A traffic convenience index evaluation method based on big data

Abstract

The application relates to the technical field of traffic management, in particular to a traffic convenience index evaluation method based on big data, which comprises the following steps: receiving vehicle flow and driving speed data from multiple traffic monitoring nodes, transmitting the data to an analysis platform in real time, integrating the vehicle speed and flow of each node, and obtaining traffic flow state indexes. In the application, the real-time integration of the vehicle flow and driving speed data of the monitoring nodes significantly improves the real-time performance and accuracy of the data, makes the traffic flow state monitoring more accurate, assists city planners and traffic management departments in rapidly responding to changes, identifies peak and trough periods by analyzing daily and weekly changes, calibrates flow anomalies through statistical analysis, effectively predicts management peaks, reduces congestion, analyzes abnormal traffic flow changes through history comparison, optimizes emergency response plans, improves the adaptability of urban traffic, uses a linear regression model to predict future trends, adjusts the traffic convenience index, and promotes the optimization of urban traffic layout.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of traffic management, and particularly relates to a traffic convenience index evaluation method based on big data. BACKGROUND

[0002] The technical field of traffic management involves the use of various tools and strategies to monitor, control, and optimize road traffic. The main goal of this field is to improve traffic efficiency, reduce congestion, enhance safety, and increase the sustainability of the transportation system. In modern traffic management, technologies such as traffic signal control systems, real-time traffic information systems, automatic license plate recognition technology, and various sensors and monitoring devices are widely used to assist traffic management centers in collecting real-time traffic flow data, vehicle types, and speed information, and then analyzing traffic conditions to develop response measures. Traffic management also includes the planning and management of public transportation systems, such as adjusting bus routes and schedules to adapt to changes in traffic demand.

[0003] Among them, the traffic convenience index evaluation method is a technology for analyzing and evaluating the convenience of the transportation system. By calculating the traffic convenience index, it can provide quantitative data on the efficiency of the transportation system for urban planners, traffic engineers, and policymakers. The calculation of the convenience index is based on factors such as traffic flow speed, road congestion, traffic accident frequency, accessibility and reliability of public transportation, etc. Using this evaluation method, relevant departments can identify bottlenecks and problem areas in the transportation system, and then optimize traffic signal settings, improve road design, or enhance public transportation services, to improve the overall efficiency of the transportation system and the convenience of the public.

[0004] Although existing technologies widely use traffic signal control systems, real-time traffic information systems, etc., there are deficiencies in the integration and real-time feedback of real-time data. Especially during peak traffic periods, existing systems cannot quickly identify and respond to sudden events, leading to increased congestion. Existing technologies rely on historical trends when analyzing traffic data, lacking the ability to quickly adapt to immediate changes such as weather or temporary events, which limits the efficiency and accuracy of traffic management. The lack of a mechanism to flexibly adjust the traffic convenience index also makes it difficult for urban planners to effectively predict and plan for future traffic pressures, affecting the long-term development and optimization of the entire urban transportation system, limiting the ability of urban traffic management to respond to sudden events and long-term planning, and affecting the overall performance of the transportation system and the convenience of public travel. SUMMARY

[0005] The purpose of the present application is to solve the shortcomings in the prior art and to propose a traffic convenience index evaluation method based on big data.

[0006] In order to achieve the above object, the present application adopts the following technical scheme, a traffic convenience index evaluation method based on big data, comprising the following steps:

[0007] S1: receiving vehicle flow and driving speed data from multiple traffic monitoring nodes, the data being transmitted to an analysis platform in real time, integrating vehicle speed and flow of each node, and obtaining traffic flow state indicators;

[0008] S2: analyzing daily and weekly changes of traffic flow according to the traffic flow state indicators, determining peak and valley periods, identifying time periods of standard deviation and mean value anomalies, and obtaining traffic fluctuation analysis results;

[0009] S3: comparing the traffic fluctuation analysis results with past data of the same period, identifying change factors that do not conform to the conventional mode, analyzing the statistical influence of the change factors, and evaluating the influence on traffic flow, and obtaining traffic anomaly factor evaluation results;

[0010] S4: adjusting the threshold of abnormal flow according to the traffic anomaly factor evaluation results through event type, referring to the comparison results of real-time data and original data, and obtaining response threshold setting results;

[0011] S5: based on the response threshold setting results, using a linear regression model to predict traffic trends in future time periods, adjusting traffic convenience index parameters, and obtaining traffic trend prediction and index adjustment results;

[0012] S6: updating the traffic convenience index according to the traffic trend prediction and index adjustment results, optimizing urban traffic layout and relieving traffic congestion, and obtaining traffic guidance and route planning adjustment results.

[0013] As a further scheme of the present application, the traffic flow state indicators include vehicle speed mean value indicators, flow accumulation indicators, and average flow indicators, the traffic fluctuation analysis results include peak period identification, valley period identification, and abnormal flow period, the traffic anomaly factor evaluation results include weather influence evaluation, holiday influence evaluation, and key event influence evaluation, the response threshold setting results include event type threshold and real-time data comparison threshold, the traffic trend prediction and index adjustment results include future traffic trends and adjusted convenience index, and the traffic guidance and route planning adjustment results include updated traffic convenience index, optimized traffic layout, and congestion relief measures.

[0014] As a further scheme of the present application, the step of receiving vehicle flow and driving speed data from multiple traffic monitoring nodes, transmitting the data to an analysis platform in real time, integrating vehicle speed and flow of each node, and obtaining traffic flow state indicators is specifically as follows:

[0015] S101: Receive vehicle flow and driving speed data from multiple traffic monitoring nodes, format check the data, eliminate data that does not conform to the format and error data, sort the data according to the timestamp, and generate a traffic data sequence;

[0016] S102: Based on the traffic data sequence, calculate the average value of the multi-node vehicle speed and flow using the moving average method, perform timed analysis on each node, identify and record the flow and speed fluctuations in multiple time periods, and obtain a node traffic mode overview;

[0017] S103: Based on the node traffic mode overview, integrate node data, calculate the total vehicle flow and the average vehicle speed of the node, use data aggregation methods to accumulate node data, and generate traffic flow state indicators.

