Target vehicle screening method, device, equipment and medium

Abstract

The invention relates to the technical field of traffic, in particular to a target vehicle screening method and device, equipment and a medium, and the method comprises the steps: carrying out the dimension reduction processing of a plurality of initial travel feature values corresponding to each first vehicle, obtaining a target travel feature value vector corresponding to each first vehicle, clustering a plurality of target travel feature value vectors, and obtaining a target travel feature value vector corresponding to each first vehicle; the method comprises the following steps: further obtaining a preset number of initial vehicle clusters, carrying out iterative clustering on the plurality of initial vehicle clusters by adopting a self-iterative clustering model according to given parameters and a plurality of target parameters obtained based on the plurality of initial vehicle clusters to obtain a plurality of final vehicle clusters, and finally screening the plurality of final vehicle clusters according to a preset screening condition. Screening out a final vehicle cluster meeting the condition from all the final vehicle clusters, and determining each first vehicle in the screened final vehicle cluster as a target vehicle; according to the method, the vehicles with stable travel characteristics in the peak period can be comprehensively and accurately screened out, and subsequent management and planning of traffic in the area are facilitated.

Description

Technical Field

[0001] The present invention relates to the field of traffic technology, and in particular to a target vehicle screening method, device, equipment and medium. Background Art

[0002] In the context of urbanization, as the commuting distance increases, more and more people are switching from traditional commuting to private car commuting. In daily traffic flow, commuting accounts for a high proportion of peak traffic and has stable time and flow. The rapid increase in private car commuting has a great impact on peak traffic. The commuting problem not only involves everyone's travel, but also reflects the traffic management level of the entire city. Therefore, accurately screening out commuting private cars from the traffic flow can effectively discover the peak commuting traffic situation from the time and space dimensions, and is also conducive to adopting real-time and efficient control strategies. At present, when judging whether a vehicle is a commuter vehicle, its travel attributes are mainly determined based on the vehicle's registration information in the transportation department or various questionnaires, which wastes a lot of manpower and has low accuracy. Some existing technologies determine their travel attributes by tracking and investigating individual vehicles, but it is difficult to generalize to the identification of many vehicles in a city or even a larger area. Summary of the invention

[0003] The purpose of the present invention is to provide a target vehicle screening method, device, equipment and medium, which can comprehensively and accurately screen out vehicles with stable travel characteristics during peak hours, which is beneficial to the subsequent management and planning of traffic in the area.

[0004] According to a first aspect of the present invention, a target vehicle screening method is provided, comprising the following steps: The factor analysis method is used to perform dimensionality reduction processing on several initial travel characteristic values ​​in the initial travel characteristic set corresponding to each first vehicle in the given first vehicle set to obtain a target travel characteristic value vector corresponding to each first vehicle; the dimension of each target travel characteristic value vector is the dimension obtained after the dimensionality reduction processing.

[0005] According to the target travel feature value vector corresponding to each first vehicle, the first vehicle set is clustered into a preset number of initial vehicle clusters using a k-means clustering model.

[0006] According to a given maximum number of merges, an initial number of iterations, an initial split coefficient and a number of target parameters obtained based on the preset number of initial vehicle clusters, a self-iterative clustering model is used to iteratively cluster the preset number of initial vehicle clusters to obtain a number of final vehicle clusters.

[0007] According to a preset screening condition, a corresponding final vehicle cluster is screened out from a plurality of final vehicle clusters, and each first vehicle in the screened final vehicle cluster is determined as a target vehicle with a given travel characteristic.

[0008] Furthermore, the initial travel feature set corresponding to the first vehicle includes the spatial stability coefficient, peak travel frequency, total travel frequency, off-peak average travel frequency, off-peak travel frequency deviation coefficient of the first vehicle in the historical time period, and the pre-acquired stability values ​​of the starting point and the stability values ​​of the end point of the first vehicle corresponding to the preset morning peak period of the historical time period, and the pre-acquired stability values ​​of the starting point and the stability values ​​of the end point corresponding to the preset evening peak period of the historical time period.

