Method, device, equipment and medium for predicting bus driving status and signal control

Abstract

The present invention provides a method, device, equipment and medium for predicting the driving state of a public bus and controlling signals, which relates to the field of artificial intelligence, and in particular to technical fields such as autonomous driving and intelligent transportation. The specific scheme is as follows: the method comprises: obtaining a target real-time distance between the public bus and a signal intersection based on real-time position information of the public bus; calculating an average driving speed of the public bus according to the target real-time distance; collecting a first real-time driving speed of the public bus at the current moment; correcting the first real-time driving speed based on the average driving speed to obtain a target real-time driving speed of the public bus at the current moment; obtaining an initial travel time of the public bus from the current moment to the signal intersection according to the target real-time distance and the target real-time driving speed; and correcting the initial travel time using a preset time correction method to obtain a target travel prediction time.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence, and in particular to technical fields such as autonomous driving and intelligent transportation, and provides a method, device, equipment and medium for predicting the driving status of a public bus and controlling signals. Background Art

[0002] In the bus priority scenario, accurate and stable prediction of the time when buses arrive at signalized intersections is required to accurately adjust the signal light scheme and achieve a better priority effect. If the time prediction is inaccurate and the signal light scheme is adjusted frequently, the bus priority effect will not be ideal and the normal traffic of vehicles at the intersection will be affected. The key to accurately and stably predicting the time of arrival at the intersection is: (1) accurately calculating the distance between the vehicle's location and the intersection; (2) accurately calculating the vehicle's driving speed; (3) adjusting the priority scheme multiple times according to the vehicle's driving status and not too frequently.

[0003] The existing scheme for predicting the arrival time at a signalized intersection in a bus priority scenario is:

[0004] (1) Distance between vehicle and intersection: a) The straight-line distance between the vehicle’s GPS (Global Positioning System) coordinates and the intersection’s GPS coordinates is used, but this solution may result in large calculation errors due to irregular road sections; b) A fixed detection position is used. This solution has poor flexibility and the algorithm cannot independently decide the time and distance to start control when making priority decisions. It also has the defect of increasing cost investment.

[0005] (2) Travel time prediction: a) Travel time prediction scheme based on Kalam (Kalman algorithm), but this scheme is based on the conditions that the vehicle is in a stable operating state and the interference factors are normally distributed, and it is assumed that the vehicle speed is reliable. There are many prerequisites for effective implementation; b) Determine the travel time based on historical speed and time patterns, but this scheme cannot respond to real-time situations and relies on a large amount of historical data to be implemented, which has certain implementation limitations; c) Predict travel time based on neural network model. This scheme needs to train the model based on a large amount of historical data, and needs to be trained separately for different road conditions. It has problems such as complex use and prone to overfitting and underfitting.

[0006] In addition, in the bus priority scenario, the queue situation at the signalized intersection also has a great impact on the time it takes for buses to arrive at the intersection. Currently, the detection of queue data generally relies on roadside detection equipment, such as video, radar, geomagnetism, etc. This detection method cannot guarantee the accuracy of the collected data when the queue length is not long, and has extremely high requirements for the stable operation of the detection equipment. However, the instability of roadside detection equipment is normal; in addition, the cost of hardware equipment construction is extremely high, and it is difficult to cover every intersection in reality. Summary of the invention

[0007] The technical problem to be solved by the present disclosure is to overcome the defect in the prior art that there is no method to ensure accurate and stable prediction of the bus driving status in the bus priority scenario, and to provide a bus driving status prediction and signal control method, device, equipment and medium.

[0008] The present invention solves the above technical problems through the following technical solutions:

[0009] According to one aspect of the present disclosure, a method for predicting a bus driving state is provided, the method comprising:

[0010] Based on the real-time position information of the public transport, obtaining the target real-time distance between the public transport and the signalized intersection;

[0011] Calculate the average speed of the public transport vehicle according to the target real-time distance;

[0012] Collecting the first real-time running speed of the public transport vehicle at the current moment;

[0013] Correcting the first real-time travel speed based on the average travel speed to obtain a target real-time travel speed of the public transport vehicle at the current moment;

[0014] According to the target real-time distance and the target real-time travel speed, obtaining the initial travel time of the public transport vehicle from the current moment to the signalized intersection;

[0015] The initial travel time is corrected using a preset time correction method to obtain a target travel prediction time.

[0016] According to another aspect of the present disclosure, a signal control method is provided. The signal control method is applied in a bus priority scenario and is implemented based on the above-mentioned bus driving state prediction method.

[0017] The signal control method comprises:

[0018] Obtaining a target travel prediction time of the public transport vehicle from the current moment to the signalized intersection based on the prediction method;

[0019] generating a control strategy for the signal light at the signalized intersection according to the target travel prediction time;

[0020] The working state of the signal light at the signalized intersection is controlled based on the control strategy.

[0021] According to another aspect of the present disclosure, a device for predicting a bus driving state is provided, the device comprising:

[0022] A target real-time distance acquisition module is used to acquire the target real-time distance between the bus and the signalized intersection based on the real-time position information of the bus;

[0023] An average driving speed acquisition module is used to calculate the average driving speed of the public transport vehicle according to the target real-time distance;

[0024] A first driving speed collection module, used to collect the first real-time driving speed of the public transport vehicle at the current moment;

[0025] A driving speed correction acquisition module, used for correcting the first real-time driving speed based on the average driving speed to obtain the target real-time driving speed of the public transport vehicle at the current moment;

[0026] An initial travel time acquisition module, used to acquire the initial travel time of the public transport vehicle from the current moment to the signalized intersection according to the target real-time distance and the target real-time travel speed;

[0027] The travel prediction time correction module is used to correct the initial travel time using a preset time correction method to obtain a target travel prediction time.

[0028] According to another aspect of the present disclosure, a signal control device is provided. The signal control device is applied in a bus priority scenario, and the signal control device is implemented based on the above-mentioned bus driving state prediction device;

[0029] The signal control device comprises:

[0030] A target travel prediction time acquisition module, used to acquire the target travel prediction time of the public transport vehicle from the current moment to the signalized intersection obtained based on the prediction device;

[0031] A control strategy generating module, used for generating a control strategy for the signal light at the signalized intersection according to the target travel prediction time;

[0032] A signal control module is used to control the working state of the signal light at the signal intersection based on the control strategy.

[0033] According to another aspect of the present disclosure, there is provided an electronic device, including:

[0034] at least one processor; and

[0035] a memory communicatively connected to the at least one processor; wherein,

[0036] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor so that the at least one processor can perform the above method.

[0037] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the above method.

[0038] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program implements the above method when executed by a processor.

