Variable lane control method and device, computer equipment and storage medium

Abstract

The invention relates to a variable lane control method and device, computer equipment and a storage medium, and the variable lane control method comprises the steps: enumerating the steering of variable lanes in each entrance lane in a target road section, and obtaining a plurality of lane steering combinations; the entrance lane comprises at least one variable lane; based on a preset statistical interval, determining a lane accumulated queuing length corresponding to different steering lane types in each entrance lane in real time; determining the maximum average lane queuing length corresponding to each lane steering combination based on the accumulated lane queuing lengths corresponding to different steering lane categories; steering instructions for each of the variable lanes are controlled on the basis of a lane steering combination in which the maximum lane average queuing length is minimized. Through the method and the device, the problem that lane turning recommendation cannot be performed based on real-time traffic demands is solved, lane turning recommendation based on the real-time traffic demands is realized, the accuracy of variable lane control is improved, and meanwhile, the universality of a variable lane control scheme is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and in particular to a variable lane control method, device, computer equipment and storage medium. Background Art

[0002] With the increasing volume of urban traffic, the traffic demand at intersections is unevenly distributed in time and space. The traffic demand in a certain direction or a certain turn is significantly greater than that in other time periods. Therefore, variable lanes are usually set at intersections with uneven turning traffic flow to optimize the space of the intersection. However, in the existing variable lane control method, the driving direction of the variable lane is fixed at different time periods, and it is impossible to make lane turning recommendations based on real-time traffic demand.

[0003] There is currently no effective solution to the problem in related technologies that lane turning recommendations cannot be made based on real-time traffic needs. Summary of the invention

[0004] In this embodiment, a variable lane control method, apparatus, computer device and storage medium are provided to solve the problem in the related art that lane turning recommendations cannot be made based on real-time traffic demand.

[0005] In a first aspect, a variable lane control method is provided in this embodiment, and the method includes:

[0006] Enumerating the turns of the variable lanes in each import lane in the target road section to obtain a plurality of lane turn combinations; the import lane includes at least one variable lane;

[0007] Based on a preset statistical interval, the accumulated queue lengths of lanes corresponding to different turning lane categories in each of the import lanes are determined in real time;

[0008] Determine a maximum lane average queue length corresponding to each lane turning combination based on the lane cumulative queue lengths corresponding to different turning lane categories;

[0009] Based on the lane turning combination that minimizes the average queue length of the maximum lane, the turning indication of each of the variable lanes is controlled.

[0010] In some of the embodiments, the real-time determination of the lane cumulative queue lengths corresponding to different turning lane categories in each of the import lanes based on a preset statistical interval includes:

[0011] Based on the preset statistical interval, obtaining real-time traffic data of each of the import lanes;

[0012] Determine corresponding multiple periodic indicator data according to the real-time traffic data;

[0013] Based on each of the cycle indicator data, the cumulative queue lengths of the lanes corresponding to the different turning lane categories in each of the import lanes are determined.

[0014] In some embodiments, determining the maximum lane average queue length corresponding to each lane turning combination based on the lane cumulative queue lengths corresponding to different turning lane categories includes:

[0015] Determining an import lane combination corresponding to the lane turning combination according to the variable lanes set by each lane turning combination and the fixed lanes in each import lane in the target road section;

[0016] Determine the number of lanes corresponding to the different turning lane categories in each of the import lane combinations;

[0017] Based on the lane cumulative queue length corresponding to each turning lane category and the number of lanes, the corresponding maximum lane average queue length is determined.

[0018] In some embodiments, the determining the maximum lane average queue length corresponding to each lane turning combination based on the lane cumulative queue lengths corresponding to different turning lane categories further includes:

[0019] Obtaining first traffic flow weights of a plurality of exit lanes corresponding to each of the import lanes;

[0020] Determining an import lane combination corresponding to the lane turning combination according to the variable lanes set by each lane turning combination and the fixed lanes in each import lane in the target road section;

[0021] Determining the lane turning combination adapted to each of the exit lanes based on the first traffic flow weight and the second traffic flow weight corresponding to each of the import lane combinations;

[0022] Based on the accumulated lane queue lengths corresponding to the different turning lane categories, the maximum lane average queue length corresponding to each lane turning combination adapted to each exit lane is determined.

[0023] In some embodiments, after determining the maximum lane average queue length corresponding to each lane turning combination based on the lane cumulative queue lengths corresponding to different turning lane categories, the method further includes:

[0024] Determine the lane turning combination with the smallest average queue length of the maximum lane as a recommended lane turning combination, and add the recommended lane turning combination to a preset first lane turning combination sequence; the first lane turning combination sequence is used to record the recommended lane turning combinations corresponding to different time periods every day;

[0025] Acquire all the first lane turning combination sequences within a preset historical period, and determine the recommended lane turning combination corresponding to the current time period in each of the first lane turning combination sequences;

[0026] The turning indication of each of the variable lanes is controlled based on the recommended lane turning combination that appears most frequently among the recommended lane turning combinations corresponding to the current time period.

[0027] In some embodiments, the method further comprises:

[0028] Determine, based on each of the first lane turning combination sequences within the preset historical period, the recommended lane turning combination with the largest number of occurrences corresponding to different time periods each day;

[0029] A second lane turning combination sequence is generated based on the recommended lane turning combinations that appear most frequently at different time periods every day.

[0030] In some embodiments, the method further comprises:

[0031] Based on the number of left-turn lanes corresponding to each of the recommended lane turning combinations in the second lane turning combination sequence, performing relationship mapping on the second lane turning combination sequence to obtain a corresponding natural number sequence;

[0032] Dividing the natural number sequence based on a natural breakpoint algorithm;

[0033] Based on the division result, the recommended lane turning combinations in the second lane turning combination sequence are merged to obtain a corresponding third lane turning combination sequence.

[0034] In some embodiments, after acquiring the latest third lane turning combination sequence each time, the method further includes:

[0035] Comparing the latest third lane turning combination sequence with the currently implemented third lane turning combination sequence to obtain the cumulative duration of different lane turning recommendations in the latest third lane turning combination sequence and the currently implemented third lane turning combination sequence;

[0036] Based on the accumulated time, determining whether the latest third lane turning combination sequence and the currently implemented third lane turning combination sequence meet a preset similarity condition;

[0037] When the preset similarity condition is met, the turning indication of each of the variable lanes is controlled based on the third lane turning combination sequence currently being implemented.