[0009] Furthermore, the step of selecting a corresponding final vehicle cluster from a plurality of final vehicle clusters according to a preset screening condition comprises the following steps: According to the number of vehicles in each final vehicle cluster, the total number of vehicles corresponding to the final vehicle clusters is obtained.

[0010] According to the total number of vehicles and a number of initial travel characteristics corresponding to each first vehicle, the first spatial stability coefficient average value η is obtained. 1 , the average value of the first peak travel frequency F 1 , the first total travel frequency average Q 1 , the average travel frequency during the first non-peak period K 1 , the average value of the deviation coefficient of the first non-peak travel frequency θ 1 , the average stability level S of the first starting point corresponding to the preset morning peak period 1 and the average stability of the first endpoint E 1 , the average stability level S of the first starting point corresponding to the preset evening peak period 0 1 and the average stability of the first endpoint E 0 1 .

[0011] According to the number of vehicles in each final vehicle cluster and a number of initial travel characteristics corresponding to each first vehicle in each final vehicle cluster, an average value η of the second spatial stability coefficient corresponding to each final vehicle cluster is obtained. 2 , the average travel frequency of the second peak F 2 , the second total travel frequency average Q 2 , the average travel frequency during the second non-peak period K 2 , the average value of the deviation coefficient of the second non-peak travel frequency θ 2 , the average stability level S of the second starting point corresponding to the preset morning peak period 2 and the average stability of the second endpoint E2 , the average stability level S of the second starting point corresponding to the preset evening peak period 0 2 and the average stability of the second endpoint E 0 2 .

[0012] Filter out all final vehicle clusters that satisfy η 2 >η 1 、F 2 >F 1 , Q 2 >Q 1 , K 2 <K 1 ,θ 2 <θ 1 , S 2 >S 1 、E 2 >E 1 , S 0 2 >S 0 1 and E 0 2 >E 0 1 The final vehicle cluster.

[0013] Furthermore, the method obtains the stability value of the starting point of the first vehicle corresponding to the preset morning / evening peak period through the following steps: For any first vehicle in a given first vehicle set, a plurality of first travel trajectories corresponding to a preset morning / evening peak period of the first vehicle in a historical time period are obtained.

[0014] According to several first travel trajectories, several first starting point hash values ​​and several second starting point hash values ​​corresponding to the first vehicle are obtained; the first starting point hash value refers to the first geohash value corresponding to the several vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory, and the second starting point hash value refers to the second geohash value corresponding to the several vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory.

[0015] The first starting point hash values ​​with the largest number and the second largest number among the plurality of first starting point hash values ​​are respectively determined as the first target hash value and the second target hash value, and the second starting point hash value with the largest number among the plurality of second starting point hash values ​​is determined as the third target hash value.

[0016] When the first target hash value exists or the second target hash value is the same as the third target hash value, the ratio of the sum of the quantities corresponding to the first target hash value and the second target hash value to the given number of days is determined as the stability value of the starting point of the first vehicle corresponding to the preset morning / evening peak period; otherwise, the ratio of the quantity corresponding to the first target hash value to the given number of days is determined as the stability value of the starting point of the first vehicle corresponding to the preset morning / evening peak period.

[0017] Furthermore, the method obtains the stability value of the first vehicle at the destination corresponding to the preset morning / evening peak period through the following steps: According to several first travel trajectories, several first destination hash values ​​and several second destination hash values ​​corresponding to the first vehicle are obtained; the first destination hash value refers to the last geohash value corresponding to the several vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory, and the second destination hash value refers to the second to last geohash value corresponding to the several vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory.

[0018] The largest and second largest first destination hash values ​​among the plurality of first destination hash values ​​are respectively determined as the fourth target hash value and the fifth target hash value, and the largest second destination hash value among the plurality of second destination hash values ​​is determined as the sixth target hash value.