[0039] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0041] Figure 1 is a first schematic diagram of a method for predicting a bus driving state according to a first embodiment of the present disclosure;

[0042] Figure 2 is a second schematic diagram of the method for predicting the travel state of a bus according to the first embodiment of the present disclosure;

[0043] Figure 3 is a schematic diagram of a scene of a certain road section according to the first embodiment of the present disclosure;

[0044] Figure 4 is a third schematic diagram of the method for predicting the travel state of a bus according to the first embodiment of the present disclosure;

[0045] Figure 5 is a fourth schematic diagram of the method for predicting the travel state of a bus according to the first embodiment of the present disclosure;

[0046] Figure 6 is a first schematic diagram of a method for predicting a bus driving state according to a second embodiment of the present disclosure;

[0047] Figure 7 is a mapping relationship table between actual driving speed and queue length according to the second embodiment of the present disclosure;

[0048] Figure 8 is a second schematic diagram of a method for predicting a bus driving state according to a second embodiment of the present disclosure;

[0049] Fig. 9 is a third schematic diagram of a method for predicting a bus driving state according to the second embodiment of the present disclosure;

[0050] Fig.10is a schematic diagram of the dissipation of queued vehicles after the green light is turned on according to the second embodiment of the present disclosure;

[0051] Fig.11 is a schematic diagram of a signal control method according to a third embodiment of the present disclosure;

[0052] Fig.12 is a first schematic diagram of a device for predicting a bus travel state according to a fourth embodiment of the present disclosure;

[0053] Fig.13 is a second schematic diagram of a device for predicting a bus travel state according to a fourth embodiment of the present disclosure;

[0054] Fig.14 is a schematic diagram of a device for predicting a bus travel state according to a fourth embodiment of the present disclosure;

[0055] Fig.15 is a schematic diagram of a signal control device according to a third embodiment of the present disclosure;

[0056] Fig.16 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present disclosure. DETAILED DESCRIPTION

[0057] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0058] Example 1

[0059] like Figure 1 As shown, the method for predicting the bus driving state of this embodiment includes:

[0060] S101. Based on the real-time position information of the public bus, obtain the target real-time distance between the public bus and the signalized intersection; wherein the real-time position information is the real-time GPS positioning information of the public bus.

[0061] S102, calculating the average speed of the public transport vehicle according to the target real-time distance;

[0062] S103, collecting the first real-time running speed of the public transport vehicle at the current moment;

[0063] S104, correcting the first real-time driving speed based on the average driving speed to obtain a target real-time driving speed of the public transport vehicle at the current moment;

[0064] S105, obtaining the initial travel time of the bus from the current time to the signalized intersection according to the target real-time distance and the target real-time travel speed;

[0065] S106: Correct the initial travel time using a preset time correction method to obtain a target travel prediction time.

[0066] In this embodiment, the real-time speed and travel time of the bus are corrected in time to ensure the accuracy, stability and reliability of the predicted travel time of the bus to the signalized intersection. Under the condition of bus priority, it is reasonably and effectively avoided that the traffic light scheme is frequently modified due to distorted prediction results, which in turn affects the normal passage of vehicles at the signalized intersection.

[0067] like Figure 2 As shown, the method for predicting the bus driving state in this embodiment is to Figure 1 Further improvements to the scheme in , specifically:

[0068] In an implementable solution, before step S101, the following steps are further included:

[0069] S100, pre-setting a number of GPS static coordinate points in different sections of the road network;

[0070] Among them, a number of set GPS static coordinate points are used to identify the shape of the corresponding road section;

[0071] Specifically, it is necessary that the distance between two adjacent set GPS static coordinate points in each road section is close to a straight line, so that the corresponding irregular road section can be accurately identified as to where the curves are and where the straight lines are. This can reflect the actual driving path of the bus and ensure that the distance between the bus and the signal intersection can be accurately determined later.

[0072] Step S101 includes:

[0073] S10111. Obtain real-time location information of public transportation vehicles;

[0074] S10112, obtaining a first GPS static coordinate point corresponding to the signalized intersection and corresponding first GPS coordinate information;

[0075] S10113, obtaining a plurality of second GPS static coordinate points between the public transport vehicle and the signalized intersection and corresponding second GPS coordinate information;

[0076] Based on the real-time position information, the first GPS coordinate information and a plurality of second GPS coordinate information, a target real-time distance between the public transport vehicle and the signalized intersection is calculated.

[0077] like Figure 3As shown, corresponding to a certain road section, point A is a bus, point B is the first GPS static coordinate point corresponding to the signal intersection, and point C between point A and point B is a second GPS static coordinate point; the second GPS static coordinate point Ck closest to point A of the bus is determined, and the first distance between the second GPS static coordinate point Ck and point A of the bus is calculated; the other second GPS static coordinate points are preset and equidistant, and the second distance between two adjacent second GPS static coordinate points is accumulated and calculated on the basis of the first distance to accumulate the cumulative distance between point A and point B, that is, the target real-time distance between the bus and the signal intersection. The specific calculation formula is as follows:

[0078]

[0079] Where D is the target real-time distance between the bus and the signal intersection, D (bus,k) is the first distance between the second GPS static coordinate point Ck and the bus point A, D (i,i+1) is the second distance between the i-th second GPS static coordinate point and the i+1-th second GPS static coordinate point; wherein the number of second GPS static coordinate points between point A and point B is N, and i is a positive integer and ≤N-1.

[0080] In this scheme, compared with the existing scheme of directly determining the distance between the bus and the signal intersection based on the straight-line distance between the bus GPS coordinates and the intersection GPS coordinates, the real-time distance between the bus and the signal intersection is calculated more reasonably and accurately, avoiding the poor reliability of the final travel time prediction due to calculation errors, and ensuring the rationality of bus priority control.

[0081] In one feasible solution, Figure 4 As shown, step S101 includes:

[0082] S10121. Based on the real-time position information of the public transport vehicle at the last moment, obtain a first real-time distance between the public transport vehicle and the signalized intersection at the last moment;

[0083] S10122. Based on the real-time position information of the public transport vehicle at the current moment, obtain a second real-time distance between the public transport vehicle and the signalized intersection at the current moment;

[0084] Step S102 includes:

[0085] S1021, obtaining a time difference between the current moment and the previous moment, and a distance difference between the first real-time distance and the second real-time distance;

[0086] S1022. Calculate a first ratio of the distance difference to the time difference to obtain an average travel speed of the public transport vehicle.

[0087] In this scheme, the average speed of the bus is determined based on the distance difference between the bus and the signal intersection at two consecutive moments and the time difference between the two moments. The specific calculation formula is as follows:

[0088]

[0089] in, is the average speed of public transport vehicles, D t-1 is the real-time distance between the bus and the signalized intersection at time t-1, D t is the real-time distance between the bus and the signal intersection at the current time t, Δt geo It is the time difference between time t-1 and time t, which can be 5s. Of course, it can be re-determined or adjusted according to actual needs.

[0090] In one feasible solution, step S104 includes:

[0091] S1041, determining that the average driving speed corresponds to a first speed weight, and that the first real-time driving speed corresponds to a second speed weight;

[0092] S1042, obtaining a first product of a first speed weight and an average driving speed, and a second product of a second speed weight and a first real-time driving speed;

[0093] S1043. Calculate the sum of the first product and the second product to obtain the corrected target real-time speed of the public transport vehicle at the current moment.

[0094] Specifically, the calculation formula corresponding to step S104 is as follows:

[0095]

[0096] in, is the target real-time speed of the bus at the current time t, is the average speed of public transport vehicles, is the real-time speed of the public transport vehicles collected; α geo is the first speed weight, (1-α geo ) is the second speed weight, α geo The possible value is 0.5, and of course it can be re-determined or adjusted according to actual needs.

