A bus precise entry and exit station operation algorithm based on intelligent networking technology application

Abstract

The application discloses a bus accurate in-and-out station operation algorithm based on intelligent network connection technology application, in order to solve the problem that other vehicles can affect the bus arrival time, the bus flow data between two adjacent bus stations is collected through multiple data sources, the influence of other vehicles on the bus driving time on the road is analyzed through the bus flow data, the bus flow on the road is collected through multiple bus lines, the influence of other vehicles on the bus arrival time is more accurately analyzed, the bus in-and-out station time analysis is accurate, and the service level of the urban bus is improved.

Description

Technical Field

[0001] This invention belongs to the field of intelligent public transportation technology, and relates to a precise bus entry and exit calculation algorithm based on intelligent network technology. Background Technology

[0002] Accurate prediction of bus stop times is needed to improve the service level of urban public transport.

[0003] Existing methods for predicting bus arrival and departure times do not take into account factors such as traffic congestion. When a bus is in operation, other vehicles will affect the arrival time of the bus. Furthermore, the vehicles on the road are not fixed, and the traffic flow is real-time changing data, which is the main reason why it is difficult to predict the arrival time of the bus. Summary of the Invention

[0004] To address the problems existing in the background technology, this invention proposes a precise bus entry and exit calculation algorithm based on intelligent connected vehicle technology.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] Obtain the distance between the first and second bus stops, as well as the bus speed;

[0007] The data processing center sets the initial arrival time of the bus based on the bus speed and the distance between the first and second bus stops;

[0008] Obtain information on the number of vehicles within the section between the first and second bus stops;

[0009] The data processing center reads road traffic flow information and corrects the initial arrival time of buses based on the traffic flow to obtain the actual arrival time of buses.

[0010] The data processing center uploads the bus arrival time to the bus stop display device.

[0011] Furthermore, the first bus stop and the second bus stop are two adjacent stations on the bus route.

[0012] Furthermore, the vehicle quantity information within the section between the first bus stop and the second bus stop includes:

[0013] Traffic flow I from the first bus stop into the section between the first and second bus stops;

[0014] Traffic flow O from the second bus stop to the section between the first and second bus stops;

[0015] The other bus route bus stop section intersects with the first bus stop and the second bus stop section, and the difference S between the traffic flow of other bus routes entering the other bus route bus stop section and the traffic flow of other bus routes leaving the other bus route bus stop section.

[0016] Furthermore, the traffic flow within the section between the first bus stop and the second bus stop is calculated as follows:

[0017] The first traffic flow is obtained by subtracting the traffic flow O from the traffic flow I entering the section between the first and second bus stations from the traffic flow O exiting the section between the first and second bus stations from the traffic flow I entering the section between the first and second bus stations.

[0018] Set a unit distance and a unit time corresponding to the unit distance. Analyze the distance between the intersection point of two adjacent bus stop sections in other bus routes and the first and second bus stop sections of this bus route. Based on the difference S between the traffic flow entering two adjacent bus stop sections in other bus routes and the traffic flow leaving the section, if the traffic flow corresponding to the S value exceeds the preset time and has not left, add the S value to the first traffic flow to obtain the second traffic flow.

[0019] The second traffic flow refers to the traffic flow between the first and second bus stops.

[0020] Furthermore, the specific method for correcting the initial arrival time of buses based on traffic flow is as follows:

[0021] By training a deep learning model using historical data, the correlation coefficient between traffic flow and bus arrival and travel time can be obtained.

[0022] Traffic flow and bus arrival and travel time are positively correlated.

[0023] Based on the correlation coefficient of the current traffic flow on the bus arrival time, the initial bus arrival time is adjusted.

[0024] Furthermore, the deep learning model is trained as follows:

[0025] The system is trained based on traffic flow data of any two adjacent bus stops under historical conditions and the time required for bus travel to obtain the minimum impact of traffic flow on bus travel time.

