Urban green traffic management system and method based on multi-source data

Abstract

The present invention discloses an urban green traffic management system and method based on multi-source data, which specifically relates to the field of big data technology, including a data acquisition module, a data preprocessing module, a multi-source data fusion module, a data processing module, an intelligent decision-making module, a traffic management module, and an efficiency optimization module; data from different sources are integrated to form a comprehensive traffic information database; the fused data are analyzed and processed using big data technology to calculate the comprehensive evaluation index of urban traffic management; based on the comprehensive evaluation index of urban traffic management, a plurality of traffic management strategies are generated using a simulated return algorithm, and the optimal traffic management strategy is screened to achieve the goal of urban green traffic management; specific traffic management measures are implemented according to the optimal traffic management strategy; application data of the traffic management strategy is monitored in real time, and the efficiency of the system is optimized, which is beneficial to improving urban traffic efficiency and reducing environmental pollution.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and more specifically, to an urban green traffic management system and method based on multi-source data. Background Art

[0002] With the acceleration of urbanization, urban traffic problems are becoming increasingly serious, including traffic congestion, environmental pollution, etc. In order to solve these problems, many cities have begun to try to manage traffic through scientific and technological means, such as using big data, artificial intelligence and other technologies.

[0003] However, most of the existing urban traffic management systems only focus on single traffic data and ignore other factors that may affect traffic; the existing urban traffic management systems have certain limitations in data processing and analysis and cannot accurately calculate the comprehensive evaluation index of urban traffic management; in addition, the existing urban traffic management systems also have shortcomings in the generation and optimization of traffic management strategies. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides an urban green traffic management system and method based on multi-source data, which collects various raw data related to traffic through various data sources, and uses multi-source data to more accurately grasp the spatiotemporal characteristics of urban functional areas; cleans, filters and corrects the collected raw data; integrates data from different sources to form a comprehensive traffic information database, makes full use of data from different sources, and integrates these data to more comprehensively understand the urban traffic conditions, so as to more accurately manage and plan traffic; uses big data technology to analyze and process the integrated data, and calculates the comprehensive evaluation index of urban traffic management; based on the comprehensive evaluation index of urban traffic management, comprehensively considers multiple factors, uses a simulated return algorithm to generate multiple traffic management strategies, and selects the optimal traffic management strategy to achieve the goal of urban green traffic management and provide intelligent decision-making support for traffic management departments; according to the optimal traffic management strategy, executes specific traffic management measures; monitors the application data of the traffic management strategy in real time, and optimizes the performance of the system, which is conducive to improving urban traffic efficiency and reducing environmental pollution, so as to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: an urban green traffic management system and method based on multi-source data, comprising:

[0006] Data collection module: collects various traffic-related raw data through various data sources;

[0007] Data preprocessing module: used to clean, filter and correct the collected raw data to obtain preprocessed data;

[0008] Multi-source data fusion module: used to integrate data from different sources to form a comprehensive traffic information database;

[0009] Data processing module: Use big data technology to analyze and process the integrated data and calculate the comprehensive evaluation index of urban traffic management;

[0010] Intelligent decision-making module: using simulated annealing algorithm, based on the comprehensive evaluation index of urban traffic management, it generates multiple traffic management strategies and selects the optimal traffic management strategy;

[0011] Traffic management module: used to implement specific traffic management measures according to the optimal traffic management strategy of the intelligent decision-making module;

[0012] Performance optimization module: used to monitor the application data of traffic management strategies in real time and optimize the performance of the system.

[0013] In a preferred embodiment, the specific processing process of the multi-source data fusion module is:

[0014] A1. Unify the formats, convert the units and align the time of data from different data sources to obtain a data set for subsequent fusion operations; the data set includes data collected by data source 1, data collected by data source 2, ..., data collected by data source n;

[0015] A2. Calculate the Jaccard similarity between each two data sets. Where A and B represent two sets respectively, |A| represents the number of elements in set A, |B| represents the number of elements in set B, |A∩B| represents the number of elements in the intersection of A and B, |A∪B| represents the number of elements in the union of A and B, and the value of Jaccard similarity is between 0 and 1; the number of elements specifically refers to the preprocessed data corresponding to each data source;

[0016] A3. Compare and analyze the calculated Jaccard similarities. The larger the Jaccard similarity, the more similar the two data sets are. The two data sets with the largest Jaccard similarity are associated and connected to establish an association relationship between the data.

[0017] A4. Use the weighted summation method to fuse and aggregate the associated data to obtain the integrated data result; the calculation formula of the weighted summation method is specifically: R=w1×x1+w2×x2+...+wn×xn, where R represents the integrated data result, w1, w2...wn represent the weights of each data set, and x1, x2...xn represent the specific values ​​in the corresponding data set;

[0018] A5. When there is a conflict in the data provided by different data sources, calculate the data quality evaluation index and the stability coefficient of the data source; the calculation formula of the data quality evaluation index Q is:

[0019] Where nc represents the number of erroneous data records, nq represents the number of missing data records, nb represents the number of inconsistent data records, N represents the number of total data records, and θ1, θ2, and θ3 represent the proportional coefficients of each item respectively;

[0020] The calculation formula of the stability coefficient W of the data source is specifically: Where N represents the total number of data records, ti represents the time interval of the i-th data record, represents the average value of all time intervals; the time interval is specifically obtained by sorting the data records according to the timestamps and calculating the time interval between adjacent data records;

[0021] A6. Calculate the data reliability coefficient according to the data quality assessment index Q and the stability coefficient W of the data source, and take the data with the highest reliability coefficient as the result of conflict resolution; the calculation formula of the data reliability coefficient Kx is: Where μ1 and μ2 represent the proportional coefficients of each item respectively;

[0022] A7. Store the integrated data in the database and establish a hash index structure to support data query and retrieval.