[0097] In this solution, the actual speed of the bus is no longer taken directly based on the collected speed data. Instead, the average speed of the bus is determined based on the GPS coordinate information, and the actual speed collected is corrected by the average speed to jointly determine the target real-time speed of the bus, which more accurately reflects the actual speed of the bus and ensures the accuracy of the subsequent travel time determination.

[0098] Among them, in the above-mentioned process of correcting the real-time driving speed of the bus, in addition to adopting the original driving speed obtained based on GPS collection, the actual more accurate real-time driving speed is recalculated according to the movement of the bus GPS coordinate point, ensuring the stability of the speed prediction results and avoiding the occurrence of inaccurate speed prediction due to deviations in a certain type of data.

[0099] In one feasible solution, step S105 includes:

[0100] S1051. Calculate and obtain a second ratio of the second real-time distance to the target real-time driving speed as an initial travel time of the bus from the current moment to the signalized intersection.

[0101] Specifically, the calculation formula corresponding to the initial travel time is as follows:

[0102]

[0103] Among them, T t is the initial travel time, D t is the real-time distance of the bus from the current time t to the signal intersection, is the target real-time speed of the bus at the current time t.

[0104] In one feasible solution, Figure 5 As shown, before step S106, the following steps are also included:

[0105] S10601, presetting two adjacent moments to correspond to a first time weight and a second time weight respectively;

[0106] S10602, select M historical moments before the current moment, where M is a positive integer;

[0107] Among them, two adjacent historical moments are separated by a set time period;

[0108] S10603, when n=1, the first historical travel time of the bus from the nth historical moment to the signalized intersection is used as the first historical travel prediction time at the nth historical moment; wherein n is a positive integer and is ≤M;

[0109] When n≥2, the first historical trip prediction time at the nth historical moment is calculated based on the first historical trip prediction time at the n-1th historical moment, the first historical trip prediction time at the nth historical moment, the first time weight and the second time weight;

[0110] Until n=M, iterative calculation is performed to obtain the target historical travel prediction time corresponding to the historical moment closest to the current moment;

[0111] Step S106 includes:

[0112] S1061. Calculate the target travel prediction time of the bus from the current time to the signalized intersection based on the target historical travel prediction time, the initial travel time corresponding to the current time, the first time weight, and the second time weight.

[0113] In one feasible solution, step S1061 includes:

[0114] Obtaining a third product of the target historical travel prediction time and the first time weight, and a fourth product of the initial travel time and the second time weight;

[0115] The sum of the third product and the fourth product is calculated to be used as the target travel prediction time of the bus from the current moment to the signal intersection.

[0116] Specifically, M historical moments before the current moment t (for example, M=10) are selected, and two consecutive historical moments can be separated by a set time (for example, 5s). A travel prediction time correction formula is pre-constructed to predict the travel prediction time of a bus from a certain moment to a signal intersection. The specific calculation formula is as follows:

[0117]

[0118] Where, 2≤n≤M, n is an integer;

[0119] When n=1, the actual travel time corresponding to the historical moment when M=1 is obtained is calculated using the following formula:

[0120]

[0121] At this time, the value of t in the following formula is the historical moment when M=1. The specific calculation process is similar to the process of calculating the initial travel time of the bus from the current moment to the signal intersection in the above step S1051, so it will not be repeated here.

[0122] When n≥2, the historical travel prediction time T^_(n-1) at historical moment n-1 and the actual travel time at historical moment n are used to calculate the corrected historical travel prediction time corresponding to historical moment n, which is used as the calculation basis for the next historical moment n+1. The calculation is iterated until n=M, at which time the target historical travel prediction time for the actual prediction scenario is obtained;

[0123] For the current time t, that is, n = t, then

[0124]

[0125] in, is the target travel time predicted for the bus from the current time to the signal intersection, is the target historical travel prediction time, T t is the initial travel time of the bus from the current moment to the signal intersection, α0 is the first time weight, and (1-α0) is the second time weight.

[0126] In this scheme, considering the gradual attenuation of time series data from near to far, there is no need to store a lot of historical data. Based on the exponential smoothing method, the data collected every 5 seconds is taken as one period of data and a total of 10 periods are collected. The exponential smoothing value at the n-1th moment (that is, the historical travel prediction time) is used as the basis for determining the exponential smoothing value at the nth moment. The calculation is continuously iterated. The closer each historical travel prediction time is to the actual travel time of the current bus, the more reliable the calculation result of the travel prediction time correction formula can be.

[0127] In this embodiment, the exponential smoothing method is used to correct the travel prediction time, which can be compatible with temporary deceleration caused by emergencies, thereby causing a sudden change in the predicted time for the bus to arrive at the intersection. This ensures the stability of the travel prediction time to a great extent, thereby avoiding frequent modifications to the traffic light scheme, reducing the impact on the intersection, and effectively ensuring the effect of bus priority.

[0128] Example 2

[0129] like Figure 6 As shown, the method for predicting the bus driving state of this embodiment is a further improvement of the embodiment 1, specifically:

[0130] In an implementable solution, after step S106, the following steps are further included:

[0131] S201, determining whether the public transport vehicles are around the signalized intersection and in a queue state, if so, executing step S202;

[0132] S202, based on the real-time location information of the public bus, obtaining the actual queue length of the public bus and the signalized intersection;

[0133] Among them, a mapping relationship table between the actual driving speed of the bus and the corresponding queue length can be constructed according to several historical driving speeds of the bus and the corresponding historical queue lengths, such as Figure 7 As shown; in the actual scenario, the queue length corresponding to the actual driving speed of the bus can be directly found in the mapping relationship table; when the bus is around the signal intersection and in a queue state, the actual driving speed of the bus is close to zero, then based on the mapping relationship table, it can be accurately estimated that the queue length of the bus is about 41 meters.

[0134] In addition, the distance between the real-time position information of the bus and the set GPS static coordinate point corresponding to the signal intersection can be used as the actual queue length between the bus and the signal intersection; the specific method for determining the actual queue length between the bus and the signal intersection can be selected according to actual conditions.

[0135] S203: Obtain, based on the queue length, the queue dissipation time required for the public transport vehicle to pass through the stop line after the green light at the signalized intersection is turned on.

[0136] In this embodiment, when it is determined that the buses are queuing at the signalized intersection, the actual queue length corresponding to the buses is determined based on the real-time position information of the buses, and then the queue dissipation time required for the buses to pass the stop line once the green light is turned on in this state is automatically calculated. While ensuring the timeliness, accuracy and reliability of the acquisition of the queue dissipation time, it is convenient to generate the corresponding signal control plan in a timely manner in the subsequent process, so as to meet the bus priority scenario in a more timely and reasonable manner, and effectively optimize the control process of the bus priority scenario.

[0137] like Figure 8 As shown, the method for predicting the bus driving state in this embodiment is to Figure 6 Further improvements to the scheme, specifically:

[0138] In one feasible solution, step S201 includes:

[0139] S2011. If the target real-time driving speed is continuously less than the first set threshold within the first set time, it is determined that the bus is located around the signalized intersection and is in a queue state; and / or,

[0140] If the moving distance corresponding to the real-time location information within the second set time is less than the second set threshold, it is determined that the bus is located around the signalized intersection and is in a queue state.