[0026] Based on the minimum impact of traffic flow exceeding traffic flow on bus travel time, the correlation coefficient between traffic flow exceeding traffic flow and bus travel time is analyzed.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] This invention analyzes traffic flow between two stations to reduce the impact of traffic congestion on the prediction of bus arrival times. Simultaneously, this invention considers the impact of vehicles merging from other routes on the current bus route. The comprehensive data analysis enables more accurate prediction of bus arrival times, thereby improving the service level of urban public transportation. Attached Figure Description

[0029] Figure 1 This is a flowchart of the operation of this invention. Detailed Implementation

[0030] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0031] Accurate prediction of bus stop times at bus stops is crucial for improving urban public transport service. This invention aims to enhance the accuracy of bus arrival and departure time prediction by analyzing traffic flow between two stations and mitigating the impact of traffic congestion on arrival time prediction. It provides a precise bus arrival and departure calculation algorithm based on intelligent connected vehicle technology. Figure 1 As shown, it includes:

[0032] Obtain the distance between the first and second bus stops, as well as the bus speed.

[0033] The data processing center sets the initial arrival time of the bus based on the bus speed and the distance between the first and second bus stops.

[0034] By considering the bus's speed and the distance it needs to travel, and adding the traffic light factor, a preliminary prediction of the bus's arrival time at the station can be made. However, this preliminary prediction is only an initial time and does not take into account the situation of other vehicles on the road that have the greatest impact on the bus's movement. Further refinement is needed to obtain the precise arrival time of the bus at the station.

[0035] Obtain vehicle quantity information within the section between the first and second bus stops. The first and second bus stops are two adjacent stations on the bus route. Using any two adjacent stations for prediction can avoid excessive interference from historical bus travel data on the current route's travel time, thus improving the accuracy of bus arrival and departure time prediction.

[0036] The vehicle quantity information within the section between the first bus stop and the second bus stop includes:

[0037] Traffic flow I from the first bus stop into the section between the first bus stop and the second bus stop.

[0038] The traffic flow between the second bus stop and the first and second bus stops is O.

[0039] The first traffic flow is obtained by subtracting the traffic flow O from the traffic flow I entering the section between the first and second bus stations from the traffic flow O exiting the section between the first and second bus stations from the traffic flow I entering the section between the first and second bus stations.

[0040] By analyzing the number of vehicles entering the section between the first and second bus stations and the number of vehicles leaving the section between the first and second bus stations from the second bus station, the first traffic flow within the section between the first and second bus stations is obtained. However, this first traffic flow only references the data from the first and second bus stations and does not consider other data, so it does not fully represent the traffic flow within the section between the first and second bus stations. The influence of other bus routes also needs to be considered.

[0041] When the bus arrives at the first bus stop, it uses network technology to send data on the current bus, including vehicle attribute information and vehicle operating status, to the first bus stop. The first bus stop receives the current bus data and determines the average speed at the current bow angle based on the data.

[0042] Other bus routes intersect with the sections between the first and second bus stops. Vehicles on other bus routes may turn and enter the section between the first and second bus stops, thus modifying the traffic flow data within that section. The difference S between the traffic flow of other bus routes entering the section between other bus routes and the traffic flow of other bus routes leaving the section between other bus routes is calculated.

[0043] The calculation method for S is as follows:

[0044] A unit distance and a corresponding unit time are set to analyze vehicle location for traffic flow on other bus routes. The analysis considers the distance between the intersection points of two adjacent bus stop sections on other bus routes and the first and second bus stop sections on this bus route. Based on the difference S between the traffic flow entering and leaving the two adjacent bus stop sections on other bus routes, if the traffic flow corresponding to S exceeds a preset time without leaving, then S is added to the first traffic flow to obtain the second traffic flow.

[0045] The second traffic flow data refers to the traffic flow within the section between the first and second bus stops. Compared to the first traffic flow data, the second traffic flow data takes into account vehicle entry data from other roads, as the roads corresponding to the bus routes are the main source of entry. At the same time, vehicles exiting between the first and second bus stops are recorded on other bus routes. Therefore, the second traffic flow data can reflect the traffic flow information within the section between the first and second bus stops with a high degree of matching.

[0046] After obtaining the traffic flow information between the first and second bus stops, the data processing center reads the road traffic flow information and corrects the initial arrival time of the buses based on the traffic flow to obtain the actual arrival time of the buses.

[0047] The specific method for adjusting the initial arrival time of buses based on traffic flow is as follows:

[0048] By using historical data to train a deep learning model, the correlation coefficient between traffic flow and bus arrival time can be obtained.