[0018] As a further scheme of the present application, according to the traffic flow state indicators, analyze the daily and weekly changes of traffic flow, determine the peak and valley periods, identify the time periods of standard deviation and mean anomaly, and obtain traffic fluctuation analysis results, the steps being specifically as follows:

[0019] S201: Based on the traffic flow state indicators, record the vehicle flow per hour and calculate the average vehicle flow per hour, mark and analyze the data of weekdays and non-weekdays respectively, and obtain a daily flow change graph;

[0020] S202: Use the data in the daily flow change graph to compare daily flow, calculate the average and fluctuation of vehicle flow on weekdays and weekends, identify the peak and valley periods in each week, draw the periodic change of flow in a week, and obtain a weekly flow trend graph;

[0021] S203: According to the weekly flow trend graph, calculate the flow standard deviation and mean value of each time period, compare the flow changes in the same time period, identify and mark the time periods of abnormal flow increase and decrease, and generate traffic fluctuation analysis results.

[0022] As a further scheme of the present application, compare the traffic fluctuation analysis results with the same period data in the past, identify the change factors that do not conform to the conventional mode, analyze the statistical influence of the change factors, and evaluate the influence on traffic flow, and obtain traffic anomaly factor evaluation results, the steps being specifically as follows:

[0023] S301: Based on the traffic fluctuation analysis results, compare the current traffic data with the original same period data, mark the date and time period by identifying the deviation value, determine the preliminary mode change, and generate a mode change marking result;

[0024] S302: Capture weather records, holiday schedules and key event information corresponding to the marked date using the mode change marker result, associate information with traffic data using classification sorting method, evaluate the influence degree of multiple factors on the difference marked date, and obtain classification factor influence result;

[0025] S303: According to the classification factor influence result, apply linear regression algorithm, integrate and calculate the influence degree of factors on traffic flow in time period, analyze the statistical value of factor influence through data correlation, evaluate the real-time influence of each factor on traffic flow state, and generate traffic anomaly factor evaluation result.

[0026] As a further scheme of the application, the formula of the linear regression algorithm is as follows:

[0027]

[0028] Calculate the traffic flow influence weight to obtain the traffic anomaly factor evaluation result, wherein y represents the traffic flow influence weight, β0 represents the intercept of the model, β1 represents the influence coefficient of weather condition, β2 represents the influence coefficient of time period, x3 represents the current traffic flow, x4 represents the average value of the original traffic flow in the same period, x1 represents the current weather condition, x2 represents whether the current time is a peak period, and β3 represents the influence weight.

[0029] As a further scheme of the application, according to the traffic anomaly factor evaluation result, the threshold of abnormal flow is adjusted through event type, and the response threshold setting result is obtained by referring to the comparison result of real-time data and original data.

[0030] S401: Based on the traffic anomaly factor evaluation result, classify the key event type, including holiday and large-scale activity, collect the original traffic flow data during the event, adjust the threshold of flow anomaly by comparing the original average flow with the current flow, and generate the adjusted event threshold result;

[0031] S402: Use the adjusted event threshold result to monitor real-time traffic data, compare the traffic flow of each time point with the threshold, identify the period of flow anomaly, reveal the real-time abnormal state of flow, and obtain the real-time abnormal flow monitoring result;

[0032] S403: According to the real-time abnormal flow monitoring result, optimize the traffic signal adjustment and route, implement corresponding traffic management measures, match the flow change of different types of events, and generate response threshold setting result.

[0033] As a further scheme of the present application, based on the response threshold setting result, the traffic trend in the future time period is predicted using a linear regression model, the traffic convenience index parameter is adjusted, and the traffic trend prediction and index adjustment result is obtained.

[0034] S501: Based on the response threshold setting result, time series data associated with the prediction period in the future time period is selected, a basic linear regression model is applied to predict the traffic in the key period, and a corrected model is obtained by calculating the data points in each period.

[0035] S502: Using the adjusted traffic prediction model, analyze the prediction data of the key event day and the non-event day, optimize the calculation parameters of the traffic convenience index, refine the setting of the traffic convenience index, and obtain the optimized traffic convenience index result.

[0036] S503: According to the optimized traffic convenience index result, apply a weighted regression algorithm to evaluate the traffic conditions in the future time period, compare the prediction data with the current real-time data, adjust the index, and generate traffic trend prediction and index adjustment result.

[0037] As a further scheme of the present application, the formula of the weighted regression algorithm is as follows:

[0038]

[0039] Calculate the traffic convenience index in the future time period to generate the adjusted traffic trend prediction value, wherein T represents the adjusted traffic convenience index, a represents the weight of the original traffic data, β represents the weight of the real-time traffic data, γ represents the change coefficient of the traffic flow, δ represents the smoothing parameter of the model, and ∈ represents the current real-time traffic convenience index. c T represents the current calculated traffic convenience index. h T represents the traffic convenience index of the original traffic data. r T represents the traffic convenience index of the real-time traffic data. r V represents the current monitored traffic flow.

[0040] As a further scheme of the present application, according to the traffic trend prediction and index adjustment result, update the traffic convenience index, optimize the urban traffic layout and relieve traffic congestion, and obtain the traffic guidance and route planning adjustment result.

[0041] S601: Based on the traffic trend prediction and index adjustment result, update the traffic convenience index parameter, adjust the threshold and index weight through the predicted traffic flow peak and trough, including increasing the adjustment of the peak period weight and the buffer parameter setting of the trough period, and obtain the updated traffic convenience index.

[0042] S602: Using the updated traffic convenience index, analyze the current traffic flow conditions in combination with real-time traffic data, identify key traffic congestion points and smooth areas, adjust routes and signal control logic, optimize traffic flow and reduce congestion, including adjusting traffic signal duration and optimizing bus lane configuration, obtain city traffic layout optimization results;

[0043] S603: According to the city traffic layout optimization results, set up temporary traffic diversion routes and increase traffic monitoring in key periods, evaluate the real-time impact of multiple measures on traffic flow, adjust and refine traffic management in future time periods, generate traffic guidance and route planning adjustment results.