[0141] When a bus is queuing at a signalized intersection, its speed will gradually decrease. When the real-time speed of the bus is continuously less than a certain value (for example, 2 m / s) for a period of time, the bus is considered to be in an idling state / queuing state; or, for example, with a sampling interval of 5 seconds, if the real-time position information of the bus for three consecutive times shows that the bus is in the same position or moves less than a certain value, the bus is considered to be in an idling state / queuing state.

[0142] In one feasible solution, step S203 includes:

[0143] S2031. Calculate the starting wave velocity of the bus at the signalized intersection using a preset kinematic starting wave model; wherein the starting wave velocity is used to characterize the velocity of the starting wave caused by the queue during the starting process;

[0144] Specifically, the calculation formula corresponding to the preset kinematic starting wave model is as follows:

[0145]

[0146] Among them, Δx is the distance between the head vehicle and the stop line when queuing, which can be 7.0m; v0 is the normal speed of the bus passing through the signal intersection, which can be 8.0m / s; h is the saturated headway, which can be 2.5s; u w The positive and negative signs indicate the propagation direction of the starting wave. A positive number indicates that the starting wave propagates forward along the driving direction, and a negative number indicates that the starting wave propagates in the opposite direction to the driving direction. Of course, the specific value of each parameter can be re-determined or adjusted according to the actual situation.

[0147] S2032. Obtain, based on the starting wave speed and the queue length, a queue dissipation time required for the bus to pass through the stop line after the green light at the signalized intersection is turned on.

[0148] In one feasible solution, Fig. 9 As shown, step S2032 includes:

[0149] S20321. Obtain the normal driving speed of a public bus passing through a signalized intersection, the first time required to accelerate from a queue state to a normal driving speed, and the starting reaction time of the head vehicle in the queue after the green light is turned on;

[0150] S20322. Based on the queue length, normal driving speed, first duration, starting wave speed and starting reaction time, calculate the queue dissipation time required for the bus to pass the stop line after the green light at the signalized intersection is turned on.

[0151] See also Fig.10 , which is a schematic diagram of the dissipation of queued vehicles after the green light is turned on.

[0152] The calculation formula for the queue dissipation time calculated in step S20322 is as follows:

[0153]

[0154] in, is the queue dissipation time, x bus is the actual queue length of buses, v0 is the normal speed of buses passing through signalized intersections, t a is the first time required to accelerate from the queue state to the normal driving speed, t h The starting reaction time of the first vehicle in the queue after the green light is turned on can be 5.0s. Of course, the specific value of each parameter can be re-determined or adjusted according to the actual situation.

[0155] In this embodiment, only GPS data is used to estimate the queue length when the bus arrives at the signalized intersection, and the dissipation of the queue is determined based on parameters such as the queue length and the starting wave speed, which facilitates the subsequent formulation of a suitable signal light priority plan, ensuring the accuracy and timeliness of signal light control in the bus priority scenario.

[0156] Example 3

[0157] like Fig.11 As shown, the signal control method of this embodiment is applied in a bus priority scenario, and the signal control method is implemented based on the prediction method of the bus driving state in the above-mentioned embodiment 1 or 2.

[0158] The signal control method of this embodiment includes:

[0159] S301, obtaining a target travel prediction time of a public transport vehicle from the current time to a signalized intersection based on a prediction method;

[0160] S302, generating a control strategy for a signal light at a signalized intersection according to the target travel prediction time;

[0161] S303. Control the working state of the traffic light at the signalized intersection based on the control strategy.

[0162] In this embodiment, based on the accurate and stable target travel prediction time obtained by the above-mentioned correction processing, a control strategy for the traffic lights at the corresponding signalized intersection is automatically generated to control the working state of the traffic lights at the corresponding signalized intersection. Relying on the stable travel prediction time, it is possible to avoid the distortion of the prediction results leading to frequent changes in the traffic light plan, which affects the normal passage of vehicles at the intersection, so as to achieve more timely and reasonable satisfaction of the bus priority scenario and effectively optimize the control process of the bus priority scenario.

[0163] Example 4

[0164] like Fig.12 As shown, the bus driving state prediction device of this embodiment includes:

[0165] The target real-time distance acquisition module 1 is used to acquire the target real-time distance between the bus and the signal intersection based on the real-time position information of the bus; wherein the real-time position information is the real-time GPS positioning information of the bus.

[0166] The average driving speed acquisition module 2 is used to calculate the average driving speed of the public transport vehicle according to the target real-time distance;

[0167] The first driving speed collection module 3 is used to collect the first real-time driving speed of the public transport vehicle at the current moment;

[0168] The driving speed correction acquisition module 4 is used to correct the first real-time driving speed based on the average driving speed to obtain the target real-time driving speed of the public transport vehicle at the current moment;

[0169] The initial travel time acquisition module 5 is used to acquire the initial travel time of the bus from the current moment to the signal intersection according to the target real-time distance and the target real-time travel speed;

[0170] The travel prediction time correction module 6 is used to correct the initial travel time using a preset time correction method to obtain a target travel prediction time.

[0171] In this embodiment, the real-time speed and travel time of the bus are corrected in time to ensure the accuracy, stability and reliability of the predicted travel time of the bus to the signalized intersection. Under the condition of bus priority, it is reasonably and effectively avoided that the traffic light scheme is frequently modified due to distorted prediction results, which in turn affects the normal passage of vehicles at the signalized intersection.

[0172] like Fig.13 As shown, the bus driving state prediction device of this embodiment is Fig.12 Further improvements to the scheme in , specifically:

[0173] In one feasible solution, the prediction device further includes:

[0174] The coordinate point presetting module 7 is used to pre-set a number of GPS static coordinate points in different sections of the road network;

[0175] Among them, a number of set GPS static coordinate points are used to identify the shape of the corresponding road section;

[0176] Specifically, it is necessary that the distance between two adjacent set GPS static coordinate points in each road section is close to a straight line, so that the corresponding irregular road section can be accurately identified as to where the curves are and where the straight lines are. This can reflect the actual driving path of the bus and ensure that the distance between the bus and the signal intersection can be accurately determined later.

[0177] The target real-time distance acquisition module 1 includes:

[0178] A real-time coordinate information acquisition unit 8 is used to acquire the real-time position information of the public transport vehicle;

[0179] A first coordinate information acquisition unit 9 is used to acquire a first GPS static coordinate point corresponding to the signalized intersection and corresponding first GPS coordinate information;

[0180] The second coordinate information acquisition unit 10 is used to acquire a plurality of second GPS static coordinate points between the public transport vehicle and the signalized intersection and the corresponding second GPS coordinate information;

[0181] The target real-time distance acquisition unit 11 is used to calculate the target real-time distance between the public transport vehicle and the signalized intersection based on the real-time position information, the first GPS coordinate information and a plurality of second GPS coordinate information.

[0182] like Figure 3 As shown, corresponding to a certain road section, point A is a bus, point B is the first GPS static coordinate point corresponding to the signal intersection, and point C between point A and point B is a second GPS static coordinate point; the second GPS static coordinate point Ck closest to point A of the bus is determined, and the first distance between the second GPS static coordinate point Ck and point A of the bus is calculated; the other second GPS static coordinate points are preset and equidistant, and the second distance between two adjacent second GPS static coordinate points is accumulated and calculated on the basis of the first distance to accumulate the cumulative distance between point A and point B, that is, the target real-time distance between the bus and the signal intersection. The specific calculation formula is as follows:

[0183]

[0184] Where D is the target real-time distance between the bus and the signal intersection, D (bus,k) is the first distance between the second GPS static coordinate point Ck and the bus point A, D (i,i+1) is the second distance between the i-th second GPS static coordinate point and the i+1-th second GPS static coordinate point; wherein the number of second GPS static coordinate points between point A and point B is N, and i is a positive integer and ≤N-1.

