A vehicle-road cooperative method, system, and storage medium based on public transport operation data

Abstract

This invention discloses a vehicle-road cooperative method, system, and storage medium based on bus operation data. The method includes: acquiring the stops of a target bus between two adjacent intersections; determining the stopping duration of the target bus at at least one of the stops; predicting the feasible speed range of the bus in each sub-segment based on road conditions; determining whether the bus can pass through the green light at the exit of the sub-segment based on the feasible speed range of the bus in the sub-segment; if so, analyzing the suggested driving speed of the bus in the sub-segment and guiding the bus to travel between the entrance and exit of the sub-segment based on the suggested driving speed; otherwise, executing a traffic light timing analysis and adjustment method at the exit of the sub-segment so that the bus can pass through the green light at the exit of the sub-segment after the traffic light is adjusted. This invention realizes the driving process control of the target bus throughout the entire driving route, improving the operating efficiency of the bus.

Description

Technical Field

[0001] This invention relates to the field of traffic control technology, specifically to a vehicle-road cooperative method, system, and storage medium based on public transport operation data. Background Technology

[0002] Currently, urban traffic congestion is a frequent occurrence, significantly reducing traffic efficiency and hindering urban development. Urban traffic problems urgently need to be addressed. Experience has shown that public transportation systems play a crucial role in reducing urban congestion, providing diverse travel options, optimizing urban passenger transport structure, and improving the quality of urban life. Currently, the operational efficiency and driving process control levels of buses are relatively low, severely impacting their reliability, attractiveness to passengers, and their share of travel demand. Summary of the Invention

[0003] To address the problems existing in the prior art, this invention provides a vehicle-road cooperative method, system, and storage medium based on bus operation data. By controlling the driving process between two adjacent intersections and the intersection passage process, the operating efficiency of buses on their routes is improved. The specific technical solution is as follows:

[0004] Firstly, a vehicle-road cooperative method based on public transport operation data is provided, including the following steps:

[0005] The two adjacent intersections in the route of the target bus are recorded as the road segment entrance and the road segment exit. The stops of the target bus between the two adjacent intersections are also recorded, and there is at least one stop.

[0006] Based on the number of people waiting at at least one of the stops, and in conjunction with the historical stopping time of buses on the target bus route at at least one of the stops, the stopping time of the target bus at at least one of the stops is determined.

[0007] The road segments between adjacent road segment entrances and stops, between stops, and between stops and road segment exits are denoted as sub-road segments. The road conditions of the sub-road segments are obtained, and the feasible speed range of the bus in the sub-road segments is predicted based on the road conditions of the sub-road segments.

[0008] Based on the feasible speed range of the bus in the sub-segment, it is determined whether the bus can pass through the green light at the exit of the segment. If so, the suggested driving speed of the bus in the sub-segment is analyzed, and the bus is guided to travel between the entrance and exit of the segment based on the suggested driving speed. Otherwise, the signal timing analysis and adjustment method at the exit of the segment is executed so that the bus can pass through the green light at the exit of the segment after the signal light is adjusted.

[0009] In some implementations, determining the dwell time of the target bus at at least one of the stops includes:

[0010] Obtain the total time for passengers to get on and off the bus at each stop of the target bus route from the historical data, as well as the number of people waiting at the stop.

[0011] Based on the stop time and the number of people waiting at the stop, the total time for passengers to get on and off at the stop, i.e. the stop duration, is used as the output. Historical data is used to mine and analyze the mapping pattern between the input and the output.

[0012] Based on the mapping pattern and the number of people waiting at the current stop, the stopping time of the target bus at the stop is determined.

[0013] In some implementations, the prediction of the feasible speed range of the bus within each sub-segment based on road conditions includes:

[0014] Obtain vehicle speeds under different road conditions from historical data, and determine the feasible range of vehicle speeds under different road conditions based on historical data;

[0015] Based on the current road conditions of each sub-segment, predict the feasible speed range of the target bus within that sub-segment.

[0016] In some implementations, the analysis of the recommended driving speed of the bus on the sub-road segment includes:

[0017] Obtain the current phase, remaining time 'a', and signal period 'T' of the traffic light at the exit of the road segment, and calculate the remaining travel time interval of the bus (a+t1+). a+t2+ ),in It is an adjustable parameter that represents the number of signal cycles. t1 is the time difference between the current phase and the start time of the next target phase, and t2 is the time difference between the current phase and the end time of the next target phase.

[0018] The optimal speed and optimal speed deviation of the bus in each sub-segment are used to determine the recommended driving speed of the bus in that sub-segment. The travel time of the bus in each sub-segment is determined by combining the path length of the sub-segment. The recommended driving speed of the bus in each sub-segment is then determined by using the sum of the travel time of the bus in each sub-segment as a constraint within the remaining travel time interval of the bus. The optimal speed and optimal speed deviation are both related to the road condition parameters of the sub-segment.

