Urban traffic flow analysis and management method

Abstract

The invention discloses an urban traffic flow analysis and management method, relates to the technical field of traffic management and information, and solves the technical problems that an average vehicle speed deviation value and vehicle position data are lacked to evaluate a lane congestion condition and analysis of traffic flows of different weather types is lacked. The method includes the following steps that the number, types, timestamps, noise and image data of vehicles are collected through a collection system; constructing a cloud platform, transmitting the data to a cloud server, and processing the data through a Spark Streami ng stream processing technology to obtain a vehicle type noise weighted calculation value and a lane congestion evaluation value; through analysis of historical and real-time data, a public transport line length deviation value, a weather type assignment value and a traffic lane number value are collected to obtain an influence factor comprehensive weighted calculation value, and a traffic operation data value is constructed by combining a vehicle type noise weighted calculation value and a lane congestion evaluation value. And carrying out grade division on the predicted traffic jam condition and sending out a corresponding early warning signal.

Description

Technical Field

[0001] The invention belongs to the field of traffic management and information technology, and specifically relates to a method for analyzing and managing urban vehicle flow. Background Art

[0002] With the acceleration of urbanization, urban traffic congestion is becoming increasingly serious. It is very important to accurately calculate the predicted values ​​of traffic operation data and predict the traffic flow trend in each time period to effectively avoid congested sections. The predicted values ​​of traffic operation data are obtained based on the weighted calculation values ​​of vehicle model noise, lane congestion evaluation values ​​and comprehensive weighted values ​​of influencing factors. The degree of traffic flow is predicted and analyzed based on the traffic operation data values, ensuring smooth and safe road traffic.

[0003] Although the existing traffic flow analysis methods have achieved the analysis and management of urban traffic flow to a certain extent, they lack the comprehensive evaluation of lane congestion by noise and image values, lack the analysis of traffic flow in different weather types, and it is difficult to accurately predict traffic operation data and predict values ​​to issue different levels of warning signals for traffic flow levels to adapt to the complex and changeable urban traffic environment. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a method for analyzing and managing urban vehicle flow, which is used to solve the following technical problems:

[0005] Although the existing traffic flow analysis methods have achieved the analysis and management of urban traffic flow to a certain extent, they lack the average speed deviation value and vehicle position data to evaluate lane congestion, lack the analysis of traffic flow in different weather types, and it is difficult to accurately predict traffic operation data and issue different levels of warning signals for traffic flow levels to adapt to the complex and changeable urban traffic environment.

[0006] To solve the above problems, the first aspect of the present invention provides a method for analyzing and managing urban vehicle flow, comprising the following steps:

[0007] S1: Deploy a multi-source traffic data collection system to collect vehicle quantity, type, timestamp, noise and image data;

[0008] S2: Build a cloud platform to transmit the collected data to the cloud server in real time, clean, denoise and enhance the data through Spark Streaming stream processing technology, and obtain the weighted calculation value of vehicle noise and lane congestion evaluation value;

[0009] S3: By analyzing historical and real-time data, the comprehensive weighted calculation value of the influencing factors in a certain period is obtained according to the public transportation line length value, weather type assignment value and lane number value data, and the traffic operation data forecast value is obtained by combining the lane congestion evaluation value and the vehicle model noise weighted calculation value to predict the traffic flow trend in each time period;

[0010] S4: According to the traffic flow data value, the predicted traffic congestion situation is classified into levels and an early warning is issued.

[0011] As a further solution of the present invention: Step S1 comprises the following steps:

[0012] By installing geomagnetic sensors, video monitors, and noise monitoring equipment in specific areas such as key sections and intersections, and using floating vehicles and mobile applications equipped with GPS devices, a multi-source traffic data collection system is built to collect the number, type, timestamp, noise, and image data of passing vehicles, and analyze the traffic conditions and congestion patterns in specific areas.