[0038] In a second aspect, a variable lane control device is provided in this embodiment, the device comprising: an enumeration module, a calculation module and a control module;

[0039] The enumeration module is used to enumerate the turns of the variable lanes in each import lane in the target road section to obtain a plurality of lane turn combinations; the import lane includes at least one variable lane;

[0040] The calculation module is used to determine the lane cumulative queue lengths corresponding to different turning lane categories in each of the import lanes in real time based on a preset statistical interval;

[0041] The calculation module is further used to determine the maximum lane average queue length corresponding to each lane turning combination based on the lane cumulative queue lengths corresponding to different turning lane categories;

[0042] The control module is used to control the turning indication of each of the variable lanes based on the lane turning combination that minimizes the average queue length of the maximum lane.

[0043] In a third aspect, a computer device is provided in this embodiment, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the variable lane control method described in the first aspect when executing the computer program.

[0044] In a fourth aspect, in this embodiment, a storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the variable lane control method described in the first aspect is implemented.

[0045] Compared with the related art, the variable lane control method, device, computer equipment and storage medium provided in this embodiment obtain multiple lane turning combinations by enumerating the turns of the variable lanes in each import lane in the target section; the import lane includes at least one variable lane; based on a preset statistical interval, the lane cumulative queue lengths corresponding to different turning lane categories in each import lane are determined in real time; based on the lane cumulative queue lengths corresponding to different turning lane categories, the maximum lane average queue length corresponding to each lane turning combination is determined; based on the lane turning combination that minimizes the maximum lane average queue length, the turning indications of each variable lane are controlled, which solves the problem that lane turning recommendations cannot be made based on real-time traffic demand, realizes lane turning recommendations based on real-time traffic demand, improves the accuracy of variable lane control, and improves the universality of the variable lane control scheme.

[0046] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0048] Figure 1 This is a hardware structure block diagram of a terminal device of a variable lane control method provided by an embodiment of the present application;

[0049] Figure 2 is a flow chart of a variable lane control method provided by an embodiment of the present application;

[0050] Figure 3 is a schematic diagram of a lane steering combination enumeration provided by an embodiment of the present application;

[0051] Figure 4 is a flow chart of a method for calculating the cumulative queue length of a lane provided in an embodiment of the present application;

[0052] Figure 5 is a flow chart of a method for calculating the average queue length of a maximum lane provided in an embodiment of the present application;

[0053] Figure 6 is a schematic diagram of generating a second lane turning combination sequence provided by an embodiment of the present application;

[0054] Figure 7 is a flow chart of a variable lane control method provided by an embodiment of the present application;

[0055] Figure 8is a flow chart of a variable lane control method provided by a preferred embodiment of the present application;

[0056] Fig. 9 It is a structural block diagram of a variable lane control device provided in one embodiment of the present application.

[0057] In the figure: 102, processor; 104, memory; 106, transmission device; 108, input and output device; 10, enumeration module; 20, calculation module; 30, control module. DETAILED DESCRIPTION

[0058] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0059] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the", "these" and the like in this application do not represent quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether directly or indirectly. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. Usually, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0060] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 is a hardware structure block diagram of a terminal of the variable lane control method of this embodiment. Figure 1 As shown, the terminal may include one or more ( Figure 1Only one is shown in the figure) processor 102 and memory 104 for storing data, wherein processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0061] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the variable lane control method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0062] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by the communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0063] In this embodiment, a variable lane control method is provided. Figure 2 is a flow chart of the variable lane control method of this embodiment. Figure 2 As shown, the process includes the following steps:

[0064] Step S210, enumerating the turns of the variable lanes in each import lane in the target road section to obtain a plurality of lane turn combinations; the import lane includes at least one variable lane;

[0065] Step S220, based on a preset statistical interval, determining in real time the accumulated queue lengths of lanes corresponding to different turning lane categories in each import lane;

[0066] Step S230, determining the maximum lane average queue length corresponding to each lane turning combination based on the accumulated lane queue lengths corresponding to different turning lane categories;

[0067] Step S240, controlling the turn indications of each variable lane based on the lane turning combination that minimizes the average queue length of the largest lane.

[0068] Specifically, the target road section includes multiple import lanes, each import lane includes a fixed lane and at least one variable lane, an enumeration method is determined according to the lane type of the fixed lanes in the target road section, and the corresponding enumeration method is used to enumerate the turns of the variable lanes in each import lane in the target road section to obtain multiple lane turning combinations, each lane turning combination includes the turning instructions of each variable lane. Take the case where the target road section contains n import lanes and each import lane contains m variable lanes as an example. When there are fixed left-turn lanes and fixed through lanes in the import lanes, there are m+1 lane turning combinations for the variable lanes, namely m through lanes, 1 left-turn lane and m-1 through lanes, 2 left-turn lanes and m-2 through lanes, …, m-1 left-turn lanes and 1 through lane, and m left-turn lanes. When there are fixed left-turn lanes in the import lanes and no fixed through lanes, there are m lane turning combinations for the variable lanes, namely m through lanes, 1 left-turn lane and m-1 through lanes, 2 left-turn lanes and m-2 through lanes, …, m-1 left-turn lanes and 1 through lane, and m left-turn lanes. left-turn lanes and 1 through lane; when there is a fixed through lane on the import lane and no fixed left-turn lane, there are m lane turning combinations for the variable lanes, namely 1 left-turn lane and m-1 through lanes, 2 left-turn lanes and m-2 through lanes, …, m-1 left-turn lanes and 1 through lane, m left-turn lanes; when there is no fixed through lane and fixed straight left-turn lane on the import lane, and the import lane contains 2 or more variable lanes, there are m-1 lane turning combinations for the variable lanes, namely 1 left-turn lane and m-1 through lanes, 2 left-turn lanes and m-2 through lanes, …, m-1 left-turn lanes and 1 through lane.

[0069] For example, the import lane includes 6 lanes, lanes a1, a5, and a6 are fixed left-turn lanes, fixed through lanes, and fixed right-turn lanes, respectively, and lanes a2, a3, and a4 are all variable lanes. Then, the lane turning combination set of the variable lanes includes 4 combinations, such as Figure 3 As shown, a2, a3 and a4 are all straight lanes ( Figure 3 A), a2 is the left turn lane, and a3 and a4 are both through lanes ( Figure 3 B), a4 is the through lane and a2 and a3 are left-turn lanes ( Figure 3C in the middle), a2, a3 and a4 are all left-turn lanes ( Figure 3 (shown in D).

[0070] Among them, when screening road sections, the lane channelization data of each import lane in different road sections is obtained, all variable lanes in the road sections are marked, and the target road section is screened out based on preset rules. The preset rules require that the import lanes of the target road section include variable lanes, and there are no mixed lanes for straight and left turns in each import lane. The variable lanes only support the configuration of dedicated lanes, and the turning only supports the configuration of straight or left turn. The layout of the import lanes is from the inner lane to the outer lane, and must follow the spatial position relationship of the left turn lane, the variable lane, the straight lane, the straight right turn lane, and the right turn lane. That is, there is no special channelization such as external left turn lanes and internal right turn lanes.