[0019] In some implementations, the method for obtaining the optimal speed includes:

[0020] Based on the current road conditions of the sub-road segment, determine the congestion level of the sub-road segment;

[0021] The weights of multi-dimensional factors associated with optimal speed are determined based on different congestion levels. These multi-dimensional factors include at least a safety factor and an efficiency factor. The safety factor is determined based on the safety probability corresponding to different driving speeds under different congestion levels, and the efficiency factor is determined based on the travel time per unit distance and the speed dispersion within a unit distance corresponding to different driving speeds under different congestion levels.

[0022] The optimal speed is determined by minimizing the weighted fusion value of multi-dimensional factors.

[0023] In some embodiments, the method for obtaining the optimal speed deviation includes:

[0024] Analyze whether the bus can pass through the exit green light when traveling at the optimal speed (i.e., when the optimal speed deviation is 0) on each sub-segment. If so, the optimal speed of the bus on each sub-segment is taken as the suggested speed; otherwise:

[0025] Based on the road conditions of each sub-segment, the range of optimal speed deviation values ​​for each sub-segment is determined. The worse the road conditions of a sub-segment, the longer the range of optimal speed deviation values ​​for each sub-segment. Based on the road conditions of each sub-segment, the priority of adjusting the optimal speed of each sub-segment using non-zero optimal speed deviation values ​​is determined. The worse the road conditions of a sub-segment, the lower the priority of adjusting the optimal speed of the sub-segment using non-zero optimal speed deviation values. When adjusting the optimal speed of a sub-segment using non-zero optimal speed deviation values ​​for two or more sub-segments, the worse the road conditions of a sub-segment, the smaller the optimal speed deviation of the bus on that sub-segment.

[0026] In some implementations, the road conditions are determined based on the distribution of vehicles on the road segment, including the number of lanes, the number of vehicles, the position and number of vehicles of different types, to characterize the degree of traffic congestion on the road segment.

[0027] The method for obtaining road conditions includes:

[0028] Based on the images collected from the road segment, the location and vehicle type of different vehicles in each lane are obtained. The vehicle distribution characteristics in the current lane of the bus are used as the main features, and the vehicle distribution characteristics in adjacent lanes are used as auxiliary features. The main features and auxiliary features are combined as preliminary road segment features.

[0029] Based on the current captured image and several subsequent captured images, the lane change characteristics of the bus and the lane change characteristics of vehicles in adjacent lanes are obtained. The lane change characteristics of vehicles in adjacent lanes include the lane change characteristics of vehicles in adjacent lanes changing to the lane where the bus is located and the lane change characteristics of vehicles in adjacent lanes changing to lanes where the bus is not located.

[0030] The weight parameters of auxiliary features in the initial road segment features are modified based on the lane-changing characteristics of buses and vehicles in adjacent lanes. The contribution of the lane-changing characteristics of buses, the lane-changing characteristics of vehicles in adjacent lanes changing to the lane where buses are located, and the lane-changing characteristics of vehicles in adjacent lanes changing to lanes where buses are not located to the modification of weight parameters decreases in that order.

[0031] Road conditions are analyzed and classified based on primary and auxiliary features with weighted parameters.

[0032] In some embodiments, the method for analyzing and adjusting the timing of traffic lights at the exits of the road segment includes:

[0033] The system obtains the time difference between the bus's arrival at the next intersection and the time interval of the adjacent green light signal at the next intersection within the feasible speed range. If the time difference is less than a preset value, the signal timing at the next intersection is adjusted; if the time difference is greater than the preset value, the signal timing at the next intersection is not adjusted.

[0034] Secondly, a vehicle-road cooperative system based on public transport operation data is provided, including:

[0035] The station acquisition unit is used to acquire two adjacent intersections in the route of the target bus, denoted as the road segment entrance and the road segment exit, and to acquire the stops of the target bus between the two adjacent intersections, wherein there is at least one stop.

[0036] The station stop duration analysis unit is used to determine the stop duration of the target bus at at least one of the stops based on the number of waiting passengers at at least one of the stops and the historical stop duration of buses on the target bus route at at least one of the stops.

[0037] The sub-segment speed feasible region analysis unit is used to record the road segments between adjacent road segment entrances and stops, between stops, and between stops and road segment exits as sub-segments, obtain the road conditions of the sub-segments, and predict the speed feasible region interval of the bus in the sub-segment based on the road conditions of the sub-segments.

[0038] The vehicle-road control unit is used to determine whether a bus can pass through the green light at the exit of a road segment based on the feasible speed range of the bus in the sub-road segment. If so, it analyzes the suggested driving speed of the bus in the sub-road segment and guides the bus to travel between the entrance and exit of the road segment based on the suggested driving speed; otherwise, it executes the road segment exit signal timing analysis and adjustment method so that the bus can pass through the green light at the exit of the road segment after the signal light is adjusted.

[0039] Thirdly, a computer-readable storage medium is provided having computer instructions stored thereon, which, when executed by a processor, implement the steps of the vehicle-road cooperative method based on public transport operation data as described in the first aspect.