[0013] As a further solution of the present invention: Step S2 comprises the following steps:

[0014] S201: Build a cloud platform to collect the quantity, type, timestamp, noise and image data collected, transmit it to the Kafka distributed streaming computing platform based on Spark Streaming stream processing technology, extract and clean the data through time windows, and store the cleaned data in the database;

[0015] S202: Preset a detection time period, and collect statistics on the noise, speed and quantity data of three types of vehicles, namely large trucks, medium-sized buses and sedans, after preliminary processing, to detect the traffic volume of the detection section in the latest predicted detection time period, and obtain a weighted calculation formula for vehicle type noise:

[0016] Large truck: L w,l =77.2+0.18V l

[0017] Medium-sized bus: L w,m =62.6+0.32V m

[0018] Sedan: L W,s =59.3+0.23V s

[0019]

[0020] Among them, V l 、V m and V sare the average speeds of large trucks, medium-sized buses and cars, respectively. w,l , L w,m and L w,s are the single vehicle noise levels corresponding to large trucks, medium-sized buses and cars, N l 、N m and N s are the average number of large trucks, medium-sized buses and cars, respectively. eq is the weighted calculation value of vehicle model noise;

[0021] The vehicle types include large trucks, medium-sized buses and sedans;

[0022] S203: Real-time images on the road are acquired through a video monitor, and denoising and enhancement preprocessing is performed on the vehicle speed, quantity and position data in the image. The vehicle speed and quantity data in the image are extracted according to a feature extraction and description algorithm to obtain an average vehicle speed deviation value. The lane congestion evaluation value is calculated through the average vehicle speed deviation value and position data.

[0023] As a further solution of the present invention: in the step S203, the lane congestion evaluation value formula includes the following steps:

[0024]

[0025]

[0026] Where σ is the average speed deviation value, V i is the current speed of the bicycle, V a is the average speed, N l 、N m and N s are the numbers corresponding to large trucks, medium-sized buses and cars respectively, e is a constant in the formula, S is the vehicle position data, and G is the lane congestion evaluation value.

[0027] As a further solution of the present invention: Step S3 comprises the following steps:

[0028] Through the historical traffic flow data, the external influencing factor data is analyzed to obtain the comprehensive weighted value of the influencing factors. According to the comprehensive weighted value of the influencing factors, the weighted calculation value of the vehicle model noise and the lane congestion evaluation value, a traffic operation data prediction formula is constructed.

[0029] As a further solution of the present invention, collecting external influencing factor data includes the following steps:

[0030] The deviation value of the length of the public transportation line, the weather type value and the number of lanes are collected through different collection plug-ins; the actual value of the length of the public transportation line is compared with the standard value of the length of the public transportation line, and the calculation formula of the deviation value of the length of the public transportation line is obtained:

[0031]

[0032] Where E is the deviation value of the length of the public transportation line, E1 is the standard value of the length of the public transportation line, and E2 is the actual value of the length of the public transportation line;

[0033] Call the weather interface through the China Weather Network API to collect weather data, analyze and assign values ​​to different weather types:

[0034] If the weather is not foggy, rainy or snowy, R = 0;

[0035] If the weather is foggy, R = 1;

[0036] If it is raining, R=2;

[0037] If it is snowing, R=3;

[0038] Calculate the number of lanes through real-time video monitoring;

[0039] The influencing factors include the deviation value of the length of the public transportation line, the weather type assignment and the number of lanes, and the comprehensive weighted formula of the influencing factors is obtained:

[0040] A=(E×W E )×(S×W S )×[(1+R)×W R ]

[0041] Among them, A is the comprehensive weighted calculation value of influencing factors, E is the deviation value of the length of the public transportation line, S is the number of lanes, R is the value assigned by the weather conditions, and W E , W S , W R are the corresponding weights, W E =50%, W S =20%, W R is 30%.

[0042] As a further solution of the present invention: constructing a traffic operation data prediction formula includes the following steps:

[0043] By introducing the weighted calculation value of vehicle noise, the lane congestion evaluation value formula and the comprehensive weighted calculation formula of influencing factors, the traffic operation data prediction formula is obtained:

[0044]

[0045] Where T is the unit time length, N l 、N m and N s are the numbers of large trucks, medium-sized buses and sedans, respectively. T is the comprehensive weighted value of the influencing factors per unit time, G T is the lane congestion evaluation value per unit time, and Q is the predicted value of traffic operation data.

[0046] As a further solution of the present invention: the step S4 comprises the following steps:

[0047] According to the data value of Q, the traffic flow can be divided into four levels:

[0048] If Q < 1000, the traffic flow is smooth;

[0049] If 1000≤Q<1500, the traffic flow level is slightly congested;

[0050] If 1500≤Q<2000, the traffic flow level is moderately congested;

[0051] If 2000≤Q, the traffic flow level is severely congested;

[0052] There are four levels of adjustment:

[0053] When the operation is smooth, the vehicle runs normally;

[0054] In case of mild congestion, a three-level traffic warning signal will be issued for the detected road section;

[0055] In case of moderate congestion, a secondary traffic warning signal will be issued for the detected road section;

[0056] In case of severe congestion, a first-level traffic warning signal will be issued for the detected road section.