[0023] In a preferred embodiment, the specific processing process of the data processing module is:

[0024] B1. Analyze and process the integrated data to calculate the traffic congestion index, weather comprehensive index, construction impact index, road section safety score, traffic signal timing optimization index, charging pile coverage rate, bicycle rental point convenience index, population mobility index, and public transportation travel index;

[0025] B2. Calculate the comprehensive evaluation index of urban traffic management Kc based on air quality data Skq, accident frequency Lsg, traffic congestion index Zjy, weather comprehensive index Ztq, construction impact index Zsg, road section safety score Faq, traffic signal timing optimization index Jdy, charging pile coverage rate Cf, bicycle rental point convenience index Zbc, population mobility index Zrl, and public transportation travel index Zgc.

[0026]

[0027] e represents a natural constant.

[0028] In a preferred embodiment, the calculation formula of the traffic congestion index is specifically: Where Zjy represents the traffic congestion index, ly represents the amount of traffic flow, ρy represents the density of traffic flow, and vy represents the speed of traffic flow;

[0029] The calculation formula of the weather comprehensive index is specifically: Ztq=β1×ta+β2×tb+β3×tc+β4×td, wherein Ztq represents the weather comprehensive index, ta represents temperature, tb represents rainfall, tc represents humidity, td represents wind force, β1, β2, β3, β4 represent the proportional coefficients of each item, β1+β2+β3+β4=1;

[0030] The calculation formula of the construction impact index is specifically: Where Zsg represents the construction impact index, ts represents the construction duration, S represents the construction area, λ represents the size of the construction impact range, specifically the number of lanes affected or the proportion of vehicles passing through the area, and L represents the total length of the road;

[0031] The calculation formula of the road section safety score is specifically:

[0032] Faq=γ1×Fxs+γ2×Fpz+γ3×Fsh+γ4×Fkd, where Faq represents the road section safety score, and Fxs represents the road section speed limit score. Xs represents the maximum speed limit score, V represents the actual speed of the vehicle, Vs represents the speed limit of the road section, and Fpz represents the road section flatness score. n represents the number of measurement points, hxi represents the elevation data of the i-th measurement point of the road, Hx represents the highest score of flatness, Fsh represents the score of road section damage degree, Fkd represents the score of pothole location of road section, γ1, γ2, γ3, γ4 represent the proportional coefficients of each item, γ1+γ2+γ3+γ4=1;

[0033] The calculation formula of the traffic light timing optimization index is specifically: Where Jdy represents the traffic light timing optimization index, df represents the maximum score, tw represents the average delay time, lct represents the vehicle flow through the traffic light, and lcz represents the total vehicle flow;

[0034] The calculation formula of the charging pile coverage rate is specifically: Where Cf represents the coverage rate of charging piles, My represents the number of installed charging piles, and M represents the number of required charging piles;

[0035] The calculation formula of the bicycle rental point convenience index is specifically as follows: Where Zbc represents the convenience index of bicycle rental points, sp represents the number of bicycle rental points, and Sq represents the area of ​​the region;

[0036] The calculation formula of the population mobility index is as follows: Where Zrl represents the population mobility index, ll represents the flow of user mobile data, lv represents the speed of user mobile data, Nr represents the population, υ1 and υ2 represent the proportional coefficients of each item, υ1+υ2=1;

[0037] The calculation formula of the public transportation travel index is specifically as follows: Among them, Zgc represents the public transportation travel index, cs represents the number of public transportation passengers, cx represents the number of boarding and alighting points, and TA represents the average travel time.

[0038] In a preferred embodiment, the specific processing process of the policy planning unit is:

[0039] D1. Based on the future comprehensive evaluation index of urban traffic management and the data of the data processing module, generate E possible traffic management strategies through simulated annealing algorithm; the traffic management strategies include traffic flow allocation plan, traffic signal timing optimization plan, road planning adjustment plan, and public transportation system improvement plan;

[0040] D2. Quantitatively evaluate and compare the generated multiple traffic management strategies by using the analytic hierarchy process in combination with pre-set evaluation indicators; the pre-set evaluation indicators include the coefficient of change of the sustainable development index, the coefficient of change of the traffic congestion index and the air quality improvement coefficient;

[0041] D3. Normalize each evaluation indicator to ensure that the data are at the same level. The calculation formula for the normalization is: Where Gpg represents the normalized evaluation index, pg represents the original evaluation index, pgmin represents the minimum value of the evaluation index, and pgmax represents the maximum value of the evaluation index; that is, in each traffic management strategy, the corresponding normalized change coefficient of the sustainable development index, the change coefficient of the traffic congestion index, and the air quality improvement coefficient are recorded as GXkc, GXjy, and GXkq respectively;

[0042] D4. Calculate the comprehensive score ZHF of each traffic management strategy. The specific calculation formula is:

[0043] ZHF=ω1×GXkc+ω2×GXjy+ω3×GXkq, where GXkc represents the coefficient of change of the sustainable development index after normalization, GXjy represents the coefficient of change of the traffic congestion index after normalization, GXkq represents the coefficient of improvement of air quality after normalization, and ω1, ω2, and ω3 represent the proportional coefficients of each item;

[0044] D5. Compare the comprehensive scores of various traffic management strategies and select the traffic management strategy with the highest score as the best performing one.