[0071] Furthermore, according to a preset statistical interval, for example, 15 minutes as a statistical interval, the real-time traffic data of each import lane is obtained through the import lane detector, and the corresponding multiple periodic indicator data are determined based on the obtained real-time traffic data, such as lane-level traffic flow, vehicle queue length at the beginning of the green light, lane space occupancy rate at the end of the green light, etc., which are not limited here. Then, according to each periodic indicator data, the cumulative queue length of the lane corresponding to the different turning lane categories in each import lane is calculated, and the cumulative queue length of the lane corresponding to each turning lane category refers to the sum of the cumulative queue lengths of all lanes in the current category. Among them, the turning lane category includes the left turn category and the straight category, the left turn category includes the left turn lane, and the straight category includes the straight lane and the straight right turn lane.

[0072] Afterwards, the import lane combination corresponding to the lane turning combination is determined according to the variable lanes set by each lane turning combination and the fixed lanes in each import lane in the target section. For example, the lane turning combination sets the variable lane a as the left turn lane and the variable lane b as the straight lane. The fixed lanes in each import lane include the straight lane and the right turn lane located on the right side of the variable lane b. At this time, the import lane combination includes the left turn lane, the straight lane, the straight lane and the right turn lane in sequence. The number of lanes corresponding to different turning lane categories in each import lane combination is calculated, and the corresponding maximum lane average queue length is calculated according to the accumulated queue length and the number of lanes corresponding to each turning lane category. From the average queue lengths of each maximum lane, the lane turning combination that minimizes the average queue length of the maximum lane is selected, and the steering instructions of each variable lane are controlled based on the selected lane turning combination.

[0073] At present, variable lanes are usually set at intersections with uneven turning traffic flow to optimize the space of the intersection. However, in the existing variable lane control method, the driving direction of the variable lane is fixed at different time periods, and it is impossible to make lane turning recommendations based on real-time traffic needs.

[0074] Compared with the prior art, the present application enumerates the turns of the variable lanes in each import lane in the target section to obtain multiple lane turn combinations; the import lane includes at least one variable lane; based on the preset statistical interval, the lane cumulative queue lengths corresponding to different turn lane categories in each import lane are determined in real time; based on the lane cumulative queue lengths corresponding to different turn lane categories, the maximum lane average queue length corresponding to each lane turn combination is determined; based on the lane turn combination that minimizes the maximum lane average queue length, the turn indication of each variable lane is controlled. Based on this, by calculating the lane cumulative queue lengths corresponding to different turn lane categories in each import lane in real time, the maximum lane average queue length corresponding to each lane turn combination is obtained, so that the lane turn combination that minimizes the maximum lane average queue length can be screened out, and the variable lane turn indication is controlled based on the screened lane turn combination, which solves the problem of being unable to make lane turn recommendations based on real-time traffic demand, realizes lane turn recommendations based on real-time traffic demand, improves the accuracy of variable lane control, and does not need to set thresholds for different indicators, thereby improving the universality of the variable lane control scheme.

[0075] In some of the embodiments, Figure 4 As shown, step S220, based on a preset statistical interval, determines in real time the lane cumulative queue lengths corresponding to different turning lane categories in each import lane, including the following steps:

[0076] Step S221, obtaining real-time traffic data of each import lane based on a preset statistical interval;

[0077] Step S222, determining corresponding multiple periodic indicator data according to the real-time traffic data;

[0078] Step S223, based on the index data of each cycle, determine the cumulative queue lengths of lanes corresponding to different turning lane categories in each import lane.

[0079] Specifically, according to the preset statistical interval, the real-time traffic data of each import lane is obtained, and multiple periodic indicator data corresponding to the corresponding statistical period are determined based on the real-time traffic data. For example, with a statistical interval of 15 minutes, for the statistical period from time t to time t+15, based on the real-time traffic data reported by the import lane detector, the lane-level traffic flow, the length of the vehicle queue at the beginning of the green light, the lane space occupancy rate at the end of the green light and other periodic indicator data are calculated.

[0080] Furthermore, for each statistical period, the cumulative queue lengths of the lanes corresponding to the different types of turning lanes in each import lane are calculated based on the index data of each period. The specific calculation formula for the cumulative queue length of each lane is as follows:

[0081]

[0082] In formula (1), CQL l represents the cumulative queue length of lane l; n represents the duration of the statistical interval; C i Indicates the length of the statistical cycle; L i Indicates the length of the vehicle queue at the beginning of the green light; L q It indicates the average headway between vehicles in the queue, and its default value is usually 5m to 10m; i Indicates the lane space occupancy rate at the end of the green light in the previous cycle; Q i Indicates the number of vehicles arriving at the lane during the green light period; L d Indicates the maximum detection distance of the radar, and its default value is usually 210m~300m; L t Indicates the distance from the radar equipment pole to the vehicle stop line. If the radar equipment is installed on the traffic light pole, L t Take the actual measurement distance. If the radar equipment is installed on the electric alarm pole, then L t Take 0; L c Indicates the vehicle's body length, and its default value is usually 3.8m to 4.8m.

[0083] It should be noted that the above-mentioned turning lane categories include left-turn categories and straight-ahead categories, the left-turn category includes left-turn lanes, and the straight-ahead category includes straight-ahead lanes and straight-ahead right-turn lanes. The lane cumulative queue length of each lane in the left-turn category and the lane cumulative queue length of each lane in the straight-ahead category are calculated respectively. Among them, the lane cumulative queue length corresponding to each turning lane category refers to the sum of the lane cumulative queue lengths of all lanes in the current category.

[0084] Through this embodiment, based on a preset statistical interval, real-time traffic data of each import lane is obtained, and based on the real-time traffic data, a plurality of corresponding periodic indicator data are determined, and based on each periodic indicator data, the cumulative queue length of the lane corresponding to the different turning lane categories in each import lane is determined, so as to accurately count the real-time traffic demand of each turning lane in the import lane.

[0085] In some of the embodiments, Figure 5 As shown, the step S230 of determining the maximum lane average queue length corresponding to each lane turning combination based on the lane cumulative queue lengths corresponding to different turning lane categories includes the following steps:

[0086] Step S231, determining an import lane combination corresponding to the lane turning combination according to the variable lanes set by each lane turning combination and the fixed lanes in each import lane in the target road section;

[0087] Step S232, determining the number of lanes corresponding to different turning lane categories in each import lane combination;

[0088] Step S233, based on the accumulated queue lengths and the number of lanes corresponding to each turning lane category, determine the corresponding maximum lane average queue length.

