Vehicle position division method, device and storage medium

Abstract

The present invention relates to the technical field of big data analysis of intelligent transportation network, and specifically to a vehicle position division method, device and storage medium. The method comprises the following steps: obtaining the degree of centering of all vehicles, taking the vehicle with the highest degree of centering as the center, screening and dividing the first vehicle cluster from all vehicles; obtaining the degree of centering of the remaining vehicles, taking the position of the vehicle with the highest degree of centering among the remaining vehicles as the center, screening and dividing the next vehicle cluster, and so on, until the screening and division are completed. It can solve the problem in the prior art that the initial centroid is randomly scattered, which is very blind, resulting in poor final clustering effect, a large gap with the user's psychological expectations, or the centroid is located in a blank position.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis of intelligent transportation network, and in particular to a vehicle position division method, device and storage medium. Background Art

[0002] With the rise of intelligent driving and unmanned driving, the management and monitoring of vehicles are becoming increasingly important. Intelligent driving network navigation solves the problems of where we are, where we are going, which lane on which road, etc. Autonomous driving is to complete driving behaviors such as lane keeping, overtaking and merging, stopping at red lights and going at green lights, and light and horn interaction under the control of the intelligent system; manual intervention means that the driver responds to the actual road conditions under a series of prompts from the intelligent system.

[0003] Whether it is intelligent driving, autonomous driving, or manual intervention, regulators are required to effectively monitor and manage all target vehicles. In order to facilitate management, the locations of all vehicles need to be divided to facilitate monitoring and management; dividing all target vehicles can also facilitate the formulation of different supervision strategies.

[0004] In the prior art, clustering algorithms such as k-means and DBSCAN are usually used to randomly scatter the positions of the initial cluster centroids. However, the initial centroids are obtained by random scattering, which is very blind, and the final clustering effect is not good, which is far from the user's psychological expectations. In addition, the final centroid position of the clustering result is most likely not a certain car in the cluster (that is, a certain data point), but a blank position in the middle of all the data points in this category. In mobile car networking applications, it is hoped that the centroid of the cluster is the position of a specific car, and the vehicle serving as the centroid is the best forwarder (of the mobile car networking) of all vehicles in this category. If the final centroid position is located in a blank position in the middle of all the data points in this category, it will make it inconvenient to execute certain operation instructions. Summary of the invention

[0005] In view of the defects existing in the prior art, the purpose of the present invention is to provide a vehicle position division method, device and storage medium, which can solve the problem in the prior art that the initial centroid is obtained by randomly scattering, which is very blind, resulting in poor final clustering effect, which is very different from the user's psychological expectations, or the centroid is located in a blank position.

[0006] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0007] The present invention provides a vehicle position division method, comprising the following steps:

[0008] Obtain the centrality of all vehicles, and select and divide the first vehicle cluster from all vehicles with the vehicle having the largest centrality as the center;

[0009] The degree of centrality of the remaining vehicles is obtained, and the position of the vehicle with the largest degree of centrality among the remaining vehicles is used as the center to screen and divide the next vehicle cluster, and so on, until the screening and division are completed.

[0010] In some optional solutions, the obtaining of the centrality of all vehicles and screening out a first vehicle cluster from all vehicles with the vehicle having the largest centrality as the center includes:

[0011] Calculate the centering degree of all vehicles based on the distance between all vehicles and the centering degree formula;

[0012] Compare the degree of centering of all vehicles and find the vehicle with the greatest degree of centering;

[0013] Taking the vehicle with the highest degree of centrality as the center, the first vehicle cluster is screened and divided from all vehicles based on the recursive deletion algorithm.

[0014] In some alternative solutions, according to the centering degree formula Determine the centering degree of the i-th vehicle den i , where n is the number of all vehicles, j = 1…,…n, and j≠i, and t(i,j) is the distance between the i-th vehicle and the j-th vehicle.

[0015] In some alternative solutions, according to the centering degree formula Determine the centering degree of the i-th vehicle den i , where n is the number of all vehicles, j = 1…,…n, and j≠i, t(i,j) is the distance between the i-th vehicle and the j-th vehicle, C is a normal number, and e is a natural base.

