Intelligent system for processing urban traffic information

Abstract

The invention relates to the technical field of traffic management, and particularly discloses an intelligent system for processing urban traffic information, which is characterized in that a traffic flow sensor and a high-definition camera are deployed to collect data such as traffic flow, vehicle speed and vehicle density of each branch in real time and transmit the data to a central platform; the system comprehensively analyzes the logicality and credibility of the data through the data accuracy evaluation module to ensure the accuracy of the data; then, the congestion analysis module calculates the congestion coefficient of each branch based on the accurate data, and judges whether congestion occurs or not and classifies the congestion; the evacuation capability analysis module evaluates the evacuation capability of the congestion branches, and finally the branch division and processing module divides the branches into easy evacuation and difficult evacuation according to the evacuation capability, and adopts different management measures, such as improvement of monitoring frequency, early warning and adjustment of signal control, so as to realize intelligent traffic management and quick response.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic management, and in particular to an intelligent system for processing urban traffic information. Background Art

[0002] With the continuous acceleration of urbanization, traffic management faces more and more challenges. Traditional traffic management methods often rely on static data or low-frequency traffic monitoring, which cannot capture the dynamic changes of traffic flow in a timely manner, resulting in delayed decision-making and inability to effectively alleviate traffic pressure. In addition, with the development of Internet of Things technology, various data collection methods such as sensors, cameras, and mobile devices have been widely used in traffic information collection, but the data collected by these devices may be interfered by various factors, resulting in problems with the timeliness, accuracy, and credibility of the data, which makes a single data analysis method insufficient to effectively evaluate traffic conditions.

[0003] However, there are still some challenges in practical applications. The accuracy and reliability of data collection is a key issue. Traditional traffic flow sensors and cameras may have problems such as data loss and false alarms, which affect the quality of data. In addition, data processing and analysis capabilities need to be further improved to achieve more accurate traffic condition assessment and prediction. Although some existing intelligent transportation systems can collect large amounts of data, they are insufficient in the logic and credibility assessment of the data, which affects the accuracy of the data analysis results. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent system for processing urban traffic information to solve the above-mentioned problems.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] An intelligent system for processing urban traffic information, comprising:

[0007] A data collection module, wherein the data collection module is used to obtain traffic flow data of each branch road;

[0008] Among them, traffic flow data include: vehicle volume, vehicle speed and vehicle density;

[0009] A data accuracy evaluation module, which is used to comprehensively analyze the logic and credibility of the acquired traffic flow data, evaluate the accuracy of the traffic flow data, and extract accurate traffic flow data based on the evaluation results;

[0010] A congestion analysis module, which is used to further analyze the accurate traffic flow data, calculate the congestion coefficient of each branch road, determine whether each branch road is congested, and divide each branch road into a congested branch road and a non-congested branch road according to the determination result;

[0011] An evacuation capacity analysis module, which is based on congested branches and calculates a congestion impact factor according to the congestion situation of each branch, and evaluates the evacuation capacity of each branch according to the congestion impact factor;

[0012] A branch division and processing module, which divides each branch into an easy-to-evacuate branch and a difficult-to-evacuate branch according to the evaluation results. Based on the easy-to-evacuate branch, no evacuation intervention is performed, the monitoring frequency is increased, and based on the difficult-to-evacuate branch, an early warning is issued and the signal control is adjusted.

[0013] As a further solution of the present invention: the comprehensive analysis of the logic and credibility of the acquired traffic flow data to evaluate the accuracy of the traffic flow data specifically includes:

[0014] Get the actual number of vehicles on the branch road within time t;

[0015] The vehicle density of the branch road is calculated according to the acquired traffic flow data, and the expected number of vehicles on the branch road is calculated according to the vehicle density of the branch road;

[0016] Processing the actual number and expected number of vehicles on the branch road, calculating the logical coefficient between the actual number and expected number of vehicles on the branch road;

[0017] The calculation expression of the logic coefficient is:

[0018]

[0019] Where, L t represents the logical coefficient, n represents the total number of acquisition time points, t represents the acquisition time point, Qy t represents the expected number of vehicles on the branch road within time t, Q t represents the actual number of vehicles on the branch road within time t;

[0020] Use fuzzy logic algorithm to process traffic flow data and calculate the credibility coefficient;

[0021] Comprehensively analyze the logic coefficient of traffic flow data and the credibility deviation coefficient of traffic flow data, perform normalization processing, and calculate the accuracy coefficient;

[0022] Based on the comparison between the obtained accuracy coefficient and the accuracy coefficient threshold, it is determined whether the traffic flow data is accurate.