[0185] In this scheme, compared with the existing scheme of directly determining the distance between the bus and the signal intersection based on the straight-line distance between the bus GPS coordinates and the intersection GPS coordinates, the real-time distance between the bus and the signal intersection is calculated more reasonably and accurately, avoiding the poor reliability of the final travel time prediction due to calculation errors, and ensuring the rationality of bus priority control.

[0186] In an implementable solution, the target real-time distance acquisition module 1 further includes:

[0187] A first real-time distance acquisition unit 12, configured to acquire a first real-time distance between the bus and the signalized intersection at a previous moment based on the real-time position information of the bus at a previous moment;

[0188] A second real-time distance acquisition unit 13, used to acquire a second real-time distance between the bus and the signalized intersection at the current moment based on the real-time position information of the bus at the current moment;

[0189] The average driving speed acquisition module 2 includes:

[0190] The time difference acquisition unit 14 is used to acquire the time difference between the current moment and the previous moment;

[0191] A distance difference acquisition unit 15 is used to acquire a distance difference between the first real-time distance and the second real-time distance;

[0192] The average travel speed acquisition unit 16 is used to calculate a first ratio of the distance difference to the time difference to obtain the first ratio as the average travel speed of the public transport vehicle.

[0193] In this scheme, the average speed of the bus is determined based on the distance difference between the bus and the signal intersection at two consecutive moments and the time difference between the two moments. The specific calculation formula is as follows:

[0194]

[0195] in, is the average speed of public transport vehicles, D t-1 is the real-time distance between the bus and the signalized intersection at time t-1, D t is the real-time distance between the bus and the signal intersection at the current time t, Δt geo It is the time difference between time t-1 and time t, which can be 5s. Of course, it can be re-determined or adjusted according to actual needs.

[0196] In an implementable solution, the driving speed correction acquisition module 4 includes:

[0197] a speed weight determination unit 17, configured to determine a first speed weight corresponding to the average driving speed and a second speed weight corresponding to the first real-time driving speed;

[0198] A first calculation unit 18 is used to obtain a first product of a first speed weight and an average driving speed, and a second product of a second speed weight and a first real-time driving speed;

[0199] The speed correction unit 19 is used to calculate the sum of the first product and the second product to serve as the corrected target real-time travel speed of the public transport vehicle at the current moment.

[0200] Specifically, the calculation formula corresponding to step S104 is as follows:

[0201]

[0202] in, is the target real-time speed of the bus at the current time t, is the average speed of public transport vehicles, is the real-time speed of the public transport vehicles collected; α geo is the first speed weight, (1-α geo ) is the second speed weight, α geo The possible value is 0.5, and of course it can be re-determined or adjusted according to actual needs.

[0203] In this solution, the actual speed of the bus is no longer taken directly based on the collected speed data. Instead, the average speed of the bus is determined based on the GPS coordinate information, and the actual speed collected is corrected by the average speed to jointly determine the target real-time speed of the bus, which more accurately reflects the actual speed of the bus and ensures the accuracy of the subsequent travel time determination.

[0204] Among them, in the above-mentioned process of correcting the real-time driving speed of the bus, in addition to adopting the original driving speed obtained based on GPS collection, the actual more accurate real-time driving speed is recalculated according to the movement of the bus GPS coordinate point, ensuring the stability of the speed prediction results and avoiding the occurrence of inaccurate speed prediction due to deviations in a certain type of data.

[0205] In an implementable solution, the initial travel time acquisition module 5 is used to calculate a second ratio of the second real-time distance to the target real-time driving speed as the initial travel time of the public transport vehicle from the current moment to the signalized intersection.

[0206] Specifically, the calculation formula corresponding to the initial travel time is as follows:

[0207]

[0208] Among them, T t is the initial travel time, D t is the real-time distance of the bus from the current time t to the signal intersection, is the target real-time speed of the bus at the current time t.

[0209] In one feasible solution, the prediction device further includes:

[0210] A time weight preset module 20, used to preset a first time weight and a second time weight corresponding to two adjacent moments respectively;

[0211] The historical moment selection module 21 is used to select M historical moments before the current moment; wherein M is a positive integer;

[0212] Among them, two adjacent historical moments are separated by a set time period;

[0213] The target historical time acquisition module 22 is used for, when n=1, the first historical travel time of the bus from the nth historical moment to the signalized intersection as the first historical travel prediction time at the nth historical moment; wherein n is a positive integer and ≤M;

[0214] When n≥2, the first historical trip prediction time at the nth historical moment is calculated based on the first historical trip prediction time at the n-1th historical moment, the first historical trip prediction time at the nth historical moment, the first time weight and the second time weight;

[0215] Until n=M, iterative calculation is performed to obtain the target historical travel prediction time corresponding to the historical moment closest to the current moment;

[0216] The travel prediction time correction module 6 is used to calculate the target travel prediction time of the bus from the current time to the signal intersection based on the target historical travel prediction time, the initial travel time corresponding to the current time, the first time weight and the second time weight.

[0217] In an implementable solution, the travel prediction time correction module 6 includes:

[0218] A second calculation unit 23 is used to obtain a third product of the target historical travel prediction time and the first time weight, and a fourth product of the initial travel time and the second time weight;

[0219] The time correction unit 24 is used to calculate the sum of the third product and the fourth product to serve as the target travel prediction time of the public transport vehicle from the current moment to the signalized intersection.

[0220] Specifically, M historical moments before the current moment t (for example, M=10) are selected, and two consecutive historical moments can be separated by a set time (for example, 5s). A travel prediction time correction formula is pre-constructed to predict the travel prediction time of a bus from a certain moment to a signal intersection. The specific calculation formula is as follows:

[0221]

[0222] Where, 2≤n≤M, n is an integer;

[0223] When n=1, the actual travel time corresponding to the historical moment when M=1 is obtained is calculated using the following formula:

[0224]

[0225] At this time, the value of t in the following formula is the historical moment when M=1. The specific calculation process is similar to the process of calculating the initial travel time of the bus from the current moment to the signal intersection in the above step S1051, so it will not be repeated here.

[0226] When n≥2, the historical travel prediction time T^_(n-1) at historical moment n-1 and the actual travel time at historical moment n are used to calculate the corrected historical travel prediction time corresponding to historical moment n, which is used as the calculation basis for the next historical moment n+1. The calculation is iterated until n=M, at which time the target historical travel prediction time for the actual prediction scenario is obtained;

[0227] For the current time t, that is, n = t, then

[0228]

[0229] in, is the target travel time predicted for the bus from the current time to the signal intersection, is the target historical travel prediction time, T t is the initial travel time of the bus from the current moment to the signal intersection, α0 is the first time weight, and (1-α0) is the second time weight.

