A method, device, equipment and storage medium for dividing traffic control time periods

Abstract

The embodiments of the present application provide a method, device, equipment and storage medium for dividing traffic control periods, which relate to the field of data processing technology. The method includes: first, dividing a preset time period into N basic time units based on a target time interval, and obtaining target traffic flow data of target traffic positions in the N basic time units. Then, in an iterative manner, the N basic time units are divided based on the target traffic flow data of the N basic time units until the iteration stop condition is met, and the output K target candidate time periods are used as K traffic control periods. The traffic control period division method in the present application enables the obtained traffic control periods to have the largest inter-class gap and the smallest intra-class gap. Finally, according to the obtained traffic control periods, a corresponding street light signal control plan is formulated to further improve the level of refined control at traffic intersections.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of data processing technology, and in particular to a method, device, equipment and storage medium for dividing traffic control time periods. Background Art

[0002] With the widespread development of traffic monitoring technology, street light signal control is moving towards intelligence and refinement. In order to adapt to the changes in traffic flow at different times at traffic intersections, it is necessary to determine different street light signal control schemes based on the traffic flow data corresponding to different traffic control periods. Therefore, the division of traffic control periods is particularly important.

[0003] At present, traffic control time periods are mainly divided into 24-hour periods based on personal experience by traffic engineering personnel, and then corresponding street light signal control plans are formulated for each traffic control period. However, the above traffic control period division method relies on personal experience, and the formulated street light signal control plan has certain limitations, and its accuracy and efficiency are low. Summary of the invention

[0004] The embodiments of the present application provide a traffic control period division method, device, equipment and storage medium for improving the accuracy and efficiency of the formulated street light signal control plan.

[0005] On the one hand, an embodiment of the present application provides a method for dividing a traffic control period, the method comprising:

[0006] Based on the target time interval, the preset time period is divided into N basic time units, and the target traffic flow data of the target traffic position in the N basic time units are obtained respectively;

[0007] In an iterative manner, the N basic time units are divided based on the target vehicle flow data of the N basic time units until an iteration stop condition is met, and the output K target candidate time periods are used as K traffic control time periods, wherein the iteration stop condition is: the N basic time units are divided into K candidate time periods, and N-K+1 division methods of dividing the N basic time units into K candidate time periods are obtained, and K candidate time periods corresponding to the division method that satisfies the minimum total value of vehicle flow deviation are selected as K target candidate time periods, N is greater than or equal to K, N is greater than or equal to 1, and K is greater than or equal to 1.

[0008] Optionally, the step of obtaining target traffic flow data of the target traffic position at the N basic time units includes:

[0009] Obtaining the original traffic flow data of the target traffic location in the N basic time units respectively;

[0010] The original vehicle flow data is cleaned of abnormal data and missing data to obtain the target vehicle flow data.

[0011] Optionally, the obtaining of the original traffic flow data of the target traffic position in the N basic time units includes:

[0012] determining a plurality of traffic phases corresponding to the target traffic position;

[0013] For the N basic time units, the following steps are performed respectively:

[0014] Collecting phase vehicle flow data corresponding to each of the multiple traffic phases at the target traffic location within a basic time unit respectively;

[0015] The phase vehicle flow data corresponding to each of the multiple traffic phases is used as the original vehicle flow data of the one basic time unit.

[0016] Optionally, for the i-th iteration process, where 2<=i<=K, the following steps are included:

[0017] Step 1: Use M-i+1 division methods to divide the first M basic time units of the N basic time units to obtain M-i+1 division results, wherein each division result includes i candidate time periods, each candidate time period includes at least one basic time unit, and M is greater than or equal to i;

[0018] Step 2: Based on the N minimum total values ​​of vehicle flow deviations obtained in the i-1th iteration, determine the minimum total value of vehicle flow deviations in the M-i+1 division methods in the i-th iteration;

[0019] Set M=M+1, and determine whether M is less than or equal to N. If so, repeat step 1 and step 2, otherwise enter the i+1th iteration process.

[0020] Optionally, the adopting M-i+1 division modes to divide the first M basic time units among the N basic time units to obtain M-i+1 division results includes:

[0021] Divide the first j basic time units among the M basic time units into the first i-1 candidate time periods, and take the other basic time units among the M basic time units as the last candidate time period, where i-1<=j<=M-1;

[0022] Set j=j+1, and determine whether j is less than or equal to M-1. If so, repeat the above steps, otherwise terminate the division.

[0023] Optionally, determining the minimum total value of vehicle flow deviation in the M-i+1 division modes in the i-th iteration process based on the N minimum total values ​​of vehicle flow deviation obtained in the i-1th iteration process includes:

[0024] Based on the N minimum total values ​​of vehicle flow deviation obtained in the i-1th iteration process, determine the total value of vehicle flow deviation corresponding to each of the M-i+1 division modes;

[0025] From the obtained M-i+1 total values ​​of vehicle flow deviation, determine the minimum total value of vehicle flow deviation in the M-i+1 division methods.

[0026] Optionally, the determining of the total vehicle flow deviation values ​​corresponding to each of the M-i+1 division modes based on the N minimum total vehicle flow deviation values ​​obtained in the i-1th iteration process includes:

[0027] For the M-i+1 partitioning methods, perform the following steps respectively:

[0028] For one division method, based on the N minimum total values ​​of vehicle flow deviations obtained in the i-1th iteration process, determine the total value of vehicle flow deviations corresponding to the first i-1 candidate time periods obtained by using the one division method;

[0029] Determine the sum of squares of traffic flow deviations of the last candidate time period based on the average traffic flow data of the last candidate time period;

[0030] Based on the total values ​​of vehicle flow deviations corresponding to the first i-1 candidate time periods and the sum of squares of vehicle flow deviations of the last candidate time period, the total value of vehicle flow deviations corresponding to the one division method is determined.

[0031] Optionally, determining the sum of square deviations of the traffic flow of the last candidate time period based on the average traffic flow data of the last candidate time period includes:

[0032] Determine the square of the vehicle flow deviation corresponding to each of the at least one basic time unit based on the target vehicle flow data corresponding to each of the at least one basic time unit in the last candidate time period and the average vehicle flow data;

[0033] The squares of the vehicle flow deviations corresponding to each of the at least one basic time unit are added together to obtain the sum of the squares of the vehicle flow deviations of the last candidate time period.

[0034] On the one hand, an embodiment of the present application provides a traffic control period division device, the device comprising:

[0035] An acquisition module, used to divide the preset time period into N basic time units based on the target time interval, and acquire the target traffic flow data of the target traffic position in the N basic time units respectively;

[0036] An iteration module is used to divide the N basic time units in an iterative manner based on the target vehicle flow data of the N basic time units until an iteration stop condition is met, and the output K target candidate time periods are used as K traffic control time periods, wherein the iteration stop condition is: dividing the N basic time units into K candidate time periods, and obtaining N-K+1 division methods for dividing the N basic time units into K candidate time periods, and selecting K candidate time periods corresponding to the division method that satisfies the minimum total value of vehicle flow deviation as K target candidate time periods, N is greater than or equal to K, N is greater than or equal to 1, and K is greater than or equal to 1.

[0037] Optionally, the acquisition module is specifically used for:

[0038] Obtaining the original traffic flow data of the target traffic location in the N basic time units respectively;

[0039] The original vehicle flow data is cleaned of abnormal data and missing data to obtain the target vehicle flow data.

[0040] Optionally, the acquisition module is specifically used for:

[0041] determining a plurality of traffic phases corresponding to the target traffic position;

[0042] For the N basic time units, the following steps are performed respectively:

[0043] Collecting phase vehicle flow data corresponding to each of the multiple traffic phases at the target traffic location within a basic time unit respectively;

[0044] The phase vehicle flow data corresponding to each of the multiple traffic phases is used as the original vehicle flow data of the one basic time unit.

[0045] Optionally, the iteration module is specifically used for:

[0046] For the i-th iteration process, where 2<=i<=K, the following steps are included:

[0047] Step 1: Use M-i+1 division methods to divide the first M basic time units of the N basic time units to obtain M-i+1 division results, wherein each division result includes i candidate time periods, each candidate time period includes at least one basic time unit, and M is greater than or equal to i;

[0048] Step 2: Based on the N minimum total values ​​of vehicle flow deviations obtained in the i-1th iteration, determine the minimum total value of vehicle flow deviations in the M-i+1 division methods in the i-th iteration;

[0049] Set M=M+1, and determine whether M is less than or equal to N. If so, repeat step 1 and step 2, otherwise enter the i+1th iteration process.

[0050] Optionally, the iteration module is specifically used for:

[0051] Divide the first j basic time units among the M basic time units into the first i-1 candidate time periods, and take the other basic time units among the M basic time units as the last candidate time period, where i-1<=j<=M-1;

[0052] Set j=j+1, and determine whether j is less than or equal to M-1. If so, repeat the above steps, otherwise terminate the division.

[0053] Optionally, the iteration module is specifically used for:

[0054] Based on the N minimum total values ​​of vehicle flow deviation obtained in the i-1th iteration process, determine the total value of vehicle flow deviation corresponding to each of the M-i+1 division modes;

[0055] From the obtained M-i+1 total values ​​of vehicle flow deviation, determine the minimum total value of vehicle flow deviation in the M-i+1 division methods.