[0045] In a preferred embodiment, the specific processing process of the performance optimization module is:

[0046] E1. Collect relevant data in the application process of traffic management strategies in real time based on monitoring equipment, including the total number of passing vehicles, total travel time, delay time, and the number of traffic accidents;

[0047] E2. After pre-processing the collected real-time data, data analysis is performed to calculate the traffic flow, delay reduction and accident reduction rate after the application of traffic management strategies;

[0048] The calculation formula of the traffic fluency Djt is specifically: Where cls represents the total number of passing vehicles, and txs represents the total travel time;

[0049] The calculation formula of the delay reduction degree TD is specifically: TD=Tdy-Tdh, where Tdy represents the delay time before the traffic management strategy is applied, and Tdh represents the current delay time;

[0050] The calculation formula of the accident reduction rate Lvs is specifically: Where ylv represents the number of accidents before the traffic management strategy is applied, and hlv represents the current number of accidents;

[0051] E3. Based on the analyzed data and the expected performance evaluation index, the performance value of the current traffic management strategy is calculated; the expected performance evaluation index includes the expected traffic flow Djt0, the expected delay reduction degree TD0 and the expected accident reduction rate Lvs0; the calculation formula of the performance value Xnb is: Where Djt represents traffic smoothness, TD represents the degree of delay reduction, and Lvs represents the accident reduction rate;

[0052] E4. Compare and judge the performance value Xnb with the pre-set performance threshold Xnb. If Xnb≥Xnb, it means that the performance of the current traffic management strategy is poor after application, and the traffic management strategy needs to be optimized and adjusted; otherwise, it means that the performance of the current traffic management strategy is good after application and can continue to be applied.

[0053] In a preferred embodiment, a method for urban green traffic management based on multi-source data comprises the following steps:

[0054] Step S1, collecting various traffic-related raw data through various data sources;

[0055] Step S2: cleaning, filtering and correcting the collected raw data;

[0056] Step S3, integrating data from different sources to form a comprehensive traffic information database;

[0057] Step S4: Use big data technology to analyze and process the fused data and calculate the comprehensive evaluation index of urban traffic management;

[0058] Step S5: Based on the comprehensive evaluation index of urban traffic management, a plurality of traffic management strategies are generated by using a simulated annealing algorithm, and the optimal traffic management strategy is screened out;

[0059] Step S6: Execute specific traffic management measures according to the optimal traffic management strategy;

[0060] Step S7: monitor the application data of the traffic management strategy in real time and optimize the performance of the system.

[0061] Technical effects and advantages of the present invention:

[0062] The present invention collects various raw data related to traffic through various data sources, and uses multi-source data to more accurately grasp the spatiotemporal characteristics of urban functional areas; cleans, filters and corrects the collected raw data; integrates data from different sources to form a comprehensive traffic information database, makes full use of data from different sources, and integrates these data to more comprehensively understand the urban traffic conditions, so as to more accurately manage and plan traffic; uses big data technology to analyze and process the integrated data, and calculates the comprehensive evaluation index of urban traffic management; based on the comprehensive evaluation index of urban traffic management, comprehensively considers multiple factors, uses a simulated return algorithm to generate multiple traffic management strategies, and selects the optimal traffic management strategy to achieve the goal of urban green traffic management and provide intelligent decision-making support for traffic management departments; implements specific traffic management measures according to the optimal traffic management strategy; monitors the application data of traffic management strategies in real time, optimizes the performance of the system, is conducive to improving urban traffic efficiency and reducing environmental pollution, has good flexibility and adaptability, and can be adjusted and optimized according to actual conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 It is the overall structural block diagram of the present invention.

[0064] Figure 2 It is a flow chart of the steps and methods of the present invention. DETAILED DESCRIPTION

[0065] 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.

[0066] The present invention provides Figure 1-Figure 2 An urban green traffic management system and method based on multi-source data is shown, comprising a data acquisition module, a data preprocessing module, a multi-source data fusion module, a data processing module, an intelligent decision-making module, a traffic management module, and an efficiency optimization module;

[0067] The data acquisition module is used to collect various traffic-related raw data through various data sources; the raw data include the quantity, density, speed, accident frequency, temperature, rainfall, humidity, wind force, latitude and longitude of the vehicle, driving direction, trajectory, construction duration, construction area, construction impact range, speed limit value of the road section, flatness, damage degree, pothole location, traffic signal timing data, vehicle punctuality data, road network data, charging pile location, number of charging piles, bicycle rental point location, number of bicycle rental points, population, user mobile data flow, user mobile data speed, number of public transportation passengers, number of boarding and alighting points, travel time, and air quality data; collecting data through different data sources provides necessary input for subsequent data processing and analysis; road network data refers to data describing the road network structure and connection relationship;

[0068] The data preprocessing module is used to clean, filter and correct the collected raw data to obtain preprocessed data, providing a high-quality data basis for subsequent data processing; the cleaning, filtering and correction belong to the existing technical means, so this embodiment does not make a specific description;

[0069] The multi-source data fusion module is used to integrate data from different sources to form a comprehensive traffic information database; by fusing data from different data sources, it can make up for the defects that may exist in the research of a single data source and more accurately grasp the spatiotemporal characteristics of urban functional areas;

[0070] It should be specifically explained in this implementation that the specific processing process of the multi-source data fusion module is as follows:

[0071] A1. Performing format unification, unit conversion and time alignment processing on data from different data sources to obtain a data set for subsequent fusion operations; the data set includes data collected by data source 1, data collected by data source 2, ... data collected by data source n; the format unification, unit conversion and time alignment processing belong to the existing technical means, so this embodiment does not make specific descriptions; the format unification includes unifying the date and time format and the numerical format;

[0072] A2. Calculate the Jaccard similarity between each two data sets. Where A and B represent two sets respectively, |A| represents the number of elements in set A, |B| represents the number of elements in set B, |A∩B| represents the number of elements in the intersection of A and B, |A∪B| represents the number of elements in the union of A and B, and the value of Jaccard similarity is between 0 and 1; the number of elements specifically refers to the preprocessed data corresponding to each data source;