[0230] In this scheme, considering the gradual attenuation of time series data from near to far, there is no need to store a lot of historical data. Based on the exponential smoothing method, the data collected every 5 seconds is taken as one period of data and a total of 10 periods are collected. The exponential smoothing value at the n-1th moment (that is, the historical travel prediction time) is used as the basis for determining the exponential smoothing value at the nth moment. The calculation is continuously iterated. The closer each historical travel prediction time is to the actual travel time of the current bus, the more reliable the calculation result of the travel prediction time correction formula can be.

[0231] In this embodiment, the exponential smoothing method is used to correct the travel prediction time, which can be compatible with temporary deceleration caused by emergencies, thereby causing a sudden change in the predicted time for the bus to arrive at the intersection. This ensures the stability of the travel prediction time to a great extent, thereby avoiding frequent modifications to the traffic light scheme, reducing the impact on the intersection, and effectively ensuring the effect of bus priority.

[0232] Example 5

[0233] like Fig.14 As shown, the prediction device for the bus driving state of this embodiment is a further improvement of the embodiment 4, specifically:

[0234] In one feasible solution, the prediction device further includes:

[0235] The judging module 25 is used to judge whether the bus is around the signalized intersection and in a queue state. If so, the actual queue length obtaining module 26 is called to obtain the actual queue length of the bus and the signalized intersection based on the real-time position information of the bus;

[0236] Among them, a mapping relationship table between the actual driving speed of the bus and the corresponding queue length can be constructed according to several historical driving speeds of the bus and the corresponding historical queue lengths, such as Figure 7 As shown; in the actual scenario, the queue length corresponding to the actual driving speed of the bus can be directly found in the mapping relationship table; when the bus is around the signal intersection and in a queue state, the actual driving speed of the bus is close to zero, then based on the mapping relationship table, it can be accurately estimated that the queue length of the bus is about 41 meters.

[0237] In addition, the distance between the real-time position information of the bus and the set GPS static coordinate point corresponding to the signal intersection can be used as the actual queue length between the bus and the signal intersection; the specific method for determining the actual queue length between the bus and the signal intersection can be selected according to actual conditions.

[0238] The queue dissipation time acquisition module 27 is used to acquire the queue dissipation time required for the public transport vehicle to pass the stop line after the green light of the signalized intersection is turned on based on the queue length.

[0239] In this embodiment, when it is determined that the buses are queuing at the signalized intersection, the actual queue length corresponding to the buses is determined based on the real-time position information of the buses, and then the queue dissipation time required for the buses to pass the stop line once the green light is turned on in this state is automatically calculated. While ensuring the timeliness, accuracy and reliability of the acquisition of the queue dissipation time, it is convenient to generate the corresponding signal control plan in a timely manner in the subsequent process, so as to meet the bus priority scenario in a more timely and reasonable manner, and effectively optimize the control process of the bus priority scenario.

[0240] In an implementable solution, the judgment module 25 is used to determine that the bus is located around the signalized intersection and is in a queue state if the target real-time driving speed is continuously less than the first set threshold within the first set time; and / or,

[0241] If the moving distance corresponding to the real-time location information within the second set time is less than the second set threshold, it is determined that the bus is located around the signalized intersection and is in a queue state.

[0242] When a bus is queuing at a signalized intersection, its speed will gradually decrease. When the real-time speed of the bus is continuously less than a certain value (for example, 2 m / s) for a period of time, the bus is considered to be in an idling state / queuing state; or, for example, with a sampling interval of 5 seconds, if the real-time position information of the bus for three consecutive times shows that the bus is in the same position or moves less than a certain value, the bus is considered to be in an idling state / queuing state.

[0243] In an implementable solution, the queue dissipation time acquisition module 27 includes:

[0244] The starting wave speed acquisition unit 28 is used to calculate the starting wave speed of the bus at the signal intersection using a preset kinematic starting wave model; wherein the starting wave speed is used to characterize the speed of the starting wave caused by the queue during the starting process;

[0245] Specifically, the calculation formula corresponding to the preset kinematic starting wave model is as follows:

[0246]

[0247] Among them, Δx is the distance between the head vehicle and the stop line when queuing, which can be 7.0m; v0 is the normal speed of the bus passing through the signal intersection, which can be 8.0m / s; h is the saturated headway, which can be 2.5s; u w The positive and negative signs of indicate the propagation direction of the starting wave. A positive number indicates that the starting wave propagates forward along the driving direction, and a negative number indicates that the starting wave propagates in the opposite direction to the driving direction. Of course, the specific value of each parameter can be re-determined or adjusted according to the actual situation.

[0248] The queue dissipation time acquisition unit 29 is used to acquire the queue dissipation time required for the bus to pass the stop line after the green light at the signalized intersection is turned on according to the starting wave speed and the queue length.

[0249] In an implementable solution, the queue-clearing time acquisition unit 28 is used to obtain the normal driving speed of the bus when passing through the signalized intersection, the first time required to accelerate from the queue state to the normal driving speed, and the starting reaction time of the head vehicle in the queue after the green light is turned on; based on the queue length, the normal driving speed, the first time, the starting wave speed and the starting reaction time, the queue-clearing time required for the bus to pass the stop line after the green light at the signalized intersection is turned on is calculated.

[0250] See also Fig.10 , which is a schematic diagram of the dissipation of queued vehicles after the green light is turned on.

[0251] The calculation formula for the queue dissipation time calculated in the queue dissipation time acquisition unit is as follows:

[0252]

[0253] in, is the queue dissipation time, x bus is the actual queue length of buses, v0 is the normal speed of buses passing through signalized intersections, t a is the first time required to accelerate from the queue state to the normal driving speed, t h The starting reaction time of the first vehicle in the queue after the green light is turned on can be 5.0s. Of course, the specific value of each parameter can be re-determined or adjusted according to the actual situation.

[0254] In this embodiment, only GPS data is used to estimate the queue length when the bus arrives at the signalized intersection, and the dissipation of the queue is determined based on parameters such as the queue length and the starting wave speed, which facilitates the subsequent formulation of a suitable signal light priority plan, ensuring the accuracy and timeliness of signal light control in the bus priority scenario.

[0255] Example 6

[0256] like Fig.15 As shown, the signal control device of this embodiment is applied in a bus priority scenario, and the signal control method is implemented based on the prediction device of the bus driving state in the above-mentioned embodiment 4 or 5.

[0257] The signal control device of this embodiment includes:

[0258] The target travel prediction time acquisition module 30 is used to obtain the target travel prediction time of the bus from the current time to the signal intersection obtained based on the prediction device;

[0259] A control strategy generating module 31, for generating a control strategy for a signal light at a signalized intersection according to a target travel prediction time;

[0260] The signal control module 32 is used to control the working state of the signal lights at the signal intersection based on the control strategy.

[0261] In this embodiment, based on the accurate and stable target travel prediction time obtained by the above-mentioned correction processing, a control strategy for the traffic lights at the corresponding signalized intersection is automatically generated to control the working state of the traffic lights at the corresponding signalized intersection. Relying on the stable travel prediction time, it is possible to avoid the distortion of the prediction results leading to frequent changes in the traffic light plan, which affects the normal passage of vehicles at the intersection, so as to achieve more timely and reasonable satisfaction of the bus priority scenario and effectively optimize the control process of the bus priority scenario.