[0056] Optionally, the iteration module is specifically used for:

[0057] For the M-i+1 partitioning methods, perform the following steps respectively:

[0058] For one division method, based on the N minimum total values ​​of vehicle flow deviations obtained in the i-1th iteration process, determine the total value of vehicle flow deviations corresponding to the first i-1 candidate time periods obtained by using the one division method;

[0059] Determine the sum of squares of traffic flow deviations of the last candidate time period based on the average traffic flow data of the last candidate time period;

[0060] Based on the total values ​​of vehicle flow deviations corresponding to the first i-1 candidate time periods and the sum of squares of vehicle flow deviations of the last candidate time period, the total value of vehicle flow deviations corresponding to the one division method is determined.

[0061] Optionally, the iteration module is specifically used for:

[0062] Determine the square of the vehicle flow deviation corresponding to each of the at least one basic time unit based on the target vehicle flow data corresponding to each of the at least one basic time unit in the last candidate time period and the average vehicle flow data;

[0063] The squares of the vehicle flow deviations corresponding to each of the at least one basic time unit are added together to obtain the sum of the squares of the vehicle flow deviations of the last candidate time period.

[0064] On the one hand, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned traffic control period division method when executing the program.

[0065] On the one hand, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program that can be executed by a computer device. When the program is run on the computer device, the computer device executes the steps of the above-mentioned traffic control period division method.

[0066] In an embodiment of the present application, the preset time period is first divided into N basic time units based on the target time interval, and the target traffic flow data of the target traffic position in the N basic time units are obtained. Then, the N basic time units are divided based on the target traffic flow data of the N basic time units in an iterative manner until the iteration stop condition is met, and the output K target candidate time periods are used as K traffic control time periods. Since the iterative method is used in the present application to divide the traffic control time periods for each basic time unit, the candidate time periods corresponding to the division method with the smallest total value of traffic flow deviation are selected as the final traffic control time periods. The similarity between at least one basic time unit included in a traffic control time period is relatively large, and the similarity between different basic time units included in different traffic control time periods is relatively small. Therefore, the traffic control time period division method in the present application makes the inter-class gap and the intra-class gap of each traffic control time period obtained the largest. Finally, according to each traffic control time period obtained, a corresponding street light signal control plan is formulated to further improve the level of refined control at the traffic intersection. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0068] Figure 1 A schematic diagram of a system architecture provided for an embodiment of the present application;

[0069] Figure 2 A flow chart of a method for dividing traffic control time periods provided in an embodiment of the present application;

[0070] Figure 3 A flowchart of a method for obtaining target vehicle flow data provided in an embodiment of the present application;

[0071] Figure 4 A structural schematic diagram of a traffic phase corresponding to a target traffic position provided in an embodiment of the present application;

[0072] Figure 5 A flow chart of a method for determining the sum of squared deviations of vehicle flow provided in an embodiment of the present application;

[0073] Figure 6 A schematic diagram of a traffic control time division method provided in an embodiment of the present application;

[0074] Figure 7 A schematic diagram of a traffic control time division method provided in an embodiment of the present application;

[0075] Figure 8 A schematic diagram of a traffic control time division method provided in an embodiment of the present application;

[0076] Fig. 9 A flow chart of a method for dividing traffic control time periods provided in an embodiment of the present application;

[0077] Fig.10 A flow chart of a method for dividing traffic control time periods provided in an embodiment of the present application;

[0078] Fig.11 A schematic diagram of a traffic control time division method provided in an embodiment of the present application;

[0079] Fig.12 A schematic diagram of a traffic control time division method provided in an embodiment of the present application;

[0080] Fig.13 A schematic diagram of a traffic control time division method provided in an embodiment of the present application;

[0081] Fig.14 A schematic diagram of a traffic control time division method provided in an embodiment of the present application;

[0082] Fig.15 A schematic diagram of a traffic control time division method provided in an embodiment of the present application;

[0083] Fig.16A schematic diagram of a traffic control time division method provided in an embodiment of the present application;

[0084] Fig.17 A schematic diagram of a traffic control time division method provided in an embodiment of the present application;

[0085] Fig.18 A schematic diagram of a traffic control time division method provided in an embodiment of the present application;

[0086] Fig.19 A schematic diagram of a traffic control time division method provided in an embodiment of the present application;

[0087] Fig. 20 A schematic diagram of a traffic control time division method provided in an embodiment of the present application;

[0088] Fig.21 A schematic diagram of a traffic control time division method provided in an embodiment of the present application;

[0089] Fig. 22 A schematic diagram of a traffic control time division method provided in an embodiment of the present application;

[0090] Fig.23 A flowchart of a method for determining the optimal number of time periods provided in an embodiment of the present application;

[0091] Fig.24 A flow chart of a method for dividing traffic control time periods provided in an embodiment of the present application;

[0092] Fig.25 A schematic diagram of the structure of a traffic control time division device provided in an embodiment of the present application;

[0093] Fig.26 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0094] In order to make the purpose, technical solution and beneficial effects of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0095] refer to Figure 1 , which is a system architecture diagram for dividing traffic control periods applicable to an embodiment of the present application. The system architecture diagram for dividing traffic control periods includes at least a terminal device 101 and a traffic control period division system 102.

[0096] The terminal device 101 is installed with a target application for dividing traffic control time periods, which may be a pre-installed client, a web application, or a small program embedded in other applications, etc. The terminal device 101 may be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto.

[0097] The traffic control period division system 102 is a background server of the target application, providing services for the target application. The traffic control period division system 102 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0098] The terminal device 101 and the traffic control period division system 102 may be directly or indirectly connected via wired or wireless communication, which is not limited in the present application.

[0099] The terminal device 101 responds to the user's operation of dividing the traffic control period, and sends a traffic control period division instruction for the preset time period to the traffic control period division system 102. The traffic control period division system 102 receives the traffic control period division instruction, divides the preset time period into N basic time units based on the target time interval, and obtains the target vehicle flow data of the target traffic position in the N basic time units. Then, the N basic time units are divided based on the target vehicle flow data of the N basic time units in an iterative manner until the iteration stop condition is met, and the output K target candidate time periods are used as K traffic control time periods, wherein the iteration stop condition is: divide the N basic time units into K candidate time periods, and obtain N-K+1 division methods for dividing the N basic time units into K candidate time periods, and select the K candidate time periods corresponding to the division method that satisfies the minimum total value of vehicle flow deviation as the K target candidate time periods, N is greater than or equal to K, N is greater than or equal to 1, and K is greater than or equal to 1.

[0100] based on Figure 1 The system architecture diagram, the embodiment of the present application provides a process of a method for dividing a traffic control period, such as Figure 2 As shown, the process of this method is Figure 1 The traffic control period division system 102 shown is executed, including the following steps:

[0101] Step S201: based on the target time interval, divide the preset time period into N basic time units, and obtain the target traffic flow data of the target traffic position in the N basic time units respectively.

[0102] Specifically, the preset time period is a natural day, that is, 24 hours. The target time interval is preset and can be in seconds, minutes, or hours. For example, the target time interval is 15 minutes.

[0103] For example, the target time interval is 15 minutes, and the preset time period is 24 hours. Based on the target time interval of 15 minutes, the preset time period of 24 hours is divided to obtain 96 basic time units.

[0104] Alternatively, if Figure 3 As shown, obtaining target traffic flow data of the target traffic position at N basic time units includes the following steps:

[0105] Step S301, obtaining the original traffic flow data of the target traffic location in N basic time units.

[0106] Specifically, the multiple traffic phases corresponding to the target traffic position are first determined, and then the following steps are performed for N basic time units: the phase traffic flow data corresponding to the target traffic position in the multiple traffic phases within a basic time unit are collected respectively; and the phase traffic flow data corresponding to the multiple traffic phases are used as the original traffic flow data of a basic time unit.

[0107] When the target traffic location is a traffic intersection, the multiple traffic phases corresponding to the target traffic location include: a north-south straight phase, an east-west straight phase, a north-south left turn phase, a north-south right turn phase, an east-west left turn phase, and an east-west right turn phase. The multiple traffic phases corresponding to the target traffic location may also include other phases, which are not limited here.

[0108] like Figure 4 As shown in FIG. 1 , when the target traffic position is a traffic intersection, the target traffic position corresponds to four traffic phases, namely, Figure 4 4(a) in the figure is the north-south straight phase. Figure 4 4(b) is the north-south left-turn phase. Figure 4 4(c) in the figure is the east-west straight phase. Figure 4 4(d) in the figure is the east-west left rotation phase.

[0109] A basic time unit includes multiple travel time units. The size of each travel time unit can be the same or different. Each travel time unit corresponds to a traffic phase. Therefore, within a basic time unit, the target traffic position corresponds to multiple traffic phases, and the multiple traffic phases change according to the change of the travel time unit.

[0110] For a basic time unit, the traffic phases corresponding to each of the passing time units in the basic time unit are determined, and the number of vehicles traveling in each passing time unit is used as the phase traffic flow data of the traffic phase corresponding to the passing time unit. Then, the phase traffic flow data corresponding to multiple traffic phases are combined into a matrix as the original traffic flow data of the basic time unit.