[0044] Compared with the prior art, the advantages and positive effects of the present application are:

[0045] In the present application, by collecting and integrating the vehicle flow and driving speed data of each monitoring node in real time, the real-time and accuracy of traffic data are significantly improved, and the integrated data makes the monitoring of traffic flow more accurate, allowing city planners and traffic management departments to quickly respond to changes in traffic conditions, identify peak and trough periods by analyzing the daily and weekly changes in traffic flow, and determine abnormal flow based on statistical analysis, which can more effectively predict and manage traffic peaks, reduce traffic congestion, and further optimize traffic emergency response plans by analyzing irregular traffic flow changes such as weather or special events, improving the adaptability and flexibility of the city's traffic system, predicting future traffic trends through linear regression models and adjusting the traffic convenience index, which helps to plan and optimize city traffic layout in advance, thereby reducing traffic pressure in future time periods and improving overall traffic system efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0046] Figure 1 is the main step schematic diagram of the present application;

[0047] Figure 2 is the S1 refinement schematic diagram of the present application;

[0048] Figure 3 is the S2 refinement schematic diagram of the present application;

[0049] Figure 4 is the S3 refinement schematic diagram of the present application;

[0050] Figure 5 is the S4 refinement schematic diagram of the present application;

[0051] Figure 6 is the S5 refinement schematic diagram of the present application;

[0052] Figure 7S6 is a detailed schematic view of the application. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application will be further described in detail below in combination with the drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application and do not limit the present application.

[0054] In the description of the present application, it should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, in the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise explicitly and specifically limited.

[0055] Example one

[0056] Please refer to Figure 1 The present application provides a technical scheme, a traffic convenience index evaluation method based on big data, comprising the following steps:

[0057] S1: receiving vehicle flow and driving speed data from multiple traffic monitoring nodes, the data is transmitted to the analysis platform in real time, the vehicle speed and flow of each node are integrated, including average and cumulative calculation, and the traffic flow state index is obtained;

[0058] S2: according to the traffic flow state index, analyze the daily and weekly changes of traffic flow, determine the peak and trough periods by statistical analysis, identify the time period of abnormal increase and decrease of traffic flow according to the standard deviation and mean value of traffic flow, and obtain the traffic fluctuation analysis result;

[0059] S3: compare the traffic fluctuation analysis result with the same period data in the past, identify the change factors that do not conform to the conventional mode, including the influence of weather, holidays and key events, analyze the statistical influence of the change factors, and evaluate the influence on traffic flow, and obtain the traffic abnormal factor evaluation result;

[0060] S4: according to the traffic abnormal factor evaluation result, adjusting the threshold value of abnormal flow through event type, including holiday and large-scale activity, setting response measures according to the comparison result of real-time data and original data, and obtaining response threshold setting result;

[0061] S5: Based on the response threshold setting result, use the linear regression model to predict the traffic trend in the future time period, adjust the traffic convenience index parameter through regression analysis to reflect the expected traffic condition in the future time period, and obtain the traffic trend prediction and index adjustment result;

[0062] S6: According to the traffic trend prediction and index adjustment result, update the traffic convenience index, and apply the current traffic data and convenience index to optimize the urban traffic layout and relieve traffic congestion, and obtain the traffic guidance and route planning adjustment result.

[0063] The traffic flow state index includes the average speed index, the cumulative flow index, and the average flow index, the traffic fluctuation analysis result includes the peak period identification, the trough period identification, and the abnormal flow period, the traffic abnormal factor evaluation result includes the weather influence evaluation, the holiday influence evaluation, and the key event influence evaluation, the response threshold setting result includes the event type threshold and the real-time data comparison threshold, the traffic trend prediction and index adjustment result includes the future traffic trend and the adjusted convenience index, and the traffic guidance and route planning adjustment result includes the updated traffic convenience index, the optimized traffic layout, and the congestion relief measures.

[0064] Specifically, as shown in Figure 2 The vehicle flow and driving speed data are received from multiple traffic monitoring nodes, the data is transmitted to the analysis platform in real time, the vehicle speed and flow of each node are integrated, and the traffic flow state index is obtained. The steps are as follows:

[0065] S101: Receive vehicle flow and driving speed data from multiple traffic monitoring nodes, perform format verification on the data, eliminate data that does not conform to the format and errors, sort the data according to the time stamp, and generate the execution flow of the traffic data sequence as follows:

[0066] The vehicle flow and driving speed data received from multiple traffic monitoring nodes need to be verified by format to ensure the accuracy and effectiveness of the data. During the data receiving process, the traffic monitoring nodes automatically collect vehicle flow and driving speed through their own sensors. The data is presented in the form of time stamp, vehicle count and speed reading. In order to ensure the consistency and integrity of the data, a format verification mechanism is introduced. This mechanism verifies the actual format of each data point against the pre-set data format requirements, such as the time stamp format YYYY-MM-DDHH:MM, the numerical value of vehicle flow and speed should be within a reasonable range, such as speed cannot be negative and flow count should be non-negative integer. By comparing the actual format of each data point with the pre-set format, the data that is format error or does not conform to the logic is filtered out. After the data is filtered out, the remaining valid data is sorted according to the time stamp to form a traffic data sequence arranged in chronological order. This sequence will provide a basis for subsequent traffic flow analysis.

[0067] S102: Based on the traffic data sequence, the moving average method is used to calculate the average values of the multi-node vehicle speed and flow, and the time analysis is performed for each node to identify and record the flow and speed fluctuations in multiple time periods, and the execution process of obtaining the node traffic mode overview is as follows:

[0068] Based on the traffic data sequence, the moving average method is used to calculate the average values of the multi-node vehicle speed and flow, and the moving average method formula is:

[0069]

[0070] The average vehicle speed and flow of each node in multiple time periods are calculated, wherein MA t represents the moving average value of time t, N represents the length of the time window, X t-i represents the data point at time t-i;

[0071] The selected time window length is set to 5 minutes, and the recorded data points X t , X t-1 , X t-2 , X t-3 , X t-4 are 20, 22, 19, 21, and 23 km / h respectively, and the formula is calculated to obtain

[0072] This result shows that the average vehicle speed of the node in this time window is 21 km / h, which reflects the smoothness of the vehicle driving in this time period.

