Precise bus entry and exit operation algorithm based on intelligent network connection technology application

Abstract

The invention discloses a bus accurate arrival and departure operation algorithm based on intelligent network connection technology application, and aims to solve the problem that other vehicles can influence the arrival time of a bus, the method comprises the following steps: collecting traffic flow data between two adjacent bus stations through multiple data sources; according to the method, the influence of other vehicles on the road on the driving time of the bus is analyzed through the traffic flow data, the traffic flow on the road is collected through the cooperation of a plurality of bus lines, the influence of other vehicles on the arrival time of the bus is analyzed more accurately, the arrival and arrival time of the bus is analyzed accurately, and the service level of the urban bus is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent public transportation and relates to an accurate bus entry and exit operation algorithm based on the application of intelligent network connection technology. Background Art

[0002] The stop time of buses at bus stops needs to be accurately predicted to improve the service level of urban public transportation.

[0003] The existing bus entry and exit prediction methods do not take into account factors such as traffic jams. When the bus line is running, other vehicles will affect the bus arrival time. In addition, the vehicles on the road are not fixed, and the traffic flow is real-time changing data. This is the main reason why it is difficult to predict the bus arrival time. Summary of the invention

[0004] In order to solve the problems existing in the background technology, the present invention proposes a precise bus entry and exit operation algorithm based on the application of intelligent network technology.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] Get the distance between the first bus stop and the second bus stop, as well as the bus running speed;

[0007] The data processing center sets the initial arrival time of the bus according to the bus speed and the distance between the first bus stop and the second bus stop;

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

[0009] The data processing center reads the road traffic flow information, corrects the initial bus arrival time according to the traffic flow, and obtains the bus arrival time;

[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 line.

[0012] Furthermore, the information on the number of vehicles between the first bus stop and the second bus stop includes:

[0013] The traffic flow I from the first bus station into the area between the first bus station and the second bus station;

[0014] The traffic volume O between the first bus station and the second bus station exits from the second bus station;

[0015] The bus stop intervals of other bus routes have intersections with the first bus stop and the second bus stop intervals, and the difference S between the vehicle flow entering the bus stop intervals of other bus routes and the vehicle flow leaving the bus stop intervals of other bus routes is greater than or equal to 0.

[0016] Furthermore, the vehicle flow rate between the first bus station and the second bus station is calculated as follows:

[0017] The first vehicle flow is obtained by subtracting the vehicle flow O from the second bus station and the first bus station from the vehicle flow I entering the first bus station and the second bus station.

[0018] Set a unit distance and a unit time corresponding to the unit distance, analyze the distance between the intersection of two adjacent bus stop intervals in other bus routes and the first bus stop and the second bus stop interval of this bus route, and according to the difference S between the vehicle flow entering the two adjacent bus stop intervals in other bus routes and the vehicle flow leaving the interval, if the vehicle flow corresponding to the S value exceeds the preset time and does not leave, then add the S value to the first vehicle flow to obtain the second vehicle flow;

[0019] The second traffic flow is the traffic flow between the first bus stop and the second bus stop.

[0020] Furthermore, the specific method for correcting the initial arrival time of the bus according to the traffic volume is as follows:

[0021] By using historical data to train a deep learning model, the correlation coefficient between traffic volume and bus arrival time is obtained;

[0022] The traffic volume and the bus arrival time are positively correlated functions;

[0023] According to the correlation coefficient of the current traffic flow on the bus arrival time, the initial bus arrival time is corrected.

[0024] Furthermore, the deep learning model is trained in the following manner:

[0025] Based on the historical traffic flow data of any two adjacent bus stations and the time required for bus travel, training is performed to obtain the minimum value of the impact of traffic flow on bus travel time;

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

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

[0028] The present invention analyzes the traffic volume between two stations and reduces the impact of traffic jams on the prediction of the arrival time. At the same time, the present invention takes into account the impact of vehicles on other routes on the current bus line. The analyzed data is comprehensive, and the arrival time of the bus can be predicted more accurately, thereby improving the service level of urban public transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is the operation flow chart of the present invention. DETAILED DESCRIPTION

[0030] 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.