[0016] In some optional schemes, according to the centering degree formula den i =a1×X1+a2×X2+……+a m ×X m , determine the centering degree of the i-th vehicle den i , a m is the number of vehicles between the m-1th and mth concentric circles divided around the i-th vehicle, X m The weight of the degree of centrality of vehicles in the area between the m-1th and mth concentric circles divided by the i-th vehicle as the center.

[0017] In some optional solutions, after calculating the centering degree of all vehicles according to the distance between all vehicles and the centering degree formula, the centering degree of all vehicles is calculated according to the formula The degree of centering of the i-th vehicle is den i The correction is made as the final centering degree of the i-th vehicle, where N is the number of areas evenly divided in 360-degree directions around the i-th vehicle, and M is the number of areas where vehicles exist in the evenly divided areas.

[0018] In some optional solutions, the method of selecting and dividing the first vehicle cluster from all vehicles based on a recursive deletion algorithm with the vehicle having the greatest degree of centralization as the center includes the following steps:

[0019] Taking the position of the vehicle with the largest degree of centralization as the center, select and divide the vehicles within the set radius from all vehicles;

[0020] Taking each vehicle position in the vehicle set as the center, the next vehicle set within the set radius is selected from the remaining vehicles, and so on, until no new vehicle is selected from the newly divided vehicle set;

[0021] The vehicle with the largest degree of centrality and the set of all vehicles are taken as the first vehicle cluster.

[0022] In some optional solutions, when screening and dividing each vehicle cluster, the vehicle with the greatest degree of centrality is the centroid of the vehicle cluster.

[0023] On the other hand, the present invention also provides a computer device, comprising a processor, a memory, and calculations and programs stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of a vehicle position division method as described above are implemented.

[0024] In yet another aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by the processor, the steps of the above-mentioned vehicle position division method are implemented.

[0025] Compared with the prior art, the advantages of the present invention are: first, among all the vehicles, a vehicle cluster is selected through the vehicle with the largest degree of centering, and the data of the vehicle cluster is screened and divided from the data of all the vehicles; then the degree of centering of the remaining vehicles is obtained, and the position of the vehicle with the largest degree of centering among the remaining vehicles is used as the center to screen and divide the next vehicle cluster, and so on, until the screening and division is completed. In this way, it can be ensured that after a vehicle with a high degree of centering is selected as a candidate centroid, its neighboring vehicles, and its neighboring vehicles (recursive neighbors), etc. are no longer selected as candidate centroids. And it is ensured that the centroid of each vehicle cluster is a vehicle, and will not appear in a blank position, which facilitates the execution of operation instructions, especially the execution of forwarding instructions. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application, 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 is a flow chart of a vehicle position division method according to an embodiment of the present invention;

[0028] Figure 2 is a flow chart of step S1 in an embodiment of the present invention;

[0029] Figure 3 A schematic diagram of calculating the degree of centering in an embodiment of the present invention;

[0030] Figure 4 is a schematic diagram of another method for calculating the degree of centering in an embodiment of the present invention;

[0031] Figure 5 The figure is a schematic block diagram of the structure of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0033] The embodiments of the present invention are further described in detail below with reference to the accompanying drawings.

[0034] like Figure 1 As shown, the present invention provides a vehicle position division method, characterized in that it includes the following steps:

[0035] S1: Obtain the centrality of all vehicles, and select and divide the first vehicle cluster from all vehicles with the vehicle having the largest centrality as the center.

[0036] In this solution, the first vehicle cluster is selected and divided from all vehicles by taking the vehicle with the greatest degree of centralization as the center, so that the center (center of mass) in the first vehicle cluster must be a vehicle, and there will be no blank area between vehicles.

[0037] The degree of centering of a vehicle is used to measure the number of nearby vehicles and their proximity to the vehicle. The more nearby vehicles there are and the closer they are to the vehicle, the greater the degree of centering of the vehicle.

[0038] like Figure 2 As shown, step S1 specifically includes the following steps:

[0039] Step S11: Calculate the centering degree of all vehicles according to the distance between all vehicles and the centering degree formula.

[0040] In this solution, three methods of calculating the degree of centering are provided.