[0089] Specifically, the turning lane category includes the left-turn category and the straight-through category, the left-turn category includes the left-turn lane, and the straight-through category includes the straight-through lane and the straight-through right-turn lane. According to the variable lanes set for each lane turning combination and the fixed lanes in each import lane in the target section, the import lane combination corresponding to the lane turning combination is determined, and the number of lanes corresponding to different turning lane categories in each import lane combination is counted to obtain the number of lanes corresponding to the left-turn category n left , and the number of lanes n corresponding to the straight category straight .

[0090] Furthermore, according to the accumulated queue lengths and number of lanes corresponding to each turning lane category, the maximum average queue length of lanes corresponding to each lane turning combination is calculated. The specific calculation formula is as follows:

[0091]

[0092] In formula (2), Queue a represents the maximum average lane queue length corresponding to each lane turning combination a; CQL left Indicates the cumulative queue length of each lane in the left-turn category; CQL straight Indicates the cumulative queue length of each lane in the through category; n left Indicates the number of lanes corresponding to the left turn category; n straight Indicates the number of lanes corresponding to the straight-ahead category.

[0093] Through this embodiment, according to the variable lanes set for each lane turning combination and the fixed lanes in each import lane in the target section, the import lane combination corresponding to the lane turning combination is determined, and the number of lanes corresponding to different turning lane categories in each import lane combination is determined. Then, based on the accumulated queue lengths and the number of lanes corresponding to each turning lane category, the corresponding maximum lane average queue length is determined, so that the maximum lane average queue length can be accurately obtained, which is helpful for the subsequent accurate screening of the best lane turning combination.

[0094] In some embodiments, determining the maximum lane average queue length corresponding to each lane turning combination based on the lane cumulative queue lengths corresponding to different turning lane categories in step S230 further includes the following steps:

[0095] Obtaining first traffic flow weights of multiple exit lanes corresponding to each import lane;

[0096] Determine an import lane combination corresponding to the lane turning combination according to the variable lanes set by each lane turning combination and the fixed lanes in each import lane in the target road section;

[0097] Determining a lane turning combination adapted to each exit lane based on the first traffic flow weight and the second traffic flow weight corresponding to each import lane combination;

[0098] Based on the accumulated queue lengths of lanes corresponding to different turning lane categories, the maximum average queue length of lanes corresponding to each lane turning combination adapted to each exit lane is determined.

[0099] Specifically, after enumerating and obtaining multiple lane turning combinations, traffic weights corresponding to different import lanes and traffic weights corresponding to exit lanes are predefined, and each import lane includes a straight lane, a left turn lane, a straight right turn lane, and a right turn lane. Next, multiple exit lanes corresponding to each import lane in the target section are determined, and the first traffic weight of each exit lane is calculated according to the number of exit lanes and the traffic weight corresponding to the exit lane. The import lane combination corresponding to the lane turning combination is determined according to the variable lanes set by each lane turning combination and the fixed lanes in each import lane in the target section. The second traffic weight corresponding to each import lane combination is calculated according to the number of different types of import lanes in each import lane combination and the traffic weight corresponding to each type of import lane. Then, based on the first traffic weight and the second traffic weight corresponding to each lane turning combination, the import lane combination adapted to each exit lane is screened out, and the lane turning combination corresponding to the screened import lane combination is used as the lane turning combination adapted to each exit lane.

[0100] For example, the traffic weights corresponding to the straight lane and the left turn lane are preset to be 1, the traffic weight corresponding to the right turn lane is 0.5, the traffic weight corresponding to the straight direction in the straight and right turn lanes is 1, the traffic weight corresponding to the right turn direction is 0.5, and the traffic weight corresponding to the exit lane is 1. If the number of exit lanes is N, the number of lanes in the current entry lane combination that enter the exit lane by turning left is N L , the number of lanes entering the exit lane through straight driving is N T , the number of lanes entering the exit lane by turning right is N R , then the weight of the first traffic flow is calculated to be N, and the weight of the second traffic flow is N L +N T +0.5*N R After that, the difference between the second traffic flow weight and the first traffic flow weight is calculated to determine whether the difference exceeds the preset threshold value, so as to determine whether the current import lane combination is reasonable, that is, whether the import lane combination obtained after applying the current lane turning combination is compatible with each exit lane. L +N T+0.5*N R When -N>0.5, it indicates that the import lane combination obtained after applying the current lane turning combination is not compatible with each exit lane, and the current lane turning combination is eliminated. Otherwise, it indicates that the import lane combination obtained after applying the current lane turning combination is compatible with each exit lane, and the current lane turning combination is used as an alternative combination of the recommended lane turning combination and added to the subsequent lane turning combination set to be screened.

[0101] Furthermore, for each lane turning combination adapted to each exit lane, the maximum lane average queue length corresponding to the lane turning combination is calculated according to the cumulative queue lengths of the lanes corresponding to different turning lane categories and the number of lanes. The calculation method of the maximum lane average queue length in this embodiment is the same as the calculation method of the maximum lane average queue length described above, and will not be repeated here.

[0102] Through this embodiment, the first traffic flow weights of multiple exit lanes corresponding to each import lane are obtained, and the import lane combination corresponding to the lane turning combination is determined according to the variable lanes set for each lane turning combination and the fixed lanes in each import lane in the target section. Based on the first traffic flow weight and the second traffic flow weight corresponding to each import lane combination, the lane turning combination adapted to each exit lane is determined, and based on the accumulated queue lengths of lanes corresponding to different turning lane categories, the maximum lane average queue length corresponding to each lane turning combination adapted to each exit lane is determined, so as to avoid congestion of the exit lanes caused by merging conflicts, which helps to improve the rationality of subsequent lane turning recommendations.

[0103] In some embodiments, after determining the maximum lane average queue length corresponding to each lane turning combination based on the lane cumulative queue lengths corresponding to different turning lane categories, the variable lane control method further includes the following steps:

[0104] Determine the lane turning combination that minimizes the average queue length of the maximum lane as the recommended lane turning combination, and add the recommended lane turning combination to a preset first lane turning combination sequence; the first lane turning combination sequence is used to record the recommended lane turning combinations corresponding to different time periods every day;

[0105] Obtain all first lane turning combination sequences within a preset historical period, and determine a recommended lane turning combination corresponding to a current period in each first lane turning combination sequence;

[0106] The turning indication of each variable lane is controlled based on the recommended lane turning combination that appears most frequently among the recommended lane turning combinations corresponding to the current time period.