[0073] S103: Based on the node traffic mode overview, integrate node data, calculate the total vehicle flow and the average vehicle speed of the node, use the data aggregation method to accumulate node data, and the execution process of generating the traffic flow state index is as follows:

[0074] According to the node traffic mode overview, integrate node data, this process first involves the data summary of multiple nodes, the traffic flow state data generated by each node needs to be integrated in the central system, including the calculation of the total vehicle flow and the average vehicle speed of each node, and in the integration process, the data aggregation method is used, which involves merging and recalculating the data of multiple data sources. The specific data aggregation can be performed by weighted average or simple accumulation to obtain global traffic state indexes such as total vehicle flow and average vehicle speed of each node, which can provide decision support for traffic management departments, optimize traffic flow and improve road use efficiency.

[0075] Specifically, as Figure 3As shown, according to the traffic flow state index, the daily and weekly changes of traffic flow are analyzed, the peak and valley periods are determined, the time periods of standard deviation and mean anomaly are identified, and the traffic fluctuation analysis result is obtained. The steps are specifically as follows:

[0076] S201: Based on the traffic flow state index, the hourly vehicle flow is recorded, and the average value of the hourly vehicle flow is calculated. The data of weekdays and non-weekdays are marked and analyzed respectively, and the execution process of obtaining the daily flow change graph is as follows:

[0077] Based on the traffic flow state index, the hourly vehicle flow is recorded, which involves automatic collection and recording of data. The traffic monitoring system automatically collects vehicle quantity data from each monitoring point every hour and records the data into the database. The data generated every hour includes specific vehicle flow numbers. In order to ensure the accuracy of the data, a data verification process is introduced to verify the time stamp and data integrity. After ensuring that the hourly recorded vehicle flow data is correct, the average value of the hourly vehicle flow is calculated by an algorithm, and the calculated average value is stored in the database for later use. In order to analyze the traffic flow difference between weekdays and non-weekdays, the system will automatically mark weekdays and non-weekdays according to the date, and analyze the data of these two types respectively, so as to generate a daily flow change graph. The graph shows the fluctuation of vehicle flow on weekdays and non-weekdays, which provides a basis for traffic planning and management.

[0078] S202: Using the data in the daily flow change graph, daily flow comparison is performed, the average and fluctuation of vehicle flow on weekdays and weekends are calculated, the peak and valley periods in each week are identified, the periodic change of flow in a week is drawn, and the execution process of obtaining the weekly flow trend graph is as follows:

[0079] Using the data in the daily flow change graph, daily flow comparison is performed, according to the formula:

[0080]

[0081] And

[0082]

[0083] The average and fluctuation of vehicle flow on weekdays and weekends are calculated, wherein x j represents the vehicle flow of the jth day, μ represents the average vehicle flow, σ 2 represents the variance of vehicle flow, and n represents the number of days.

[0084] For example, if the vehicle flow data of weekdays is x j =[2000, 2100, 2200, 2300, 2400], the formula is substituted to calculate:

[0085] The variance calculation is: This result shows that the average value of vehicle flow on weekdays is 2200, and the variance is 20000, reflecting the stability and volatility of vehicle flow within weekdays.

[0086] S203: According to the weekly traffic trend chart, calculate the standard deviation and mean of the traffic in each time period, compare the traffic changes in the same time period, identify and mark the time period of abnormal traffic increase and decrease, and generate the execution process of traffic fluctuation analysis result as follows:

[0087] According to the weekly traffic trend chart, first, the standard deviation and mean of the traffic in each time period need to be calculated, including statistical analysis of the recorded traffic data in each time period, statistical analysis including calculating the sum of traffic in each time period and its average value, then using statistical data, using the standard deviation formula to calculate the traffic fluctuation in each time period, the standard deviation calculation involves the deviation of each time point traffic from the average traffic, the larger the standard deviation, the greater the traffic fluctuation, the calculation process plays a key role in identifying traffic anomalies, by comparing the traffic standard deviation of different time periods, abnormal time periods of traffic sudden increase or decrease can be identified, after marking the anomaly, traffic management measures will be adjusted or further traffic analysis will be carried out, the generated traffic fluctuation analysis result will provide a scientific basis for urban traffic planning.

[0088] Specifically, as shown in Figure 4 traffic fluctuation analysis results and past data of the same period are compared to identify factors that do not conform to the regular pattern, analyze the statistical impact of the change factors, and evaluate the impact on traffic flow, the steps to obtain the traffic anomaly factor evaluation result are as follows:

[0089] S301: Based on the traffic fluctuation analysis result, compare the current traffic data with the original data of the same period, mark the date and time period by identifying the deviation value, determine the preliminary pattern change, and generate the execution process of the pattern change marking result as follows:

[0090] Based on the traffic wave analysis results, the current traffic data is compared with the original same period data, which involves extracting the historical traffic data of the same period from the historical database and comparing it with the current data. During the comparison process, the numerical deviation analysis method is used to calculate the quantitative difference of the traffic flow of each period, automatically calculate the traffic flow difference between the current data and the historical data, and determine whether there is a significant traffic pattern change. If the current traffic flow is significantly higher or lower than the historical same period data, mark the date and period as abnormal, and record the deviation value during the marking process for further analysis of the reasons. This deviation value calculation not only assists in identifying preliminary pattern changes, but also helps subsequent in-depth analysis and decision making. The generated pattern change marking results will be used for further traffic management and planning optimization.

[0091] S302: Using the pattern change marking results, capture the weather records, holiday schedules and key event information corresponding to the marked date, use the classification and sorting method to associate the information with the traffic data, and evaluate the influence degree of multiple factors on the marked date. The execution process of the classification factor influence result is as follows:

[0092] Using the pattern change marking results, capture the weather records, holiday schedules and key event information corresponding to the marked date, automatically extract the weather conditions, holiday arrangements and special event records such as large-scale activities or public engineering corresponding to the traffic data from multiple external data sources. Information is systematically associated with the traffic data of each marked date through data mining and classification and sorting methods. Through this association, analysts can evaluate the specific influence degree of classification factors such as weather, holidays or special events on traffic flow in differentiating dates. Analysis not only reveals how each factor affects daily traffic patterns, but also provides a basis for real-time adjustment of traffic flow management, ensuring efficient operation of the traffic system.