[0041] The first calculation method is:

[0042] First, obtain the distance t(i,j) between every two vehicles among all vehicles, where i and j represent the vehicle numbers respectively, and t(i,j) represents the distance between the i-th vehicle and the j-th vehicle.

[0043] According to the centering formula Determine the centering degree of the i-th vehicle den i , where n is the number of all vehicles, i, j = 1…,…n, and j≠i, and t(i,j) is the distance between the i-th vehicle and the j-th vehicle.

[0044] like Figure 3 As shown, taking 5 vehicles as an example, a specific implementation example of the calculation method is given below:

[0045] The dotted circle represents the range (radius r) centered on vehicle 2, and the blue circle represents the range (radius r) centered on vehicle 5. The density of vehicle 2 is greater than that of vehicle 5, because although the number of other vehicles in their ranges is the same, the distance from vehicle 2 to its other vehicles (1, 3, 4, 5) is generally smaller than the distance from vehicle 5 to its other vehicles (1, 2, 3, 4), so the density is greater.

[0046] Use t (i,j) represents the distance between the i-th vehicle and the j-th vehicle, and f(i,j)=1 / t(i,j): the density of vehicle No. 2 (den v2 )=(1 / t(2,1))*1+(1 / t(2,3))*1+(1 / t(2,4))*1+(1 / t(2,5))*1, where the multiplication is 1, 1 represents the number of vehicles (vnum).

[0047] Similarly, the density of vehicle 5 is v5 =(1 / t(5,1))*1+(1 / t(5,2))*1+(1 / t(5,3))*1+(1 / t(5,4))*1

[0048] The second calculation method is:

[0049] In this calculation method, when calculating the degree of centering of vehicle i using a degree of centering calculation method with different weighted weight functions, the weight f of vehicle j near i is calculated according to the formula f(i, j) = C*e^-t(i, j).

[0050] Then all vehicles, according to the center degree formula Determine the centering degree of the i-th vehicle den i , where n is the number of all vehicles, i, j = 1…,…n, and j≠i, t(i,j) is the distance between the i-th vehicle and the j-th vehicle, C is a normal number, and e is a natural base. In this example, in order to amplify the function value and avoid memory overflow, C is taken as a normal number, such as C = 10.

[0051] The third calculation method is:

[0052] In this calculation method, when calculating the degree of centering for a vehicle, the area is first divided according to different radii with the vehicle as the center, and different weights are set for vehicles in different areas. The closer the neighboring vehicles in the ring are to the vehicle, the greater their contribution to the degree of centering of the given vehicle, and the greater their weight. For example, with the vehicle as the center, a circle with a first radius is drawn to form a first ring, and the weight of the vehicles in the first ring is X1. With the vehicle as the center, a circle with a second radius is drawn to form a second ring, and the second radius is greater than the first radius. The weight of the vehicles between the first and second rings is X2, and so on, after all the vehicles are divided.

[0053] According to the center degree formula den i =a1×X1+a2×X2+……+a m ×X m , determine the centering degree of the i-th vehicle den i , a m is the number of vehicles between the m-1th and mth concentric circles divided around the i-th vehicle, X m The weight of the degree of centrality of the vehicle in the area between the m-1th and mth concentric circles divided by the i-th vehicle as the center. In this example, X1>X2>……X m , and a1+a2+……+a m =n, where n is the number of all vehicles.

[0054] like Figure 4 As shown, taking 5 vehicles as an example, a specific implementation example of the calculation method is given below:

[0055] Assume that the inner ring weight is X1, the middle ring weight is X2, and the outer ring weight is X3, X1>X2>X3;

[0056] The degree of centrality of the first vehicle is den1 = 2*X1+1*X2+1*X3, because there are two neighboring vehicles on the inner ring, one on the middle ring and one on the outer ring.

[0057] In some optional embodiments, when calculating the degree of centering of a given ith vehicle, intuitively, when there are the same number and the same distance of neighboring vehicles, the more completely the neighboring vehicles "surround" the ith vehicle, the greater the degree of centering of the ith vehicle should be; if there are the same number and the same distance of neighboring vehicles, but the ith vehicle is not completely surrounded by them and there are gaps, the degree of centering of the ith vehicle should be reduced accordingly.