[0107] Specifically, after screening out the lane turning combination that minimizes the average queue length of the maximum lane, the recommended lane turning combination is added to the first lane turning combination sequence of the day. The first lane turning combination sequence is used to record the recommended lane turning combinations corresponding to different time periods of each day, and the length of each time period is determined by a preset statistical interval.

[0108] Furthermore, all first lane turn combination sequences [a1, a2, …, a m ], that is, the first lane turn combination sequence of each day in the preset historical period, a1, a2, …, a m The recommended lane turning combinations corresponding to different time periods every day are calculated. Taking 15 minutes as the statistical interval, each first lane turning combination sequence contains the recommended lane turning combinations corresponding to 96 time slices throughout the day. The recommended lane turning combinations corresponding to the current time period in each first lane turning combination sequence are counted, and the recommended lane turning combinations that appear the most times in each recommended lane turning combination corresponding to the current time period are screened out, and the recommended lane turning combination that appears the most times is used as the optimal lane turning combination, and the turning instructions of each variable lane are controlled based on the optimal lane turning combination. Among them, the preset historical period is usually a historical time range of one month or more. For example, the first lane turning combination sequence generated every day from January 1 to January 31 is obtained.

[0109] Through this embodiment, the lane turning combination that minimizes the average queue length of the maximum lane is determined as the recommended lane turning combination, and the recommended lane turning combination is added to the preset first lane turning combination sequence. The first lane turning combination sequence is used to record the recommended lane turning combinations corresponding to different time periods every day, and obtain all first lane turning combination sequences in a preset historical period, and determine the recommended lane turning combination corresponding to the current time period in each first lane turning combination sequence. Based on the recommended lane turning combination that appears most frequently in each recommended lane turning combination corresponding to the current time period, the turning indication of each variable lane is controlled, so as to realize variable lane control, and at the same time avoid the influence of accidental factors such as unexpected traffic events on the variable lane control, and improve the stability of the control scheme.

[0110] In some embodiments, the variable lane control method further includes the following steps:

[0111] Based on each first lane turning combination sequence within a preset historical period, determine the recommended lane turning combination with the most occurrences corresponding to different time periods of each day;

[0112] A second lane turning combination sequence is generated based on the recommended lane turning combinations that appear most frequently at different time periods every day.

[0113] Specifically, all first lane turning combination sequences within a preset historical period are obtained, and the recommended lane turning combinations corresponding to each time period in each first lane turning combination sequence are counted. For each time period, the recommended lane turning combination that appears most frequently in each first lane turning combination sequence is obtained, and based on the recommended lane turning combination that appears most frequently corresponding to different time periods every day, a second lane turning combination sequence is generated. The second lane turning combination sequence is used as a daily plan to control the turning indications of each variable lane at different time periods every day.

[0114] It should be noted that in this embodiment, each week can be divided to generate multiple daily plans per week, for example, each week can be divided into working days (Monday to Friday) and non-working days (Saturday and Sunday), so as to generate working day plans and non-working day plans, which are not limited here. When generating each daily plan, the corresponding historical data should be obtained, for example, for the non-working day plan, the first lane turning combination sequence of each Saturday and Sunday in the preset historical period is obtained.

[0115] For example, Figure 6 As shown, the first lane turn combination sequence generated every day from January 1 to January 31 is obtained. Figure 6 Different lane turning combinations in the sequence are distinguished by different colors, that is, yellow and green marks represent different lane turning combinations. The recommended lane turning combinations corresponding to 7:30 a.m. each day are further obtained in each first lane turning combination sequence, so as to count the most frequently appearing recommended lane turning combinations for 7:30 a.m. (e.g. Figure 6 The lane turning combination represented by the yellow mark in the middle) is taken as the best lane turning combination at 7:30 a.m. Similarly, for each other time period, the recommended lane turning combination with the most occurrences is counted to generate the second lane turning combination sequence [A1, A2, …, A m ],A1,A2,…,A m It is the optimal lane turning combination corresponding to different time periods of the day.

[0116] Through this embodiment, based on each first lane turning combination sequence within a preset historical period, the recommended lane turning combination with the largest number of occurrences corresponding to different time periods of each day is determined, and based on the recommended lane turning combination with the largest number of occurrences corresponding to different time periods of each day, a second lane turning combination sequence is generated, thereby effectively improving the utilization rate of the variable lanes, and at the same time being able to implement variable lane control based on historical data, so as to improve the matching degree between the variable lane turning control and the actual traffic conditions of the target section.

[0117] In some embodiments, the variable lane control method further includes the following steps:

[0118] Based on the number of left-turn lanes corresponding to each recommended lane turning combination in the second lane turning combination sequence, a relationship mapping is performed on the second lane turning combination sequence to obtain a corresponding natural number sequence;

[0119] Based on the natural breakpoint algorithm, the natural number series is divided;

[0120] Based on the division result, each recommended lane turning combination in the second lane turning combination sequence is merged to obtain the corresponding third lane turning combination sequence.

[0121] Specifically, obtain the second lane turning combination sequence [A1, A2, …, A m ], and the second lane turning combination sequence is mapped based on the number of left-turn lanes to obtain the natural number sequence [N1, N2, …, N m ], when the recommended lane turning combination includes N m When there are left-turn lanes, the natural number of its mapping is N m For example, when the recommended lane turning combination indicates that the three variable lanes are a left turn lane, a through lane, and a through lane, the mapped natural number is 1. Each element in the natural number sequence corresponds one-to-one to each element in the second lane turning combination sequence.

[0122] The natural breakpoint algorithm is used to divide the natural number series to obtain the best classification in the group sequence, so that the sum of the squares of the deviations of each type of data after the series classification is minimized, so that lane turning recommendations with similar characteristics in each group are made. It should be noted that the series classification [X i ,…,X j ]The sum of squared deviations ssd i,j The calculation formula is as follows:

[0123]

[0124] In formula (3) and formula (4), Represents the classification of sequence [X i ,…,X j ] is the average value. Correspondingly, the loss function of the discontinuity point k of the series is as follows:

[0125]

[0126] In formula (5), L(N,K) represents the loss function; SSD represents the total sum of square deviations of the periodic sequence; N represents a natural number sequence; K is the number of time periods; i k is the subscript of the first period of the kth class.

[0127] When the natural breakpoint algorithm is used to divide the natural number sequence, the number of divisions K=n is preset, and the natural number sequence [N1, N2, ..., N m ] as a sample, from sample length l = 1 to l = m, traverse the subsequence f of the sample starting from 0 l , for each subsequence, calculate the classification loss SSD with a time segmentation number of 1 l , and store it in the preset record table SSDTable. Then, from the sample length l = 2 to l = m, traverse all sample subsequences, for each subsequence, from the number of divisions k = 1 to k = K, traverse all the time period division numbers, and traverse 2 to l to solve the subsequence f l,k The best partition point position CB l,k , the best partition point is f l,k The last partition point, whose classification loss is based on the f stored in the preset record table SSDTable l,k-1 The output sample length is l = m, the number of divisions k = K, and the set of time segment division points and their corresponding SSDs are obtained to obtain the time slice segmentation points and time segment division results.