[0040] The present invention provides a vehicle-road cooperative method, system, and storage medium based on bus operation data, which has the following beneficial effects: The present invention performs vehicle-road cooperative control on the bus driving process between the entrance and exit of a road segment, and improves the bus operating efficiency by guiding the bus speed and making minor adjustments to the traffic light phase scheme. Attached Figure Description

[0041] Figure 1 This is a schematic diagram of the vehicle-road cooperative method based on public transport operation data in the embodiments of this application;

[0042] Figure 2 This is a flowchart illustrating the traffic light timing analysis and adjustment method in an embodiment of this application.

[0043] Figure 3 This is a schematic diagram of the vehicle-road cooperative system based on public transport operation data in an embodiment of this application. Detailed Implementation

[0044] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0045] This application provides a vehicle-road cooperative method based on public transport operation data, including the following steps:

[0046] Step 1: Obtain two adjacent intersections in the target bus's route and label them as the road segment entrance and road segment exit. Obtain the stops of the target bus between the two adjacent intersections. There must be at least one stop.

[0047] Step 2: Based on the number of people waiting at at least one of the stops, and combined with the historical stopping time of buses on the target bus route at at least one of the stops, determine the stopping time of the target bus at at least one of the stops.

[0048] Step 3: Record the road segments between adjacent road segment entrances and stops, between stops, and between stops and road segment exits as sub-segments, obtain the road conditions of the sub-segments, and predict the feasible speed range of buses in the sub-segments based on the road conditions of the sub-segments. The road conditions are determined based on the vehicle distribution on the road segment, including the number of lanes, the number of vehicles, the position and number of different vehicle types, which are used to characterize the traffic congestion of the road segment.

[0049] Step 4: Based on the feasible speed range of the bus in the sub-segment, determine whether the bus can pass through the green light at the exit of the segment. If so, analyze the suggested driving speed of the bus in the sub-segment and guide the bus to travel between the entrance and exit of the segment based on the suggested driving speed; otherwise, execute the segment exit signal timing analysis and adjustment method so that the bus can pass through the green light at the exit of the segment after the signal light is adjusted.

[0050] In this embodiment, vehicle-road cooperative control is implemented for the bus travel process between the entrance and exit of a road segment. Combining bus operation data, including vehicle speed and stop times at various stops, with consideration of road conditions and traffic light status, the system guides bus speed and makes minor adjustments to traffic light phases to reduce waiting time at traffic lights. This allows buses to pass through the road segment exit directly on a green light without stopping at the exit, improving bus operating efficiency. It is understood that "passing through on a green light at the road segment exit" in this application means traveling through the exit directly on a green light without stopping at a red light. Utilizing the vehicle operation control of adjacent intersections in this application, the travel process between any two adjacent intersections along the target bus's route can also be controlled, thereby achieving control over the target bus's entire route and controlling the arrival time at each stop and destination. It should be noted that this application considers that the various bus stops on a road segment may interfere with normal traffic flow. For example, passengers at bus stops may need to take buses, taxis, or other vehicles. Each bus stop is equivalent to a point of interference, resulting in different road conditions on a road segment. In this application, the road segments between adjacent road segment entrances and bus stops, between bus stops, and between bus stops and road segment exits are denoted as sub-road segments, and each sub-road segment has corresponding road conditions.

[0051] In one implementation, step 2 above, determining the stop duration of the target bus at at least one of the stops, includes:

[0052] Step 21: Obtain the total time for passengers to get on and off the bus and the number of people waiting at the stop for each bus stop of the target bus route in the historical data.

[0053] Step 22: Based on the stop time and the number of people waiting at the stop, the total time for passengers to get on and off at the stop, i.e. the stop duration, is used as the output. Historical data is used to mine and analyze the mapping pattern between the input and output.

[0054] Step 23: Based on the mapping pattern and the number of people waiting at the current stop, determine the stopping time of the target bus at the stop.

[0055] In this embodiment, historical data is used to analyze patterns in the stopping time of buses on the target bus route at each target stop. Based on these patterns, the stopping time of the current target bus at the stop is predicted. It is understood that at certain times, a large number of people are waiting at the stop, resulting in longer boarding and alighting times for bus passengers. Historical data can also be used to analyze the proportion of people waiting at the target stop who are actually boarding the target bus, thereby assessing the boarding and alighting times for passengers at the target stop.

[0056] In one implementation, step 3 above, which predicts the feasible speed range of the bus in each sub-road segment based on the road conditions of the sub-road segment, includes:

[0057] Step 31: Obtain vehicle speeds under different road conditions from historical data, and determine the feasible range of vehicle speeds under different road conditions based on historical data.

[0058] Step 32: Based on the current road conditions of each sub-segment, predict the feasible speed range of the target bus in each sub-segment.

[0059] Specifically, step 31 involves determining the feasible speed range for vehicles under different road conditions based on historical data, including:

[0060] Step 311: Initially divide the interval between the maximum and minimum vehicle speeds into multiple continuous and non-overlapping intervals;

[0061] Step 312: Construct a preliminary matching relationship between the intervals and different road conditions;

[0062] Step 313: Based on the degree of conformity between the preliminary matching relationship and the vehicle speed under different road conditions in the historical data as feedback data, the initially divided interval is optimized to obtain the optimized division interval.