[0111] against Figure 4 There are 4 traffic phases in the basic time unit, 00:00:00-00:15:00, and the size of the travel time unit corresponding to each traffic phase is 3 minutes. Set the traffic phase corresponding to the travel time unit 00:00:00-00:03:00 as the north-south straight phase, the traffic phase corresponding to the travel time unit 00:03:00-00:06:00 as the north-south left-turn phase, the traffic phase corresponding to the travel time unit 00:06:00-00:09:00 as the east-west straight phase, the traffic phase corresponding to the travel time unit 00:09:00-00:12:00 as the east-west left-turn phase, and the traffic phase corresponding to the travel time unit 00:12:00-00:15:00 as the north-south straight phase. Therefore, within the basic time unit 00:00:00-00:15:00, the target traffic position corresponds to 5 traffic phases, namely the north-south straight phase, the north-south left turn phase, the east-west straight phase, the east-west left turn phase and the north-south straight phase.

[0112] Among them, the number of vehicles going straight in the north-south direction within the travel time unit 00:00:00-00:03:00 is 20, the number of vehicles turning left in the north-south direction within the travel time unit 00:03:00-00:06:00 is 30, the number of vehicles going straight in the east-west direction within the travel time unit 00:06:00-00:09:00 is 23, the number of vehicles turning left in the east-west direction within the travel time unit 00:09:00-00:12:00 is 25, and the number of vehicles going straight in the north-south direction within the travel time unit 00:12:00-00:15:00 is 10. Therefore, the phase vehicle flow data corresponding to the north-south straight phase is 20+10=30, the phase vehicle flow data corresponding to the north-south left turn phase is 30, the phase vehicle flow data corresponding to the east-west straight phase is 23, and the phase vehicle flow data corresponding to the east-west left turn phase is 25.

[0113] Based on the phase traffic flow data corresponding to each of the above four traffic phases, a matrix is ​​combined as the original traffic flow data of the basic time unit 00:00:00-00:15:00, that is,

[0114] Step S302, cleaning the original vehicle flow data for abnormal data and missing data to obtain target vehicle flow data.

[0115] If there are abnormal data in the original traffic flow data, such as -1, etc., the original traffic flow data is cleaned for abnormal data. Common abnormal data cleaning methods can be to set the original traffic flow data to a zero matrix or to set the abnormal data in the original traffic flow data to 0.

[0116] If there is missing data in the original traffic flow data, the original traffic flow data is cleaned of missing data. Common missing data cleaning methods can be to set the original traffic flow data to a zero matrix or to set the missing data in the original traffic flow data to 0.

[0117] For example, the original traffic flow data is The original traffic flow data contains abnormal data -1, and the abnormal data in the original traffic flow data is set to 0, and the target traffic flow data is obtained as follows:

[0118] In an embodiment of the present application, taking into account multiple traffic phases corresponding to the target traffic location, the original traffic flow data of a basic time unit is determined based on the phase traffic flow data corresponding to the target traffic location in the multiple traffic phases within a basic time unit, and the difference between the traffic phases of different target traffic locations is fully considered, that is, the characteristics of the spatial dimension of the target traffic location are fully considered, which is conducive to improving the accuracy of the division of traffic control periods.

[0119] By cleaning the original traffic flow data for abnormal data and missing data and obtaining the target traffic flow data, noise data can be removed and the accuracy of traffic control period division can be further improved.

[0120] Step S202, in an iterative manner, based on the target vehicle flow data of the N basic time units, the N basic time units are divided until the iteration stop condition is met, and the output K target candidate time periods are used as K traffic control time periods.

[0121] Specifically, the iteration stopping condition is: divide N basic time units into K candidate time periods, and obtain N-K+1 ways of dividing N basic time units into K candidate time periods, and select K candidate time periods corresponding to the division method that satisfies the minimum total value of vehicle flow deviation as K target candidate time periods, N is greater than or equal to K, N is greater than or equal to 1, and K is greater than or equal to 1.

[0122] Among them, for the Kth iteration, N-K+1 ways of dividing N basic time units into K candidate time periods are obtained, and the total value of the traffic flow deviation corresponding to each division method is calculated. The specific steps are as follows:

[0123] The first division method is: divide the first K-1 basic time units among N basic time units into the first K-1 candidate time periods; then take the other basic time units among the N basic time units (i.e., N-K+1 basic time units) as the last candidate time period, and obtain a total of K candidate time periods.

[0124] The second division method is: divide the first K basic time units among N basic time units into the first K-1 candidate time periods; and then take the other basic time units among the N basic time units (ie, NK basic time units) as the last candidate time period, and obtain a total of K candidate time periods.

[0125] By analogy, the N-K+1th division method is: divide the first N-1 basic time units among the N basic time units into the first K-1 candidate time periods; and then take the other basic time units among the N basic time units (i.e., 1 basic time period) as the last candidate time period, and obtain a total of K candidate time periods.

[0126] For any of the above division methods, determine the total value of the traffic flow deviation corresponding to the division method, and perform the following steps:

[0127] First, based on the target traffic flow data corresponding to at least one basic time unit in the last candidate period, the average traffic flow data of the last candidate period is determined. Then, based on the average traffic flow data of the last candidate period, the sum of squares of traffic flow deviations of the last candidate period is determined. Finally, based on the total traffic flow deviations corresponding to the first K-1 candidate periods and the sum of squares of traffic flow deviations corresponding to the last candidate period, the total traffic flow deviation corresponding to the division method is determined.

[0128] Among them, since the total deviation value of the traffic flow corresponding to the K-1 candidate time periods is determined when performing the K-1th iteration, the total deviation value of the traffic flow corresponding to the first K-1 candidate time periods can be directly obtained when performing the Kth iteration.

[0129] Optionally, based on the average traffic flow data of the last candidate period, determining the sum of square deviations of the traffic flow of the last candidate period includes the following steps: Figure 5 As shown:

[0130] Step S501, based on the target vehicle flow data corresponding to at least one basic time unit in the last candidate time period and the average vehicle flow data, determine the vehicle flow deviation square corresponding to at least one basic time unit.

[0131] Specifically, the target traffic flow data corresponding to at least one basic time unit in the last candidate period is subtracted from the average traffic flow data to obtain the traffic flow deviation corresponding to at least one basic time unit. The traffic flow deviation corresponding to at least one basic time unit is then squared to obtain the square of the traffic flow deviation corresponding to at least one basic time unit.

[0132] Step S502: Add the squares of the vehicle flow deviations corresponding to at least one basic time period to obtain the sum of the squares of the vehicle flow deviations of the last candidate time period.

[0133] Specifically, it is assumed that one candidate time period includes L basic time units (i.e., the pth basic time unit to the qth basic time unit), where L=q-p+1, and the square sum of the traffic flow deviation corresponding to one candidate time period is obtained using the following formula (1):

[0134] in,

[0135] Among them, SSD p,q represents the sum of square deviations of traffic flow corresponding to a candidate period (including the pth basic time unit to the qth basic time unit), f v represents the target traffic flow data corresponding to the vth basic time unit, represents the average traffic flow data of a candidate period, represents the traffic flow deviation corresponding to the vth basic time unit, Represents the square of the traffic flow deviation corresponding to the vth basic time unit.

[0136] Finally, for the total value of traffic flow deviation obtained by each division method, K candidate time periods corresponding to the division method that satisfies the minimum total value of traffic flow deviation are selected as K target candidate time periods.

[0137] For example, set N=6, K=4, and in the fourth iteration, the six basic time units are divided into four candidate time periods in three ways:

[0138] The first division method is Figure 6As shown, the first three basic time units among the six basic time units are divided into the first three candidate time periods; and the other basic time units among the N basic time units (ie, the three basic time units) are taken as the last candidate time period, so that a total of four candidate time periods are obtained.

[0139] In the fourth iteration, the total deviation of the traffic flow corresponding to the first three candidate time periods is known. The total deviation of the traffic flow corresponding to the first three candidate time periods is set to 70. The last candidate time period includes three basic time units, namely the fourth basic time unit to the sixth basic time unit. The target traffic flow data corresponding to each of the three basic time units are and According to formula 1, calculate the average traffic flow data of the last candidate period The traffic flow deviations corresponding to the three basic time units are: and The squares of traffic flow deviations corresponding to the three basic time units are: and Therefore, the sum of squares of traffic flow deviations corresponding to the last candidate period is Finally, the total value of the traffic flow deviation corresponding to the four candidate time periods obtained by the first division method is 70+50=120.

[0140] The second division method is Figure 7 As shown, the first four basic time units among the six basic time units are divided into the first three candidate time periods; and the other basic time units among the six basic time units (ie, two basic time units) are taken as the last candidate time period, so that a total of four candidate time periods are obtained.

[0141] The total value of the traffic flow deviation of the four candidate time periods obtained by the second division method is calculated as the total value of the traffic flow deviation corresponding to the second division method. The specific calculation method is similar to the above method and will not be repeated here.

[0142] The third division method is Figure 8 As shown, the first five basic time units among the six basic time units are divided into the first three candidate time periods; and the other basic time units among the six basic time units (ie, one basic time unit) are taken as the last candidate time period, so that a total of four candidate time periods are obtained.