[0049] The training method for the deep learning model is as follows:

[0050] The system is trained using historical data on traffic flow between any two adjacent bus stops and the travel time required for buses to reach their destinations, to obtain the minimum impact of traffic flow on bus travel time. This is because when the traffic flow between the first and second bus stops is less than a certain value, it has virtually no impact on bus travel. For example, if a bus is traveling on a four-lane road with a traffic flow of 2 lanes, the traffic flow is too low to affect the bus's normal operation. Therefore, it is necessary to exclude the minimum impact of traffic flow on bus travel time.

[0051] Based on the minimum impact of traffic flow exceeding the minimum traffic flow on bus travel time, the correlation coefficient between the excess traffic flow and bus travel time is analyzed. This aims to reduce the impact of the minimum traffic flow on bus travel time and improve the accuracy of bus arrival time prediction.

[0052] Traffic flow and bus arrival time are positively correlated, and the correlation coefficient should satisfy the characteristic of positive correlation. Based on the correlation coefficient of the current traffic flow's impact on bus arrival time, the initial bus arrival time is adjusted.

[0053] Correcting the initial arrival time of buses also includes the impact of factors such as traffic light information on bus arrival time. Fuzzy position prediction is added during the normal operation of the bus, and the bus is judged whether it passes the traffic light based on the predicted fuzzy position, thereby correcting the bus arrival time caused by traffic lights at intersections.

[0054] The data processing center corrects the initial arrival time of the bus to obtain the actual arrival time, and then uploads the bus arrival time to the bus stop display device. The upload process is achieved through V2X, which not only uploads the bus arrival time to the local bus stop display device, but also transmits the bus arrival time to the cloud to achieve data sharing.

[0055] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A bus precise in-and-out station operation algorithm based on intelligent networking technology application, characterized in that, The application comprises the following steps: Obtain the distance between the first bus station and the second bus station, and the bus running speed; The data processing center sets the initial time of the bus arriving at the station according to the bus speed and the distance between the first bus station and the second bus station; Obtain the vehicle quantity information in the interval between the first bus station and the second bus station; The data processing center reads the road traffic information and corrects the initial time of the bus arriving at the station according to the traffic flow, to obtain the bus arrival time; The data processing center uploads the bus arrival time to the bus station display device; The vehicle quantity information in the interval between the first bus station and the second bus station comprises: The traffic flow I entering the interval between the first bus station and the second bus station from the first bus station; The traffic flow O leaving the interval between the first bus station and the second bus station from the second bus station; The difference between the traffic flow entering the interval of the bus station of other bus routes and the traffic flow leaving the interval of the bus station of other bus routes; The calculation method of the traffic flow in the interval between the first bus station and the second bus station is as follows: The first traffic flow is obtained by subtracting the traffic flow O leaving the interval between the first bus station and the second bus station from the traffic flow I entering the interval between the first bus station and the second bus station; Set a unit distance and a unit time corresponding to the unit distance, analyze the distance between the intersection point of the interval between the first bus station and the second bus station and the interval between two adjacent bus stations of other bus routes, and according to the difference S between the traffic flow entering the interval between two adjacent bus stations of other bus routes and the traffic flow leaving the interval, if the traffic flow corresponding to the S value exceeds the preset time and does not leave, then the S value is added to the first traffic flow to obtain the second traffic flow; The second traffic flow is the traffic flow in the interval between the first bus station and the second bus station. 2.The bus precise in-and-out station operation algorithm based on intelligent network technology application of claim 1, wherein The first bus station and the second bus station are two adjacent bus stations on a bus route. 3.The bus precise in-and-out station operation algorithm based on intelligent network technology application of claim 1, wherein The specific method for correcting the initial time of the bus arriving at the station according to the traffic flow is as follows: Obtain the correlation coefficient between the traffic flow and the bus arrival time by training a deep learning model using historical data; The traffic flow and the bus arrival time are positively correlated; According to the correlation coefficient of the influence of the current traffic flow on the bus arrival time, the initial time of the bus arriving at the station is corrected. 4.The bus precise entry and exit station algorithm based on intelligent network technology application of claim 3, wherein The training method of the deep learning model is as follows: Train the traffic flow and the bus arrival time based on the traffic flow data and the bus travel time of any two adjacent bus stations in the historical state, to obtain the minimum value of the influence of the traffic flow on the bus travel time; Based on the part of the traffic flow exceeding the minimum value of the influence of the traffic flow on the bus travel time, analyze the correlation coefficient between the exceeding traffic flow and the bus travel time.

Images