[0063] Step 314: Repeat the previous step until the compliance is greater than the preset threshold to obtain the feasible range of vehicle speed under different road conditions.

[0064] Specifically, the compliance degree is the ratio of the number of records in historical data where vehicle speeds under different road conditions meet the initial matching relationship to the total number of records in the historical data. During the feedback optimization process, the interval size is continuously adjusted so that the compliance degree is greater than a preset threshold, resulting in a division interval that conforms to the pattern of historical data, i.e., the feasible domain interval for vehicle speeds under different road conditions. The compliance degree includes the compliance degree of a single matching relationship between a single road condition and a single interval with the actual situation (the speed distribution under that single road condition in the historical data) (i.e., local compliance degree) and the compliance degree of all matching relationships between all road conditions and their corresponding intervals with the actual situation (i.e., global compliance degree). That is, in this application, when determining the feasible domain interval for vehicle speeds under different road conditions, both local compliance degree and global compliance degree are considered simultaneously. In implementation, the weights of global compliance degree and each local compliance degree are flexibly adjusted as needed.

[0065] In one implementation, step 4 above, analyzing the recommended driving speed of the bus on the sub-road segment, includes:

[0066] Step 41: Obtain the current phase, remaining time 'a', and signal period 'T' of the traffic light at the road segment exit; calculate the remaining travel time interval for the bus (a+t1+...). a+t2+ ),in It is an adjustable parameter that represents the number of signal cycles. t1 is the time difference between the current phase and the start time of the next target phase, and t2 is the time difference between the current phase and the end time of the next target phase.

[0067] Step 42: The optimal speed and optimal speed deviation of the bus in the sub-segment are determined as the suggested driving speed of the bus in the sub-segment. The travel time of the bus in the sub-segment is determined by combining the path length of the sub-segment. The suggested driving speed of the bus in the sub-segment is solved by using the sum of the travel time of the bus in each sub-segment as a constraint within the remaining travel time interval of the bus. The optimal speed and optimal speed deviation are both related to the road condition parameters of the sub-segment.

[0068] In this embodiment, the target phase is when the light is green in the direction of travel of the target bus on the road segment. This means the bus's speed on the sub-segment must be within the feasible speed range of that sub-segment. In one implementation, considering that the bus needs to pass through the road segment exit during the non-end of the green light period (i.e., the bus cannot pass through the intersection at the end of the green light period), a preset time period preceding the target phase can be set as the preferred passage time period. Therefore, t1 can be modified to the time difference between the start time of the preferred passage time period from the current phase to the next target phase, and t2 can be modified to the time difference between the end time of the preferred passage time period from the current phase to the next target phase. It is understood that the methods in steps 41 and 42 of this application can be applied to the analysis of suggested driving speeds from the road segment entrance as the starting point, through at least one stop, to the road segment exit, or to the analysis of suggested driving speeds from the current real-time location of the bus as the starting point, through one or more stops, to the road segment exit. In this case, the path from the current real-time location of the bus to the next nearest stop is a sub-segment. If there is no next nearest stop after the current real-time location of the bus, i.e., it directly reaches the road segment exit, then the path from the current real-time location of the bus to the road segment exit is a sub-segment. The suggested driving speed analysis for each sub-segment can be performed using the methods in steps 41 and 42 described above.

[0069] In one embodiment, the method for obtaining the optimal speed in step 42 above includes:

[0070] Step 4201: Determine the congestion level of the sub-road segment based on the current road conditions.

[0071] Step 4202: Determine the weights of multi-dimensional factors associated with the optimal speed based on different congestion levels. The multi-dimensional factors include at least a safety factor and an efficiency factor. The safety factor is a function of driving speed as an independent variable under different congestion levels. The efficiency factor is a function of driving speed as an independent variable under different congestion levels. The safety factor is determined based on the safety probability (e.g., the safety probability can be measured by the probability of an accident) corresponding to different driving speeds under different congestion levels. The efficiency factor is determined based on the travel time per unit distance and the speed dispersion per unit distance corresponding to different driving speeds under different congestion levels.

[0072] Step 4203: Determine the optimal speed based on minimizing the weighted fusion value of multi-dimensional factors.

[0073] In this embodiment, the multi-dimensional factors associated with optimal speed include various types, at least including safety factors and efficiency factors.

[0074] The bias towards multi-dimensional factors varies depending on the level of congestion. For example, in heavily congested conditions, the rationality of safety factors is prioritized, while in less congested conditions, efficiency factors are considered in addition to safety factors. The weighting ratio between safety and efficiency factors differs across congestion levels. The safety factor is a function of driving speed as the independent variable under different congestion levels. This safety factor function can be a variable with respect to one parameter (driving speed) under different congestion levels, or it can be expressed as a variable with respect to both congestion level and driving speed. Based on historical data, a relationship model between the safety factor function and the driving speed parameter, or a relationship model between the safety factor function and both parameters (congestion level and driving speed), can be derived using fitting functions or neural networks. The most accurate model is then selected. The efficiency factor is determined based on the travel time per unit distance and the speed dispersion per unit distance at different driving speeds under different congestion levels. It can be understood that the shorter the travel time per unit distance, the larger the efficiency factor. At the same time, the smaller the speed dispersion per unit distance, the larger the efficiency factor. That is, the smaller the rate of speed change in a distance, the larger the efficiency factor.