[0143] The total value of the traffic flow deviation of the four candidate time periods obtained by the third division method is calculated as the total value of the traffic flow deviation corresponding to the third division method. The specific calculation method is similar to the above method and will not be repeated here.

[0144] Assuming that the total value of the traffic flow deviation corresponding to the third division method is the smallest, the four candidate time periods corresponding to the third division method are used as the four target candidate time periods.

[0145] In an embodiment of the present application, the preset time period is first divided into N basic time units based on the target time interval, and the target traffic flow data of the target traffic position in the N basic time units are obtained. Then, the N basic time units are divided based on the target traffic flow data of the N basic time units in an iterative manner until the iteration stop condition is met, and the output K target candidate time periods are used as K traffic control time periods. Since the iterative method is used in the present application to divide the traffic control time periods for each basic time unit, the candidate time periods corresponding to the division method with the smallest total value of traffic flow deviation are selected as the final traffic control time periods. The similarity between at least one basic time unit included in a traffic control time period is relatively large, and the similarity between different basic time units included in different traffic control time periods is relatively small. Therefore, the traffic control time period division method in the present application makes the inter-class gap and the intra-class gap of each traffic control time period obtained the largest. Finally, according to each traffic control time period obtained, a corresponding street light signal control plan is formulated to further improve the level of refined control at the traffic intersection.

[0146] Optionally, in the above step S202, the i-th iteration process, where i=1, includes the following steps:

[0147] Set the initial value of M to 1.

[0148] Step 0: Use a division method to divide the first M basic time units of the N basic time units into one candidate time period to obtain a division result. The division result includes one candidate time period, and the candidate time period includes M basic time period units. Determine the minimum total vehicle flow deviation value corresponding to the division method.

[0149] Set M=M+1, and determine whether M is less than or equal to N. If so, repeat the above step zero; otherwise, enter the i+1th iteration process.

[0150] Optionally, in the above step S202, the i-th iteration process, where 2<=i<=K, includes the following steps:

[0151] Set the initial value of i to 2 and the initial value of M to i.

[0152] Step 1: Use M-i+1 division methods to divide the first M basic time units among N basic time units to obtain M-i+1 division results, where each division result includes i candidate time periods, each candidate time period includes at least one basic time unit, and M is greater than or equal to i.

[0153] Step 2: Based on the N minimum total values ​​of vehicle flow deviations obtained during the i-1th iteration, determine the minimum total value of vehicle flow deviations in the M-i+1 division methods during the i-th iteration.

[0154] Set M=M+1, and determine whether M is less than or equal to N. If so, repeat steps 1 and 2, otherwise enter the i+1th iteration process.

[0155] Optionally, in the above step 1, for the i-th iteration, the first M basic time units in the N basic time units are divided using M-i+1 division methods to obtain M-i+1 division results, which specifically includes the following execution steps: Fig. 9 As shown:

[0156] Step S901, setting the initial value of j to i-1.

[0157] Step S902: divide the first j basic time units among the M basic time units into first i-1 candidate time periods, and take the other basic time units among the M basic time units as the last candidate time period.

[0158] Step S903, set j=j+1.

[0159] Step S904, determine whether j is less than or equal to M-1, if so, execute the above step S902, otherwise end the division.

[0160] Optionally, in the above step 2, for the i-th iteration, based on the N minimum total values ​​of vehicle flow deviations obtained during the i-1-th iteration, the minimum total value of vehicle flow deviations in M-i+1 division methods during the i-th iteration is determined, specifically including the following execution steps:

[0161] First, based on the N minimum total traffic flow deviation values ​​obtained in the i-1th iteration, determine the total traffic flow deviation values ​​corresponding to each of the M-i+1 division methods in the i-th iteration. Then, from the obtained M-i+1 total traffic flow deviation values, determine the minimum total traffic flow deviation value in the M-i+1 division methods.

[0162] Specifically, Fig.10 As shown, for M-i+1 partitioning methods, perform the following steps respectively:

[0163] Step S1001, for a division method, based on the N minimum total values ​​of vehicle flow deviations obtained in the i-1th iteration process, determine the total value of vehicle flow deviations corresponding to the first i-1 candidate time periods obtained by using a division method.

[0164] Step S1002: Determine the square sum of the traffic flow deviations of the last candidate time period based on the average traffic flow data of the last candidate time period.

[0165] Specifically, firstly, based on the target traffic flow data corresponding to at least one basic time unit in the last candidate time period, the average traffic flow data of the last candidate time period is determined. Then, based on the target traffic flow data corresponding to at least one basic time unit in the last candidate time period and the average traffic flow data, the square of the traffic flow deviation corresponding to at least one basic time unit is determined. Then, the square of the traffic flow deviation corresponding to at least one basic time unit is added to obtain the sum of the square of the traffic flow deviation of the last candidate time period.

[0166] Step S1003, based on the total values ​​of traffic flow deviations corresponding to the first i-1 candidate time periods and the sum of squares of traffic flow deviations of the last candidate time period, determine the total value of traffic flow deviations corresponding to a division method.

[0167] Specifically, the total value of the traffic flow deviation corresponding to the first i-1 candidate time periods and the sum of the squares of the traffic flow deviation of the last candidate time period are added together, and the result obtained is used as the total value of the traffic flow deviation corresponding to a division method.

[0168] In this application, an iterative method is adopted to divide N basic time units based on the target traffic flow data of N basic time units until the iteration stop condition is met, and the output K target candidate time periods are used as K traffic control time periods. Fig.11 As shown in the figure, the K optimal division positions corresponding to the K target candidate time periods are set to be p1, p2, ..., p k-1 、p k , where p k = N, the 1st basic time unit to the p1th basic time unit is regarded as a target candidate time period, the p1+1th basic time unit to the p2th basic time unit is regarded as a target candidate time period, ..., the pth basic time unit k-1 +1 base time unit to pth k A basic time unit is taken as a target candidate period.

[0169] The above division process is expressed by recursive formula (2):

[0170]

[0171]

[0172] …

[0173]

[0174]

[0175] Among them, Min L (N, K) represents the minimum total deviation of vehicle flow when N basic time units are divided into K candidate time periods. k-1 ,K-1) means to convert the previous p k-1 The total value of the minimum traffic flow deviation corresponding to the K-1 candidate time periods divided into basic time units, Represents a candidate time period (including the pth k-1 +1 base time unit to pth k The square sum of traffic flow deviations corresponding to basic time units) is Min L(p k-2 ,K-2) means to convert the previous p k-2 The total value of the minimum traffic flow deviation corresponding to the K-2 candidate time periods divided into basic time units, Represents a candidate time period (including the pth k-2 +1 base time unit to pth k-1 Min L(p2,2) represents the minimum total traffic flow deviation when the first p2 basic time units are divided into 2 candidate time periods, and Min L(p1,1) represents the minimum total traffic flow deviation when the first p1 basic time units are divided into 1 candidate time period. represents the sum of squares of traffic flow deviations corresponding to a candidate time period (including the p1+1th basic time unit to the p2th basic time unit), It represents the sum of squares of traffic flow deviations corresponding to a candidate time period (including the 1st basic time unit to the p1th basic time unit).

[0176] For example, set N = 6, K = 3, and perform the following steps when performing the i = 1th iteration, such as Fig.12 As shown:

[0177] When M=1, a division method is adopted to divide the first basic time unit of the six basic time units into one candidate time period to obtain a division result. When there is only one basic time unit in the candidate time period, the square sum of the traffic flow deviation of the candidate time period is determined to be 0 through calculation. The square sum of the traffic flow deviation of the candidate time period is used as the minimum total traffic flow deviation corresponding to this division method.

[0178] Therefore, the first basic time unit is divided into one candidate time period, and the corresponding minimum total value of vehicle flow deviation is d11=0.

[0179] When M=2, a division method is adopted to divide the first two basic time units of the six basic time units into a candidate time period to obtain a division result. Based on the target traffic flow data corresponding to each of the two basic time units in the candidate time period, the average traffic flow data of the candidate time period is determined. Based on the target traffic flow data corresponding to each of the two basic time units in the candidate time period and the average traffic flow data, the square of the traffic flow deviation corresponding to each of the two basic time units is determined. Then, the square of the traffic flow deviation corresponding to each of the two basic time units is added to obtain the sum of the square of the traffic flow deviation of the candidate time period d12. The sum of the square of the traffic flow deviation of the candidate time period d12 is used as the minimum total value of the traffic flow deviation corresponding to this division method.

[0180] Therefore, the first two basic time units are divided into one candidate period, and the corresponding minimum total traffic flow deviation value is d12.

[0181] When M=3, a division method is adopted to divide the first three basic time units of the six basic time units into a candidate time period to obtain a division result. The same method is adopted to calculate the minimum total value of vehicle flow deviation corresponding to the division method. The specific calculation process is not repeated here.

[0182] Finally, the first three basic time units are divided into one candidate period, and the corresponding minimum total traffic flow deviation value is d13.

[0183] When M=4, a division method is adopted to divide the first 4 basic time units of the 6 basic time units into a candidate time period to obtain a division result. The same method is adopted to calculate the minimum total value of vehicle flow deviation corresponding to the division method. The specific calculation process is not repeated here.