[0058] Therefore, the present invention provides a quadrant reduction ratio coefficient method including but not limited to the following to correct the degree of centering obtained by the above three methods of calculating the degree of centering as the final degree of centering:

[0059] First, calculate the centering degree den of the given i-th vehicle according to the above three methods of calculating the centering degree i Then divide the 360 ​​degrees around the i-th vehicle into N directional intervals (each interval has the same angle). Suppose there are vehicles that are close to A in M ​​intervals, and there are no vehicles that are close to A in NM intervals.

[0060] According to the formula The degree of centering of the i-th vehicle is den i The correction is made as the final centering degree of the i-th vehicle, where N is the number of areas evenly divided in 360-degree directions around the i-th vehicle, and M is the number of areas where vehicles exist in the evenly divided areas.

[0061] Step S12: Compare the centering degrees of all vehicles to obtain the vehicle with the greatest centering degree.

[0062] In this example, after calculating the degree of centering of all vehicles by the three methods of calculating the degree of centering mentioned above, the degree of centering of all vehicles can be corrected by the quadrant reduction proportional coefficient method mentioned in the above scheme, and then compared as the final degree of centering to obtain the vehicle with the greatest degree of centering.

[0063] In addition, all vehicles may be arranged in a list from largest to smallest according to the degree of centering (when calculating each vehicle, directly compare and arrange them before placing them in a data list), and the vehicle with the greatest degree of centering may be directly selected when in use.

[0064] Step S13: Taking the vehicle with the highest degree of centralization as the center, based on the recursive deletion algorithm, a first vehicle cluster is screened and divided from all vehicles.

[0065] Intuitively, the more centered a vehicle is, the more suitable it is to be the centroid. However, we cannot directly take the first k vehicles with the highest degree of centeredness as the centroid, because they may be closely connected to each other and belong to the same intuitive cluster.

[0066] In order to remove vehicles with high centrality that are not in the same cluster, after selecting a vehicle with high centrality as a candidate centroid, its neighboring vehicles and its neighboring vehicles (recursive neighbors) are no longer selected as candidate centroids. This ensures that each candidate centroid is the only candidate in its cluster and that each candidate centroid belongs to a different cluster.

[0067] In this example, a vehicle cluster is first selected from all vehicles through the vehicle with the highest degree of centrality, and the data of the vehicle cluster is deleted from the data of all vehicles. This ensures that after a vehicle with a high degree of centrality is selected as a candidate centroid, its neighboring vehicles, and its neighboring neighbor vehicles (recursive neighbors), etc. are no longer selected as candidate centroids.

[0068] Step 13 specifically includes the following steps:

[0069] A: Taking the position of the most centered vehicle as the center, select the vehicles within the set radius from all vehicles.

[0070] In this example, the vehicle M with the greatest degree of centralization is determined, and all vehicles whose direct distance from M is less than r are screened out and divided as M1 (M1 is a vehicle set, representing all vehicles whose direct distance from M is less than r).

[0071] B: Taking the position of each vehicle in the vehicle set as the center, the next vehicle set within the set radius is selected from the remaining vehicles, and so on, until no new vehicles are selected from the newly divided vehicle set.

[0072] In this example, taking the vehicle positions of all vehicles in the vehicle set M1 as the center, all vehicles with a distance less than r are screened out from the remaining vehicles as M2 (M2 is also a vehicle set, representing all vehicles with a direct distance less than r from any vehicle in M1), and so on to M3, M4...Mi, until no new vehicles are screened out in a certain Mi.

[0073] C: The vehicle with the largest degree of centrality and the set of all vehicles are taken as the first vehicle cluster.

[0074] In this embodiment, M, M1, M2 ... Mi are taken as the first vehicle cluster after the union. The vehicle data of the first vehicle cluster is deleted from all vehicles, and the next vehicle cluster is selected from the remaining vehicles. In this way, it is possible to avoid selecting a high-centrality vehicle as a candidate centroid and then selecting its neighboring vehicles, and its neighboring neighboring vehicles (recursive neighbors), etc. as candidate centroids.