[0128] Afterwards, based on the division result, each recommended lane turning combination in the second lane turning combination sequence is merged to obtain the corresponding third lane turning combination sequence, which is used as a daily plan to control the turning instructions of each variable lane at different time periods every day. For example, the second lane turning combination sequence is divided into 5 time period division points, and based on each time period division point, each recommended lane turning combination in the second lane turning combination sequence is merged, so that the whole day is divided into 6 time periods, and each time period has lane turning recommendations with similar characteristics, and then based on the lane turning combinations with higher frequency in each time period, the lane turning recommendations in each time period are unified. For example, in the range of 6 am to 9 am, most lane turning combinations limit each variable lane to be a left turn lane, so each variable lane is set as a left turn lane in the time period from 6 am to 9 am.

[0129] Furthermore, the third lane steering combination sequences corresponding to each day of the week are determined by grouping by week, and the third lane steering combination sequences are combined to obtain a final variable lane control scheme for implementing daily variable lane control.

[0130] Through this embodiment, based on the number of left-turn lanes corresponding to each recommended lane turning combination in the second lane turning combination sequence, the second lane turning combination sequence is mapped to obtain a corresponding natural number series. Based on the natural breakpoint algorithm, the natural number series is divided, and based on the division result, the recommended lane turning combinations in the second lane turning combination sequence are merged to obtain a corresponding third lane turning combination sequence, so that the recommended lane turning combinations in the second lane turning combination sequence are classified and merged to generate a corresponding variable lane control scheme, thereby reducing traffic flow fluctuations and helping to improve the stability of lane steering control at different time periods every day.

[0131] In some of the embodiments, after acquiring the latest third lane turning combination sequence each time, the variable lane control method further includes the following steps:

[0132] Compare the latest third lane turning combination sequence with the currently implemented third lane turning combination sequence to obtain the cumulative duration of different lane turning recommendations in the latest third lane turning combination sequence and the currently implemented third lane turning combination sequence;

[0133] Based on the accumulated time, determining whether the latest third lane turning combination sequence and the currently implemented third lane turning combination sequence meet a preset similarity condition;

[0134] When the preset similarity conditions are met, the turning indication of each variable lane is controlled based on the third lane turning combination sequence currently implemented.

[0135] Specifically, after each acquisition of the latest third lane turn combination sequence, the latest third lane turn combination sequence is compared with the currently implemented third lane turn combination sequence to obtain the cumulative duration of the different lane turn recommendations in the two third lane turn combination sequences. For example, if the latest third lane turn combination sequence indicates that the variable lane is set as a left turn lane during the time period from 6:00 to 7:00, and the currently implemented third lane turn combination sequence indicates that the variable lane is set as a straight lane during the time period from 6:00 to 7:00, then the cumulative duration of the different lane turn recommendations in the two second lane turn combination sequences increases by 1 hour.

[0136] Further, according to the accumulated time, it is determined whether the latest third lane turning combination sequence and the currently implemented third lane turning combination sequence meet the preset similarity condition. For example, it is predefined that when the accumulated time exceeds 1 hour, it indicates that the two lane turning combination sequences do not meet the preset similarity condition, and vice versa, it indicates that the two lane turning combination sequences meet the preset similarity condition. When the preset similarity condition is met, the turning indication of each variable lane is controlled based on the currently implemented third lane turning combination sequence; when the preset similarity condition is not met, the latest third lane turning combination sequence is used to replace the previously implemented third lane turning combination sequence.

[0137] Through this embodiment, the latest third lane turning combination sequence is compared with the currently implemented third lane turning combination sequence, and the cumulative duration of different lane turning recommendations in the latest third lane turning combination sequence and the currently implemented third lane turning combination sequence is obtained, and based on the cumulative duration, it is judged whether the latest third lane turning combination sequence and the currently implemented third lane turning combination sequence meet the preset similarity condition; when the preset similarity condition is met, the turning indication of each variable lane is controlled based on the currently implemented third lane turning combination sequence, thereby reducing traffic flow fluctuations and helping to improve the stability of lane steering control at different time periods of the day.

[0138] The present embodiment is described and illustrated by means of specific examples below.

[0139] Figure 7 is a flow chart of the variable lane control method of this embodiment, such as Figure 7 As shown, the variable lane control method specifically includes the following steps:

[0140] All lane turning data within a preset historical period are obtained S710, and a first lane turning combination sequence is generated for each day within the preset historical period, wherein the first lane turning combination sequence includes recommended lane turning combinations corresponding to different time periods of each day S720. Based on each first lane turning combination sequence within the preset historical period, the recommended lane turning combination with the largest number of occurrences corresponding to different time periods of each day is determined, and based on the recommended lane turning combination with the largest number of occurrences corresponding to different time periods of each day, a second lane turning combination sequence is generated S730.

[0141] Further, based on the number of left-turn lanes corresponding to each recommended lane turning combination in the second lane turning combination sequence, the second lane turning combination sequence is relationally mapped to obtain a corresponding natural number sequence. Based on the natural breakpoint algorithm, the natural number sequence is divided S740, and according to the division result, each recommended lane turning combination in the second lane turning combination sequence is merged to obtain a corresponding third lane turning combination sequence. The third lane turning combination sequence corresponding to each day of the week is determined by grouping by week, and each third lane turning combination sequence is combined to obtain a final variable lane control scheme S750.

[0142] Afterwards, it is determined whether the newly generated variable lane control scheme is similar to the currently implemented variable lane control scheme S760. If the two are similar, the currently implemented variable lane control scheme is maintained S770. If the two are not similar, the newly generated variable lane control scheme is output to replace the implemented variable lane control scheme S780.

[0143] The present embodiment is described and illustrated below through preferred embodiments.