[0184] Finally, the first four basic time units are divided into one candidate period, and the corresponding minimum total traffic flow deviation value is d14.

[0185] When M=5, a division method is adopted to divide the first 5 basic time units of the 6 basic time units into a candidate time period to obtain a division result. The same method is adopted to calculate the minimum total value of vehicle flow deviation corresponding to the division method. The specific calculation process is not repeated here.

[0186] Finally, the first five basic time units are divided into one candidate period, and the corresponding minimum total traffic flow deviation value is d15.

[0187] When M=6, a division method is adopted to divide the first 6 basic time units of the 6 basic time units into a candidate time period to obtain a division result. The same method is adopted to calculate the minimum total value of vehicle flow deviation corresponding to the division method. The specific calculation process is not repeated here.

[0188] Finally, the first six basic time units are divided into one candidate period, and the corresponding minimum total traffic flow deviation value is d16.

[0189] When performing the i=2th iteration, the following steps are performed:

[0190] When M = 2, Fig.13 As shown, a division method is adopted to divide the first two basic time units of the six basic time units into two candidate time periods to obtain a division result.

[0191] Specifically, the first basic time unit of the two basic time units is divided into the first candidate time period, and the other basic time units of the two basic time units are taken as the last candidate time period.

[0192] Based on d11 of the six minimum traffic flow deviation total values ​​obtained in the first iteration, the total traffic flow deviation value corresponding to the first candidate period is determined as d11. Based on the average traffic flow data of the last candidate period, the sum of squares of traffic flow deviations of the last candidate period is determined. The total traffic flow deviation value d11 corresponding to the first candidate period is added to the sum of squares of traffic flow deviations of the last candidate period, and the result is obtained as the total traffic flow deviation value d22 corresponding to the division method.

[0193] Since when M=2, there is only one way to divide the first two basic time units into two candidate time periods. Therefore, the total traffic flow deviation value d22 corresponding to this division method is the minimum total traffic flow deviation value. Finally, when the first two basic time units are divided into two candidate time periods, the corresponding minimum total traffic flow deviation value is d22.

[0194] When M = 3, Fig.14 As shown, two division methods are used to divide the first three basic time units among the six basic time units into two candidate time periods, and two division results are obtained.

[0195] Specifically, in the first division method, the first basic time unit among the three basic time units is divided into the first candidate time period, and the other basic time units among the three basic time units are divided into the last candidate time period.

[0196] Based on d11 of the six minimum traffic flow deviation total values ​​obtained in the first iteration, the total traffic flow deviation value corresponding to the first candidate period is determined as d11. Based on the average traffic flow data of the last candidate period, the sum of squares of traffic flow deviations of the last candidate period is determined. The total traffic flow deviation value d11 corresponding to the first candidate period is added to the sum of squares of traffic flow deviations of the last candidate period, and the result is used as the total traffic flow deviation value corresponding to the first division method.

[0197] The second division method is to divide the first two basic time units among the three basic time units into the first candidate time period, and divide the other basic time units among the three basic time units into the last candidate time period.

[0198] Based on d12 of the six minimum traffic flow deviation total values ​​obtained in the first iteration, the total traffic flow deviation value corresponding to the first candidate period is determined as d12. Based on the average traffic flow data of the last candidate period, the sum of squares of traffic flow deviations of the last candidate period is determined. The total traffic flow deviation value d12 corresponding to the first candidate period is added to the sum of squares of traffic flow deviations of the last candidate period, and the result is used as the total traffic flow deviation value corresponding to the second division method.

[0199] Since when M=3, the first three basic time units are divided into two candidate time periods, and there are two ways of division. The total traffic flow deviation value corresponding to the first division method is set to 1, and the total traffic flow deviation value corresponding to the second division method is set to 2. The total traffic flow deviation value corresponding to the first division method is less than the total traffic flow deviation value corresponding to the second division method. Therefore, the total traffic flow deviation value corresponding to the first division method is the minimum traffic flow deviation total value d23. Finally, the first three basic time units are divided into two candidate time periods, and the corresponding minimum traffic flow deviation total value is d23.

[0200] When M = 4, Fig.15 As shown, three division methods are used to divide the first four basic time units of the six basic time units into two candidate time periods, and three division results are obtained.

[0201] Specifically, in the first division method, the first basic time unit among the four basic time units is divided into the first candidate time period, and the other basic time units among the four basic time units are divided into the last candidate time period.

[0202] In the second division method, the first two basic time units among the four basic time units are divided into the first candidate time period, and the other basic time units among the four basic time units are divided into the last candidate time period.

[0203] In a third division method, the first three basic time units among the four basic time units are divided into the first candidate time period, and the other basic time units among the four basic time units are divided into the last candidate time period.

[0204] When M=4, the first 4 basic time units are divided into 2 candidate time periods in three ways. The method of determining the minimum total value of vehicle flow deviation is similar to the above process and will not be described in detail here.

[0205] The total traffic flow deviation value corresponding to the first division method is set to 2, the total traffic flow deviation value corresponding to the second division method is set to 2, and the total traffic flow deviation value corresponding to the third division method is set to 1. Since the total traffic flow deviation value corresponding to the third division method is the smallest, the total traffic flow deviation value corresponding to the third division method is the minimum total traffic flow deviation value d24.

[0206] Finally, the first four basic time units are divided into two candidate time periods, and the corresponding minimum total traffic flow deviation value is d24.

[0207] When M = 5, Fig.16 As shown, four division methods are used to divide the first five basic time units among the six basic time units into two candidate time periods, and four division results are obtained.

[0208] Specifically, in the first division method, the first basic time unit among the five basic time units is divided into the first candidate time period, and the other basic time units among the five basic time units are divided into the last candidate time period.

[0209] In the second division method, the first two basic time units among the five basic time units are divided into the first candidate time period, and the other basic time units among the five basic time units are divided into the last candidate time period.

[0210] In a third division method, the first three basic time units among the five basic time units are divided into the first candidate time period, and the other basic time units among the five basic time units are divided into the last candidate time period.

[0211] The fourth division method is to divide the first four basic time units among the five basic time units into the first candidate time period, and divide the other basic time units among the five basic time units into the last candidate time period.

[0212] When M=5, the first five basic time units are divided into two candidate time periods, and there are four division methods. The method of determining the minimum total value of vehicle flow deviation is similar to the above process and will not be described in detail here.

[0213] The total traffic flow deviation value corresponding to the first division method is set to 2, the total traffic flow deviation value corresponding to the second division method is set to 1, the total traffic flow deviation value corresponding to the third division method is set to 2, and the total traffic flow deviation value corresponding to the fourth division method is set to 3. Since the total traffic flow deviation value corresponding to the second division method is the smallest, the total traffic flow deviation value corresponding to the second division method is the minimum total traffic flow deviation value d25.

[0214] Finally, the first five basic time units are divided into two candidate time periods, and the corresponding minimum total traffic flow deviation value is d25.

[0215] When M = 6, Fig.17 As shown, five division methods are used to divide the first six basic time units among the six basic time units into candidate time periods, and five division results are obtained.

[0216] Specifically, in the first division method, the first basic time unit among the 6 basic time units is divided into the first candidate time period, and the other basic time units among the 6 basic time units are divided into the last candidate time period.

[0217] In the second division method, the first two basic time units among the six basic time units are divided into the first candidate time period, and the other basic time units among the six basic time units are divided into the last candidate time period.

[0218] In a third division method, the first three basic time units among the six basic time units are divided into the first candidate time period, and the other basic time units among the six basic time units are divided into the last candidate time period.

[0219] The fourth division method is to divide the first four basic time units among the six basic time units into the first candidate time period, and divide the other basic time units among the six basic time units into the last candidate time period.

[0220] In a fifth division method, the first five basic time units among the six basic time units are divided into the first candidate time period, and the other basic time units among the six basic time units are divided into the last candidate time period.

[0221] When M=6, the first 6 basic time units are divided into 2 candidate time periods, and there are five ways of division. The method of determining the minimum total value of vehicle flow deviation is similar to the above process and will not be described here.

[0222] Set the total traffic flow deviation value corresponding to the first division method to 5, the total traffic flow deviation value corresponding to the second division method to 2, the total traffic flow deviation value corresponding to the third division method to 4, the total traffic flow deviation value corresponding to the fourth division method to 3, and the total traffic flow deviation value corresponding to the fifth division method to 3. Since the total traffic flow deviation value corresponding to the second division method is the smallest, the total traffic flow deviation value corresponding to the second division method is the minimum total traffic flow deviation value d26.

[0223] Finally, the first 6 basic time units are divided into 2 candidate time periods, and the corresponding minimum total traffic flow deviation value is d26.

[0224] When performing the i=3rd iteration, the following steps are performed:

[0225] When M = 3, Fig.18 As shown, a division method is adopted to divide the first three basic time units among the six basic time units into three candidate time periods to obtain a division result.

[0226] Specifically, the first two basic time units among the three basic time units are divided into the first two candidate time periods, and the other basic time units among the three basic time units are taken as the last candidate time period.