[0262] Example 7

[0263] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0264] Fig.16 A schematic block diagram of an example electronic device 800 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0265] like Fig.16 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0266] A number of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0267] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as the above method. For example, in some embodiments, the above method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the above method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the above method in any other appropriate manner (e.g., by means of firmware).

[0268] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0269] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0270] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0271] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0272] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0273] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0274] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0275] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for predicting a bus driving state, the method comprising: Based on the real-time position information of the public transport, obtaining the target real-time distance between the public transport and the signalized intersection; Calculate the average speed of the public transport vehicle according to the target real-time distance; Collecting the first real-time running speed of the public transport vehicle at the current moment; Correcting the first real-time travel speed based on the average travel speed to obtain a target real-time travel speed of the public transport vehicle at the current moment; According to the target real-time distance and the target real-time travel speed, obtaining the initial travel time of the public transport vehicle from the current moment to the signalized intersection; Correcting the initial travel time by using a preset time correction method to obtain a target travel prediction time; The prediction method further comprises: Determine whether the bus is around the signalized intersection and in a queue state, and if so, obtain the actual queue length between the bus and the signalized intersection based on the real-time position information of the bus; The starting wave velocity of the bus at the signal intersection is calculated by using a preset kinematic starting wave model; wherein the starting wave velocity is used to characterize the velocity of the starting wave caused by the queue during the starting process; Obtain the normal driving speed of the public transport vehicle passing through the signalized intersection, the first time required to accelerate from the queue state to the normal driving speed, and the starting reaction time of the head vehicle in the queue after the green light is turned on; Based on the queue length, the normal driving speed, the first duration, the starting wave speed and the starting reaction time, the queue dissipation time required for the public transport vehicle to pass the stop line after the green light of the signalized intersection is turned on is calculated; The calculation formula for calculating the queue dissipation time is as follows: in, is the queue dissipation time, x bus is the actual queue length of the bus, v0 is the normal speed of the bus passing through the signalized intersection, t a is the first time required to accelerate from the queue state to the normal driving speed, t h is the starting reaction time of the first car in the queue after the green light is turned on, u w is the starting wave speed.

2. The method for predicting the driving state of a public transportation vehicle according to claim 1, before the step of obtaining the target real-time distance between the public transportation vehicle and the signalized intersection at the current moment based on the real-time location information of the public transportation vehicle, further comprising: Pre-set several GPS static coordinate points in different sections of the road network; Wherein, the plurality of set GPS static coordinate points are used to identify the shape of the corresponding road section; The step of obtaining the target real-time distance between the public transport vehicle and the signalized intersection at the current moment based on the real-time position information of the public transport vehicle comprises: Acquiring the real-time location information of the public transport vehicle; Obtaining a first GPS static coordinate point corresponding to the signalized intersection and corresponding first GPS coordinate information; Acquire a plurality of second GPS static coordinate points between the public transport vehicle and the signalized intersection and corresponding second GPS coordinate information; The target real-time distance between the public transport vehicle and the signalized intersection is calculated based on the real-time location information, the first GPS coordinate information and a plurality of the second GPS coordinate information.

3. The method for predicting the driving state of a public transport according to claim 2, wherein the step of obtaining the target real-time distance between the public transport and the signalized intersection based on the real-time position information of the public transport comprises: Based on the real-time position information of the public transport vehicle at the last moment, obtaining a first real-time distance between the public transport vehicle and the signalized intersection at the last moment; Based on the real-time position information of the public transport vehicle at the current moment, obtaining a second real-time distance between the public transport vehicle and the signalized intersection at the current moment; The step of calculating the average speed of the public transport vehicle according to the target real-time distance comprises: Acquire a time difference between the current moment and the previous moment, and a distance difference between the first real-time distance and the second real-time distance; A first ratio of the distance difference to the time difference is calculated and obtained as the average travel speed of the public transport vehicle.

4. The method for predicting the driving state of a public transport according to claim 3, wherein the step of correcting the first real-time driving speed based on the average driving speed to obtain the target real-time driving speed of the public transport at the current moment comprises: Determining that the average driving speed corresponds to a first speed weight, and the first real-time driving speed corresponds to a second speed weight; Obtaining a first product of the first speed weight and the average driving speed, and a second product of the second speed weight and the first real-time driving speed; The sum of the first product and the second product is calculated to be used as the corrected target real-time travel speed of the public transport vehicle at the current moment.

5. The method for predicting the driving state of a public transport according to claim 3, wherein the step of obtaining the initial travel time of the public transport from the current moment to the signalized intersection according to the target real-time distance and the target real-time driving speed comprises: A second ratio of the second real-time distance to the target real-time travel speed is calculated to serve as the initial travel time of the public transport vehicle from the current moment to the signalized intersection.

6. The method for predicting the travel status of a public transport according to claim 5, further comprising: The two adjacent moments before and after are preset to correspond to the first time weight and the second time weight respectively; Select M historical moments before the current moment; where M is a positive integer; When n=1, the first historical travel time of the public transport vehicle from the nth historical moment to the signalized intersection is used as the first historical travel prediction time at the nth historical moment; wherein n is a positive integer and is ≤M; When n≥2, the first historical travel prediction time at the nth historical moment is calculated based on the first historical travel prediction time at the n-1th historical moment, the first historical travel time at the nth historical moment, the first time weight, and the second time weight; Until n=M, iterative calculation is performed to obtain the target historical travel prediction time corresponding to a historical moment closest to the current moment; The step of correcting the initial travel time by a preset time correction method to obtain a target travel prediction time includes: The target travel prediction time of the bus from the current moment to the signalized intersection is calculated based on the target historical travel prediction time, the initial travel time corresponding to the current moment, the first time weight, and the second time weight.

7. The method for predicting the driving state of a public transportation vehicle according to claim 6, wherein the step of calculating the target travel prediction time of the public transportation vehicle from the current moment to the signalized intersection based on the target historical travel prediction time, the initial travel time corresponding to the current moment, the first time weight and the second time weight comprises: Obtaining a third product of the target historical travel prediction time and the first time weight, and a fourth product of the initial travel time and the second time weight; The sum of the third product and the fourth product is calculated to be used as the target travel prediction time of the public transport vehicle from the current moment to the signalized intersection.

8. The method for predicting the driving status of a public transportation system as claimed in claim 6, wherein two adjacent historical moments are separated by a set time period.

9. The method for predicting the driving status of a public transport according to claim 1, wherein the step of determining whether the public transport vehicle is around the signalized intersection and in a queue state comprises: If the target real-time driving speed is continuously less than the first set threshold within the first set time, it is determined that the public transport vehicle is located around the signalized intersection and is in a queue state; and / or, If the moving distance corresponding to the real-time position information within the second set time is less than a second set threshold, it is determined that the bus is located around the signalized intersection and is in a queue state.

10. A signal control method, which is applied in a bus priority scenario and is implemented based on the bus driving state prediction method according to any one of claims 1 to 9; The signal control method comprises: Obtaining a target travel prediction time of the public transport vehicle from the current moment to the signalized intersection based on the prediction method; generating a control strategy for the signal light at the signalized intersection according to the target travel prediction time; The working state of the signal light at the signalized intersection is controlled based on the control strategy.