[0023] As a further solution of the present invention: the process of obtaining the credibility coefficient is:

[0024] Determine the input variables including: the actual number of vehicles on the branch road at time t, Q t , the average speed of vehicles on the branch road V t and the density of vehicles on the branch road D t ;

[0025] Define fuzzy logic for each input variable, including low, medium, and high;

[0026] Build fuzzy rule base;

[0027] According to the actual traffic flow data, each input variable is fuzzified to obtain their membership in each fuzzy set;

[0028] Use fuzzy reasoning method to reason according to the rule base and calculate the output fuzzy set;

[0029] Use the centroid method to defuzzify the inference result to get the final output value, and calculate the ratio of the output value to the input value to get the credibility offset coefficient DC t ;

[0030] The calculation expression of the output value is:

[0031]

[0032] In the formula, C represents the output value, x represents the input variable, and μ(x) represents the membership degree of the input variable x to the fuzzy set.

[0033] As a further solution of the present invention: the further analysis of accurate traffic flow data to calculate the congestion coefficient of each branch road specifically includes:

[0034] Use the elbow rule and silhouette coefficient to determine the number of clusters k;

[0035] Select k traffic flow data points as initial cluster centers;

[0036] For each traffic flow data point y i , calculate the traffic flow data point y i With each cluster center z j The Euclidean distance is calculated as:

[0037]

[0038] In the formula, i represents the number of data points, j represents the number of cluster centers, k represents the number of clusters, m represents the maximum number of clusters, and dij Represents traffic flow data point y i With each cluster center z j The Euclidean distance, y ik represents the kth eigenvalue of each traffic flow data point, z jk represents the cluster center z j The kth eigenvalue of ;

[0039] Assign the traffic flow data point to the nearest cluster center, according to the traffic flow data point y i With each cluster center z j The shortest Euclidean distance is used for allocation;

[0040] Calculate the mean of all traffic flow data points in each cluster and update the cluster center;

[0041] Repeat the allocation and update of traffic flow data points until the cluster center no longer changes;

[0042] After completing the k-means clustering, the congestion coefficient is calculated for each cluster. The calculation expression is:

[0043]

[0044] In the formula, S j represents the congestion coefficient of cluster j, D j represents the mean vehicle density in cluster j, D max Indicates the maximum allowable vehicle density of the corresponding branch, V j represents the average speed in cluster j, V m The preset target speed.

[0045] As a further solution of the present invention: the determining whether each branch road is congested specifically includes:

[0046] Determine the congestion coefficient S of each branch j Is it greater than or equal to the preset congestion coefficient threshold? If so, it is recorded as a congested branch; if not, it is recorded as a non-congested branch.

[0047] As a further solution of the present invention: the congestion impact factor is calculated based on the congested branches according to the congestion situation of each branch, specifically including:

[0048] Obtain the congestion coefficient and vehicle density of each congested branch road;

[0049] For each branch, the congestion coefficient is multiplied by the vehicle density and the ratio is calculated with the maximum allowable speed of the branch to obtain the congestion impact factor F. a :

[0050] Wherein, a represents the number of branches.

[0051] As a further solution of the present invention: according to the congestion impact factor, the evacuation capacity of each branch is evaluated, which specifically includes:

[0052] For each branch, the evacuation capacity of each branch is calculated according to the congestion impact factor. The calculation expression is:

[0053]

[0054] In the formula, EA a represents the evacuation capacity of the a-th branch, F a represents the congestion impact factor of the a-th branch, T is the preset impact threshold, and e is the base of the natural logarithm;

[0055] Determine the evacuation capacity of each branch EA a Are they all greater than or equal to the preset evacuation capacity threshold? If so, it is recorded as an easy evacuation branch; if not, it is recorded as a difficult evacuation branch.