[0073] A3. Compare and analyze the calculated Jaccard similarities. The larger the Jaccard similarity, the more similar the two data sets are. Associate and connect the two data sets with the largest Jaccard similarity to establish an association relationship between the data. For example, the Jaccard similarity between set A and set B is 0.8, which means that the proportion of their common elements to the total number of elements is high, indicating that set A and set B are relatively similar; the Jaccard similarity between set A and set C is 0.4, which means that the proportion of their common elements to the total number of elements is low, indicating that set A and set C are relatively dissimilar. ; The Jaccard similarity between set A and set D is 0.2, indicating that the proportion of their common elements to the total number of elements is very low, indicating that set A and set D are very dissimilar; the Jaccard similarity between set B and set C is 0.9, indicating that the proportion of their common elements to the total number of elements is high, indicating that set B and set C are relatively similar; the Jaccard similarity between set B and set D is 0.1, indicating that the proportion of their common elements to the total number of elements is very low, indicating that set B and set D are very dissimilar; therefore, set A is associated with set B, and set B is associated with set C;

[0074] A4. Use the weighted summation method to fuse and aggregate the associated data to obtain the integrated data result; the calculation formula of the weighted summation method is specifically: R=w1×x1+w2×x2+...+wn×xn, where R represents the integrated data result, w1, w2...wn represent the weights of each data set, and x1, x2...xn represent the specific values ​​in the corresponding data set;

[0075] A5. When there is a conflict in the data provided by different data sources, calculate the data quality evaluation index and the stability coefficient of the data source; the calculation formula of the data quality evaluation index Q is:

[0076] Where nc represents the number of erroneous data records, nq represents the number of missing data records, nb represents the number of inconsistent data records, N represents the number of total data records, θ1, θ2, and θ3 represent the proportional coefficients of each item respectively. The size of the proportional coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the proportional coefficient can be determined as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0077] The calculation formula of the stability coefficient W of the data source is specifically: Where N represents the total number of data records, ti represents the time interval of the i-th data record, represents the average value of all time intervals; the time interval is specifically obtained by sorting the data records according to the timestamps and calculating the time interval between adjacent data records;

[0078] A6. Calculate the data reliability coefficient according to the data quality assessment index Q and the stability coefficient W of the data source, and take the data with the highest reliability coefficient as the result of conflict resolution; the calculation formula of the data reliability coefficient Kx is: Among them, μ1 and μ2 represent the proportional coefficients of each item respectively. The size of the proportional coefficient is to quantify each parameter to obtain a specific value, which is convenient for subsequent comparison. The size of the proportional coefficient can be whatever as long as it does not affect the proportional relationship between the parameter and the quantized value;

[0079] A7. Store the integrated data in the database and establish a hash index structure to support efficient data query and retrieval;

[0080] The data processing module is used to analyze and process the fused data using big data technology, calculate the comprehensive evaluation index of urban traffic management, and provide a basis for subsequent intelligent decision-making;

[0081] It should be specifically explained in this implementation that the specific processing process of the data processing module is as follows:

[0082] B1. Analyze and process the integrated data to calculate the traffic congestion index, weather comprehensive index, construction impact index, road section safety score, traffic signal timing optimization index, charging pile coverage rate, bicycle rental point convenience index, population mobility index, and public transportation travel index;

[0083] The calculation formula of the traffic congestion index is specifically: Where Zjy represents the traffic congestion index, ly represents the amount of traffic flow, ρy represents the density of traffic flow, and vy represents the speed of traffic flow;

[0084] The calculation formula of the weather comprehensive index is specifically: Ztq=β1×ta+β2×tb+β3×tc+β4×td, wherein Ztq represents the weather comprehensive index, ta represents temperature, tb represents rainfall, tc represents humidity, td represents wind force, β1, β2, β3, β4 represent proportional coefficients of each item, β1+β2+β3+β4=1, the size of the proportional coefficient is to quantify each parameter to obtain a specific value, which is convenient for subsequent comparison. As for the size of the proportional coefficient, as long as it does not affect the proportional relationship between the parameter and the quantized value; for example, β1=0.1, β2=0.2, β3=0.5, β4=0.2;

[0085] The calculation formula of the construction impact index is specifically: Where Zsg represents the construction impact index, ts represents the construction duration, S represents the construction area, λ represents the size of the construction impact range, specifically the number of lanes affected or the proportion of vehicles passing through the area, and L represents the total length of the road;

[0086] The calculation formula of the road section safety score is specifically:

[0087] Faq=γ1×Fxs+γ2×Fpz+γ3×Fsh+γ4×Fkd, where Faq represents the road section safety score, and Fxs represents the road section speed limit score. Xs represents the maximum speed limit score, V represents the actual speed of the vehicle, Vs represents the speed limit of the road section, and Fpz represents the road section flatness score. n represents the number of measuring points, hxi represents the elevation data of the ith measuring point of the road, Hx represents the highest score of flatness, Fsh represents the score of road section damage degree, different levels are set according to the category, area and severity of the damage degree, and corresponding scores are assigned to each level, Fkd represents the score of the pothole position of the road section, which is formulated according to the relative position, affected area and severity of the pothole position, and corresponding scores are assigned to potholes of different positions and severity, γ1, γ2, γ3, γ4 represent the proportional coefficients of each item, γ1+γ2+γ3+γ4=1, the size of the proportional coefficient is to quantify each parameter to obtain a specific value, which is convenient for subsequent comparison, and the size of the proportional coefficient is not affected as long as it does not affect the proportional relationship between the parameter and the quantified value; for example, γ1=0.2, γ2=0.1, γ3=0.4, γ4=0.3;

[0088] The relative position of the pothole position specifically refers to the center line or road edge close to the vehicle's driving trajectory; the maximum speed limit score specifically refers to the maximum score obtained when the road speed limit value is fully met. For example, if the maximum score is set to 10, it means that when the actual driving speed is completely consistent with the road speed limit, the maximum score of 10 will be obtained. If there is a gap between the actual driving speed and the road speed limit, the score will be reduced accordingly according to the size of the gap; the maximum flatness score specifically refers to the maximum score set for a completely flat road. For example, if 10 is used as the maximum score, a completely flat road will obtain the maximum score of 10, while a less flat road will obtain a lower score; when calculating the flatness score, the smaller the flatness value, that is, the flatter the road surface, the higher the score; the larger the flatness value, that is, the less flat the road surface, the lower the score;