[0057] Beneficial effects of the present invention:

[0058] The present invention discloses a method for analyzing and managing urban vehicle flow, relates to the field of traffic management and information technology, solves the problems of real-time collection of traffic data, dynamic analysis of vehicle flow, and adjustment of traffic signal control and route planning accordingly, collects vehicle quantity, type, timestamp, noise and image data through a collection system, cleans, denoises and enhances the data using Spark Streaming stream processing technology, obtains vehicle model noise weighted calculation values ​​and lane congestion evaluation values, realizes conversion of noise level and image data into quantifiable values, facilitates subsequent processing, obtains a traffic operation data prediction formula in combination with comprehensive weighted values ​​of influencing factors, realizes automatic issuance of traffic warning level signals according to traffic congestion conditions, and improves the efficiency of traffic vehicle flow management. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0060] Figure 1 It is a schematic diagram of the system flow of the present invention. DETAILED DESCRIPTION

[0061] 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.

[0062] See also Figure 1 As shown, the present invention is a method for analyzing and managing urban vehicle flow, comprising the following steps:

[0063] S1: Deploy a multi-source traffic data collection system to collect vehicle quantity, type, timestamp, noise and image data;

[0064] S2: Build a cloud platform to transmit the collected data to the cloud server in real time, clean, denoise and enhance the data through Spark Streaming stream processing technology, and obtain the weighted calculation value of vehicle noise and lane congestion evaluation value;

[0065] S3: By analyzing historical and real-time data, the comprehensive weighted calculation value of the influencing factors in a certain period is obtained according to the public transportation line length value, weather type assignment value and lane number value data, and the traffic operation data forecast value is obtained by combining the lane congestion evaluation value and the vehicle model noise weighted calculation value to predict the traffic flow trend in each time period;

[0066] S4: According to the traffic flow data value, the predicted traffic congestion situation is classified into levels and an early warning is issued.

[0067] Specifically, the number, type, timestamp, noise and image data of vehicles are collected through the collection system; a cloud platform is built to transmit the collected data to the cloud server in real time, and the data is cleaned, denoised and enhanced through Spark Streaming stream processing technology to obtain the weighted calculation value of vehicle model noise and lane congestion evaluation value; through historical and real-time data analysis, the deviation value of public transportation line length, weather type assignment and number of lanes are collected to obtain the comprehensive weighted calculation value of influencing factors, and the traffic operation data value is constructed by combining the weighted calculation value of vehicle model noise and lane congestion evaluation value, and the predicted traffic congestion situation is graded and the corresponding warning signal is issued. The traffic capacity of the urban road network has been greatly improved.

[0068] In one embodiment of the present invention, the step S1 comprises the following steps:

[0069] By installing geomagnetic sensors and video surveillance in specific areas such as key sections and intersections, using floating vehicles equipped with GPS devices and mobile applications, a multi-source traffic data collection system is built to collect the number, type, timestamp, noise and image data of passing vehicles, and analyze the traffic conditions and congestion patterns in specific areas.

[0070] Specifically, the multi-source data acquisition system combines the advantages of different types of sensors and the sources of collected quantity, type, timestamp, noise and image data, and can provide more comprehensive and accurate traffic information, providing a scientific basis for traffic conditions and congestion patterns in specific areas.

[0071] In one embodiment of the present invention, step S2 comprises the following steps:

[0072] S201: Build a cloud platform to collect the quantity, type, timestamp, noise and image data collected, transmit it to the Kafka distributed streaming computing platform based on Spark Streaming stream processing technology, extract and clean the data through time windows, and store the cleaned data in the database;

[0073] S202: Preset a detection time period, and collect statistics on the noise, speed and quantity data of three types of vehicles, namely large trucks, medium-sized buses and sedans, after preliminary processing, to detect the traffic volume of the detection section in the latest predicted detection time period, and obtain a weighted calculation formula for vehicle type noise:

[0074] Large truck: L w,l =77.2+0.18V l

[0075] Medium-sized bus: L w,m =62.6+0.32V m

[0076] Sedan: L W,s =59.3+0.23V s

[0077]

[0078] Among them, V l 、V m and V s are the average speeds of large trucks, medium-sized buses and cars, respectively. w,l , L w,m and L w,s are the single vehicle noise levels corresponding to large trucks, medium-sized buses and cars, N l 、N m and N s are the average number of large trucks, medium-sized buses and cars, respectively. eq is the weighted calculation value of vehicle model noise;

[0079] The vehicle types include large trucks, medium-sized buses and sedans;

[0080] S203: Real-time images on the road are acquired through a video monitor, and denoising and enhancement preprocessing is performed on the vehicle speed, quantity and position data in the image. The vehicle speed and quantity data in the image are extracted according to a feature extraction and description algorithm to obtain an average vehicle speed deviation value. The lane congestion evaluation value is calculated through the average vehicle speed deviation value and position data.