[0056] As a further solution of the present invention: based on the easy evacuation branch, no evacuation intervention is performed, the monitoring frequency is increased, and based on the difficult evacuation branch, an early warning is performed and the signal control is adjusted, which specifically includes:

[0057] Based on the easy-to-evacuate branch roads, no evacuation intervention will be carried out, and the monitoring frequency of traffic flow data on the easy-to-evacuate branch roads will be increased to ensure the latest traffic flow data is obtained in real time;

[0058] and continue to use existing traffic signal control strategies;

[0059] Based on difficult evacuation branches, monitor the real-time traffic conditions of difficult evacuation branches, and immediately send warning information to the traffic management center when congestion or abnormal conditions are found;

[0060] Adjust traffic signal cycles in real time based on current traffic flow and congestion conditions;

[0061] Dynamically adjust the signals on main roads or evacuation directions with priority.

[0062] Beneficial effects of the present invention:

[0063] (1) The present invention uses a comprehensive data accuracy assessment module and fuzzy logic algorithm to strictly evaluate and correct the logic and credibility of traffic flow data, ensuring the high accuracy and real-time nature of the data. This sophisticated data processing flow provides a solid foundation for the subsequent congestion analysis module and evacuation capacity analysis module, enabling it to comprehensively and accurately evaluate the traffic conditions of each branch road, thereby providing a scientific and accurate decision-making basis for traffic signal control and evacuation strategy adjustment; by dynamically adjusting the signal cycle and optimizing the evacuation strategy, the present invention effectively alleviates traffic congestion, improves the road's traffic capacity and evacuation efficiency, and minimizes misjudgment or waste of resources caused by inaccurate data, promoting the transformation of urban traffic management from the traditional model to the refined and intelligent direction, and realizing the efficient operation and sustainable development of the transportation system;

[0064] (2) The present invention proposes a highly innovative solution for dealing with traffic congestion and improving evacuation efficiency. In particular, through the branch division and processing module, it accurately identifies and dynamically manages branches that are easy to evacuate and difficult to evacuate. For branches that are easy to evacuate, the system enhances the frequency of data monitoring to grasp the fluctuation trend of traffic flow in real time to ensure rapid response when the flow changes, and relies on traditional traffic signal control strategies to maintain smooth and stable traffic. For branches that are difficult to evacuate, the system implements a more refined management strategy. Through real-time monitoring, intelligent early warning and dynamic signal adjustment, it can quickly issue an early warning to the traffic management center when traffic congestion or other abnormal situations occur, and timely adjust the signal cycle to give priority to ensuring traffic in the evacuation direction. This flexible strategy based on real-time data feedback and intelligent decision-making not only effectively improves evacuation efficiency, but also avoids the waste of traffic resources, realizes personalized and dynamic traffic management, and ensures the efficient operation of the road network under high load conditions and the safe guidance of passengers. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] The present invention will be further described below in conjunction with the accompanying drawings.

[0066] Figure 1 It is a flowchart of a smart system for processing urban traffic information of the present invention;

[0067] Figure 2 It is a flowchart of the specific steps in the present invention. DETAILED DESCRIPTION

[0068] 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.