[0089] The calculation formula of the traffic light timing optimization index is specifically: Where Jdy represents the traffic light timing optimization index, df represents the maximum score, tw represents the average delay time, lct represents the vehicle flow through the traffic light, and lcz represents the total vehicle flow; the maximum score df is a pre-set constant used to represent the best timing performance under ideal conditions. The specific value is set according to the actual situation and needs, and generally depends on the goals and requirements of urban traffic planning; the effect of the current timing plan is evaluated by calculating the traffic light timing optimization index. The higher the traffic light timing optimization index, the more optimized the timing plan, the higher the traffic flow, and the less delay time;

[0090] The calculation formula of the charging pile coverage rate is specifically: Where Cf represents the coverage rate of charging piles, My represents the number of installed charging piles, and M represents the number of required charging piles;

[0091] The calculation formula of the bicycle rental point convenience index is specifically as follows: Where Zbc represents the convenience index of bicycle rental points, sp represents the number of bicycle rental points, and Sq represents the area of ​​the region;

[0092] The calculation formula of the population mobility index is as follows: Where Zrl represents the population mobility index, ll represents the flow of user mobile data, lv represents the speed of user mobile data, Nr represents the population, υ1 and υ2 represent the proportional coefficients of each item, υ1+υ2=1, and the size of the proportional coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the proportional coefficient can be determined as long as it does not affect the proportional relationship between the parameter and the quantified value;

[0093] The calculation formula of the public transportation travel index is specifically as follows: Where Zgc is the public transportation travel index, cs is the number of public transportation passengers, cx is the number of boarding and alighting points, and TA is the average travel time. The public transportation travel index measures the efficiency of the urban public transportation system and indicates the number of boarding and alighting points that each passenger can reach within the average travel time. It can help evaluate the coverage of the public transportation system and the travel convenience of passengers. For example, if there are 100 trips in an hour, the total travel time is 600 minutes, and there are 50 boarding and alighting points in the area, then the public transportation travel index is: 100×(50 / 600)=8.33, that is, each passenger can reach about 8.33 boarding and alighting points per minute.

[0094] B2. Calculate the comprehensive evaluation index of urban traffic management Kc based on air quality data Skq, accident frequency Lsg, traffic congestion index Zjy, weather comprehensive index Ztq, construction impact index Zsg, road section safety score Faq, traffic signal timing optimization index Jdy, charging pile coverage rate Cf, bicycle rental point convenience index Zbc, population mobility index Zrl, and public transportation travel index Zgc.

[0095]

[0096] e represents a natural constant;

[0097] The intelligent decision-making module is used to generate multiple traffic management strategies based on the comprehensive evaluation index of urban traffic management by using a simulated annealing algorithm, and screen out the optimal traffic management strategy to reduce environmental impact and improve traffic efficiency;

[0098] It should be specifically noted that in this implementation, a model prediction method can be provided, which specifically includes the following steps:

[0099] C1. Collect historical data and the corresponding historical urban traffic management comprehensive evaluation index as a data set;

[0100] C2, taking air quality data, accident frequency, traffic congestion index, weather comprehensive index, construction impact index, road section safety score, traffic signal timing optimization index, charging pile coverage, bicycle rental point convenience index, population mobility index, and public transportation travel index as independent variables, and taking the historical urban traffic management comprehensive evaluation index as the target variable;

[0101] C3. Standardize the independent variables and target variables, and select the time series model as the prediction model; the calculation formula for the standardization is as follows: Where Bzh represents the standardized data, xa represents the original data, represents the mean, σ represents the standard deviation;

[0102] C4. Divide the historical data into a training set and a validation set, use the training set to train the time series model, and adjust the model parameters to obtain a better fitting effect. Through iterative optimization, find the best model parameters;

[0103] C5. Use the validation set to verify and evaluate the trained model, and calculate the mean absolute error between the predicted result and the actual value to evaluate the model performance; the calculation formula of the mean absolute error MAE is: Where u represents the number of samples, mai represents the predicted value of the i-th sample, and mei represents the actual value of the i-th sample;

[0104] The mean absolute error MAE is compared with the preset error threshold M threshold. If MAE ≥ M threshold, it means that the model performance does not meet expectations and parameter adjustment and model optimization are required; otherwise, it means that the model performance meets expectations; the preset error threshold M threshold can be set according to specific circumstances, and this embodiment does not specifically limit the specific data;

[0105] C6. Use the trained time series model to predict the future comprehensive evaluation index of urban traffic management. By providing the latest input data to the model, the prediction result of the future comprehensive evaluation index of urban traffic management is obtained.

[0106] C7. Evaluate the credibility of the prediction results, apply the prediction results to decision-making and planning, provide intelligent decision-making support for traffic management departments, and further promote the sustainable development of cities; the credibility of the prediction results is evaluated and quantified using a confidence interval, which is a statistical method used to estimate the range of true parameter values; the confidence interval of the prediction results is calculated using the standard deviation of the prediction error and the confidence level, and the confidence level is selected as 95%, indicating that there is a 95% confidence that the true parameter value is within the confidence interval. The calculation formula of the confidence interval is as follows: Confidence interval = predicted value ± Z × standard deviation, where Z represents the quantile of the normal distribution, which is determined according to the confidence level. For example, the Z value corresponding to 95% is 1.96, and the standard deviation is the standard deviation of the prediction error;

[0107] What needs to be specifically explained in this implementation is that the specific processing process of the intelligent decision-making module is:

[0108] D1. Based on the comprehensive evaluation index of urban traffic management, E possible traffic management strategies are generated by simulated annealing algorithm; the traffic management strategies include traffic flow distribution scheme, traffic signal timing optimization scheme, road planning adjustment scheme, and public transportation system improvement scheme; the simulated annealing algorithm belongs to the existing technical means, so it is not specifically described in this embodiment;

[0109] D2. Quantitatively evaluate and compare the generated multiple traffic management strategies by using the analytic hierarchy process in combination with pre-set evaluation indicators; the pre-set evaluation indicators include the coefficient of change of the sustainable development index, the coefficient of change of the traffic congestion index and the air quality improvement coefficient; wherein the analytic hierarchy process specifically refers to a multi-criteria decision-making method for solving complex decision-making problems, which belongs to the existing technical means, and therefore is not specifically described in this embodiment;

[0110] The calculation formula of the coefficient of change Xkc of the sustainable development index is: Where kcd represents the current comprehensive evaluation index of urban traffic management, jkc represents the benchmark comprehensive evaluation index of urban traffic management, which specifically refers to the reference value set in advance according to the actual situation;

[0111] The calculation formula of the change degree coefficient Xjy of the traffic congestion index is: Where jyd represents the current traffic congestion index, and Jy represents the benchmark traffic congestion index, which specifically refers to the reference value set in advance according to the actual situation;

[0112] The calculation formula of the air quality improvement coefficient Xkq is: Where kcq represents the current air quality, jkq represents the benchmark air quality, which specifically refers to the reference value set in advance according to the actual situation;

[0113] D3. Normalize each evaluation indicator to ensure that the data are at the same level. The calculation formula for the normalization is: Where Gpg represents the normalized evaluation index, pg represents the original evaluation index, pgmin represents the minimum value of the evaluation index, and pgmax represents the maximum value of the evaluation index; that is, in each traffic management strategy, the corresponding normalized change coefficient of the sustainable development index, the change coefficient of the traffic congestion index, and the air quality improvement coefficient are recorded as GXkc, GXjy, and GXkq respectively;

[0114] D4. Calculate the comprehensive score ZHF of each traffic management strategy. The specific calculation formula is:

[0115] ZHF=ω1×GXkc+ω2×GXjy+ω3×GXkq, where GXkc represents the coefficient of change of the sustainable development index after normalization, GXjy represents the coefficient of change of the traffic congestion index after normalization, GXkq represents the coefficient of improvement of air quality after normalization, ω1, ω2, ω3 represent the proportional coefficients of each item, and the size of the proportional coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. As for the size of the proportional coefficient, it is acceptable as long as it does not affect the proportional relationship between the parameter and the quantified value;

[0116] D5. Compare the comprehensive scores of various traffic management strategies and select the traffic management strategy with the highest score as the best performing one;

[0117] The traffic management module is used to execute specific traffic management measures according to the optimal traffic management strategy of the intelligent decision-making module;

[0118] It should be noted that the traffic management module reasonably distributes the traffic flow in the road network based on the optimal traffic management strategy generated by the intelligent decision-making module, balances traffic flow and alleviates congestion by adjusting the timing of traffic lights, restricting or guiding vehicles to enter specific roads or areas, etc.; optimizes and adjusts traffic lights, optimizes the passing efficiency of vehicles through reasonable timing and timing settings, reduces waiting time and queue length, and improves road traffic conditions; adjusts road planning, including adding new roads, optimizing road layouts, adding or adjusting intersections, etc., to improve road capacity and traffic environment; based on the optimal traffic management strategy of the intelligent decision-making module, takes improvement measures, such as increasing the number of public buses, optimizing route settings, providing real-time information services, etc., to improve the operating efficiency and convenience of public transportation and encourage more people to use public transportation;

[0119] The performance optimization module is used to monitor the application data of the traffic management strategy in real time and optimize the performance of the system to improve the accuracy and efficiency of traffic management, so as to better adapt to changes in urban traffic;

[0120] It should be specifically explained in this implementation that the specific processing process of the performance optimization module is as follows:

[0121] E1. Collect relevant data in the application process of traffic management strategies in real time based on monitoring equipment, including the total number of passing vehicles, total travel time, delay time, and the number of traffic accidents;

[0122] E2. After pre-processing the collected real-time data, data analysis is performed to calculate the traffic flow, delay reduction and accident reduction rate after the application of traffic management strategies;

[0123] The calculation formula of the traffic fluency Djt is specifically: Where cls represents the total number of passing vehicles, and txs represents the total travel time;

[0124] The calculation formula of the delay reduction degree TD is specifically: TD=Tdy-Tdh, where Tdy represents the delay time before the traffic management strategy is applied, and Tdh represents the current delay time;

[0125] The calculation formula of the accident reduction rate Lvs is specifically: Where ylv represents the number of accidents before the traffic management strategy is applied, and hlv represents the current number of accidents;

[0126] E3. Based on the analyzed data and the expected performance evaluation index, the performance value of the current traffic management strategy is calculated; the expected performance evaluation index includes the expected traffic flow Djt0, the expected delay reduction degree TD0 and the expected accident reduction rate Lvs0; the calculation formula of the performance value Xnb is: Among them, Djt represents traffic smoothness, TD represents the degree of delay reduction, and Lvs represents the accident reduction rate. By comparing the actual value with the expected value, the performance of the current traffic management strategy can be evaluated. The closer the performance value is to 0, the closer the effectiveness of the current strategy is to the expected goal.