[0081] Specifically, a cloud platform is built to receive data from multiple data sources, including geomagnetic sensors, video monitors, GPS devices, floating vehicles and mobile applications. These data are cleaned using Spark Streaming technology to remove redundant data, and the noise values ​​of three types of vehicles, large trucks, medium-sized buses and sedans, are calculated to obtain weighted calculation values ​​of vehicle noise and data values ​​after image preprocessing. This enables efficient data collection.

[0082] In one embodiment of the present invention, in step S203, the lane congestion evaluation value formula includes the following steps:

[0083]

[0084]

[0085] Where σ is the average speed deviation value, V i is the current speed of the bicycle, V a is the average speed, N l 、N m and N sare the numbers corresponding to large trucks, medium-sized buses and cars respectively, e is a constant in the formula, S is the vehicle position data, and G is the lane congestion evaluation value.

[0086] Specifically, denoising and enhancement preprocessing is performed on the vehicle speed, number and position data collected through real-time images to eliminate the impact of camera noise and environmental interference factors and improve the clarity and contrast of the image. The average speed deviation value is obtained by comparing the current speed of the vehicle with the average speed, which helps to understand the difference between the current traffic condition and the normal condition. Combined with the average speed deviation value and the vehicle's position data, the congestion evaluation value of the lane can be calculated to reflect the vehicle density and moving speed on the lane. By comparing the congestion evaluation values ​​in different time periods, the peaks and valleys of traffic flow can be understood.

[0087] In one embodiment of the present invention, step S3 comprises the following steps:

[0088] Through the historical traffic flow data, the external influencing factor data is analyzed to obtain the comprehensive weighted value of the influencing factors. According to the comprehensive weighted value of the influencing factors, the weighted calculation value of the vehicle model noise and the lane congestion evaluation value, a traffic operation data prediction formula is constructed.

[0089] Specifically, historical traffic flow data is collected, external factors that may affect traffic flow are determined, and relevant data of these external factors are analyzed, including the deviation value of public transportation line length, weather type assignment, and number of lanes. According to the results of correlation analysis, corresponding weights are assigned to each influencing factor, and the comprehensive weighted value of the influencing factors is calculated. Then, a traffic operation data prediction formula is constructed based on the weighted calculation value of vehicle type noise and the lane congestion evaluation value. Future traffic conditions can be predicted based on historical data and real-time data, providing a scientific basis for traffic management.

[0090] In one embodiment of the present invention, collecting external influencing factor data includes the following steps:

[0091] The deviation value of the length of the public transportation line, the weather type value and the number of lanes are collected through different collection plug-ins; the actual value of the length of the public transportation line is compared with the standard value of the length of the public transportation line, and the calculation formula of the deviation value of the length of the public transportation line is obtained:

[0092] E= E2-E1 ×100%

[0093] E1

[0094] Where E is the deviation value of the length of the public transportation line, E1 is the standard value of the length of the public transportation line, and E2 is the actual value of the length of the public transportation line;

[0095] Call the weather interface through the China Weather Network API to collect weather data, analyze and assign values ​​to different weather types:

[0096] If the weather is not foggy, rainy or snowy, R = 0;

[0097] If the weather is foggy, R = 1;

[0098] If it is raining, R=2;

[0099] If it is snowing, R=3;

[0100] Calculate the number of lanes through real-time video monitoring;

[0101] The influencing factors include the deviation value of the length of the public transportation line, the weather type assignment and the number of lanes, and the comprehensive weighted formula of the influencing factors is obtained:

[0102] A=(E×W E )×(S×W S )×[(1+R)×W R ]

[0103] Among them, A is the comprehensive weighted calculation value of influencing factors, E is the deviation value of the length of the public transportation line, S is the number of lanes, R is the value assigned by the weather conditions, and W E , W S , W R are the corresponding weights, W E =50%, W S =20%, W R is 30%.