[0075] In one embodiment, the method for obtaining the optimal speed deviation in step 42 above includes:

[0076] Step 4211: Analyze whether the bus can pass through the green light at the exit of each sub-segment when traveling at the optimal speed (i.e., the optimal speed deviation is 0). If so, the optimal speed of the bus in each sub-segment is taken as the suggested speed; otherwise:

[0077] Step 4212: Based on the road conditions of each sub-segment, determine the value range of the optimal speed deviation for each sub-segment. The worse the road conditions of a sub-segment, the longer the value range of the optimal speed deviation for each sub-segment. Based on the road conditions of each sub-segment, determine the priority of adjusting the optimal speed of each sub-segment using a non-zero optimal speed deviation. The worse the road conditions of a sub-segment, the lower the priority of adjusting the optimal speed of the sub-segment using a non-zero optimal speed deviation. When adjusting the optimal speed of a sub-segment using a non-zero optimal speed deviation for two or more sub-segments, the worse the road conditions of the sub-segment, the smaller the optimal speed deviation of the bus on that sub-segment.

[0078] In this embodiment, based on the current road conditions of the sub-segment, the more congested the road conditions, the smaller the optimal speed deviation of the bus. It can be understood that, firstly, the optimal speed is considered for each segment. If the bus can pass through the green light at the exit of each segment while traveling at the optimal speed, the optimal speed deviation is set to 0. If the bus cannot pass through the green light at the exit of each segment while traveling at the optimal speed, the optimal speed deviation is set to be non-zero to adjust the vehicle's speed, allowing the bus to pass through the green light at the exit. During adjustment, priority is given to adjusting the speed of sub-segments with better road conditions, adjusting the optimal speed deviation accordingly to achieve speed adjustment for each sub-segment. The optimal speed deviation of each sub-segment has a corresponding range limit, which is determined based on the road conditions of the sub-segment. For example, the worse the road conditions (the more congested), the smaller the range of the optimal speed deviation. It's understandable that after adjusting the speed of a sub-road segment with relatively good road conditions based on the range of optimal speed deviation, if the bus cannot pass through the exit green light, it can choose a sub-road segment with relatively good road conditions from the remaining sub-road segments for speed adjustment. Alternatively, the speed can be adjusted simultaneously based on multiple sub-road segments with relatively good road conditions, where the optimal speed deviation value of the sub-road segment with relatively good road conditions is greater than that of the sub-road segment with poor road conditions during the adjustment process.

[0079] In one implementation, in step 3 above, the road conditions are determined based on the vehicle distribution on the road segment, including the number of lanes, the number of vehicles, the position and number of vehicles of different types, which are used to characterize the degree of vehicle congestion on the road segment.

[0080] The method for obtaining road conditions includes:

[0081] Step 301: Based on the collected images of the road segment, obtain the location and vehicle type of different vehicles in each lane. Use the vehicle distribution characteristics in the current lane of the bus as the main feature and the vehicle distribution characteristics in adjacent lanes as auxiliary features. Combine the main feature and auxiliary features as preliminary road segment features.

[0082] Step 302: Based on several subsequent frames of the currently acquired image, obtain the lane change features of the bus and the lane change features of vehicles in adjacent lanes. The lane change features of vehicles in adjacent lanes include lane change features of vehicles in adjacent lanes changing to the lane where the bus is located and lane change features of vehicles in adjacent lanes changing to lanes where the bus is located.

[0083] Step 303: Modify the weight parameters of the auxiliary features in the preliminary road segment features based on the lane change characteristics of the bus and the lane change characteristics of vehicles in adjacent lanes. The contribution of the lane change characteristics of the bus, the lane change characteristics of vehicles in adjacent lanes changing to the lane where the bus is located, and the lane change characteristics of vehicles in adjacent lanes changing to the lane where the bus is not located to the modification of the weight parameters decreases in that order.

[0084] Road conditions are analyzed and classified based on primary and auxiliary features with weighted parameters.

[0085] In this embodiment, road condition analysis is performed on the bus based on the distribution characteristics of vehicles in front of and behind the bus in its lane (i.e., the positions and types of different vehicles in the bus's lane). Considering the characteristics of bus operation, the bus's lane at a stop is fixed, and sometimes the bus has a specific lane during its journey. Furthermore, this application further optimizes the bus's road condition analysis process using vehicle lane-changing characteristics over a continuous time period. It can be understood that if the bus does not change lanes (does not change lanes) and vehicles in adjacent lanes do not change lanes to the bus's lane, the correlation between the bus's own road condition and the distribution of vehicles in lanes other than the bus's is very small. The bus's own road condition is analyzed primarily based on the vehicle distribution characteristics in the bus's current lane.