[0127] E4. Compare the performance value Xnb with the preset performance threshold Xnb. If Xnb≥Xnb, it means that the performance of the current traffic management strategy is poor after application, and the traffic management strategy needs to be optimized and adjusted; otherwise, it means that the performance of the current traffic management strategy is good after application, and it can continue to be applied; the preset performance threshold Xnb can be set according to specific circumstances, and this embodiment does not specifically limit the specific data; the traffic management strategy is optimized and adjusted; specific optimization measures can be determined according to actual conditions and evaluation results, for example: encourage the development of car sharing platforms, ride-sharing services and carpooling services, promote resource sharing, reduce the number of vehicles and traffic congestion; advocate green travel methods, such as encouraging walking, bicycles, electric vehicles and public transportation, etc., to reduce exhaust emissions and traffic pressure;

[0128] In this embodiment, it should be specifically explained that a method for urban green traffic management based on multi-source data includes the following steps:

[0129] Step S1, collecting various traffic-related raw data through various data sources;

[0130] Step S2: cleaning, filtering and correcting the collected raw data;

[0131] Step S3, integrating data from different sources to form a comprehensive traffic information database;

[0132] Step S4: Use big data technology to analyze and process the fused data and calculate the comprehensive evaluation index of urban traffic management;

[0133] Step S5: Based on the comprehensive evaluation index of urban traffic management, a plurality of traffic management strategies are generated by using a simulated annealing algorithm, and the optimal traffic management strategy is screened out;

[0134] Step S6: Execute specific traffic management measures according to the optimal traffic management strategy;

[0135] Step S7: monitor the application data of the traffic management strategy in real time and optimize the performance of the system.