[0104] Specifically, by comparing the actual value of the public transportation line length with the standard value of the public transportation line length, the deviation value of the public transportation line length is obtained. Traffic lines that are too long or too short will cause traffic jams. Reasonable route length helps to ensure the balance and efficiency of transportation services; encode non-numerical influencing factors, convert weather types into numerical variables, and assign different numerical values ​​to them according to the degree of impact of weather types on traffic, which is convenient for subsequent analysis; calculate the number of lanes, and analyze the usage frequency and capacity of each lane, providing a basis for traffic signal control and lane allocation.

[0105] In one embodiment of the present invention, constructing a traffic operation data prediction formula includes the following steps:

[0106] By introducing the weighted calculation value of vehicle noise, the lane congestion evaluation value formula and the comprehensive weighted calculation formula of influencing factors, the traffic operation data prediction formula is obtained:

[0107]

[0108] Where T is the unit time length, N l 、N m and N s are the numbers of large trucks, medium-sized buses and sedans, respectively. T is the comprehensive weighted value of the influencing factors per unit time, G T is the lane congestion evaluation value per unit time, and Q is the predicted value of traffic operation data.

[0109] Specifically, by introducing the weighted calculation value of vehicle type noise, the lane congestion evaluation value formula and the comprehensive weighted calculation formula of influencing factors, a comprehensive traffic operation data prediction formula can be obtained. Through in-depth analysis of historical and real-time traffic data, accurate traffic flow prediction can be provided, thus providing a scientific basis for traffic management and planning.

[0110] In one embodiment of the present invention, the step S4 includes the following steps:

[0111] According to the data value of Q, the traffic flow can be divided into four levels:

[0112] If Q < 1000, the traffic flow is smooth;

[0113] If 1000≤Q<1500, the traffic flow level is slightly congested;

[0114] If 1500≤Q<2000, the traffic flow level is moderately congested;

[0115] If 2000≤Q, the traffic flow level is severely congested;

[0116] There are four levels of adjustment:

[0117] When the operation is smooth, the vehicle runs normally;

[0118] In case of mild congestion, a three-level traffic warning signal will be issued for the detected road section;

[0119] In case of moderate congestion, a secondary traffic warning signal will be issued for the detected road section;

[0120] In case of severe congestion, a first-level traffic warning signal will be issued for the detected road section.

[0121] Specifically, through comprehensive traffic operation data prediction values, we can take into account a variety of factors, divide the traffic volume into four levels according to the traffic operation data prediction values, and conduct corresponding analysis and planning, so as to improve the accuracy and practicality of traffic operation status prediction, and help traffic management departments better understand and control traffic flow, thereby alleviating traffic congestion and improving the efficiency and safety of urban transportation systems.

[0122] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A method for analyzing and managing urban traffic flow, characterized in that: The following steps are involved: S1: Deploy a multi-source traffic data collection system to collect vehicle quantity, type, timestamp, noise and image data; S2: Build a cloud platform to transmit the collected data to the cloud server in real time, clean, denoise and enhance the data through Spark Streaming stream processing technology, and obtain the weighted calculation value of vehicle noise and lane congestion evaluation value; S3: By analyzing historical and real-time data, the comprehensive weighted calculation value of the influencing factors in a certain period is obtained according to the public transportation line length value, weather type assignment value and lane number value data, and the traffic operation data forecast value is obtained by combining the lane congestion evaluation value and the vehicle model noise weighted calculation value to predict the traffic flow trend in each time period; S4: According to the traffic flow data value, the predicted traffic congestion situation is classified into levels and an early warning is issued.

2. A method for analyzing and managing urban vehicle flow according to claim 1, characterized in that: The step S1 comprises the following steps: By installing geomagnetic sensors, video monitors, and noise monitoring equipment in specific areas such as key sections and intersections, and using floating vehicles and mobile applications equipped with GPS devices, a multi-source traffic data collection system is built to collect the number, type, timestamp, noise, and image data of passing vehicles, and analyze the traffic conditions and congestion patterns in specific areas.