[0093] S303: According to the classification factor influence result, apply linear regression algorithm, integrate and calculate the influence degree of factors on traffic flow in period, analyze the statistical value of factor influence through data association, evaluate the real-time influence of each factor on traffic flow state, and the execution process of traffic abnormal factor evaluation result is as follows:

[0094] The formula of linear regression algorithm is as follows:

[0095]

[0096] The traffic flow influence weight is calculated to obtain a traffic anomaly factor evaluation result, wherein y represents the traffic flow influence weight, β0 represents a model intercept, β1 represents an influence coefficient of weather conditions, β2 represents an influence coefficient of a time period, x3 represents a current traffic flow, x4 represents an average value of a same-period original traffic flow, x1 represents a current weather condition, x2 represents whether a current time is a peak period, and β3 represents an influence weight;

[0097] The formula details and formula calculation derivation process are as follows:

[0098] The linear regression model is used to evaluate the influence of weather conditions, time periods, and current traffic flow on baseline traffic flow, and specific parameters are as follows:

[0099] β0 (intercept) represents a baseline traffic flow without any factor influence, which is obtained from a report published by a city traffic management department. Historical data show that the average value of the baseline traffic flow is 500 vehicle times / hour without any external influence.

[0100] β1 (influence coefficient of weather conditions) is obtained by analyzing the correlation between historical weather data and traffic flow data. Data shows that traffic flow decreases by 15% on rainy days, and therefore β1 is set to -0.15.

[0101] β2 (influence coefficient of time period) is obtained by analyzing traffic flow statistical data of different time periods. Traffic flow increases by 30% during peak periods (such as morning and evening peak periods), and therefore β2 is set to 0.30.

[0102] x1 represents a current weather condition, which is obtained through a real-time weather monitoring system, wherein 1 represents a sunny day and 0 represents a rainy day.

[0103] x2 represents whether a current time is a peak period, which is monitored in real time by a traffic flow monitoring system, wherein 1 represents a peak period and 0 represents a non-peak period.

[0104] x3 represents a current traffic flow, which is obtained in real time by a road camera and a vehicle flow monitoring device. It is assumed that the measured value in a certain period is 800 vehicle times / hour.

[0105] x4 represents an average value of a same-period original traffic flow, which is calculated according to data of the same time period in the past three years. It is assumed that the value is 650 vehicle times / hour.

[0106] Actual numerical values are substituted into the calculation:

[0107]

[0108] y = 500 + 0 + 0.30 x 1 + (-0.20) x 1.23

[0109] y = 500 + 0.30 - 0.246

[0110] y = 500.054

[0111] The results show that after referring to the ratio of current traffic flow to historical average value during peak hours, the predicted traffic flow is 500.054 vehicles per hour, which shows that during peak hours, even if the current traffic flow is slightly higher than the historical average, the overall traffic flow is close to the baseline, indicating that the model is very effective in assessing the real-time impact of traffic flow, and through this model, the traffic management department can more accurately predict and manage the flow state of urban traffic, so as to adjust the traffic signal system in advance or issue traffic control measures to reduce traffic congestion.

[0112] Specifically, as shown in Figure 5 the traffic anomaly factor evaluation result, the threshold of abnormal flow is adjusted through the event type, and the response threshold setting result is obtained by referring to the comparison result of real-time data and original data. The specific steps are as follows:

[0113] S401: Based on the traffic anomaly factor evaluation result, classify the key event types, including holidays and large activities, collect the original traffic flow data during the event, adjust the threshold of flow anomaly by comparing the original average flow with the current flow, and the execution process of generating the adjusted event threshold result is as follows:

[0114] Based on the traffic anomaly factor evaluation result, classify the key event types, this classification process includes identifying which event types, such as holidays or large activities, have a significant impact on traffic flow, the system identifies events that have a greater impact on traffic flow by analyzing historical data, and classifies them as key event types, then, collect the original traffic flow data during the event, during the collection process, the data collection system will obtain traffic data from multiple monitoring points to ensure that the obtained data can represent the traffic conditions of the entire city or a specific area, by comparing the original average flow with the current flow, using statistical analysis methods such as z-score or standard deviation analysis, adjusting the threshold of flow anomaly, this adjustment is based on historical data and current observed data changes, generating the adjusted event threshold result, this result is used for further monitoring and management to ensure that the traffic system can respond quickly to predicted and actual events.

[0115] S402: Use the adjusted event threshold result to monitor real-time traffic data, compare the traffic flow at each time point with the threshold, identify the period of flow anomaly, reveal the real-time abnormal state of flow, and obtain the execution process of real-time abnormal flow monitoring result as follows:

[0116] Use the adjusted event threshold result to monitor real-time traffic data, according to the formula:

[0117] T = q + k x u

[0118] Real-time monitoring of traffic anomalies is performed, where T represents the threshold value, q represents the historical average traffic, u represents the standard deviation of historical traffic, and k represents the coefficient for adjusting sensitivity;

[0119] Setting the average traffic during holidays q = 1000 vehicles / hour, the standard deviation u = 100 vehicles / hour, to increase the sensitivity of monitoring, set k = 2, then the threshold value is calculated as T = 1000 + 2 x 100 = 1200 vehicles / hour, this threshold value is used to identify abnormal periods when the actual traffic exceeds 1200 vehicles / hour, the result shows that any traffic exceeding 1200 vehicles / hour will be marked as abnormal, providing the basis for real-time monitoring and immediate response.

[0120] S403: According to the real-time abnormal traffic monitoring result, optimize the traffic signal adjustment and route, implement the corresponding traffic management measures, match the traffic changes of different types of events, and generate the execution process of the response threshold setting result as follows;

[0121] According to the real-time abnormal traffic monitoring result, optimize the traffic signal adjustment and route, which involves analyzing real-time data and making corresponding traffic signal and route adjustments based on real-time traffic changes, optimization measures include changing the timing of traffic lights, increasing or decreasing the number of lanes on certain routes, or implementing traffic control measures, adjustments are based on real-time abnormal traffic monitoring results and are automatically executed through advanced traffic management systems to ensure smooth traffic flow, reduce congestion and improve safety, and also include adjusting traffic according to different types of events such as holidays or special events to ensure effective management in each situation, the generated response threshold setting result will be used for future traffic prediction and management to improve the overall efficiency and responsiveness of the urban transportation system.