[0019] When there is a fourth target hash value or the fifth target hash value is the same as the sixth target hash value, the ratio of the sum of the quantities corresponding to the fourth target hash value and the fifth target hash value to the given number of days is determined as the stability value of the destination corresponding to the preset morning / evening peak period of the first vehicle; otherwise, the ratio of the quantity corresponding to the fourth target hash value to the given number of days is determined as the stability value of the destination corresponding to the preset morning / evening peak period of the first vehicle; the stability value of the destination corresponding to the preset evening peak period is obtained in the same way as the stability value of the destination corresponding to the preset morning peak period.

[0020] Furthermore, the target parameters include the number of clusters, the center point vector corresponding to each cluster, the initial number of samples corresponding to each cluster, the sample standard deviation threshold corresponding to each cluster and the initial shortest distance between clusters.

[0021] According to a second aspect of the present invention, there is provided a target vehicle screening device, the device comprising: The processing module is used to use the factor analysis method to perform dimensionality reduction processing on a number of initial travel characteristic values ​​in the initial travel characteristic set corresponding to each first vehicle in the given first vehicle set, so as to obtain a target travel characteristic value vector corresponding to each first vehicle; the dimension of each target travel characteristic value vector is the dimension obtained after the dimensionality reduction processing.

[0022] The first clustering module is used to cluster the first vehicle set into a preset number of initial vehicle clusters using a k-means clustering model according to the target travel feature value vector corresponding to each first vehicle.

[0023] The second clustering module is used to iteratively cluster the preset number of initial vehicle clusters using a self-iterative clustering model according to a given maximum merger number, an initial number of iterations, an initial splitting coefficient and a number of target parameters obtained based on the preset number of initial vehicle clusters to obtain a number of final vehicle clusters.

[0024] The first screening module is used to screen out a corresponding final vehicle cluster from a plurality of final vehicle clusters according to a preset screening condition, and determine each first vehicle in the screened final vehicle cluster as a target vehicle with a given travel characteristic.

[0025] Furthermore, the initial travel feature set corresponding to the first vehicle in the historical time period includes the spatial stability coefficient, peak travel frequency, total travel frequency, off-peak average travel frequency, off-peak travel frequency deviation coefficient corresponding to the first vehicle, and the pre-acquired stability values ​​of the starting point and the stability values ​​of the end point corresponding to the preset morning peak period of the historical time period, and the pre-acquired stability values ​​of the starting point and the stability values ​​of the end point corresponding to the preset evening peak period of the historical time period.

[0026] Furthermore, the first screening module includes: The first acquisition module is used to acquire the total number of vehicles corresponding to a plurality of final vehicle clusters according to the number of vehicles in each final vehicle cluster.

[0027] The second acquisition module is used to obtain the first spatial stability coefficient average value η according to the total number of vehicles and a number of initial travel characteristics corresponding to each first vehicle. 1 , the average value of the first peak travel frequency F 1 , the first total travel frequency average Q 1 , the average travel frequency during the first non-peak period K 1 , the average value of the deviation coefficient of the first non-peak travel frequency θ 1 , the average stability level S of the first starting point corresponding to the preset morning peak period 1 and the average stability of the first endpoint E 1 , the average stability level S of the first starting point corresponding to the preset evening peak period 0 1 and the average stability of the first endpoint E 0 1 .

[0028] The third acquisition module is used to obtain the second spatial stability coefficient average value η corresponding to each final vehicle cluster according to the number of vehicles in each final vehicle cluster and a number of initial travel characteristics corresponding to each first vehicle in each final vehicle cluster. 2 , the average travel frequency of the second peak F 2 , the second total travel frequency average Q 2 , the average travel frequency during the second non-peak period K 2 , the average value of the deviation coefficient of the second non-peak travel frequency θ 2 , the average stability level S of the second starting point corresponding to the preset morning peak period 2 and the average stability of the second endpoint E 2 , the average stability level S of the second starting point corresponding to the preset evening peak period 0 2 and the average stability of the second endpoint E 0 2 .

[0029] The second screening module is used to screen out the final vehicle clusters that meet η 2 >η 1 、F 2 >F 1 , Q 2 >Q 1 , K 2 <K 1 ,θ 2 <θ 1 , S 2 >S 1 、E 2 >E 1 , S 0 2 >S 0 1 and E 0 2 >E 0 1 The final vehicle cluster.

