to verify the matching degree between the actual congestion situation and the traffic congestion index; If they match, go to step S33; If not matched, go to step S323; S323. According to the difference in matching degree between the actual congestion situation and the traffic congestion index, adjust the preset weight coefficients α, β, γ, and return to step S322.

6. The intelligent real-time analysis method for traffic congestion based on multi-dimensional spatial geographic features as claimed in claim 4, characterized in that: The specific steps of step S34 are as follows: S341. Pre-select a feature whose correlation with the congestion index is greater than a threshold from the multidimensional space features as an input feature x; S342. Use the support vector regression model to construct a traffic congestion prediction model in advance as follows: The objective function is: Among them, w is the mass vector, C is the regularization parameter, and is a slack variable that allows users to handle situations where data points deviate from the regression line; The constraints are as follows: in, is the congestion index, is a multidimensional space feature, is the parameter of the insensitive loss function, and b is the bias term; The prediction formula is as follows: in, It is the predicted congestion index; S343. Divide the historical multidimensional spatial feature data into a training set and a test set; S344. Use the training set to train the support vector regression model and adjust the regularization parameter C and the insensitive loss function parameter during the training process Perform support vector regression model optimization on the model; S345. Use cross-validation to evaluate the performance of the support vector regression model on the test set, obtain the optimal model parameters, and then determine the traffic congestion prediction model; S346. Input the multi-dimensional spatial features in the real-time traffic data into the traffic congestion prediction model to predict the traffic congestion index.

7. The intelligent real-time analysis method for traffic congestion based on multi-dimensional spatial geographic features as claimed in claim 4, characterized in that: The specific steps of step S4 are as follows: S41. Introduce social media servers and smart speakers as non-traditional data distribution channels; S42. The backend data center publishes the real-time congestion index and the predicted congestion index on the vehicle terminal, user mobile terminal APP, traffic guidance screen and non-traditional data release channels as traditional data release channels; S43. The backend data center obtains the historical data of user travel, extracts the user's travel frequency, travel time distribution, and route preference to generate user preferences; S44. The back-end data center compares the user's deviation with the real-time congestion index, identifies the target travel scenario that may be affected by congestion, generates congestion planning suggestions for the target travel scenario, and pushes the congestion planning suggestions to the user.

8. An intelligent real-time traffic congestion analysis system based on multi-dimensional spatial geographic features, characterized in that: include: Data collection module, used to introduce non-traditional data collection equipment and collect traffic data simultaneously with traditional data collection equipment, and build a transmission communication network to transmit the collected traffic data to the back-end data center; The data processing module is used to clean the traffic data using a distributed computing framework in the back-end data center and then integrate the multi-source data, and perform quality control on the integrated data to obtain processed data; The analysis and decision-making module is used to extract multi-dimensional spatial features of the processed data using the GIS system in the back-end data center, calculate the congestion index based on the extracted multi-dimensional spatial features and using the pre-built congestion index calculation model, and use the big data analysis algorithm to analyze the traffic data and predict the traffic congestion trend; The information release module is used to introduce non-traditional data release channels in the back-end data center, and publish the congestion index that represents the real-time congestion situation and the predicted traffic congestion trend on the non-traditional data release channel and the traditional data release channel at the same time, and generate congestion planning suggestions for each user based on the user's travel habits and push them to the user.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the intelligent real-time analysis method for traffic congestion based on multi-dimensional spatial geographic features as described in any one of claims 1 to 7 are implemented.

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 the intelligent real-time analysis method for traffic congestion based on multi-dimensional spatial geographic features as claimed in any one of claims 1 to 7 are implemented.

Images