[0075] S2: Obtain the degree of centrality of the remaining vehicles, and use the position of the vehicle with the largest degree of centrality among the remaining vehicles as the center to screen and divide the next vehicle cluster, and so on, until the screening and division are completed.

[0076] In this example, since the first vehicle cluster has been selected from all vehicles, it is necessary to re-determine the vehicle with the highest degree of centrality among the remaining vehicles.

[0077] Therefore, it is necessary to first calculate the degree of centrality of all remaining vehicles according to the distance between the remaining vehicles and the centrality formula; compare the degrees of centrality of all remaining vehicles to obtain the vehicle with the largest degree of centrality among all remaining vehicles, and screen and divide the next vehicle cluster with the position of the vehicle with the largest degree of centrality among the remaining vehicles as the center, and so on, until all vehicles are screened and divided.

[0078] In addition, in order to avoid too many individual vehicles forming a single vehicle cluster, when setting the value of r, you can choose to set an appropriate r, and appropriately screen and divide all vehicles into reasonable clusters to avoid individual vehicles forming a single cluster. Of course, in actual use, other factors should also be considered to give a reasonable division method.

[0079] In some optional embodiments, when screening and dividing each vehicle cluster, the vehicle with the greatest degree of centrality is the centroid of the vehicle cluster.

[0080] The more centered a vehicle is, the more suitable it is for the centroid. However, we cannot directly take the first k vehicles with the highest degree of centeredness as the centroid, because they may be closely connected to each other and belong to the same intuitive cluster.

[0081] In this example, a vehicle cluster is first selected from all vehicles through the vehicle with the highest degree of centrality, and the data of the vehicle cluster is deleted from the data of all vehicles. This ensures that after a vehicle with a high degree of centrality is selected as a candidate centroid, its neighboring vehicles, and its neighboring neighbor vehicles (recursive neighbors), etc. are no longer selected as candidate centroids.

[0082] It should be noted that technicians in the relevant field can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described device and each module and unit can refer to the corresponding process in the aforementioned vehicle position division method embodiment, and will not be repeated here.

[0083] The apparatus provided in the above embodiment may be implemented in the form of a computer program. The computer program may be Figure 5 Runs on the computer device shown.

[0084] See also Figure 5 , Figure 5 A schematic block diagram of the structure of a computer device provided in an embodiment of the present application. The computer device may be a terminal.

[0085] like Figure 5 As shown, the computer device includes a processor, a memory, and a network interface connected via a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.

[0086] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any vehicle position division method.

[0087] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0088] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any vehicle position division method.

[0089] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0090] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0091] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

[0092] S1: Obtain the centrality of all vehicles, and select and divide the first vehicle cluster from all vehicles with the vehicle having the largest centrality as the center.

[0093] Step S1 specifically includes the following steps:

[0094] Step S11: Calculate the centering degree of all vehicles according to the distance between all vehicles and the centering degree formula.

[0095] In this solution, three methods of calculating the degree of centering are provided.

[0096] The first calculation method is:

[0097] First, obtain the distance t(i,j) between every two vehicles among all vehicles, where i and j represent the vehicle numbers respectively, and t(i,j) represents the distance between the i-th vehicle and the j-th vehicle.

[0098] According to the centering formula Determine the centering degree of the i-th vehicle den i , where n is the number of all vehicles, j = 1…,…n, and j≠i, and t(i,j) is the distance between the i-th vehicle and the j-th vehicle.

[0099] The second calculation method is:

[0100] According to the centering formula Determine the centering degree of the i-th vehicle den i, where n is the number of all vehicles, j = 1…,…n, and j≠i, t(i,j) is the distance between the i-th vehicle and the j-th vehicle, C is a normal number, and e is a natural base. In this example, in order to amplify the function value and avoid memory overflow, C is taken as a normal number, such as C = 10.

[0101] The third calculation method is:

[0102] First, the area is divided according to different radii with the vehicle as the center. Different weights are set for vehicles in different areas. The closer the neighboring vehicles in the ring are to the vehicle, the greater their contribution to the centrality of the given vehicle, and the greater their weight. For example, with the vehicle as the center, a circle with a first radius is drawn to form a first ring, and the weight of the vehicles in the first ring is X1. With the vehicle as the center, a circle with a second radius is drawn to form a second ring, and the second radius is greater than the first radius. The weight of the vehicles between the first and second rings is X2, and so on, after all the vehicles are divided.