[0031] The stop time of public buses at bus stops needs to be accurately predicted to improve the service level of urban public transportation. In order to improve the accuracy of prediction of bus entry and exit times, the present invention analyzes the traffic volume between two stations and reduces the impact of traffic jams on the prediction of entry time. Figure 1 As shown, including:

[0032] Get the distance between the first bus stop and the second bus stop, as well as the bus running speed.

[0033] The data processing center sets the initial arrival time of the bus according to the bus speed and the distance between the first bus stop and the second bus stop.

[0034] By taking into account the speed of the bus and the distance it needs to travel, and adding the traffic light factor, we can make a preliminary prediction of the time when the bus will enter the station. The time obtained by the preliminary prediction is only an initial time, and the situation of other vehicles on the road that has the greatest impact on the bus's travel is not taken into account. Further correction is needed to obtain the specific time when the bus will enter the station.

[0035] The number of vehicles between the first bus stop and the second bus stop is obtained. The first bus stop and the second bus stop are two adjacent stations on the bus line. By making predictions based on any two adjacent stations, it is possible to avoid excessive interference of historical data of bus travel on the travel time of the current section, thereby improving the accuracy of prediction of bus entry and exit times.

[0036] The information about the number of vehicles between the first bus stop and the second bus stop includes:

[0037] The traffic flow I from the first bus stop into the area between the first bus stop and the second bus stop.

[0038] The traffic volume O between the first bus station and the second bus station exits from the second bus station.

[0039] The first vehicle flow is obtained by subtracting the vehicle flow O from the second bus station and leaving the first bus station from the second bus station.

[0040] By analyzing the number of vehicles entering the area between the first bus station and the second bus station from the first bus station and the number of vehicles leaving the area between the first bus station and the second bus station from the second bus station, the first vehicle flow rate within the area between the first bus station and the second bus station is obtained. The first vehicle flow rate obtained at this time refers to the data obtained from the first bus station and the second bus station, and does not consider other data. It is not enough to fully represent the vehicle flow rate within the area between the first bus station and the second bus station, and the impact on other bus routes must also be considered.

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

[0042] The bus stop intervals of other bus routes intersect with the first bus stop and the second bus stop intervals. Vehicles on other bus routes may turn and enter the first bus stop and the second bus stop intervals, and the traffic flow data in the first bus stop and the second bus stop intervals are modified. The difference S between the traffic flow entering the bus stop intervals of other bus routes and the traffic flow leaving the bus stop intervals of other bus routes is calculated.

[0043] The calculation method of S is:

[0044] Set a unit distance and a unit time corresponding to the unit distance to perform vehicle position analysis on the traffic volume in other bus routes. Analyze the distance between the intersection of two adjacent bus stop intervals in other bus routes and the first bus stop and the second bus stop interval of this bus route. Based on the difference S between the traffic volume entering the two adjacent bus stop intervals in other bus routes and the traffic volume leaving the interval, if the traffic volume corresponding to the S value exceeds the preset time and does not leave, then add the S value to the first traffic volume to obtain the second traffic volume.

[0045] The second traffic volume is the traffic volume between the first bus stop and the second bus stop. Compared with the first traffic volume, the second traffic volume takes into account the vehicle entry data on other roads, because the roads corresponding to the bus routes are the main source of entry, and the vehicles leaving the first bus stop and the second bus stop are recorded on other bus routes. Therefore, the second traffic volume data can reflect the traffic volume information between the first bus stop and the second bus stop with a high degree of matching.

[0046] After obtaining the traffic flow information between the first bus station and the second bus station, the data processing center reads the road traffic flow information, corrects the initial bus arrival time according to the traffic flow, and obtains the bus arrival time.

[0047] The specific method for correcting the initial arrival time of buses according to traffic volume is as follows:

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

[0049] The training method of the deep learning model is:

[0050] Based on the traffic flow data of any two adjacent bus stations in the historical state and the time required for bus travel, the minimum value of the impact of traffic flow on bus travel time is obtained. Because when the traffic flow between the first bus station and the second bus station is less than a certain value, it will basically not affect the bus travel. For example, when a bus is traveling on a 4-lane road with a traffic flow of 2, the traffic flow is too small to affect the normal travel of the bus. Therefore, the minimum value of the impact of traffic flow on bus travel time needs to be eliminated.