[0030] Furthermore, the processing module includes: The fourth acquisition module is used to acquire, for any first vehicle in a given first vehicle set, a plurality of first travel trajectories corresponding to a preset morning / evening peak period of the first vehicle in a historical time period.

[0031] The fifth acquisition module is used to obtain several first starting point hash values ​​and several second starting point hash values ​​corresponding to the first vehicle based on several first travel trajectories; the first starting point hash value refers to the first geohash value corresponding to the several vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory, and the second starting point hash value refers to the second geohash value corresponding to the several vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory.

[0032] The first determination module is used to determine the first starting point hash values ​​with the largest number and the second largest number of the same among the plurality of first starting point hash values ​​as the first target hash value and the second target hash value respectively, and to determine the second starting point hash value with the largest number of the same among the plurality of second starting point hash values ​​as the third target hash value.

[0033] The second determination module is used to determine the stability value of the starting point of the first vehicle corresponding to the preset morning / evening peak period by the ratio of the sum of the quantities corresponding to the first target hash value and the second target hash value to the given number of days when the first target hash value exists or the second target hash value is the same as the third target hash value; otherwise, determine the stability value of the starting point of the first vehicle corresponding to the preset morning / evening peak period by the ratio of the quantity corresponding to the first target hash value to the given number of days.

[0034] Furthermore, the processing module also includes: The sixth acquisition module is used to obtain several first destination hash values ​​and several second destination hash values ​​corresponding to the first vehicle based on several first travel trajectories; the first destination hash value refers to the last geohash value corresponding to the several vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory, and the second destination hash value refers to the second to last geohash value corresponding to the several vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory.

[0035] The third determination module is used to determine the largest and second largest first destination hash values ​​among the plurality of first destination hash values ​​as the fourth target hash value and the fifth target hash value respectively, and to determine the largest second destination hash value among the plurality of second destination hash values ​​as the sixth target hash value.

[0036] The fourth determination module is used to determine the ratio of the sum of the quantities corresponding to the fourth target hash value and the fifth target hash value to a given number of days as the stability value of the first vehicle at the preset morning / evening peak period when there is a fourth target hash value or the fifth target hash value is the same as the sixth target hash value; otherwise, determine the ratio of the quantity corresponding to the fourth target hash value to the given number of days as the stability value of the first vehicle at the preset morning / evening peak period; the stability value of the first vehicle at the preset evening peak period is obtained in the same manner as the stability value of the terminal corresponding to the preset morning peak period.

[0037] Furthermore, the target parameters include the number of clusters, the center point vector corresponding to each cluster, the initial number of samples corresponding to each cluster, the sample standard deviation threshold corresponding to each cluster and the initial shortest distance between clusters.

[0038] According to a third aspect of the present invention, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned target vehicle screening method when executing the computer program.

[0039] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned target vehicle screening method is implemented.