3. The urban vehicle flow analysis and management method according to claim 1 is characterized in that: The step S2 comprises the following steps: S201: Build a cloud platform to collect the quantity, type, timestamp, noise and image data collected, transmit it to the Kafka distributed streaming computing platform based on Spark Streaming stream processing technology, extract and clean the data through time windows, and store the cleaned data in the database; S202: Preset a detection time period, and collect statistics on the noise, speed and quantity data of three types of vehicles, namely large trucks, medium-sized buses and sedans, after preliminary processing, to detect the traffic volume of the detection section in the latest predicted detection time period, and obtain a weighted calculation formula for vehicle type noise: Large truck: L w,l =77.2+0.18V l Medium-sized bus: L w,m =62.6+0.32V m Sedan: L W,s =59.3+0.23V s Among them, V l 、V m and V s are the average speeds of large trucks, medium-sized buses and cars, respectively. w,l , L w,m and L w,s are the single vehicle noise levels corresponding to large trucks, medium-sized buses and cars, N l 、N m and N s are the average number of large trucks, medium-sized buses and cars, respectively. eq is the weighted calculation value of vehicle model noise; The vehicle types include large trucks, medium-sized buses and sedans; S203: Real-time images on the road are acquired through a video monitor, and denoising and enhancement preprocessing is performed on the vehicle speed, quantity and position data in the image. The vehicle speed and quantity data in the image are extracted according to a feature extraction and description algorithm to obtain an average vehicle speed deviation value. The lane congestion evaluation value is calculated through the average vehicle speed deviation value and position data.

4. A method for analyzing and managing urban vehicle flow according to claim 3, characterized in that: In step S203, the lane congestion evaluation value formula includes the following steps: Where σ is the average speed deviation value, V i is the current speed of the bicycle, V a is the average speed, N l 、N m and N s are the numbers corresponding to large trucks, medium-sized buses and cars respectively, e is a constant in the formula, S is the vehicle position data, and G is the lane congestion evaluation value.

5. The urban vehicle flow analysis and management method according to claim 1 is characterized in that: The step S3 comprises the following steps: Through the historical traffic flow data, the external influencing factor data is analyzed to obtain the comprehensive weighted value of the influencing factors. According to the comprehensive weighted value of the influencing factors, the weighted calculation value of the vehicle model noise and the lane congestion evaluation value, a traffic operation data prediction formula is constructed.

6. A method for analyzing and managing urban vehicle flow according to claim 5, characterized in that: Collecting data on external influencing factors includes the following steps: The deviation value of the length of the public transportation line, the weather type value and the number of lanes are collected through different collection plug-ins; the calculation formula of the deviation value of the length of the public transportation line is obtained by comparing the actual value of the length of the public transportation line with the standard value of the length of the public transportation line: E＝ E2-E1 ×100％ E1 Where E is the deviation value of the length of the public transportation line, E1 is the standard value of the length of the public transportation line, and E2 is the actual value of the length of the public transportation line; Call the weather interface through the China Weather Network API to collect weather data, analyze and assign values ​​to different weather types: If the weather is not foggy, rainy or snowy, R = 0; If the weather is foggy, R = 1; If it is raining, R=2; If it is snowing, R=3; Calculate the number of lanes through real-time video monitoring; The influencing factors include the deviation value of the length of the public transportation line, the weather type assignment and the number of lanes, and the comprehensive weighted formula of the influencing factors is obtained: A=(E×W E )×(S×W S )×[(1+R)×W R ] Among them, A is the comprehensive weighted calculation value of influencing factors, E is the deviation value of the length of the public transportation line, S is the number of lanes, R is the value assigned by the weather conditions, and W E , W S , W R are the corresponding weights, W E =50%, W S =20%, W R is 30%.

7. A method for analyzing and managing urban vehicle flow according to claim 6, characterized in that: Constructing the traffic operation data prediction formula includes the following steps: By introducing the weighted calculation value of vehicle noise, the lane congestion evaluation value formula and the comprehensive weighted calculation formula of influencing factors, the traffic operation data prediction formula is obtained: Where T is the unit time length, N l 、N m and N s are the numbers of large trucks, medium-sized buses and sedans, respectively. T is the comprehensive weighted value of the influencing factors per unit time, G T is the lane congestion evaluation value per unit time, and Q is the predicted value of traffic operation data.

8. A method for analyzing and managing urban vehicle flow according to claim 7, characterized in that: The step S4 comprises the following steps: According to the data value of Q, the traffic flow can be divided into four levels: If Q < 1000, the traffic flow is smooth; If 1000≤Q<1500, the traffic flow level is slightly congested; If 1500≤Q<2000, the traffic flow level is moderately congested; If 2000≤Q, the traffic flow level is severely congested; There are four levels of adjustment: When the operation is smooth, the vehicle runs normally; In case of mild congestion, a three-level traffic warning signal will be issued for the detected road section; In case of moderate congestion, a secondary traffic warning signal will be issued for the detected road section; In case of severe congestion, a first-level traffic warning signal will be issued for the detected road section.

Images