[0103] According to the center degree formula den i =a1×X1+a2×X2+……+a m ×X m , determine the centering degree of the i-th vehicle den i , a m is the number of vehicles between the m-1th and mth concentric circles divided around the i-th vehicle, X m The weight of the degree of centrality of the vehicle in the area between the m-1th and mth concentric circles divided by the i-th vehicle as the center. In this example, X1>X2>……X m , and a1+a2+……+a m =n, where n is the number of all vehicles.

[0104] In some optional embodiments,

[0105] First, calculate the centering degree den of the given i-th vehicle according to the above three methods of calculating the centering degree i Then divide the 360 ​​degrees around the i-th vehicle into N directional intervals (each interval has the same angle). Suppose there are vehicles that are close to A in M ​​intervals, and there are no vehicles that are close to A in NM intervals.

[0106] According to the formula The degree of centering of the i-th vehicle is den i The correction is made as the final centering degree of the i-th vehicle, where N is the number of evenly divided areas in 360-degree directions around the i-th vehicle, and M is the number of vehicles in the evenly divided areas.

[0107] Step S12: Compare the centering degrees of all vehicles to obtain the vehicle with the greatest centering degree.

[0108] After calculating the degree of centering of all vehicles using the three methods of calculating the degree of centering mentioned above, the degree of centering of all vehicles can be corrected using the quadrant reduction proportional coefficient method mentioned in the above scheme and compared as the final degree of centering to obtain the vehicle with the greatest degree of centering.

[0109] Step S13: Taking the vehicle with the highest degree of centralization as the center, based on the recursive deletion algorithm, a first vehicle cluster is screened and divided from all vehicles.

[0110] Step 13 specifically includes the following steps:

[0111] A: Taking the position of the most centered vehicle as the center, select the vehicles within the set radius from all vehicles.

[0112] In this example, the vehicle M with the greatest degree of centralization is determined, and all vehicles whose direct distance from M is less than r are screened out and divided as M1 (M1 is a vehicle set, representing all vehicles whose direct distance from M is less than r).

[0113] B: Taking the position of each vehicle in the vehicle set as the center, the next vehicle set within the set radius is selected from the remaining vehicles, and so on, until no new vehicles are selected from the newly divided vehicle set.

[0114] In this example, taking the vehicle positions of all vehicles in the vehicle set M1 as the center, all vehicles with a distance less than r are screened out from the remaining vehicles as M2 (M2 is also a vehicle set, representing all vehicles with a direct distance less than r from any vehicle in M1), and so on to M3, M4...Mi, until no new vehicles are screened out in a certain Mi.

[0115] C: The vehicle with the largest degree of centrality and the set of all vehicles are taken as the first vehicle cluster.

[0116] In this embodiment, M, M1, M2 ... Mi are taken as the first vehicle cluster after the union. The vehicle data of the first vehicle cluster is deleted from all vehicles, and the next vehicle cluster is selected from the remaining vehicles. In this way, it is possible to avoid selecting a high-centrality vehicle as a candidate centroid and then selecting its neighboring vehicles, and its neighboring neighboring vehicles (recursive neighbors), etc. as candidate centroids.

[0117] S2: Obtain the degree of centrality of the remaining vehicles, and use the position of the vehicle with the largest degree of centrality among the remaining vehicles as the center to screen and divide the next vehicle cluster, and so on, until the screening and division are completed.

[0118] In this example, it is necessary to first calculate the degree of centrality of all remaining vehicles according to the distance between the remaining vehicles and the centrality formula; compare the degrees of centrality of all remaining vehicles to obtain the vehicle with the greatest degree of centrality among all remaining vehicles, and screen and divide the next vehicle cluster with the position of the vehicle with the greatest degree of centrality among the remaining vehicles as the center, and so on, until all vehicles are screened and divided.