[0144] Figure 8 is a flow chart of the variable lane control method of this preferred embodiment, such as Figure 8 As shown, the variable lane control method includes the following steps:

[0145] Step S810, enumerating the turns of the variable lanes in each import lane in the target road section to obtain a plurality of lane turn combinations; the import lane includes at least one variable lane;

[0146] Step S820, based on a preset statistical interval, obtaining real-time traffic data of each import lane, and determining corresponding multiple periodic indicator data according to the real-time traffic data;

[0147] Step S830, based on the index data of each cycle, determining the accumulated queue lengths of lanes corresponding to different turning lane categories in each import lane;

[0148] Step S840, determining an import lane combination corresponding to the lane turning combination according to the variable lanes set by each lane turning combination and the fixed lanes in each import lane in the target road section;

[0149] Step S850, obtaining first traffic flow weights of multiple exit lanes corresponding to each import lane, and determining a lane turning combination adapted to each exit lane based on the first traffic flow weight and a second traffic flow weight corresponding to each import lane combination;

[0150] Step S860, based on the accumulated queue lengths of lanes corresponding to different turning lane categories, determining the maximum average queue length of lanes corresponding to each lane turning combination adapted to each exit lane;

[0151] Step S870, controlling the turning indications of each variable lane based on the lane turning combination that minimizes the average queue length of the largest lane.

[0152] Through this embodiment, the turns of the variable lanes in each import lane in the target road section are enumerated to obtain multiple lane turn combinations, and the import lane includes at least one variable lane. Based on a preset statistical interval, the real-time traffic data of each import lane is obtained, and the corresponding multiple periodic index data are determined according to the real-time traffic data, and based on each periodic index data, the lane cumulative queue length corresponding to the different turn lane categories in each import lane is determined.

[0153] Furthermore, according to the variable lanes set by each lane turning combination and the fixed lanes in each import lane in the target section, the import lane combination corresponding to the lane turning combination is determined, and the first traffic flow weights of multiple exit lanes corresponding to each import lane are obtained. Based on the first traffic flow weight and the second traffic flow weight corresponding to each import lane combination, the lane turning combination adapted to each exit lane is determined. Based on the accumulated queue lengths of lanes corresponding to different turning lane categories, the maximum lane average queue length corresponding to each lane turning combination adapted to each exit lane is determined, and based on the lane turning combination that minimizes the maximum lane average queue length, the turning instructions of each variable lane are controlled, which solves the problem that lane turning recommendations cannot be made based on real-time traffic demand, realizes lane turning recommendations based on real-time traffic demand, improves the accuracy of variable lane control, and improves the universality of variable lane control schemes.

[0154] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0155] In this embodiment, a variable lane control device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. The terms "module", "unit", "subunit", etc. used below can implement a combination of software and / or hardware of predetermined functions. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0156] Fig. 9 : is a structural block diagram of the variable lane control device of this embodiment, such as Fig. 9 As shown, the device includes: an enumeration module 10, a calculation module 20 and a control module 30;

[0157] The enumeration module 10 is used to enumerate the turns of the variable lanes in each import lane in the target road section to obtain a plurality of lane turn combinations; the import lane includes at least one variable lane;

[0158] A calculation module 20, for determining in real time, based on a preset statistical interval, the accumulated queue lengths of lanes corresponding to different turning lane categories in each import lane;

[0159] The calculation module 20 is further used to determine the maximum lane average queue length corresponding to each lane turning combination based on the accumulated lane queue lengths corresponding to different turning lane categories;

[0160] The control module 30 is used to control the turning indication of each variable lane based on the lane turning combination that minimizes the average queue length of the largest lane.

[0161] Through the device provided by this embodiment, the turns of the variable lanes in each import lane in the target section are enumerated to obtain multiple lane turning combinations; the import lane includes at least one variable lane; based on the preset statistical interval, the lane cumulative queue lengths corresponding to different turning lane categories in each import lane are determined in real time; based on the lane cumulative queue lengths corresponding to different turning lane categories, the maximum lane average queue length corresponding to each lane turning combination is determined; based on the lane turning combination that minimizes the maximum lane average queue length, the turning indications of each variable lane are controlled, which solves the problem that lane turning recommendations cannot be made based on real-time traffic demand, realizes lane turning recommendations based on real-time traffic demand, improves the accuracy of variable lane control, and improves the universality of variable lane control schemes.

[0162] In some of the embodiments, the calculation module 20 is also used to obtain real-time traffic data of each import lane based on a preset statistical interval; determine a corresponding plurality of periodic indicator data based on the real-time traffic data; and determine the cumulative queue length of the lane corresponding to different turning lane categories in each import lane based on each periodic indicator data.

[0163] In some of the embodiments, the calculation module 20 is further used to determine the import lane combination corresponding to the lane turning combination based on the variable lanes set for each lane turning combination and the fixed lanes in each import lane in the target section; determine the number of lanes corresponding to different turning lane categories in each import lane combination; and determine the maximum lane average queue length corresponding to each lane turning combination based on the cumulative queue length of the lanes corresponding to each turning lane category and the number of lanes.

[0164] In some of the embodiments, the calculation module 20 is further used to obtain a first traffic flow weight of multiple exit lanes corresponding to each import lane; determine an import lane combination corresponding to the lane turning combination according to the variable lanes set for each lane turning combination and the fixed lanes in each import lane in the target section; determine a lane turning combination adapted to each exit lane based on the first traffic flow weight and the second traffic flow weight corresponding to each import lane combination; and determine a maximum lane average queue length corresponding to each lane turning combination adapted to each exit lane based on the cumulative queue lengths of lanes corresponding to different turning lane categories.

[0165] In some of the embodiments, the control module 30 is further used to determine the lane turning combination that minimizes the average queue length of the maximum lane as the recommended lane turning combination, and add the recommended lane turning combination to a preset first lane turning combination sequence; the first lane turning combination sequence is used to record the recommended lane turning combinations corresponding to different time periods every day; obtain all first lane turning combination sequences within a preset historical period, and determine the recommended lane turning combination corresponding to the current time period in each first lane turning combination sequence; based on the recommended lane turning combination that appears most times in each recommended lane turning combination corresponding to the current time period, control the turning indication of each variable lane.

[0166] In some of the embodiments, the calculation module 20 is further used to determine the recommended lane turning combination with the largest number of occurrences corresponding to different time periods every day based on each first lane turning combination sequence within a preset historical period; and generate a second lane turning combination sequence based on the recommended lane turning combination with the largest number of occurrences corresponding to different time periods every day.

[0167] In some of the embodiments, the calculation module 20 is further used to perform relationship mapping on the second lane turning combination sequence based on the number of left-turn lanes corresponding to each recommended lane turning combination in the second lane turning combination sequence to obtain a corresponding natural number series; divide the natural number series based on a natural breakpoint algorithm; and based on the division result, merge the recommended lane turning combinations in the second lane turning combination sequence to obtain a corresponding third lane turning combination sequence.