[0069] See also Figure 1 or Figure 2 As shown, the present invention is an intelligent system for processing urban traffic information, comprising:

[0070] A data collection module, wherein the data collection module is used to obtain traffic flow data of each branch road;

[0071] Among them, traffic flow data include: vehicle volume, vehicle speed and vehicle density;

[0072] A data accuracy evaluation module, which is used to comprehensively analyze the logic and credibility of the acquired traffic flow data, evaluate the accuracy of the traffic flow data, and extract accurate traffic flow data based on the evaluation results;

[0073] A congestion analysis module, which is used to further analyze the accurate traffic flow data, calculate the congestion coefficient of each branch road, determine whether each branch road is congested, and divide each branch road into a congested branch road and a non-congested branch road according to the determination result;

[0074] An evacuation capacity analysis module, which is based on congested branches and calculates a congestion impact factor according to the congestion situation of each branch, and evaluates the evacuation capacity of each branch according to the congestion impact factor;

[0075] A branch division and processing module, which divides each branch into an easy-to-evacuate branch and a difficult-to-evacuate branch according to the evaluation results. Based on the easy-to-evacuate branch, no evacuation intervention is performed, the monitoring frequency is increased, and based on the difficult-to-evacuate branch, an early warning is issued and the signal control is adjusted.

[0076] The traffic flow data of each branch is obtained through the data acquisition module. The specific acquisition process is as follows:

[0077] Traffic flow data includes:

[0078] Traffic flow: refers to the number of vehicles passing through the branch road per unit time;

[0079] Vehicle speed: the average speed of vehicles on the branch road;

[0080] Vehicle density: the number of vehicles per unit length of road;

[0081] Install traffic flow sensors (such as geomagnetic sensors, radar sensors) and high-definition cameras at key locations on each branch road to monitor vehicle traffic in real time;

[0082] All sensors, cameras and mobile devices are connected via the network, and the collected data is transmitted to the central data processing platform in real time to detect the network and ensure the high bandwidth and low latency characteristics of the network;

[0083] The received data is preprocessed and formatted into a unified data structure for subsequent analysis;

[0084] The traffic flow data is obtained by combining sensor counting and video analysis based on the number of vehicles in a specific time period;

[0085] Using radar sensors or video analysis technology, calculate the average speed data of each vehicle on the branch road;

[0086] The number of vehicles on a unit length of road is calculated through the traffic volume and the length of the branch roads, and the vehicle density data is calculated;

[0087] Through the data accuracy assessment module, the logic and credibility of the acquired traffic flow data are comprehensively analyzed to assess the accuracy of the traffic flow data, and accurate traffic flow data is extracted based on the assessment results;

[0088] Get the actual number of vehicles passing through the branch road per unit time;

[0089] Get the average speed of vehicles on the branch road;

[0090] Get the number of vehicles on a unit length road;

[0091] Calculate the vehicle density of the branch road based on the acquired traffic flow data;

[0092] Wherein, the calculation expression of the vehicle density is:

[0093]

[0094] Where D t represents the density of vehicles on the branch road within time t, Q t represents the actual number of vehicles on the branch road within time t, V t It represents the average speed of vehicles on the branch road within time t, where t represents the period of time collected;

[0095] The expected number of vehicles on the branch road is calculated based on the vehicle density, and the basic relationship is verified. The calculation expression is:

[0096] QUR t =Dt *V t ;

[0097] In the formula, Qy t represents the expected number of vehicles on the branch road within time t;

[0098] Within time t, the actual number and expected number of vehicles on the branch road are processed, and the logical coefficient between the actual number and expected number of vehicles on the branch road is calculated;

[0099] The calculation expression of the logic coefficient is:

[0100]

[0101] Where, L t represents the logical coefficient, n represents the total number of acquisition time points, t represents the acquisition time point, Qy t represents the expected number of vehicles on the branch road within time t, Q t represents the actual number of vehicles on the branch road within time t;

[0102] It should be noted that the logical coefficient L t It reflects the logic of traffic flow data, and when the logic coefficient L t The smaller it is, the stronger the logic of the corresponding traffic flow data is, and the higher the accuracy of the corresponding data is;

[0103] Use fuzzy logic algorithm to process traffic flow data, calculate the credibility coefficient, and evaluate the credibility of traffic flow data, including:

[0104] Determine the input variables including: the actual number of vehicles on the branch road at time t, Q t , the average speed of vehicles on the branch road V t and the density of vehicles on the branch road D t ;

[0105] Define fuzzy logic for each input variable, including low, medium, and high;

[0106] Construct a fuzzy rule base, for example:

[0107] If the actual number of vehicles on the branch road is high and the speed is low, the vehicle density is dense;

[0108] If the actual number of vehicles on the branch road is medium and the speed is medium, then the vehicle density is medium;

[0109] If the actual number of vehicles on the branch road is low and the speed is high, the vehicle density is sparse;

[0110] According to the actual data, each input variable is fuzzified to obtain their membership in each fuzzy set, for example:

[0111] If the actual number of vehicles on the branch road is Q t There are 50 vehicles, and the corresponding membership degrees are:

[0112] μ l =0.2: indicates that the actual number of vehicles on the branch road belongs to the low fuzzy set with a membership degree of 0.2;

[0113] μ M =0.7: indicates that the actual number of vehicles on the branch road belongs to the middle fuzzy set with a membership degree of 0.7;

[0114] μ M =0.1: indicates that the actual number of vehicles on the branch road belongs to the high fuzzy set with a membership degree of 0.1;

[0115] Use fuzzy reasoning method to reason according to the rule base and calculate the output fuzzy set;

[0116] Use the centroid method to defuzzify the inference result to get the final output value, and calculate the ratio of the output value to the input value to get the credibility offset coefficient DC t ;

[0117] The calculation expression of the output value is:

[0118]

[0119] In the formula, C represents the output value, x represents the input variable, and μ(x) represents the membership degree of the input variable x to the fuzzy set;

[0120] It should be noted that the credibility coefficient DC t It reflects the credibility of traffic flow data, and when the credibility deviation coefficient DC t The smaller it is, the more reliable the traffic flow data is;

[0121] Comprehensively analyze the logic coefficient of traffic flow data and the credibility deviation coefficient of traffic flow data, perform normalization processing, and calculate the accuracy coefficient;

[0122] Among them, the accuracy coefficient calculation expression is:

[0123]

[0124] In the formula, A t represents the accuracy coefficient of the traffic flow data within time t, c1 and c2 are preset proportional coefficients, and both c1 and c2 are greater than 0;

[0125] It should be noted that the accuracy coefficient A of traffic flow data t It reflects the accuracy of the collected data, and when the accuracy coefficient A t The larger the value, the more accurate the collected data;

[0126] The accuracy coefficient A t comparing with a preset accuracy coefficient threshold;

[0127] If the accuracy coefficient is greater than or equal to the preset accuracy coefficient threshold, it means that the corresponding traffic flow data is accurate;

[0128] If the accuracy coefficient is less than the preset accuracy coefficient threshold, it means that the corresponding traffic flow data is accurate.

[0129] Accurate traffic flow data is extracted for subsequent traffic congestion assessment.

[0130] Through the congestion analysis module, the accurate traffic flow data is further analyzed to calculate the congestion coefficient of each branch road, and determine whether each branch road is congested. Based on the judgment results, each branch road is divided into congested branches and non-congested branches, including:

[0131] Obtain accurate traffic flow data;

[0132] Standardize all traffic flow data and convert them into the same dimension for clustering;

[0133] Use K-means clustering algorithm to process traffic flow data and calculate congestion coefficient;

[0134] The specific process of the K-means clustering algorithm is as follows:

[0135] First, the elbow rule and silhouette coefficient are used to determine the number of clusters k;

[0136] Select k traffic flow data points as initial cluster centers;

[0137] For each traffic flow data point y i , calculate the traffic flow data point y i With each cluster center z j The Euclidean distance is calculated as:

[0138]

[0139] In the formula, i represents the number of data points, j represents the number of cluster centers, k represents the number of clusters, m represents the maximum number of clusters, and d ij Represents traffic flow data point y i With each cluster center z j The Euclidean distance, yik represents the kth eigenvalue of each traffic flow data point, z jk represents the cluster center z j The kth eigenvalue of ;

[0140] Assign the traffic flow data point to the nearest cluster center, according to the traffic flow data point y i With each cluster center z j The shortest Euclidean distance is used for allocation;

[0141] Calculate the mean of all traffic flow data points in each cluster and update the cluster center;