[0122] Specifically, as shown in Figure 6 Based on the response threshold setting result, a linear regression model is used to predict traffic trends in future time periods, and the traffic convenience index parameters are adjusted, the steps for obtaining traffic trend prediction and index adjustment results are as follows:

[0123] S501: Based on the response threshold setting result, select time series data associated with the prediction period in the future time period, apply a basic linear regression model to predict traffic in key periods, and correct the model by calculating data points in each period, the execution process of the adjusted traffic prediction model is as follows:

[0124] Based on the response threshold setting result, the time series data associated with the prediction period in the future time period is selected, involving data selection and processing to ensure that the data used is closely related to the prediction period in the future time period, and the traffic prediction of the key period is carried out using a basic linear regression model. The model learns from historical data and predicts future traffic based on historical data. The time series corresponding to the prediction period needs to be extracted from the batch historical traffic data. The data is used to train the model to accurately predict the traffic of the key period. By calculating the data points in each period, the model is corrected to adapt to new trends or patterns. Adjusting the traffic prediction model is a dynamic process that needs to be optimized in real time to improve the accuracy of the prediction. Finally, the adjusted traffic prediction model is obtained, which will be applied to traffic management and planning in the future time period to provide scientific basis and decision support.

[0125] S502: Using the adjusted traffic prediction model, analyze the prediction data of the key event day and the non-event day, optimize the calculation parameters of the traffic convenience index, refine the setting of the traffic convenience index, and obtain the execution process of the optimized traffic convenience index result as follows:

[0126] Using the adjusted traffic prediction model, analyze the prediction data of the key event day and the non-event day. During the analysis process, the model will be processed separately according to whether the differentiated type of day is an event day to ensure the accuracy and adaptability of the prediction. The step of optimizing the calculation parameters of the traffic convenience index includes analyzing the deviation between the model prediction and the actual data, adjusting the model parameters according to the deviation result, and optimizing the calculation of the traffic convenience index. This involves a complex mathematical process, including statistical analysis and pattern recognition. The refinement of the traffic convenience index setting is achieved by quantitatively analyzing various influencing factors such as traffic density, driving speed and traffic accidents to ensure that the index more accurately reflects the actual traffic conditions. The optimized traffic convenience index result will more effectively assist city planners and traffic managers to evaluate and improve urban traffic conditions.

[0127] S503: According to the optimized traffic convenience index result, apply the weighted regression algorithm to evaluate the traffic conditions in the future time period, compare the prediction data with the current real-time data, adjust the index, and generate the traffic trend prediction and index adjustment result execution process as follows:

[0128] The formula of the weighted regression algorithm is as follows:

[0129]

[0130] The traffic convenience index in the future time period is calculated, and an adjusted traffic trend prediction value is generated, wherein T represents the adjusted traffic convenience index, a represents the weight of the original traffic data, β represents the weight of the real-time traffic data, γ represents the change coefficient of the traffic flow, δ represents the smoothing parameter of the model, and ∈ represents the current real-time traffic convenience index, T c represents the current calculated traffic convenience index, T h represents the traffic convenience index of the original traffic data, T r represents the traffic convenience index of the real-time traffic data, V r represents the current monitored traffic flow;

[0131] The specific meanings and calculation processes of the parameters in the formula are as follows:

[0132] a represents the weight of the original traffic data, which is obtained by analyzing the average traffic index in the same time period in the past week. The historical traffic data weight is calculated as the average value of the traffic convenience index at the same time of each day. Assuming that the historical traffic data is the traffic index of the following seven days: 80, 75, 82, 78, 84, 77, and 79, then the value of a is the average value divided by 100 for normalization, and the calculation result is

[0133] β represents the weight of the real-time traffic data, which is adjusted in real time by analyzing the traffic convenience index in the same time period of the day. The real-time traffic data weight depends on the difference between the real-time traffic index and the historical traffic index. Assuming that the real-time traffic convenience index is 85, then the value of β is

[0134] γ represents the change coefficient of the traffic flow, reflecting the sensitivity of traffic flow changes to traffic condition prediction. This parameter is calculated based on the traffic flow data monitored by traffic cameras and sensors. Assuming that the average traffic flow during the monitoring period is 3200 vehicles / hour and the reference flow is 3000 vehicles / hour, then γ is

[0135] δ is the smoothing parameter of the model, which is set to 1 to ensure that the denominator is not zero and the calculation is stable.

[0136] ∈ represents the current real-time traffic convenience index, which is obtained through real-time data acquisition and is set to 85.

[0137] T c represents the current calculated traffic convenience index, which is calculated by the aforementioned formula and is the comprehensive evaluation result of the aforementioned weights and traffic data;

[0138] T hTraffic convenience index of historical traffic data, which is the average value calculated from the traffic data of the same time period in the past period (for example, the past week or month), reflecting the historical traffic conditions, set to 80 currently;

[0139] T r Traffic convenience index of real-time traffic data, which is the traffic convenience index at the current or latest time point obtained during the calculation process, reflecting the real-time traffic conditions, set to 85 currently;

[0140] V r Current monitored traffic flow, data obtained by real-time monitoring of traffic cameras and sensors, representing the number of vehicles passing through a certain section within a certain time, set to 10;

[0141] Substitute all parameter values into the formula for calculation:

[0142]

[0143] The result shows that under the given parameters and current traffic conditions, the adjusted traffic convenience index is 2.01, which is a low value, indicating that under the current conditions, the traffic conditions are relatively congested or there are certain inconveniences. Through this result, further traffic management and adjustment measures can be taken to improve the actual traffic conditions and make them more smooth.