[0040] Compared with the prior art, the present invention has at least the following beneficial effects: When the target vehicle screening method of the present invention is implemented, firstly, a dimensionality reduction process is performed on a plurality of initial travel characteristic values ​​corresponding to each first vehicle to obtain a target travel characteristic value vector corresponding to each first vehicle. By means of the dimensionality reduction process, the parameters contained in each vector can be reduced, thereby improving the accuracy of clustering. Then, a clustering process is performed on a plurality of target travel characteristic value vectors corresponding to the first vehicle set to obtain a clustering result and further obtain a preset number of initial vehicle clusters. According to the maximum number of merges, the initial number of iterations, the initial splitting coefficient and other target parameters required by the self-iterative clustering model obtained based on the plurality of initial vehicle clusters, the self-iterative clustering model is adopted. Iterative clustering is performed on several initial vehicle clusters to obtain several final vehicle clusters. The self-iterative clustering model adds the merging and splitting operations on the clustering results on the basis of the k-means clustering model, and iterates to make the sample characteristics in each cluster more similar, thereby obtaining a more accurate classification result. Finally, according to the preset screening conditions, one or more final vehicle clusters that meet the conditions are screened out from all final vehicle clusters, and each first vehicle in the screened final vehicle clusters is determined as the target vehicle. In this way, vehicles with stable travel characteristics during peak hours can be screened out more comprehensively and accurately, which is conducive to the subsequent management and planning of traffic in the region. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0042] Figure 1 A flow chart of a target vehicle screening method provided in Embodiment 1 of the present invention; Figure 2 A flowchart of the steps of obtaining the stability value of the starting point provided in the first embodiment of the present invention; Figure 3 A flowchart of the steps of obtaining the stability value of the endpoint provided in the first embodiment of the present invention; Figure 4 A flowchart of step S400 provided in the first embodiment of the present invention; Figure 5 A schematic diagram of the structure of a target vehicle screening device provided in Embodiment 2 of the present invention; Figure 6 A schematic diagram of the structure of the processing module 100 provided in the second embodiment of the present invention; Figure 7 Another structural schematic diagram of the processing module 100 provided in the second embodiment of the present invention; Figure 8 This is a schematic diagram of the structure of the first screening module 400 provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0044] Embodiment 1 like Figure 1 As shown, this embodiment provides a target vehicle screening method, including the following steps: S100, using factor analysis to perform dimensionality reduction processing on a number of initial travel feature values ​​in an initial travel feature set corresponding to each first vehicle in a given first vehicle set, to obtain a target travel feature value vector corresponding to each first vehicle; the dimension of each target travel feature value vector is the dimension obtained after the dimensionality reduction processing.

[0045] Specifically, the first vehicle is any one of several randomly selected vehicles.

[0046] Specifically, performing dimensionality reduction processing on the initial travel characteristic values ​​refers to reducing the dimension of the vector composed of the initial travel characteristic values ​​corresponding to each first vehicle to a preset number of dimensions; for ease of understanding, the following explanation is made: When factor analysis is used for dimensionality reduction, a multidimensional vector composed of several initial travel characteristic values ​​is input into the factor analysis model, and the number of output factors can be actively set. In the present embodiment, the number of output factors is set to three, that is, the vector composed of several initial travel characteristic values ​​is reduced to three dimensions. Since the present application directly adopts the factor analysis method of the prior art, its specific implementation process will not be described in detail.

[0047] Specifically, the initial travel feature set corresponding to the first vehicle includes the spatial stability coefficient, peak travel frequency, total travel frequency, off-peak average travel frequency, off-peak travel frequency deviation coefficient of the first vehicle in the historical time period, and the pre-acquired stability values ​​of the starting point and the stability values ​​of the end point of the first vehicle corresponding to the preset morning peak period of the historical time period, and the stability values ​​of the starting point and the stability values ​​of the end point corresponding to the preset evening peak period of the historical time period; in a specific implementation, the preset morning peak period is 7:00-9:00, and the preset evening peak period is 18:00-20:00.

[0048] As described above, by using the factor analysis method to perform dimensionality reduction processing on several initial travel characteristic values ​​of the first vehicle, some linear relationships between multiple indicators can be eliminated, the dimension of the vector can be reduced, and clustering can be performed using the vector after dimensionality reduction, which can reduce the clustering complexity and thus improve the reliability of clustering.

[0049] Specifically, Figure 2 As shown, the method obtains the stability value of the starting point of the first vehicle corresponding to the preset morning / evening peak period through the following steps: S101, for any first vehicle in a given first vehicle set, obtain a number of first travel trajectories corresponding to a preset morning / evening peak period of the first vehicle in a historical time period; it can be understood that: the number of first travel trajectories corresponding to the preset morning peak period of the first vehicle in the historical time period are obtained in the same manner as the number of first travel trajectories corresponding to the preset evening peak period of the first vehicle in the historical time period.

[0050] Specifically, step S101 includes the following steps: S1011, receiving a plurality of vehicle position information reported by the GPS device of the first vehicle within a historical time period; it can be understood that: the vehicle position information refers to the latitude and longitude information of the vehicle reported in real time by the GPS device.