[0142] Repeat the allocation and update of traffic flow data points until the cluster center no longer changes;

[0143] After completing the k-means clustering, the congestion coefficient is calculated for each cluster. The calculation expression is:

[0144]

[0145] In the formula, S j represents the congestion coefficient of cluster j, d j represents the mean vehicle density in cluster j, D max Indicates the maximum allowable vehicle density of the corresponding branch, V j represents the average speed in cluster j, V m is the preset target vehicle speed;

[0146] The congestion coefficient S of each branch j comparing with a preset congestion coefficient threshold;

[0147] If the congestion coefficient S of each branch j If it is greater than or equal to the preset congestion coefficient threshold, it means that the corresponding branch is congested and is recorded as a congested branch;

[0148] If the congestion coefficient S of each branch j If it is less than the preset congestion coefficient threshold, it means that the corresponding branch is congested and is recorded as a non-congested branch;

[0149] It should be noted that the congestion coefficient S j It reflects the congestion situation of each branch, and the larger the congestion coefficient, the more congested the corresponding branch.

[0150] Through the evacuation capacity analysis module, the congestion impact factor is calculated according to the congestion situation of each branch road. According to the congestion impact factor, the evacuation capacity of each branch road is evaluated, including:

[0151] Obtain the congestion coefficient and vehicle density of each congested branch road;

[0152] For each branch, the congestion coefficient is multiplied by the vehicle density and the ratio is calculated with the maximum allowable speed of the branch to obtain the congestion impact factor F. a :

[0153] Where a represents the number of branches;

[0154] For each branch, the evacuation capacity of each branch is calculated according to the congestion impact factor. The calculation expression is:

[0155]

[0156] In the formula, EA a represents the evacuation capacity of the a-th branch, F a represents the congestion impact factor of the a-th branch, T is the preset impact threshold, and e is the base of the natural logarithm;

[0157] It should be noted that: T represents the impact of the congestion impact factor on the evacuation capacity, and when the congestion impact factor F a When it is greater than or equal to the preset impact threshold T, the impact of congestion on evacuation capacity will increase, which means that the negative impact of congestion on evacuation capacity will be stronger.

[0158] Through the branch division and processing module, each branch is divided into an easy evacuation branch and a difficult evacuation branch. Based on the easy evacuation branch, no evacuation intervention is performed, the monitoring frequency is increased, and based on the difficult evacuation branch, an early warning is issued and the signal is adjusted, including:

[0159] The evacuation capacity EA of each branch a Compare with preset evacuation capacity threshold;

[0160] If the evacuation capacity EA of each branch a If it is greater than or equal to the preset evacuation capacity threshold, it means that the corresponding branch has strong evacuation capacity and is recorded as an easy evacuation branch;

[0161] If the evacuation capacity EA of each branch a If it is less than the preset evacuation capacity threshold, it means that the corresponding branch has strong evacuation capacity and is recorded as a difficult evacuation branch;

[0162] Based on the easy-to-evacuate branch roads, no evacuation intervention will be carried out, and the monitoring frequency of traffic flow data on the easy-to-evacuate branch roads will be increased to ensure the latest traffic flow data is obtained in real time;

[0163] Regularly evaluate the traffic conditions of the branch road to ensure the timeliness and accuracy of traffic flow data;

[0164] and continue to use existing traffic signal control strategies to ensure smooth traffic flow;

[0165] Based on difficult evacuation branches, monitor the real-time traffic conditions of difficult evacuation branches, and immediately send warning information to the traffic management center when congestion or abnormal conditions are found;

[0166] Push warning information to drivers through navigation systems or traffic information release systems to remind them to choose alternative routes;

[0167] Adjust traffic signal cycles in real time based on current traffic flow and congestion conditions;

[0168] Adjust the priority of signals on main roads or in the direction of evacuation to ensure that vehicles heading to the evacuation area have priority;

[0169] Through traffic monitoring systems and sensors, real-time feedback on adjustment effects is provided to ensure that signal adjustment measures are effective and improve evacuation efficiency;

[0170] Regularly evaluate the effectiveness of signal adjustments and monitoring strategies, including changes in traffic flow, congestion, and evacuation efficiency;

[0171] Based on the evaluation results, the strategy will be further optimized and the monitoring frequency and signal control parameters will be adjusted to ensure continuous improvement in traffic management effectiveness.