[0144] Specifically, as shown in Figure 7 According to the traffic trend prediction and index adjustment results, update the traffic convenience index, optimize the urban traffic layout and relieve traffic congestion, and obtain the traffic guidance and route planning adjustment results. The specific steps are as follows:

[0145] S601: Update the traffic convenience index parameters based on the traffic trend prediction and index adjustment results, adjust the threshold and index weight by predicting the traffic flow peak and trough, including increasing the adjustment of the peak period weight and setting the buffer parameters of the trough period, and obtain the execution process of the updated traffic convenience index as follows:

[0146] Based on the traffic trend prediction and index adjustment results, update the traffic convenience index parameters, involving data analysis and new parameter setting, including consideration of traffic flow peak and valley periods, adjustment of threshold and index weight, including emphasis on peak period weight and setting buffer parameters for valley period, adjustment needs to be accurately completed according to historical traffic flow data and model prediction, by analyzing the flow changes of differentiated time periods, determine the specific values of weight adjustment, for example, increase the weight of peak period to reflect its actual impact on traffic system pressure, and reduce the weight of valley period to adapt to the actual changes of traffic flow, get the updated traffic convenience index, which more accurately reflects the actual traffic conditions and provides a more scientific basis for urban traffic management.

[0147] S602: Use the updated traffic convenience index to analyze the current traffic flow conditions combined with real-time traffic data, identify key traffic congestion points and smooth areas, adjust routes and signal control logic to optimize traffic flow and reduce congestion, including adjusting traffic signal duration and optimizing bus lane configuration, the execution process of obtaining urban traffic layout optimization results is as follows;

[0148] Use the updated traffic convenience index to analyze the current traffic flow conditions combined with real-time traffic data, including identifying key congestion points and smooth areas in the traffic system, adjusting routes and signal control logic to optimize traffic flow and reduce congestion, adjusting traffic signal duration and optimizing bus lane configuration are key measures, determine which road sections need to increase signal duration, which road sections can reduce, and where to add or optimize bus lanes through data analysis, the adjustment is based on the results of real-time and historical data analysis to ensure that it can effectively cope with current and predicted traffic conditions, obtain urban traffic layout optimization results, which will directly affect the daily travel of urban residents and the sustainable development of urban traffic.

[0149] S603: According to the urban traffic layout optimization results, set up temporary traffic diversion routes and increase traffic monitoring in key periods, evaluate the real-time impact of multiple measures on traffic flow, adjust and refine traffic management in future time periods, the execution process of generating traffic guidance and route planning adjustment results is as follows;

[0150] Evaluate the traffic conditions in future time periods according to the formula:

[0151]

[0152] Compare the predicted data with the current real-time data and adjust the index, where Y represents the predicted traffic condition index, w z represents the weight of the zth factor, x z represents the value of the zth factor, and m represents the total number of factors;

[0153] Set three factors: traffic volume x1 = 300 cars / hour, speed x2 = 50 km / h, the number of accidents x3 = 2, the weight is set as w1 = 0.5, w2 = 0.3, w3 = 0.2, then calculate: Y = 0.5 * 300 + 0.3 * 50 + 0.2 * 2 = 160;

[0154] This result shows that under the given weight and factor values, the predicted traffic condition index is 160, which helps to monitor and evaluate traffic conditions in real time, providing decision support for traffic management.

[0155] The above is only the preferred embodiment of the present application, not other forms of the present application, any skilled in the art can use the above disclosed technical content to change or modify as equivalent embodiments applied to other fields, but any simple modification, equivalent change and modification of the above embodiments without departing from the technical solution content of the present application, according to the technical essence of the present application, still belongs to the protection scope of the technical solution of the present application.

Claims

1. A traffic convenience index evaluation method based on big data, characterized in that: The following steps are involved: Receive vehicle flow and speed data from multiple traffic monitoring nodes, transmit the data to the analysis platform in real time, integrate the speed and flow of each node, and obtain traffic flow status indicators; Based on the traffic flow status indicators, analyze the daily and weekly changes in traffic flow, determine the peak and valley periods, identify the time periods with abnormal standard deviations and mean values, and obtain traffic fluctuation analysis results; Comparing the traffic fluctuation analysis results with past data for the same period to identify factors that do not conform to normal patterns, analyzing the statistical impact of the factors, and evaluating the impact on traffic flow to obtain traffic anomaly factor assessment results; According to the evaluation results of traffic abnormality factors, the threshold of abnormal traffic flow is adjusted by event type, and the response threshold setting result is obtained by referring to the comparison results of real-time data and original data; Based on the response threshold setting result, a linear regression model is used to predict the traffic trend in the future time period, and the traffic convenience index parameters are adjusted to obtain traffic trend prediction and index adjustment results; The steps for obtaining the traffic trend prediction and index adjustment results are specifically as follows: Based on the response threshold setting result, time series data associated with the forecast period in the future time period are selected, a basic linear regression model is applied to predict the flow rate for the key period, and the model is corrected by calculating the data points in each period to obtain an adjusted flow rate prediction model; Using the adjusted traffic flow prediction model, analyzing the prediction data for key event days and non-event days, optimizing the calculation parameters of the traffic convenience index, refining the settings of the traffic convenience index, and obtaining an optimized traffic convenience index result; Based on the optimized traffic convenience index results, a weighted regression algorithm is applied to evaluate traffic conditions in a future time period, the predicted data is compared with the current real-time data, the index is adjusted, and a traffic trend forecast and index adjustment results are generated; The formula of the weighted regression algorithm is as follows: ； Calculate the traffic convenience index in the future time period and generate the adjusted traffic trend forecast value, where T represents the adjusted traffic convenience index. represents the weight of the original traffic data, Represents the weight of real-time traffic data, represents the coefficient of variation of traffic flow, represents the smoothing parameter of the model, Represents the current real-time traffic convenience index, Represents the currently calculated traffic convenience index, represents the traffic convenience index of the original traffic data, represents the traffic convenience index of real-time traffic data, Indicates the currently monitored traffic flow; Based on the traffic trend prediction and index adjustment results, the traffic convenience index is updated, the urban traffic layout is optimized and traffic congestion is alleviated, and the traffic guidance and route planning adjustment results are obtained.