[0168] In some of the embodiments, the control module 30 is further used to compare the latest third lane turning combination sequence with the currently implemented third lane turning combination sequence to obtain the cumulative duration of different lane turning recommendations in the latest third lane turning combination sequence and the currently implemented third lane turning combination sequence; based on the cumulative duration, determine whether the latest third lane turning combination sequence and the currently implemented third lane turning combination sequence meet a preset similarity condition; when the preset similarity condition is met, maintain the control of the turning indication of each variable lane based on the currently implemented third lane turning combination sequence.

[0169] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0170] In this embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0171] Optionally, the computer device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0172] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0173] S1, enumerating the turns of the variable lanes in each import lane in the target road section to obtain a plurality of lane turning combinations; the import lane includes at least one variable lane;

[0174] S2, based on a preset statistical interval, determining in real time the accumulated queue lengths of lanes corresponding to different turning lane categories in each import lane;

[0175] S3, determining a maximum lane average queue length corresponding to each lane turning combination based on the accumulated queue lengths of the lanes corresponding to the different turning lane categories;

[0176] S4: Control the turning instructions of each variable lane based on the lane turning combination that minimizes the average queue length of the largest lane.

[0177] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.

[0178] In addition, in combination with the variable lane control method provided in the above embodiments, a storage medium may be provided in this embodiment to implement the variable lane control method. The storage medium stores a computer program; when the computer program is executed by a processor, any variable lane control method in the above embodiments is implemented.

[0179] It should be understood that the specific embodiments described herein are only used to explain the application, rather than to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.

[0180] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.

[0181] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0182] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of patent protection. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.

Claims

1. A variable lane control method, characterized in that: The method comprises: Enumerating the turns of the variable lanes in each import lane in the target road section to obtain a plurality of lane turn combinations; the import lane includes at least one variable lane; Based on a preset statistical interval, the accumulated queue lengths of lanes corresponding to different turning lane categories in each of the import lanes are determined in real time; Determine a maximum lane average queue length corresponding to each lane turning combination based on the lane cumulative queue lengths corresponding to different turning lane categories; Based on the lane turning combination that minimizes the average queue length of the maximum lane, the turning indication of each of the variable lanes is controlled.

2. The variable lane control method according to claim 1, characterized in that: The method of determining in real time the accumulated queue lengths of lanes corresponding to different types of turning lanes in the import lanes based on a preset statistical interval includes: Based on the preset statistical interval, obtaining real-time traffic data of each of the import lanes; Determine corresponding multiple periodic indicator data according to the real-time traffic data; Based on each of the cycle indicator data, the cumulative queue lengths of the lanes corresponding to the different turning lane categories in each of the import lanes are determined.

3. The variable lane control method according to claim 1 or 2, characterized in that: The determining, based on the lane cumulative queue lengths corresponding to the different turning lane categories, the maximum lane average queue length corresponding to each lane turning combination comprises: Determining an import lane combination corresponding to the lane turning combination according to the variable lanes set by each lane turning combination and the fixed lanes in each import lane in the target road section; Determine the number of lanes corresponding to the different turning lane categories in each of the import lane combinations; Based on the lane cumulative queue length corresponding to each turning lane category and the number of lanes, the corresponding maximum lane average queue length is determined.

4. The variable lane control method according to claim 1, characterized in that: The determining, based on the lane cumulative queue lengths corresponding to the different turning lane categories, of the maximum lane average queue length corresponding to each lane turning combination further includes: Obtaining first traffic flow weights of a plurality of exit lanes corresponding to each of the import lanes; Determining an import lane combination corresponding to the lane turning combination according to the variable lanes set by each lane turning combination and the fixed lanes in each import lane in the target road section; Determining the lane turning combination adapted to each of the exit lanes based on the first traffic flow weight and the second traffic flow weight corresponding to each of the import lane combinations; Based on the accumulated lane queue lengths corresponding to the different turning lane categories, the maximum lane average queue length corresponding to each lane turning combination adapted to each exit lane is determined.

5. The variable lane control method according to claim 1, characterized in that: After determining the maximum lane average queue length corresponding to each lane turning combination based on the lane cumulative queue lengths corresponding to different turning lane categories, the method further includes: Determine the lane turning combination with the smallest average queue length of the maximum lane as a recommended lane turning combination, and add the recommended lane turning combination to a preset first lane turning combination sequence; the first lane turning combination sequence is used to record the recommended lane turning combinations corresponding to different time periods every day; Acquire all the first lane turning combination sequences within a preset historical period, and determine the recommended lane turning combination corresponding to the current time period in each of the first lane turning combination sequences; The turning indication of each of the variable lanes is controlled based on the recommended lane turning combination that appears most frequently among the recommended lane turning combinations corresponding to the current time period.

6. The variable lane control method according to claim 5, characterized in that: The method further comprises: Determine, based on each of the first lane turning combination sequences within the preset historical period, the recommended lane turning combination with the largest number of occurrences corresponding to different time periods each day; A second lane turning combination sequence is generated based on the recommended lane turning combinations that appear most frequently at different time periods every day.

7. The variable lane control method according to claim 6, characterized in that: The method further comprises: Based on the number of left-turn lanes corresponding to each of the recommended lane turning combinations in the second lane turning combination sequence, performing relationship mapping on the second lane turning combination sequence to obtain a corresponding natural number sequence; Dividing the natural number sequence based on a natural breakpoint algorithm; Based on the division result, the recommended lane turning combinations in the second lane turning combination sequence are merged to obtain a corresponding third lane turning combination sequence.

8. The variable lane control method according to claim 7, characterized in that: After acquiring the latest third lane turning combination sequence each time, the method further includes: Comparing the latest third lane turning combination sequence with the currently implemented third lane turning combination sequence to obtain the cumulative duration of different lane turning recommendations in the latest third lane turning combination sequence and the currently implemented third lane turning combination sequence; Based on the accumulated time, determining whether the latest third lane turning combination sequence and the currently implemented third lane turning combination sequence meet a preset similarity condition; When the preset similarity condition is met, the turning indication of each of the variable lanes is controlled based on the third lane turning combination sequence currently being implemented.

9. A variable lane control device, characterized in that: The device comprises: an enumeration module, a calculation module and a control module; The enumeration module is used to enumerate the turns of the variable lanes in each import lane in the target road section to obtain a plurality of lane turn combinations; the import lane includes at least one variable lane; The calculation module is used to determine the lane cumulative queue lengths corresponding to different turning lane categories in each of the import lanes in real time based on a preset statistical interval; The calculation module is further used to determine the maximum lane average queue length corresponding to each lane turning combination based on the lane cumulative queue lengths corresponding to different turning lane categories; The control module is used to control the turning indication of each of the variable lanes based on the lane turning combination that minimizes the average queue length of the maximum lane.

10. A computer device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps of the variable lane control method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the variable lane control method according to any one of claims 1 to 8 are implemented.

Images