[0172] Working principle of the present invention: The present invention installs traffic flow sensors and high-definition cameras at key positions of each branch road to monitor data such as vehicle flow, vehicle speed and vehicle density in real time, and transmits the data to a central data processing platform in real time; the data accuracy evaluation module performs logic and credibility analysis on the collected data to ensure the accuracy of the data; the congestion analysis module calculates the congestion coefficient of each branch road based on accurate data using the K-means clustering algorithm, determines whether the branch road is congested, and classifies it into congested branches and non-congested branches; the evacuation capacity analysis module evaluates the evacuation capacity of congested branches and calculates congestion influencing factors; the branch division and processing module divides branches into easy-to-evacuate branches and difficult-to-evacuate branches according to the evacuation capacity, increases the monitoring frequency of easy-to-evacuate branches, and issues early warnings and adjusts signal control for difficult-to-evacuate branches to ensure smooth traffic.

[0173] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0174] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0175] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0176] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not 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 embodiments of the present application.

[0177] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. An intelligent system for processing urban traffic information, characterized in that: include: A data collection module, wherein the data collection module is used to obtain traffic flow data of each branch road; Among them, traffic flow data include: vehicle volume, vehicle speed and vehicle density; A data accuracy evaluation module, which is used to comprehensively analyze the logic and credibility of the acquired traffic flow data, evaluate the accuracy of the traffic flow data, and extract accurate traffic flow data based on the evaluation results; A congestion analysis module, which is used to further analyze the accurate traffic flow data, calculate the congestion coefficient of each branch road, determine whether each branch road is congested, and divide each branch road into a congested branch road and a non-congested branch road according to the determination result; An evacuation capacity analysis module, which is based on congested branches and calculates a congestion impact factor according to the congestion situation of each branch, and evaluates the evacuation capacity of each branch according to the congestion impact factor; A branch division and processing module, which divides each branch into an easy-to-evacuate branch and a difficult-to-evacuate branch according to the evaluation results. Based on the easy-to-evacuate branch, no evacuation intervention is performed, the monitoring frequency is increased, and based on the difficult-to-evacuate branch, an early warning is issued and the signal control is adjusted.

2. The intelligent system for processing urban traffic information according to claim 1, characterized in that: The comprehensive analysis of the logic and credibility of the acquired traffic flow data to evaluate the accuracy of the traffic flow data specifically includes: Get the actual number of vehicles on the branch road within time t; The vehicle density of the branch road is calculated according to the acquired traffic flow data, and the expected number of vehicles on the branch road is calculated according to the vehicle density of the branch road; Processing the actual number and expected number of vehicles on the branch road, calculating the logical coefficient between the actual number and expected number of vehicles on the branch road; The calculation expression of the logic coefficient is: Where, L t represents the logical coefficient, n represents the total number of acquisition time points, t represents the acquisition time point, Qy t represents the expected number of vehicles on the branch road within time t, Q t represents the actual number of vehicles on the branch road within time t; Use fuzzy logic algorithm to process traffic flow data and calculate the credibility coefficient; Comprehensively analyze the logic coefficient of traffic flow data and the credibility deviation coefficient of traffic flow data, perform normalization processing, and calculate the accuracy coefficient; Based on the comparison between the obtained accuracy coefficient and the accuracy coefficient threshold, it is determined whether the traffic flow data is accurate.