[0227] Based on d22 of the six minimum traffic flow deviation total values ​​obtained in the second iteration, the total traffic flow deviation value corresponding to the first two candidate time periods is determined as d22. Based on the average traffic flow data of the last candidate time period, the sum of squares of traffic flow deviations of the last candidate time period is determined. The total traffic flow deviation value d22 corresponding to the first two candidate time periods is added to the sum of squares of traffic flow deviations of the last candidate time period, and the result obtained is used as the total traffic flow deviation value d33 corresponding to the first division method.

[0228] Since when M=3, there is only one way to divide the first three basic time units into three candidate time periods. Therefore, the total traffic flow deviation value d33 corresponding to this division method is the minimum total traffic flow deviation value. Finally, when the first three basic time units are divided into three candidate time periods, the corresponding minimum total traffic flow deviation value is d33.

[0229] When M = 4, Fig.19 As shown, two division methods are used to divide the first four basic time units of the six basic time units into three candidate time periods, and two division results are obtained.

[0230] Specifically, in the first division method, the first two basic time units among the four basic time units are divided into the first two candidate time periods, and the other basic time units among the four basic time units are used as the last candidate time period.

[0231] Based on d22 of the six minimum traffic flow deviation total values ​​obtained in the second iteration, the total traffic flow deviation value corresponding to the first two candidate time periods is determined as d22. Based on the average traffic flow data of the last candidate time period, the sum of squares of traffic flow deviations of the last candidate time period is determined. The total traffic flow deviation value d22 corresponding to the first candidate time period is added to the sum of squares of traffic flow deviations of the last candidate time period, and the result obtained is used as the total traffic flow deviation value corresponding to the first division method.

[0232] The second division method is to divide the first three basic time units among the four basic time units into the first two candidate time periods, and to divide the other basic time units among the four basic time units into the last candidate time period.

[0233] Based on d23 of the six minimum traffic flow deviation total values ​​obtained in the second iteration, the total traffic flow deviation value corresponding to the first two candidate time periods is determined as d23. Based on the average traffic flow data of the last candidate time period, the sum of squares of traffic flow deviations of the last candidate time period is determined. The total traffic flow deviation value d23 corresponding to the first two candidate time periods is added to the sum of squares of traffic flow deviations of the last candidate time period, and the result obtained is used as the total traffic flow deviation value corresponding to the second division method.

[0234] Since M=4, the first 4 basic time units are divided into 3 candidate time periods in two ways. The total traffic flow deviation value corresponding to the first division method is set to 2, and the total traffic flow deviation value corresponding to the second division method is set to 4. The total traffic flow deviation value corresponding to the first division method is less than the total traffic flow deviation value corresponding to the second division method. Therefore, the total traffic flow deviation value corresponding to the first division method is the minimum traffic flow deviation total value d34. Finally, the first 4 basic time units are divided into 3 candidate time periods, and the corresponding minimum traffic flow deviation total value is d34.

[0235] When M = 5, Fig. 20 As shown, three division methods are used to divide the first five basic time units out of six basic time units into three candidate time periods, and three division results are obtained.

[0236] Specifically, in the first division method, the first two basic time units among the five basic time units are divided into the first two candidate time periods, and the other basic time units among the five basic time units are used as the last candidate time period.

[0237] Based on d22 of the six minimum traffic flow deviation total values ​​obtained in the second iteration, the total traffic flow deviation value corresponding to the first two candidate time periods is determined as d22. Based on the average traffic flow data of the last candidate time period, the sum of squares of traffic flow deviations of the last candidate time period is determined. The total traffic flow deviation value d22 corresponding to the first candidate time period is added to the sum of squares of traffic flow deviations of the last candidate time period, and the result obtained is used as the total traffic flow deviation value corresponding to the first division method.

[0238] The second division method is to divide the first three basic time units among the five basic time units into the first two candidate time periods, and to divide the other basic time units among the five basic time units into the last candidate time period.

[0239] Based on d23 of the six minimum traffic flow deviation total values ​​obtained in the second iteration, the total traffic flow deviation value corresponding to the first two candidate time periods is determined as d23. Based on the average traffic flow data of the last candidate time period, the sum of squares of traffic flow deviations of the last candidate time period is determined. The total traffic flow deviation value d23 corresponding to the first two candidate time periods is added to the sum of squares of traffic flow deviations of the last candidate time period, and the result obtained is used as the total traffic flow deviation value corresponding to the second division method.

[0240] In a third division method, the first four basic time units among the five basic time units are divided into the first two candidate time periods, and the other basic time units among the five basic time units are used as the last candidate time period.

[0241] Based on d24 of the six minimum traffic flow deviation values ​​obtained in the second iteration, the total traffic flow deviation value corresponding to the first two candidate time periods is determined as d24. Based on the average traffic flow data of the last candidate time period, the sum of squares of traffic flow deviations of the last candidate time period is determined. The total traffic flow deviation value d24 corresponding to the first two candidate time periods is added to the sum of squares of traffic flow deviations of the last candidate time period, and the result obtained is used as the total traffic flow deviation value corresponding to the third division method.

[0242] Since M=5, the first five basic time units are divided into three candidate time periods, and there are three ways of division. The total traffic flow deviation value corresponding to the first division method is set to 6, the total traffic flow deviation value corresponding to the second division method is set to 5, and the total traffic flow deviation value corresponding to the third division method is set to 4. Since the total traffic flow deviation value corresponding to the third division method is the smallest, the total traffic flow deviation value corresponding to the third division method is the minimum traffic flow deviation total value d35. Finally, the first five basic time units are divided into three candidate time periods, and the corresponding minimum traffic flow deviation total value is d35.

[0243] When M = 6, Fig.21As shown, four division methods are used to divide the first six basic time units of the six basic time units into three candidate time periods, and four division results are obtained.

[0244] Specifically, in the first division method, the first two basic time units among the six basic time units are divided into the first two candidate time periods, and the other basic time units among the six basic time units are used as the last candidate time period.

[0245] Based on d22 of the six minimum traffic flow deviation total values ​​obtained in the second iteration, the total traffic flow deviation value corresponding to the first two candidate time periods is determined as d22. Based on the average traffic flow data of the last candidate time period, the sum of squares of traffic flow deviations of the last candidate time period is determined. The total traffic flow deviation value d22 corresponding to the first candidate time period is added to the sum of squares of traffic flow deviations of the last candidate time period, and the result obtained is used as the total traffic flow deviation value corresponding to the first division method.

[0246] The second division method is to divide the first three basic time units among the six basic time units into the first two candidate time periods, and to divide the other basic time units among the six basic time units into the last candidate time period.

[0247] Based on d23 of the six minimum traffic flow deviation total values ​​obtained in the second iteration, the total traffic flow deviation value corresponding to the first two candidate time periods is determined as d23. Based on the average traffic flow data of the last candidate time period, the sum of squares of traffic flow deviations of the last candidate time period is determined. The total traffic flow deviation value d23 corresponding to the first two candidate time periods is added to the sum of squares of traffic flow deviations of the last candidate time period, and the result obtained is used as the total traffic flow deviation value corresponding to the second division method.

[0248] In a third division method, the first four basic time units among the six basic time units are divided into the first two candidate time periods, and the other basic time units among the six basic time units are used as the last candidate time period.

[0249] Based on d24 of the six minimum traffic flow deviation values ​​obtained in the second iteration, the total traffic flow deviation value corresponding to the first two candidate time periods is determined as d24. Based on the average traffic flow data of the last candidate time period, the sum of squares of traffic flow deviations of the last candidate time period is determined. The total traffic flow deviation value d24 corresponding to the first two candidate time periods is added to the sum of squares of traffic flow deviations of the last candidate time period, and the result obtained is used as the total traffic flow deviation value corresponding to the third division method.

[0250] The fourth division method is to divide the first five basic time units among the six basic time units into the first two candidate time periods, and to divide the other basic time units among the six basic time units into the last candidate time period.

[0251] Based on d25 of the six minimum traffic flow deviation total values ​​obtained in the second iteration, the total traffic flow deviation value corresponding to the first two candidate time periods is determined as d25. Based on the average traffic flow data of the last candidate time period, the sum of squares of traffic flow deviations of the last candidate time period is determined. The total traffic flow deviation value d25 corresponding to the first two candidate time periods is added to the sum of squares of traffic flow deviations of the last candidate time period, and the result is used as the total traffic flow deviation value corresponding to the fourth division method.

[0252] Since M=6, the first 6 basic time units are divided into 3 candidate time periods, and there are four ways of division. The total traffic flow deviation value corresponding to the first division method is set to 9, the total traffic flow deviation value corresponding to the second division method is set to 8, the total traffic flow deviation value corresponding to the third division method is set to 7, and the total traffic flow deviation value corresponding to the fourth division method is set to 8. Since the total traffic flow deviation value corresponding to the third division method is the smallest, the total traffic flow deviation value corresponding to the third division method is the minimum traffic flow deviation total value d36. Finally, the first 6 basic time units are divided into 3 candidate time periods, and the corresponding minimum traffic flow deviation total value is d36.

[0253] At this time, the six basic time units are divided into three candidate time periods, and the corresponding minimum total value of vehicle flow deviation is d36, and the iteration stops.