[0119] In addition, in order to avoid too many individual vehicles forming a single vehicle cluster, when setting the value of r, you can choose to set an appropriate r, and appropriately screen and divide all vehicles into reasonable clusters to avoid individual vehicles forming a single cluster. Of course, in actual use, other factors should also be considered to give a reasonable division method.

[0120] In some optional embodiments, when screening and dividing each vehicle cluster, the vehicle with the greatest degree of centrality is the centroid of the vehicle cluster.

[0121] In this example, a vehicle cluster is first selected from all vehicles through the vehicle with the highest degree of centrality, and the data of the vehicle cluster is deleted from the data of all vehicles. This ensures that after a vehicle with a high degree of centrality is selected as a candidate centroid, its neighboring vehicles, and its neighboring neighbor vehicles (recursive neighbors), etc. are no longer selected as candidate centroids.

[0122] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions. The method implemented when the program instructions are executed can refer to the various embodiments of the vehicle position division method of the present application.

[0123] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc., equipped on the computer device.

[0124] It should be noted that, in this application, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0125] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.

Claims

1. A vehicle position division method, characterized in that: The following steps are involved: Obtain the centrality of all vehicles, and select and divide the first vehicle cluster from all vehicles with the vehicle having the largest centrality as the center; Obtain the degree of centering of the remaining vehicles, and use the position of the vehicle with the largest degree of centering among the remaining vehicles as the center to screen and divide the next vehicle cluster, and so on, until the screening and division are completed; The obtaining of the degree of centering of all vehicles, taking the vehicle with the greatest degree of centering as the center, and screening out a first vehicle cluster from all vehicles includes: Calculate the centering degree of all vehicles based on the distance between all vehicles and the centering degree formula; Compare the degree of centering of all vehicles and find the vehicle with the greatest degree of centering; Taking the vehicle with the highest degree of centralization as the center, the first vehicle cluster is selected from all vehicles based on the recursive deletion algorithm; After calculating the centering degree of all vehicles based on the distance between all vehicles and the centering degree formula, we also use the formula The degree of centering of the i-th vehicle is den i The correction is made as the final centering degree of the i-th vehicle, where N is the number of areas evenly divided in 360-degree directions around the i-th vehicle, and M is the number of areas where vehicles exist in the evenly divided areas.

2. The vehicle position division method according to claim 1, characterized in that: According to the centering formula Determine the degree of centering of the i-th vehicle den i , where n is the number of all vehicles, j = 1…,…n, and j≠i, and t(i,j) is the distance between the i-th vehicle and the j-th vehicle.

3. The vehicle position division method according to claim 1, characterized in that: According to the centering formula Determine the degree of centering of the i-th vehicle den i , where n is the number of all vehicles, j = 1…,…n, and j≠i, t(i,j) is the distance between the i-th vehicle and the j-th vehicle, C is a normal number, and e is a natural base.

4. The vehicle position division method according to claim 1, characterized in that: According to the center degree formula den i =a1×X1+a2×X2+……+a m ×X m , determine the centering degree of the i-th vehicle den i , a m is the number of vehicles between the m-1th and mth concentric circles divided around the i-th vehicle, X m The weight of the degree of centrality of vehicles in the area between the m-1th and mth concentric circles divided by the i-th vehicle as the center.

5. The vehicle position division method according to claim 1, characterized in that: The method of taking the vehicle with the greatest degree of centralization as the center and selecting and dividing the first vehicle cluster from all vehicles based on a recursive deletion algorithm comprises the following steps: Taking the position of the vehicle with the largest degree of centralization as the center, select and divide the vehicles within the set radius from all vehicles; Taking each vehicle position in the vehicle set as the center, the next vehicle set within the set radius is selected from the remaining vehicles, and so on, until no new vehicle is selected from the newly divided vehicle set; The vehicle with the largest degree of centrality and the set of all vehicles are taken as the first vehicle cluster.

6. The vehicle position division method according to claim 1, characterized in that: When screening and dividing each vehicle cluster, the vehicle with the greatest degree of centrality is the centroid of the vehicle cluster.

7. A computer device, characterized in that: The computer device comprises a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps according to any one of claims 1 to 6 are implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps according to any one of claims 1 to 6 are implemented.

Images