11. A device for predicting a bus driving state, the device comprising: A target real-time distance acquisition module is used to acquire the target real-time distance between the bus and the signalized intersection based on the real-time position information of the bus; An average driving speed acquisition module is used to calculate the average driving speed of the public transport vehicle according to the target real-time distance; A first driving speed collection module, used to collect the first real-time driving speed of the public transport vehicle at the current moment; A driving speed correction acquisition module, used for correcting the first real-time driving speed based on the average driving speed to obtain the target real-time driving speed of the public transport vehicle at the current moment; An initial travel time acquisition module, used to acquire the initial travel time of the public transport vehicle from the current moment to the signalized intersection according to the target real-time distance and the target real-time travel speed; A travel prediction time correction module, used to correct the initial travel time using a preset time correction method to obtain a target travel prediction time; The prediction device also includes a judgment module and a queue dissipation time acquisition module; The judging module is used to judge whether the public transport vehicle is around the signalized intersection and in a queue state. If so, the actual queue length obtaining module is called to obtain the actual queue length between the public transport vehicle and the signalized intersection based on the real-time position information of the public transport vehicle. The queue dissipation time acquisition module includes: A starting wave speed acquisition unit is used to calculate the starting wave speed of the bus at the signal intersection using a preset kinematic starting wave model; wherein the starting wave speed is used to characterize the speed of the starting wave caused by the queue during the starting process; The queue dissipation time acquisition unit is used to acquire the normal driving speed of the public transport vehicle passing through the signalized intersection, the first time required to accelerate from the queue state to the normal driving speed, and the start reaction time of the head vehicle in the queue after the green light is turned on; based on the queue length, the normal driving speed, the first time, the start wave speed and the start reaction time, the queue dissipation time required for the public transport vehicle to pass the stop line after the green light of the signalized intersection is turned on is calculated; The calculation formula for calculating the queue dissipation time is as follows: in, is the queue dissipation time, x bus is the actual queue length of the bus, v0 is the normal speed of the bus passing through the signalized intersection, t a is the first time required to accelerate from the queue state to the normal driving speed, t h is the starting reaction time of the first car in the queue after the green light is turned on, u w is the starting wave speed.

12. The device for predicting the travel status of a public transportation system according to claim 11, further comprising: The coordinate point preset module is used to pre-set a number of GPS static coordinate points in different sections of the road network; Wherein, the plurality of set GPS static coordinate points are used to identify the shape of the corresponding road section; The target real-time distance acquisition module includes: A real-time coordinate information acquisition unit, used to acquire the real-time position information of the public transport vehicle; A first coordinate information acquisition unit, used to acquire a first GPS static coordinate point corresponding to the signalized intersection and corresponding first GPS coordinate information; A second coordinate information acquisition unit, used to acquire a plurality of second GPS static coordinate points between the public transport vehicle and the signalized intersection and corresponding second GPS coordinate information; The target real-time distance acquisition unit is used to calculate the target real-time distance between the public transport vehicle and the signalized intersection based on the real-time position information, the first GPS coordinate information and a plurality of the second GPS coordinate information.

13. The device for predicting the travel status of a public transportation system according to claim 12, wherein the target real-time distance acquisition module further comprises: A first real-time distance acquisition unit, configured to acquire a first real-time distance between the public transport vehicle and the signalized intersection at the last moment based on the real-time position information of the public transport vehicle at the last moment; A second real-time distance acquisition unit, configured to acquire a second real-time distance between the public transport vehicle and the signalized intersection at the current moment based on the real-time position information of the public transport vehicle at the current moment; The average driving speed acquisition module comprises: A time difference acquisition unit, used to acquire the time difference between the current moment and the previous moment; a distance difference obtaining unit, configured to obtain a distance difference between the first real-time distance and the second real-time distance; The average travel speed acquisition unit is used to calculate a first ratio of the distance difference to the time difference to obtain the first ratio as the average travel speed of the public transport vehicle.

14. The device for predicting the driving state of a public transportation system according to claim 13, wherein the driving speed correction acquisition module comprises: a speed weight determination unit, configured to determine a first speed weight corresponding to the average driving speed and a second speed weight corresponding to the first real-time driving speed; a first calculation unit, configured to obtain a first product of the first speed weight and the average driving speed, and a second product of the second speed weight and the first real-time driving speed; The speed correction unit is used to calculate the sum of the first product and the second product to serve as the corrected target real-time travel speed of the public transport vehicle at the current moment.

15. The device for predicting the driving state of a public transportation vehicle as claimed in claim 13, wherein the initial travel time acquisition module is used to calculate a second ratio of the second real-time distance to the target real-time driving speed as the initial travel time of the public transportation vehicle from the current moment to the signalized intersection.

16. The device for predicting the travel status of a public transportation system according to claim 15, further comprising: A time weight preset module, used to preset the first time weight and the second time weight corresponding to two adjacent moments respectively; A historical moment selection module, used to select M historical moments before the current moment; wherein M is a positive integer; A target historical time acquisition module is used for, when n=1, taking the first historical travel time of the public transport vehicle from the nth historical moment to the signalized intersection as the first historical travel prediction time at the nth historical moment; wherein n is a positive integer and is ≤M; When n≥2, the first historical travel prediction time at the nth historical moment is calculated based on the first historical travel prediction time at the n-1th historical moment, the first historical travel time at the nth historical moment, the first time weight, and the second time weight; Until n=M, iterative calculation is performed to obtain the target historical travel prediction time corresponding to a historical moment closest to the current moment; The travel prediction time correction module is used to calculate the target travel prediction time of the bus from the current moment to the signal intersection based on the target historical travel prediction time, the initial travel time corresponding to the current moment, the first time weight and the second time weight.

17. The device for predicting the travel status of a public transportation system according to claim 16, wherein the travel prediction time correction module comprises: a second calculation unit, configured to obtain a third product of the target historical travel prediction time and the first time weight, and a fourth product of the initial travel time and the second time weight; The time correction unit is used to calculate the sum of the third product and the fourth product to serve as the target travel prediction time of the public transport vehicle from the current moment to the signal intersection.

18. The device for predicting the travel status of a public transportation system as claimed in claim 16, wherein two adjacent historical moments are separated by a set time period.

19. The device for predicting the driving state of a public transport according to claim 11, wherein the judging module is configured to determine that the public transport vehicle is located around the signalized intersection and is in a queue state if the target real-time driving speed is continuously less than a first set threshold value within a first set time; and / or, If the moving distance corresponding to the real-time position information within the second set time is less than a second set threshold, it is determined that the bus is located around the signalized intersection and is in a queue state.

20. A signal control device, which is applied in a bus priority scenario, and is implemented based on the prediction device for bus driving status according to any one of claims 11 to 19; The signal control device comprises: A target travel prediction time acquisition module, used to acquire the target travel prediction time of the public transport vehicle from the current moment to the signalized intersection obtained based on the prediction device; A control strategy generating module, used for generating a control strategy for the signal light at the signalized intersection according to the target travel prediction time; A signal control module is used to control the working state of the signal light at the signal intersection based on the control strategy.

21. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 9, or the method of claim 10.

22. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 9, or the method according to claim 10.

23. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method according to any one of claims 1 to 9, or the method according to claim 10.

Images