[0254] According to the above iterative process, based on Fig.12 The corresponding division method when M=3 is: Fig.15 The third division method in Fig.21 The third division method in determines that the six basic time units are divided into three candidate time periods. The specific division method is as follows: Fig. 22 shown. Fig. 22 The method of dividing the six basic time units into three candidate time periods has the smallest total value of traffic flow deviation.

[0255] In the embodiment of the present application, an iterative method is used to divide each basic time unit into traffic control periods, and the candidate period corresponding to the division method with the smallest total value of vehicle flow deviation is selected as each traffic control period finally determined. The similarity between at least one basic time unit included in a traffic control period is relatively large, and the similarity between different basic time units included in different traffic control periods is relatively small. Therefore, the traffic control period division method in the present application makes the inter-class gap and the intra-class gap of each traffic control period obtained the largest. Finally, according to each traffic control period obtained, a corresponding street light signal control plan is formulated to further improve the level of refined control at traffic intersections.

[0256] Through the recursive solution method, the minimum total traffic flow deviation corresponding to the division of N basic time units into K candidate time periods is finally determined, and the division method corresponding to the minimum total traffic flow deviation is also determined. Due to the use of the recursive solution method, even when there are many basic time units, the results can still be obtained quickly, which improves the efficiency of traffic control period division.

[0257] Optionally, the number K of target candidate time periods in step S202 above can be set in the following two ways:

[0258] In the first method, K is the number of custom time periods. K can be any value between 1 and N.

[0259] In the second method, K is the optimal number of time periods.

[0260] Specifically, Fig.23 As shown, the steps to determine the optimal number of time periods are as follows:

[0261] Step S2301, set the initial value of variable num to 1.

[0262] Step S2302, using an iterative method, based on the target traffic flow data of N basic time units, divide the N basic time units into num candidate time periods, obtain N-num+1 division methods, and determine the minimum traffic flow deviation total value as L1.

[0263] Step S2303, set num=num+1.

[0264] Step S2304, determine whether num is less than or equal to N, if so, execute step S2305; otherwise, end.

[0265] Step S2305, using an iterative method, based on the target traffic flow data of N basic time units, divide the N basic time units into num candidate time periods, obtain N-num+1 division methods, and determine the minimum traffic flow deviation total value as L2.

[0266] Step S2306, determine whether L2 / L1 is less than a threshold, if so, execute step S2308; otherwise, execute step S2307.

[0267] Step S2307, set L1=L2.

[0268] Step S2308, num is used as the optimal time period number and ends.

[0269] In the embodiment of the present application, two methods of setting the number K of target candidate time periods are provided. Setting K by customizing the number of time periods is relatively simple and convenient. Setting K by the optimal number of time periods can effectively determine the optimal number of target candidate time periods.

[0270] In order to better explain the embodiment of the present application, the following describes a traffic control period division method provided by the embodiment of the present application in combination with a specific implementation scenario, and the traffic control period division system performs the following steps, such as: Fig.24 shown.

[0271] Step S2401: divide the preset time period into N basic time units based on the target time interval.

[0272] Step S2402, obtaining the original traffic flow data of the target traffic location in N basic time units.

[0273] Step S2403, cleaning the original vehicle flow data for abnormal data and missing data to obtain target vehicle flow data.

[0274] Step S2404, determine whether K is set by a custom time period number, if so, execute step S2405; otherwise, execute step S2406.

[0275] Step S2405, input the custom time period number as K.

[0276] Step S2406, set the initial value of the variable num to 1.

[0277] Step S2407, using an iterative method, based on the target traffic flow data of N basic time units, divide the N basic time units into num candidate time periods, obtain N-num+1 division methods, and determine the minimum traffic flow deviation total value as L1.

[0278] Step S2408, set num=num+1.

[0279] Step S2409, determine whether num is less than or equal to N, if so, execute step S2410; otherwise, end.

[0280] Step S2410, using an iterative method, based on the target traffic flow data of N basic time units, divide the N basic time units into num candidate time periods, obtain N-num+1 division methods, and determine the minimum traffic flow deviation total value as L2.

[0281] Step S2411, determine whether L2 / L1 is less than a threshold, if so, execute step S2413; otherwise, execute step S2412.

[0282] Step S2412, set L1=L2.

[0283] Step S2413, num is used as the optimal time period number.

[0284] Step S2414, taking the optimal number of time periods as K.

[0285] Step S2415, using an iterative method, based on the target vehicle flow data of the N basic time units, divide the N basic time units until the iteration stop condition is met, and use the output K target candidate time periods as K traffic control time periods, and end.

[0286] In the embodiment of the present application, an iterative method is used to divide each basic time unit into traffic control periods, and the candidate period corresponding to the division method with the smallest total value of vehicle flow deviation is selected as each traffic control period finally determined. The similarity between at least one basic time unit included in a traffic control period is relatively large, and the similarity between different basic time units included in different traffic control periods is relatively small. Therefore, the traffic control period division method in the present application makes the inter-class gap and the intra-class gap of each traffic control period obtained the largest. Finally, according to each traffic control period obtained, a corresponding street light signal control plan is formulated to further improve the level of refined control at traffic intersections.

[0287] Through the recursive solution method, the minimum total traffic flow deviation corresponding to the division of N basic time units into K candidate time periods is finally determined, and the division method corresponding to the minimum total traffic flow deviation is also determined. Due to the use of the recursive solution method, even when there are many basic time units, the results can still be obtained quickly, which improves the efficiency of traffic control period division.

[0288] At the same time, the present application provides two methods for setting the number K of target candidate time periods. Setting K by customizing the number of time periods is relatively simple and convenient. Setting K by the optimal number of time periods can effectively determine the optimal number of target candidate time periods.

[0289] Based on the same technical concept, the embodiment of the present application provides a traffic control period division device, such as Fig.25As shown, the traffic control period division device 2500 includes:

[0290] An acquisition module 2501 is used to divide a preset time period into N basic time units based on a target time interval, and acquire target vehicle flow data of a target traffic position in the N basic time units respectively;

[0291] The iteration module 2502 is used to divide the N basic time units based on the target vehicle flow data of the N basic time units in an iterative manner until the iteration stop condition is met, and the output K target candidate time periods are used as K traffic control time periods, wherein the iteration stop condition is: divide the N basic time units into K candidate time periods, and obtain N-K+1 division methods for dividing the N basic time units into K candidate time periods, and select K candidate time periods corresponding to the division method that satisfies the minimum total vehicle flow deviation value as K target candidate time periods, N is greater than or equal to K, N is greater than or equal to 1, and K is greater than or equal to 1.

[0292] Optionally, the acquisition module 2501 is specifically used for:

[0293] Obtaining the original traffic flow data of the target traffic location in the N basic time units respectively;

[0294] The original vehicle flow data is cleaned of abnormal data and missing data to obtain the target vehicle flow data.

[0295] Optionally, the acquisition module 2501 is specifically used for:

[0296] determining a plurality of traffic phases corresponding to the target traffic position;

[0297] For the N basic time units, the following steps are performed respectively:

[0298] Collecting phase vehicle flow data corresponding to each of the multiple traffic phases at the target traffic location within a basic time unit respectively;

[0299] The phase vehicle flow data corresponding to each of the multiple traffic phases is used as the original vehicle flow data of the one basic time unit.

[0300] Optionally, the iteration module 2502 is specifically used for:

[0301] For the i-th iteration process, where 2<=i<=K, the following steps are included:

[0302] Step 1: Use M-i+1 division methods to divide the first M basic time units of the N basic time units to obtain M-i+1 division results, wherein each division result includes i candidate time periods, each candidate time period includes at least one basic time unit, and M is greater than or equal to i;

[0303] Step 2: Based on the N minimum total values ​​of vehicle flow deviations obtained in the i-1th iteration, determine the minimum total value of vehicle flow deviations in the M-i+1 division methods in the i-th iteration;

[0304] Set M=M+1, and determine whether M is less than or equal to N. If so, repeat step 1 and step 2, otherwise enter the i+1th iteration process.

[0305] Optionally, the iteration module 2502 is specifically used for:

[0306] Divide the first j basic time units among the M basic time units into the first i-1 candidate time periods, and take the other basic time units among the M basic time units as the last candidate time period, where i-1<=j<=M-1;

[0307] Set j=j+1, and determine whether j is less than or equal to M-1. If so, repeat the above steps, otherwise terminate the division.

[0308] Optionally, the iteration module 2502 is specifically used for:

[0309] Based on the N minimum total values ​​of vehicle flow deviation obtained in the i-1th iteration process, determine the total value of vehicle flow deviation corresponding to each of the M-i+1 division modes;

[0310] From the obtained M-i+1 total values ​​of vehicle flow deviation, determine the minimum total value of vehicle flow deviation in the M-i+1 division methods.

[0311] Optionally, the iteration module 2502 is specifically used for:

[0312] For the M-i+1 partitioning methods, perform the following steps respectively:

[0313] For one division method, based on the N minimum total values ​​of vehicle flow deviations obtained in the i-1th iteration process, determine the total value of vehicle flow deviations corresponding to the first i-1 candidate time periods obtained by using the one division method;

[0314] Determine the sum of squares of traffic flow deviations of the last candidate time period based on the average traffic flow data of the last candidate time period;

[0315] Based on the total values ​​of vehicle flow deviations corresponding to the first i-1 candidate time periods and the sum of squares of vehicle flow deviations of the last candidate time period, the total value of vehicle flow deviations corresponding to the one division method is determined.