[0086] The analysis and classification of road conditions based on primary and secondary features with weighted parameters can be achieved by training algorithms such as neural networks or random forests to obtain a road condition classification model. In one implementation, the weighted parameters of the primary and secondary features can be determined based on preset values. When analyzing the currently acquired image, the weight coefficients of the primary and secondary features are initially determined, with the weight coefficient of the primary feature being greater than that of the secondary feature. For example, the primary feature is weighted at 0.8, and the secondary feature at 0.2. Further, when analyzing subsequent frames of the currently acquired image, the weight correction coefficients of the secondary features are determined based on a weighted sum of the number of lane changes by the bus, the weighted coefficient of the number of lane changes by the bus, the number of lane changes by vehicles in adjacent lanes, and the weighted coefficient of the number of lane changes by vehicles in adjacent lanes. Here, the weighted coefficient of the number of lane changes by the bus is greater than that of the number of lane changes by vehicles in adjacent lanes. In the lane-changing features of vehicles in adjacent lanes, the weight coefficient for lane-changing features where vehicles change lanes to the lane where buses are located is greater than the weight coefficient for lane-changing features where vehicles change lanes to lanes other than the lane where buses are located. Specifically, the lane-changing features of vehicles in adjacent lanes can be determined based on the weighted sum of the number of lane-changing events where vehicles change lanes to the lane where buses are located and the number of lane-changing events where vehicles change lanes to lanes other than the lane where buses are located. The weight parameters of the main and auxiliary features can be determined using an adaptive method in another implementation. The main features, auxiliary features, and lane-changing features are taken as input, and the adaptive weighting module outputs two weight parameters. These parameters are then processed through a deep network layer for feature analysis, and finally, the road condition classification result is output. In this case, the road condition classification model, after the input layer, includes an adaptive weighting module, a deep network layer (i.e., the feature analysis layer), and an output layer. The adaptive weighting module can be obtained by training a supervised machine learning model based on sample data. Among them, the contribution of the lane-changing characteristics of buses, the lane-changing characteristics of vehicles in adjacent lanes changing to the lane where buses are located, and the lane-changing characteristics of vehicles in adjacent lanes changing to lanes where buses are not located to the modification of the weight parameters decreases in the following order: the weight coefficient of the number of lane changes of buses is greater than the weight coefficient of the number of lane changes of vehicles in adjacent lanes, and the weight coefficient of the lane-changing characteristic of vehicles in adjacent lanes changing to the lane where buses are located is greater than the weight coefficient of the lane-changing characteristic of vehicles in adjacent lanes changing to lanes where buses are not located.

[0087] In one implementation, step 4 above, the method for analyzing and adjusting the timing of traffic lights at road exits, includes:

[0088] The system obtains the time difference between the bus's arrival at the next intersection and the time interval of the adjacent green light signal at the next intersection within the feasible speed range. If the time difference is less than a preset value, the signal timing at the next intersection is adjusted; if the time difference is greater than the preset value, the signal timing at the next intersection is not adjusted.

[0089] It is understood that the signal timing adjustment principle in this application embodiment is based on minimizing the disturbance to the original signal phase strategy. Considering the continuity of the signal phase over a long period of time, if the duration of a certain phase in the current signal cycle increases or decreases, it will affect the signal display of adjacent phases or adjacent cycles, thereby affecting the smooth traffic flow of other lanes.

[0090] It is understood that, according to the method of this application, in one case where there is no stop between the previous and next intersections, the vehicle-road cooperative method includes:

[0091] Based on the road conditions between the previous and next intersections, the feasible speed range of the bus between the previous and next intersections is predicted;

[0092] Based on the speed feasible region between the previous intersection and the next intersection, the travel time feasible region of the bus between the previous intersection and the next intersection is predicted;

[0093] Based on the feasible travel time of the bus between the previous and next intersections, determine whether the bus can pass through the next intersection in green wave mode within the feasible speed range.

[0094] If so, the recommended driving speed of the bus between the previous and next intersection is analyzed based on the current traffic light phase, the remaining time of the current phase, and the signal cycle at the next intersection, and the bus is guided to drive based on the recommended driving speed.

[0095] If not, determine the time difference between the bus's arrival at the next intersection and the time between the adjacent green light signals at the next intersection within the feasible speed range. If the time difference is less than the preset value, adjust the signal timing at the next intersection. If the time difference is greater than the preset value, do not adjust the signal timing at the next intersection.

[0096] This application also provides a vehicle-road cooperative system based on public transport operation data, including:

[0097] The station acquisition unit is used to acquire two adjacent intersections in the route of the target bus, denoted as the road segment entrance and the road segment exit, and to acquire the stops of the target bus between the two adjacent intersections, wherein there is at least one stop.

[0098] The station stop duration analysis unit is used to determine the stop duration of the target bus at at least one of the stops based on the number of waiting passengers at at least one of the stops and the historical stop duration of buses on the target bus route at at least one of the stops.

[0099] The sub-segment speed feasible region analysis unit is used to record the road segments between adjacent road segment entrances and stops, between stops, and between stops and road segment exits as sub-segments, obtain the road conditions of the sub-segments, and predict the speed feasible region interval of the bus in the sub-segment based on the road conditions of the sub-segments.