[0051] Based on the minimum value of the impact of vehicle flow on bus travel time, the correlation coefficient between the excess vehicle flow and bus travel time is analyzed. The impact of the minimum value of the impact of vehicle flow on bus travel time is reduced, and the accuracy of bus arrival time prediction is improved.

[0052] The traffic volume and the bus arrival time are positively correlated functions, and the correlation coefficient should satisfy the positive correlation characteristic. According to the correlation coefficient of the current traffic volume on the bus arrival time, the initial bus arrival time is corrected.

[0053] Correction of the initial arrival time of the bus also includes the impact of factors such as traffic light information at intersections on the arrival time of the bus. Fuzzy position prediction is added during the normal driving of the bus, and whether the bus passes the traffic light is determined based on the predicted fuzzy position, so as to complete the correction of the arrival time of the bus caused by the traffic light at the intersection.

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

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

Claims

1. A bus precise entry and exit calculation algorithm based on the application of intelligent network technology, characterized in that: Included are: Get the distance between the first bus stop and the second bus stop, as well as the bus running speed; The data processing center sets the initial arrival time of the bus according to the bus speed and the distance between the first bus stop and the second bus stop; Obtain information on the number of vehicles between the first bus stop and the second bus stop; The data processing center reads the road traffic flow information, corrects the initial bus arrival time according to the traffic flow, and obtains the bus arrival time; The data processing center uploads the bus arrival time to the bus stop display device.

2. According to claim 1, a bus precise entry and exit calculation algorithm based on the application of intelligent network technology is characterized by ,The first bus station and the second bus station are two adjacent stations on the bus line.

3. According to claim 1, a bus precise entry and exit calculation algorithm based on intelligent network technology application is characterized by ,The information about the number of vehicles between the first bus station and the second bus station includes: The traffic volume I from the first bus station into the area between the first bus station and the second bus station; The traffic volume O between the first bus station and the second bus station exits from the second bus station; The bus stop intervals of other bus routes have intersections with the first bus stop and the second bus stop intervals, and the difference S between the vehicle flow entering the bus stop intervals of other bus routes and the vehicle flow leaving the bus stop intervals of other bus routes is greater than or equal to 0.

4. According to claim 3, a precise bus entry and exit calculation algorithm based on the application of intelligent network technology is characterized in that ,The calculation method of the traffic volume between the first bus station and the second bus station is as follows: The first vehicle flow is obtained by subtracting the vehicle flow O from the second bus station and the first bus station from the vehicle flow I entering 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 of two adjacent bus stop intervals in other bus routes and the first bus stop and the second bus stop interval of this bus route, and according to the difference S between the vehicle flow entering the two adjacent bus stop intervals in other bus routes and the vehicle flow leaving the interval, if the vehicle flow corresponding to the S value exceeds the preset time and does not leave, then add the S value to the first vehicle flow to obtain the second vehicle flow; The second traffic flow is the traffic flow between the first bus stop and the second bus stop.

5. According to claim 1, a precise bus entry and exit calculation algorithm based on the application of intelligent network technology is characterized by ,The specific method for correcting the initial arrival time of the bus according to the ,traffic flow is as follows: By using historical data to train a deep learning model, the correlation coefficient between traffic volume and bus arrival time is obtained; The traffic volume and the bus arrival time are positively correlated functions; According to the correlation coefficient of the current traffic flow on the bus arrival time, the initial bus arrival time is corrected.

6. According to claim 5, a precise bus entry and exit calculation algorithm based on the application of intelligent network technology is characterized in that ,The training method of the deep learning model is: Based on the historical traffic flow data of any two adjacent bus stations and the time required for bus travel, training is performed to obtain the minimum value of the impact of traffic flow on bus travel time; Based on the minimum part of the impact of vehicle flow exceeding vehicle flow on bus travel time, the correlation coefficient between excess vehicle flow and bus travel time is analyzed.

Images