[0316] Optionally, the iteration module 2502 is specifically used for:

[0317] Determine the square of the vehicle flow deviation corresponding to each of the at least one basic time unit based on the target vehicle flow data corresponding to each of the at least one basic time unit in the last candidate time period and the average vehicle flow data;

[0318] The squares of the vehicle flow deviations corresponding to each of the at least one basic time unit are added together to obtain the sum of the squares of the vehicle flow deviations of the last candidate time period.

[0319] Based on the same technical concept, the embodiment of the present application provides a computer device, which may be a terminal or a server, such as Fig.26 As shown, it includes at least one processor 2601 and a memory 2602 connected to the at least one processor. The specific connection medium between the processor 2601 and the memory 2602 is not limited in the embodiment of the present application. Fig.26 For example, the processor 2601 and the memory 2602 are connected via a bus. The bus can be divided into an address bus, a data bus, a control bus, etc.

[0320] In the embodiment of the present application, the memory 2602 stores instructions that can be executed by at least one processor 2601. The at least one processor 2601 can execute the steps included in the above-mentioned traffic control period division method by executing the instructions stored in the memory 2602.

[0321] The processor 2601 is the control center of the computer device, and can use various interfaces and lines to connect various parts of the computer device, and divide the traffic control period by running or executing instructions stored in the memory 2602 and calling data stored in the memory 2602. Optionally, the processor 2601 may include one or more processing units, and the processor 2601 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 2601. In some embodiments, the processor 2601 and the memory 2602 may be implemented on the same chip, and in some embodiments, they may also be implemented separately on independent chips.

[0322] Processor 2601 can be a general-purpose processor, such as a central processing unit (CPU), a digital signal processor, an application-specific integrated circuit (ASIC), a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, and can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. A general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware processor for execution, or can be executed by a combination of hardware and software modules in the processor.

[0323] Memory 2602, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer executable programs and modules. Memory 2602 may include at least one type of storage medium, such as flash memory, hard disk, multimedia card, card-type memory, random access memory (Random Access Memory, RAM), static random access memory (Static Random Access Memory, SRAM), programmable read-only memory (Programmable Read Only Memory, PROM), read-only memory (Read Only Memory, ROM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), magnetic memory, disk, optical disk, etc. Memory 2602 is any other medium that can be used to carry or store a desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 2602 in the embodiment of the present application can also be a circuit or any other device that can realize a storage function, for storing program instructions and / or data.

[0324] Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium storing a computer program executable by a computer device. When the program runs on the computer device, the computer device executes the steps of the above-mentioned traffic control period division method.

[0325] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0326] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0327] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0328] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0329] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for dividing traffic control time periods, characterized in that: include: Based on the target time interval, the preset time period is divided into N basic time units, and the target traffic flow data of the target traffic position in the N basic time units are obtained respectively; In an iterative manner, based on the target vehicle flow data of the N basic time units, the N basic time units are divided until an iteration stop condition is met, and the output K target candidate time periods are used as K traffic control time periods, wherein the iteration stop condition is: the N basic time units are divided into K candidate time periods, and N-K+1 division methods for dividing the N basic time units into K candidate time periods are obtained, and K candidate time periods corresponding to the division method that satisfies the minimum total value of vehicle flow deviation are selected as K target candidate time periods, N is greater than or equal to K, N is greater than or equal to 1, and K is greater than or equal to 1; For the i-th iteration process, where 2<=i<=K, the following steps are included: Step 1: Use M-i+1 division methods to divide the first M basic time units of the N basic time units to obtain M-i+1 division results, wherein each division result includes i candidate time periods, each candidate time period includes at least one basic time unit, and M is greater than or equal to i; Step 2: Based on the N minimum total values ​​of vehicle flow deviations obtained in the i-1th iteration, determine the minimum total value of vehicle flow deviations in the M-i+1 division methods in the i-th iteration; Set M=M+1, and determine whether M is less than or equal to N. If so, repeat step 1 and step 2, otherwise enter the i+1th iteration process; The method adopts M-i+1 division methods to divide the first M basic time units among the N basic time units to obtain M-i+1 division results, including: dividing the first j basic time units among the M basic time units into the first i-1 candidate time periods, and taking the other basic time units among the M basic time units as the last candidate time period, wherein i-1<=j<=M-1; setting j=j+1, and determining whether j is less than or equal to M-1, if so, repeating the above steps, otherwise terminating the division.

2. The method according to claim 1, characterized in that The step of obtaining target traffic flow data of the target traffic position at the N basic time units includes: Obtaining the original traffic flow data of the target traffic location in the N basic time units respectively; The original vehicle flow data is cleaned of abnormal data and missing data to obtain the target vehicle flow data.

3. The method according to claim 2, characterized in that The obtaining of the original traffic flow data of the target traffic position in the N basic time units includes: determining a plurality of traffic phases corresponding to the target traffic position; For the N basic time units, the following steps are performed respectively: Collecting phase vehicle flow data corresponding to each of the multiple traffic phases at the target traffic location within a basic time unit respectively; The phase vehicle flow data corresponding to each of the multiple traffic phases is used as the original vehicle flow data of the one basic time unit.

4. The method according to claim 1, characterized in that The method of determining the minimum total value of vehicle flow deviation in the M-i+1 division modes during the i-th iteration based on the N minimum total values ​​of vehicle flow deviation obtained during the i-1th iteration includes: Based on the N minimum total values ​​of vehicle flow deviation obtained in the i-1th iteration process, determine the total value of vehicle flow deviation corresponding to each of the M-i+1 division modes; From the obtained M-i+1 total values ​​of vehicle flow deviation, determine the minimum total value of vehicle flow deviation in the M-i+1 division methods.

5. The method according to claim 4, characterized in that The method of determining the total vehicle flow deviation values ​​corresponding to each of the M-i+1 division modes based on the N minimum vehicle flow deviation total values ​​obtained in the i-1th iteration process includes: For the M-i+1 partitioning methods, perform the following steps respectively: For one division method, based on the N minimum total values ​​of vehicle flow deviations obtained in the i-1th iteration process, determine the total value of vehicle flow deviations corresponding to the first i-1 candidate time periods obtained by using the one division method; Determine the sum of squares of traffic flow deviations of the last candidate time period based on the average traffic flow data of the last candidate time period; Based on the total values ​​of vehicle flow deviations corresponding to the first i-1 candidate time periods and the sum of squares of vehicle flow deviations of the last candidate time period, the total value of vehicle flow deviations corresponding to the one division method is determined.

6. The method according to claim 5, characterized in that The determining the sum of square deviations of the traffic flow of the last candidate time period based on the average traffic flow data of the last candidate time period comprises: Determine the square of the vehicle flow deviation corresponding to each of the at least one basic time unit based on the target vehicle flow data corresponding to each of the at least one basic time unit in the last candidate time period and the average vehicle flow data; The squares of the vehicle flow deviations corresponding to each of the at least one basic time unit are added together to obtain the sum of the squares of the vehicle flow deviations of the last candidate time period.

7. A traffic control time division device, characterized in that: include: An acquisition module, used to divide the preset time period into N basic time units based on the target time interval, and acquire the target traffic flow data of the target traffic position in the N basic time units respectively; An iteration module, for dividing the N basic time units in an iterative manner based on the target vehicle flow data of the N basic time units, until an iteration stop condition is satisfied, and outputting K target candidate time periods as K traffic control time periods, wherein the iteration stop condition is: dividing the N basic time units into K candidate time periods, and obtaining N-K+1 division methods for dividing the N basic time units into K candidate time periods, and selecting K candidate time periods corresponding to the division method that satisfies the minimum total value of vehicle flow deviation as K target candidate time periods, N is greater than or equal to K, N is greater than or equal to 1, and K is greater than or equal to 1; For the i-th iteration process, where 2<=i<=K, the following steps are included: Step 1: Use M-i+1 division methods to divide the first M basic time units of the N basic time units to obtain M-i+1 division results, wherein each division result includes i candidate time periods, each candidate time period includes at least one basic time unit, and M is greater than or equal to i; Step 2: Based on the N minimum total values ​​of vehicle flow deviations obtained in the i-1th iteration, determine the minimum total value of vehicle flow deviations in the M-i+1 division methods in the i-th iteration; Set M=M+1, and determine whether M is less than or equal to N. If so, repeat step 1 and step 2, otherwise enter the i+1th iteration process; The method adopts M-i+1 division methods to divide the first M basic time units among the N basic time units to obtain M-i+1 division results, including: dividing the first j basic time units among the M basic time units into the first i-1 candidate time periods, and taking the other basic time units among the M basic time units as the last candidate time period, wherein i-1<=j<=M-1; setting j=j+1, and determining whether j is less than or equal to M-1, if so, repeating the above steps, otherwise terminating the division.

8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of any one of the methods of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that: It stores a computer program executable by a computer device. When the program is run on the computer device, the computer device executes the steps of any method described in claims 1 to 6.

Images