[0100] The vehicle-road control unit is used to determine whether a bus can pass through the green light at the exit of a road segment based on the feasible speed range of the bus in the sub-road segment. If so, it analyzes the suggested driving speed of the bus in the sub-road segment and guides the bus to travel between the entrance and exit of the road segment based on the suggested driving speed; otherwise, it executes the road segment exit signal timing analysis and adjustment method so that the bus can pass through the green light at the exit of the road segment after the signal light is adjusted.

[0101] In this embodiment, the specific limitations of the vehicle-road cooperative system based on public transport operation data can be found in the limitations of the vehicle-road cooperative method based on public transport operation data described above, and will not be repeated here. Each unit in the aforementioned vehicle-road cooperative system based on public transport operation data can be implemented entirely or partially through software, hardware, or a combination thereof. Each of these units can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each of the above units.

[0102] In some embodiments, the vehicle-road cooperative system based on public transport operation data provided in this invention can be implemented using a combination of hardware and software. As an example, the vehicle-road cooperative system based on public transport operation data provided in this invention can be directly embodied as a combination of software modules executed by a processor. The software modules can be located in a storage medium, which is located in a memory. The processor reads the executable instructions included in the software modules in the memory and combines them with necessary hardware (e.g., including the processor and other components connected to the bus) to complete the vehicle-road cooperative method based on public transport operation data provided in this invention.

[0103] This application also provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the steps of the vehicle-road cooperative method for bus operation data described above. For example, the computer-readable storage medium may be a read-only memory (ROM), random access memory (RAM), compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, or optical data storage node, etc.

[0104] This invention is not limited to the specific embodiments described above. Any modifications made by those skilled in the art based on the above concept without creative effort are within the scope of protection of this invention.

Claims

1. A vehicle-road cooperative method based on public transport operation data, characterized in that, Includes the following steps: The two adjacent intersections in the route of the target bus are recorded as the road segment entrance and the road segment exit. The stops of the target bus between the two adjacent intersections are also recorded, and there is at least one stop. Based on the number of people waiting at at least one of the stops, and in conjunction with the historical stopping time of buses on the target bus route at at least one of the stops, the stopping time of the target bus at at least one of the stops is determined. The road segments between adjacent road segment entrances and stops, between stops, and between stops and road segment exits are denoted as sub-road segments. The road conditions of the sub-road segments are obtained, and the feasible speed range of the bus in the sub-road segments is predicted based on the road conditions of the sub-road segments. Based on the feasible speed range of the bus in the sub-segment, it is determined whether the bus can pass through the green light at the exit of the segment. If so, the suggested driving speed of the bus in the sub-segment is analyzed, and the bus is guided to drive between the entrance and exit of the segment based on the suggested driving speed. Otherwise, implement the method of analyzing and adjusting the timing of traffic lights at the exit of the road segment so that buses can pass through the green light at the exit of the road segment after the traffic lights are adjusted.

2. The vehicle-road cooperative method based on public transport operation data according to claim 1, characterized in that, Determining the stop duration of the target bus at at least one of the stops includes: Obtain the total time for passengers to get on and off the bus at each stop of the target bus route from the historical data, as well as the number of people waiting at the stop. Based on the stop time and the number of people waiting at the stop, the total time for passengers to get on and off at the stop, i.e. the stop duration, is used as the output. Historical data is used to mine and analyze the mapping pattern between the input and the output. Based on the mapping pattern and the number of people waiting at the current stop, the stopping time of the target bus at the stop is determined.

3. The vehicle-road cooperative method based on public transport operation data according to claim 1, characterized in that, The prediction of the feasible speed range of the bus within each sub-segment based on road conditions includes: Obtain vehicle speeds under different road conditions from historical data, and determine the feasible range of vehicle speeds under different road conditions based on historical data; Based on the current road conditions of each sub-segment, predict the feasible speed range of the target bus within that sub-segment.

4. The vehicle-road cooperative method based on public transport operation data according to claim 1, characterized in that, The analysis of recommended driving speeds for buses on sub-road segments includes: Obtain the current phase, remaining time 'a', and signal period 'T' of the traffic light at the exit of the road segment, and calculate the remaining travel time interval of the bus (a+t1+). a+t2+ ),in It is an adjustable parameter that represents the number of signal cycles. t1 is the time difference between the current phase and the start time of the next target phase, and t2 is the time difference between the current phase and the end time of the next target phase. The optimal speed and optimal speed deviation of the bus in each sub-segment are used to determine the recommended driving speed of the bus in that sub-segment. The travel time of the bus in each sub-segment is determined by combining the path length of the sub-segment. The recommended driving speed of the bus in each sub-segment is then determined by using the sum of the travel time of the bus in each sub-segment as a constraint within the remaining travel time interval of the bus. The optimal speed and optimal speed deviation are both related to the road condition parameters of the sub-segment.