3. The intelligent system for processing urban traffic information according to claim 2, characterized in that: The process of obtaining the credibility coefficient is as follows: Determine the input variables including: the actual number of vehicles on the branch road at time t, Q t , the average speed of vehicles on the branch road V t and the density of vehicles on the branch road D t ; Define fuzzy logic for each input variable, including low, medium, and high; Build fuzzy rule base; According to the actual traffic flow data, each input variable is fuzzified to obtain their membership in each fuzzy set; Use fuzzy reasoning method to reason according to the rule base and calculate the output fuzzy set; Use the centroid method to defuzzify the inference result to get the final output value, and calculate the ratio of the output value to the input value to get the credibility offset coefficient DC t ; The calculation expression of the output value is: In the formula, C represents the output value, x represents the input variable, and μ(x) represents the membership degree of the input variable x to the fuzzy set.

4. The intelligent system for processing urban traffic information according to claim 1, characterized in that: The accurate traffic flow data is further analyzed to calculate the congestion coefficient of each branch road, specifically including: Use the elbow rule and silhouette coefficient to determine the number of clusters k; Select k traffic flow data points as initial cluster centers; For each traffic flow data point y i , calculate the traffic flow data point y i With each cluster center z j The Euclidean distance is calculated as: In the formula, i represents the number of data points, j represents the number of cluster centers, k represents the number of clusters, m represents the maximum number of clusters, and d ij Represents traffic flow data point y i With each cluster center z j The Euclidean distance, y ik represents the kth eigenvalue of each traffic flow data point, z jk represents the cluster center z j The kth eigenvalue of ; Assign the traffic flow data point to the nearest cluster center, according to the traffic flow data point y i With each cluster center z j The shortest Euclidean distance is used for allocation; Calculate the mean of all traffic flow data points in each cluster and update the cluster center; Repeat the allocation and update of traffic flow data points until the cluster center no longer changes; After completing the k-means clustering, the congestion coefficient is calculated for each cluster. The calculation expression is: In the formula, S j represents the congestion coefficient of cluster j, D j represents the mean vehicle density in cluster j, D max Indicates the maximum allowable vehicle density of the corresponding branch, V j represents the average speed in cluster j, V m The preset target speed.

5. The intelligent system for processing urban traffic information according to claim 1, characterized in that: The determining whether each branch road is congested specifically includes: Determine the congestion coefficient S of each branch j Is it greater than or equal to the preset congestion coefficient threshold? If so, it is recorded as a congested branch; if not, it is recorded as a non-congested branch.

6. The intelligent system for processing urban traffic information according to claim 1, characterized in that: The congestion-based branch is used to calculate the congestion impact factor according to the congestion situation of each branch, specifically including: Obtain the congestion coefficient and vehicle density of each congested branch road; For each branch, the congestion coefficient is multiplied by the vehicle density and the ratio is calculated with the maximum allowable speed of the branch to obtain the congestion impact factor F. a : Wherein, a represents the number of branches.

7. The intelligent system for processing urban traffic information according to claim 1, characterized in that: According to the congestion impact factors, the evacuation capacity of each branch is evaluated, including: For each branch, the evacuation capacity of each branch is calculated according to the congestion impact factor. The calculation expression is: In the formula, EA a represents the evacuation capacity of the a-th branch, F a represents the congestion impact factor of the a-th branch, T is the preset impact threshold, and e is the base of the natural logarithm; Determine the evacuation capacity of each branch EA a Are they all greater than or equal to the preset evacuation capacity threshold? If so, it is recorded as an easy evacuation branch; if not, it is recorded as a difficult evacuation branch.

8. The intelligent system for processing urban traffic information according to claim 1, characterized in that: Based on the easy evacuation branch, no evacuation intervention is performed, the monitoring frequency is increased, and based on the difficult evacuation branch, an early warning is performed and the signal control is adjusted, which specifically includes: Based on the easy-to-evacuate branch roads, no evacuation intervention will be carried out, and the monitoring frequency of traffic flow data on the easy-to-evacuate branch roads will be increased to ensure the latest traffic flow data is obtained in real time; and continue to use existing traffic signal control strategies; Based on difficult evacuation branches, monitor the real-time traffic conditions of difficult evacuation branches, and immediately send warning information to the traffic management center when congestion or abnormal conditions are found; Adjust traffic signal cycles in real time based on current traffic flow and congestion conditions; Dynamically adjust the signals on main roads or evacuation directions with priority.

Images