[0136] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0137] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An urban green traffic management system based on multi-source data, characterized by: include: Data collection module: collects various traffic-related raw data through various data sources; Data preprocessing module: used to clean, filter and correct the collected raw data to obtain preprocessed data; Multi-source data fusion module: used to integrate data from different sources to form a comprehensive traffic information database; The specific processing process of the multi-source data fusion module is as follows: A1. Unify the formats, convert the units and align the time of data from different data sources to obtain a data set for subsequent fusion operations; the data set includes data collected by data source 1, data collected by data source 2, ..., data collected by data source n; A2. Calculate the Jaccard similarity between each two data sets. Where A and B represent two sets respectively, |A| represents the number of elements in set A, |B| represents the number of elements in set B, |A∩B| represents the number of elements in the intersection of A and B, |A∪B| represents the number of elements in the union of A and B, and the value of Jaccard similarity is between 0 and 1; the number of elements specifically refers to the preprocessed data corresponding to each data source; A3. Compare and analyze the calculated Jaccard similarities. The larger the Jaccard similarity, the more similar the two data sets are. The two data sets with the largest Jaccard similarity are associated and connected to establish an association relationship between the data. A4. Use the weighted summation method to fuse and aggregate the associated data to obtain the integrated data result; the calculation formula of the weighted summation method is specifically: R=w1×x1+w2×x2+...+wn×xn, where R represents the integrated data result, w1, w2...wn represent the weights of each data set, and x1, x2...xn represent the specific values ​​in the corresponding data set; A5. When there is a conflict in the data provided by different data sources, calculate the data quality evaluation index and the stability coefficient of the data source; the calculation formula of the data quality evaluation index Q is: Where nc represents the number of erroneous data records, nq represents the number of missing data records, nb represents the number of inconsistent data records, N represents the number of total data records, and θ1, θ2, and θ3 represent the proportional coefficients of each item respectively; The calculation formula of the stability coefficient W of the data source is specifically: Where N represents the total number of data records, ti represents the time interval of the i-th data record, represents the average value of all time intervals; the time interval is specifically obtained by sorting the data records according to the timestamps and calculating the time interval between adjacent data records; A6. Calculate the data reliability coefficient according to the data quality assessment index Q and the stability coefficient W of the data source, and take the data with the highest reliability coefficient as the result of conflict resolution; the calculation formula of the data reliability coefficient Kx is: Where μ1 and μ2 represent the proportional coefficients of each item respectively; A7. Store the integrated data in the database and establish a hash index structure to support data query and retrieval; Data processing module: Use big data technology to analyze and process the integrated data and calculate the comprehensive evaluation index of urban traffic management; The specific processing process of the data processing module is as follows: B1. Analyze and process the integrated data to calculate the traffic congestion index, weather comprehensive index, construction impact index, road section safety score, traffic signal timing optimization index, charging pile coverage rate, bicycle rental point convenience index, population mobility index, and public transportation travel index; B2. Calculate the comprehensive evaluation index of urban traffic management Kc based on air quality data Skq, accident frequency Lsg, traffic congestion index Zjy, weather comprehensive index Ztq, construction impact index Zsg, road section safety score Faq, traffic signal timing optimization index Jdy, charging pile coverage rate Cf, bicycle rental point convenience index Zbc, population mobility index Zrl, and public transportation travel index Zgc. ， e represents a natural constant; Intelligent decision-making module: using simulated annealing algorithm, based on the comprehensive evaluation index of urban traffic management, it generates multiple traffic management strategies and selects the optimal traffic management strategy; The calculation formula of the traffic congestion index is specifically: Where Zjy represents the traffic congestion index, ly represents the amount of traffic flow, ρy represents the density of traffic flow, and vy represents the speed of traffic flow; The calculation formula of the weather comprehensive index is specifically: Ztq=β1×ta+β2×tb+β3×tc+β4×td, wherein Ztq represents the weather comprehensive index, ta represents temperature, tb represents rainfall, tc represents humidity, td represents wind force, β1, β2, β3, β4 represent the proportional coefficients of each item, β1+β2+β3+β4=1; The calculation formula of the construction impact index is specifically: Where Zsg represents the construction impact index, ts represents the construction duration, S represents the construction area, λ represents the size of the construction impact range, specifically the number of lanes affected or the proportion of vehicles passing through the area, and L represents the total length of the road; The calculation formula of the road section safety score is specifically: Faq=γ1×Fxs+γ2×Fpz+γ3×Fsh+γ4×Fkd, where Faq represents the road section safety score, and Fxs represents the road section speed limit score. Xs represents the maximum speed limit score, V represents the actual speed of the vehicle, Vs represents the speed limit of the road section, and Fpz represents the road section flatness score. n represents the number of measurement points, hxi represents the elevation data of the i-th measurement point of the road, Hx represents the highest score of flatness, Fsh represents the score of road section damage degree, Fkd represents the score of pothole location of road section, γ1, γ2, γ3, γ4 represent the proportional coefficients of each item, γ1+γ2+γ3+γ4=1; The calculation formula of the traffic light timing optimization index is specifically: Where Jdy represents the traffic light timing optimization index, df represents the maximum score, tw represents the average delay time, lct represents the vehicle flow through the traffic light, and lcz represents the total vehicle flow; The calculation formula of the charging pile coverage rate is specifically: Where Cf represents the coverage rate of charging piles, My represents the number of installed charging piles, and M represents the number of required charging piles; The calculation formula of the bicycle rental point convenience index is specifically as follows: Where Zbc represents the convenience index of bicycle rental points, sp represents the number of bicycle rental points, and Sq represents the area of ​​the region; The calculation formula of the population mobility index is as follows: Where Zrl represents the population mobility index, ll represents the flow of user mobile data, lv represents the speed of user mobile data, Nr represents the population, υ1 and υ2 represent the proportional coefficients of each item, υ1+υ2=1; The calculation formula of the public transportation travel index is specifically as follows: Where Zgc represents the public transportation travel index, cs represents the number of public transportation passengers, cx represents the number of boarding and alighting points, and TA represents the average travel time; Traffic management module: used to implement specific traffic management measures according to the optimal traffic management strategy of the intelligent decision-making module; The specific processing process of the policy planning unit is as follows: D1. Based on the comprehensive evaluation index of urban traffic management, generate E possible traffic management strategies through simulated annealing algorithm; the traffic management strategies include traffic flow allocation plan, traffic signal timing optimization plan, road planning adjustment plan, and public transportation system improvement plan; D2. Quantitatively evaluate and compare the generated multiple traffic management strategies by using the analytic hierarchy process in combination with pre-set evaluation indicators; the pre-set evaluation indicators include the coefficient of change of the sustainable development index, the coefficient of change of the traffic congestion index and the air quality improvement coefficient; D3. Normalize each evaluation indicator to ensure that the data are at the same level. The calculation formula for the normalization is: Where Gpg represents the normalized evaluation index, pg represents the original evaluation index, pgmin represents the minimum value of the evaluation index, and pgmax represents the maximum value of the evaluation index; that is, in each traffic management strategy, the corresponding normalized change coefficient of the sustainable development index, the change coefficient of the traffic congestion index, and the air quality improvement coefficient are recorded as GXkc, GXjy, and GXkq respectively; D4. Calculate the comprehensive score ZHF of each traffic management strategy. The specific calculation formula is: ZHF=ω1×GXkc+ω2×GXjy+ω3×GXkq, where GXkc represents the coefficient of change of the sustainable development index after normalization, GXjy represents the coefficient of change of the traffic congestion index after normalization, GXkq represents the coefficient of improvement of air quality after normalization, and ω1, ω2, and ω3 represent the proportional coefficients of each item; D5. Compare the comprehensive scores of various traffic management strategies and select the traffic management strategy with the highest score as the best performing one; Performance optimization module: used to monitor the application data of traffic management strategies in real time and optimize the performance of the system; The specific processing process of the performance optimization module is as follows: E1. Collect relevant data in the application process of traffic management strategies in real time based on monitoring equipment, including the total number of passing vehicles, total travel time, delay time, and the number of traffic accidents; E2. After pre-processing the collected real-time data, data analysis is performed to calculate the traffic flow, delay reduction and accident reduction rate after the application of traffic management strategies; The calculation formula of the traffic fluency Djt is specifically: Where cls represents the total number of passing vehicles, and txs represents the total travel time; The calculation formula of the delay reduction degree TD is specifically: TD=Tdy-Tdh, where Tdy represents the delay time before the traffic management strategy is applied, and Tdh represents the current delay time; The calculation formula of the accident reduction rate Lvs is specifically: Where ylv represents the number of accidents before the traffic management strategy is applied, and hlv represents the current number of accidents; E3. Based on the analyzed data and the expected performance evaluation index, the performance value of the current traffic management strategy is calculated; the expected performance evaluation index includes the expected traffic flow Djt0, the expected delay reduction degree TD0 and the expected accident reduction rate Lvs0; the calculation formula of the performance value Xnb is: Where Djt represents traffic smoothness, TD represents the degree of delay reduction, and Lvs represents the accident reduction rate; E4. Compare and judge the performance value Xnb with the pre-set performance threshold Xnb. If Xnb≥Xnb, it means that the performance of the current traffic management strategy is poor after application, and the traffic management strategy needs to be optimized and adjusted; otherwise, it means that the performance of the current traffic management strategy is good after application and can continue to be applied.

2. A method for urban green traffic management based on multi-source data, the method being used to implement the urban green traffic management system based on multi-source data as claimed in claim 1, characterized in that: The following steps are involved: Step S1, collecting various traffic-related raw data through various data sources; Step S2: cleaning, filtering and correcting the collected raw data; Step S3, integrating data from different sources to form a comprehensive traffic information database; Step S4: Use big data technology to analyze and process the fused data and calculate the comprehensive evaluation index of urban traffic management; Step S5: Based on the comprehensive evaluation index of urban traffic management, a plurality of traffic management strategies are generated by using a simulated annealing algorithm, and the optimal traffic management strategy is screened out; Step S6: Execute specific traffic management measures according to the optimal traffic management strategy; Step S7: monitor the application data of the traffic management strategy in real time and optimize the performance of the system.

Images