5. The vehicle-road cooperative method based on public transport operation data according to claim 4, characterized in that, The method for obtaining the optimal speed includes: Based on the current road conditions of the sub-road segment, determine the congestion level of the sub-road segment; The weights of multi-dimensional factors associated with optimal speed are determined based on different congestion levels. These multi-dimensional factors include at least a safety factor and an efficiency factor. The safety factor is determined based on the safety probability corresponding to different driving speeds under different congestion levels, and the efficiency factor is determined based on the travel time per unit distance and the speed dispersion within a unit distance corresponding to different driving speeds under different congestion levels. The optimal speed is determined by minimizing the weighted fusion value of multi-dimensional factors.

6. The vehicle-road cooperative method based on public transport operation data according to claim 4, characterized in that, The method for obtaining the optimal speed deviation includes: Analyze whether the bus can pass through the exit green light when traveling at the optimal speed (i.e., when the optimal speed deviation is 0) on each sub-segment. If so, the optimal speed of the bus on each sub-segment is taken as the suggested speed; otherwise: Based on the road conditions of each sub-segment, the range of optimal speed deviation values ​​for each sub-segment is determined. The worse the road conditions of a sub-segment, the longer the range of optimal speed deviation values ​​for each sub-segment. Based on the road conditions of each sub-segment, the priority of adjusting the optimal speed of each sub-segment using non-zero optimal speed deviation values ​​is determined. The worse the road conditions of a sub-segment, the lower the priority of adjusting the optimal speed of the sub-segment using non-zero optimal speed deviation values. When adjusting the optimal speed of a sub-segment using non-zero optimal speed deviation values ​​for two or more sub-segments, the worse the road conditions of a sub-segment, the smaller the optimal speed deviation of the bus on that sub-segment.

7. The vehicle-road cooperative method based on public transport operation data according to claim 1, characterized in that, The road conditions are determined based on the distribution of vehicles on the road segment, including the number of lanes, the number of vehicles, the position and number of vehicles of different types, and are used to characterize the degree of traffic congestion on the road segment. The method for obtaining road conditions includes: Based on the images collected from the road segment, the location and vehicle type of different vehicles in each lane are obtained. The vehicle distribution characteristics in the current lane of the bus are used as the main features, and the vehicle distribution characteristics in adjacent lanes are used as auxiliary features. The main features and auxiliary features are combined as preliminary road segment features. Based on the current captured image and several subsequent captured images, the lane change characteristics of the bus and the lane change characteristics of vehicles in adjacent lanes are obtained. The lane change characteristics of vehicles in adjacent lanes include the lane change characteristics of vehicles in adjacent lanes changing to the lane where the bus is located and the lane change characteristics of vehicles in adjacent lanes changing to lanes where the bus is not located. The weight parameters of auxiliary features in the initial road segment features are modified based on the lane-changing characteristics of buses and vehicles in adjacent lanes. The contribution of the lane-changing characteristics of buses, the lane-changing characteristics of vehicles in adjacent lanes changing to the lane where buses are located, and the lane-changing characteristics of vehicles in adjacent lanes changing to lanes where buses are not located to the modification of weight parameters decreases in that order. Road conditions are analyzed and classified based on primary and auxiliary features with weighted parameters.

8. The vehicle-road cooperative method based on public transport operation data according to claim 1, characterized in that, The method for analyzing and adjusting the timing of traffic lights at the exits of the aforementioned road section includes: The system obtains the time difference between the bus's arrival at the next intersection and the time interval between the adjacent green light signals at that intersection, within the feasible speed range. If the time difference is less than a preset value, the signal timing at the next intersection is adjusted; if the time difference is greater than the preset value, then... Do not adjust the signal timing at the next intersection.

9. A vehicle-road cooperative system based on public transport operation data, characterized in that, include: The station acquisition unit is used to acquire two adjacent intersections in the route of the target bus, denoted as the road segment entrance and the road segment exit, and to acquire the stops of the target bus between the two adjacent intersections, wherein there is at least one stop. The station stop duration analysis unit is used to determine the stop duration of the target bus at at least one of the stops based on the number of waiting passengers at at least one of the stops and the historical stop duration of buses on the target bus route at at least one of the stops. The sub-segment speed feasible region analysis unit is used to record the road segments between adjacent road segment entrances and stops, between stops, and between stops and road segment exits as sub-segments, obtain the road conditions of the sub-segments, and predict the speed feasible region interval of the bus in the sub-segment based on the road conditions of the sub-segments. The vehicle-road control unit is used to determine whether the bus can pass through the green light at the exit of the road segment based on the feasible speed range of the bus in the sub-road segment. If so, it analyzes the suggested driving speed of the bus in the sub-road segment and guides the bus to travel between the entrance and exit of the road segment based on the suggested driving speed. Otherwise, implement the method of analyzing and adjusting the timing of traffic lights at the exit of the road segment so that buses can pass through the green light at the exit of the road segment after the traffic lights are adjusted.

10. A computer-readable storage medium storing computer instructions thereon, characterized in that, When the instruction is executed by the processor, it implements the steps of the vehicle-road cooperative method based on public transport operation data as described in any one of claims 1-8.

Images