2. The method for evaluating the traffic convenience index based on big data according to claim 1 is characterized in that: The traffic flow status indicators include the mean vehicle speed indicator, the traffic accumulation indicator, and the average traffic indicator. The traffic fluctuation analysis results include the identification of peak hours, valley hours, and abnormal traffic hours. The traffic abnormality factor assessment results include the weather impact assessment, the holiday impact assessment, and the key event impact assessment. The response threshold setting results include the event type threshold and the real-time data comparison threshold. The traffic trend prediction and index adjustment results include the future traffic trend and the adjusted convenience index. The traffic guidance and route planning adjustment results include the updated traffic convenience index, the optimized traffic layout, and congestion relief measures.

3. The method for evaluating the traffic convenience index based on big data according to claim 1, characterized in that: The vehicle flow and speed data are received from multiple traffic monitoring nodes. The data is transmitted to the analysis platform in real time. The speed and flow of each node are integrated to obtain traffic flow status indicators. The specific steps are as follows: Receive vehicle flow and speed data from multiple traffic monitoring nodes, perform data format verification, remove non-compliant and erroneous data, sort the data by timestamp, and generate a traffic data sequence; Based on the traffic data sequence, a moving average method is used to calculate the average vehicle speed and flow rate of multiple nodes, and a timing analysis is performed on each node to identify and record flow rate and speed fluctuations in multiple time periods to obtain an overview of the node traffic pattern; Based on the overview of the node traffic pattern, the node data is integrated, the total traffic volume and the average speed of the node are calculated, and the node data are accumulated using the data aggregation method to generate the traffic flow status index.

4. The method for evaluating the traffic convenience index based on big data according to claim 1, characterized in that: Based on the traffic flow status indicators, the daily and weekly changes in traffic flow are analyzed, peak and valley periods are determined, and time periods with abnormal standard deviations and mean values ​​are identified. The specific steps for obtaining traffic fluctuation analysis results are as follows: Based on the traffic flow status indicators, record the traffic volume per hour and calculate the average traffic volume per hour. Mark and analyze the data for working days and non-working days respectively to obtain a daily traffic volume change graph. Using the data in the daily traffic change graph, a daily traffic comparison is performed. By calculating the mean and fluctuation of traffic volume on weekdays and weekends, the peak and trough periods of the week are identified, and the cyclical changes of traffic volume within a week are plotted to obtain a weekly traffic trend graph; Based on the weekly traffic trend chart, the standard deviation and mean of the traffic in each time period are calculated, the traffic changes in the same time period are compared, the time periods with abnormal traffic increases and decreases are identified and marked, and the traffic fluctuation analysis results are generated.

5. The method for evaluating the traffic convenience index based on big data according to claim 1 is characterized in that: The traffic fluctuation analysis results are compared with the data of the same period in the past to identify the factors of change that do not conform to the normal pattern, analyze the statistical impact of the factors of change, and evaluate the impact on traffic flow. The specific steps for obtaining the evaluation results of traffic abnormality factors are as follows: Based on the traffic fluctuation analysis results, current traffic data is compared with original data from the same period, and preliminary pattern changes are determined by identifying deviation value marked dates and time periods, thereby generating pattern change marking results; Using the pattern change marking results, capturing weather records, holiday schedules, and key event information corresponding to the marked dates, using a classification and organization method to associate this information with traffic data, evaluating the impact of multiple factors on the differentiated marked dates, and obtaining classification factor impact results; Based on the impact results of the classification factors, a linear regression algorithm is applied to integrate and calculate the degree of influence of the factors on traffic flow within the time period. Through data association analysis of the statistical values ​​of the factor influence, the real-time influence of each factor on traffic flow is evaluated, and the traffic abnormality factor evaluation results are generated.

6. The method for evaluating the traffic convenience index based on big data according to claim 5 is characterized in that: The formula of the linear regression algorithm is as follows: ； Calculate the traffic flow impact weight and obtain the traffic anomaly factor assessment result, where y represents the traffic flow impact weight, represents the intercept of the model, represents the influence coefficient of weather conditions, represents the influence coefficient of the time period, Represents the current traffic flow, represents the average value of the original traffic volume in the same period, Indicates the current weather conditions. Indicates whether the current time is peak period. Indicates the influence weight.

7. The method for evaluating the traffic convenience index based on big data according to claim 1, characterized in that: According to the traffic anomaly factor assessment results, the abnormal traffic threshold is adjusted by event type, and the response threshold setting result is obtained by referring to the comparison results of real-time data and original data. Specifically, the steps are as follows: Based on the traffic anomaly factor assessment results, key event types are classified, including holidays and large-scale events, and raw traffic flow data during the event is collected. By comparing the raw average flow with the current flow, the threshold of traffic anomaly is adjusted to generate an adjusted event threshold result; Using the adjusted event threshold results, real-time traffic data is monitored, traffic flow at each time point is compared with the threshold, time periods of abnormal traffic flow are identified, the real-time abnormal state of traffic flow is revealed, and real-time abnormal traffic flow monitoring results are obtained; Based on the real-time abnormal traffic monitoring results, traffic signal adjustments and routes are optimized, corresponding traffic management measures are implemented, traffic changes corresponding to differentiated types of events are matched, and response threshold setting results are generated.

8. The method for evaluating the traffic convenience index based on big data according to claim 1, characterized in that: Based on the traffic trend prediction and index adjustment results, the traffic convenience index is updated, the urban traffic layout is optimized, traffic congestion is alleviated, and the steps for obtaining traffic guidance and route planning adjustment results are as follows: Based on the traffic trend prediction and index adjustment results, the traffic convenience index parameters are updated, and the thresholds and index weights are adjusted according to the predicted traffic flow peaks and troughs, including adding adjustments to the weights during peak periods and setting buffer parameters during trough periods, to obtain an updated traffic convenience index; Utilizing the updated traffic convenience index in combination with real-time traffic data to analyze current traffic flow conditions, identify key traffic congestion points and smooth areas, adjust routes and signal light control logic, optimize traffic flow and reduce congestion, including adjusting traffic signal durations and optimizing bus lane configurations, and obtain urban traffic layout optimization results; Based on the urban traffic layout optimization results, temporary traffic diversion routes are set up and traffic monitoring is increased during key periods. The real-time impact of multiple measures on traffic flow is evaluated, traffic management in future time periods is adjusted and refined, and traffic guidance and route planning adjustment results are generated.

Images