[0051] S1012, dividing the plurality of vehicle location information into a plurality of vehicle location information sets; the reporting time of the vehicle location information in each vehicle location information set is continuous and the reporting time interval is not greater than a preset time threshold; the time interval between each two adjacent vehicle location information sets is greater than a preset time threshold.

[0052] For better understanding, the following explanation is made: for example, the preset time threshold is 15 minutes. If the GPS device reports the vehicle location information three times consecutively at 6:50, 7:10 and 7:11 respectively, the vehicle location information reported at 6:50 will be divided into the previous vehicle location information set, and the vehicle location information reported at 7:10 and 7:11 will be divided into the latter vehicle location information set.

[0053] S1013, based on the multiple vehicle location information in each vehicle location information set, obtain the initial travel trajectory corresponding to each vehicle location information set; in a specific implementation, the GPS device usually uploads the vehicle location information every few seconds, and connects the multiple vehicle location information in the vehicle location information set in series to obtain the corresponding initial travel trajectory.

[0054] S1014, when the travel time corresponding to the initial travel trajectory overlaps with the preset morning / evening peak period, the initial travel trajectory itself is obtained as a first travel trajectory corresponding to the preset morning / evening peak period of the first vehicle in the historical time period.

[0055] As mentioned above, when obtaining the first trip trajectory corresponding to the morning / evening peak period of a vehicle within multiple days, the driving time of each first trip trajectory is first obtained, without considering the overlap between the driving time and the morning / evening peak period. As long as there is an overlap, it is determined to be the first trip trajectory corresponding to the morning / evening peak period. In this way, the different working hours of different people, the different distances between home and company, etc., which lead to inconsistent travel times, are taken into account, and thus a number of vehicles with morning / evening peak travel characteristics can be determined more comprehensively and reasonably.

[0056] S103, according to several first travel trajectories, obtain several first starting point hash values ​​and several second starting point hash values ​​corresponding to the first vehicle; the first starting point hash value refers to the first geohash value corresponding to the several vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory, and the second starting point hash value refers to the second geohash value corresponding to the several vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory; it can be understood as: the first geohash hash block and the second geohash hash block passed in the first travel trajectory; in a specific implementation, the geohash values ​​corresponding to the first hash block and the second hash block are both seven bits.

[0057] As mentioned above, by obtaining several first starting point hash values, the starting position of each trip of the first vehicle corresponding to several preset morning / evening peak periods can be known, and then whether each starting point position is the same can be known, which is conducive to determining the stability of subsequent starting points, and at the same time can provide an important reference for the screening of vehicles with morning / evening peak travel characteristics.

[0058] S105, determining the first starting point hash values ​​with the largest number and the second largest number among the plurality of first starting point hash values ​​as the first target hash value and the second target hash value respectively, and determining the second starting point hash value with the largest number among the plurality of second starting point hash values ​​as the third target hash value.

[0059] For better understanding, the following explanation is made: for example, there are a total of ten first starting point hash values, five of which represent the first area, four of which represent the second area, and one first starting point hash value represents the third area. Then the first starting point hash value corresponding to the first area is used as the first target hash value, and the first starting point hash value corresponding to the second area is used as the second target hash value.

[0060] S107, when there is a first target hash value or the second target hash value is the same as the third target hash value, the ratio of the sum of the quantities corresponding to the first target hash value and the second target hash value to the given number of days is determined as the stability value of the starting point of the first vehicle corresponding to the preset morning / evening peak period; otherwise, the ratio of the quantity corresponding to the first target hash value to the given number of days is determined as the stability value of the starting point of the first vehicle corresponding to the preset morning / evening peak period; it can be understood that: the stability value of the starting point of the first vehicle corresponding to the preset evening peak period is obtained in the same way as the stability value of the starting point corresponding to the preset morning peak period.

[0061] Specifically, the given number of days refers to the number of working days in the historical time period; in a specific implementation, the historical time period is generally selected from the past month, and the working days are Monday to Friday of each week.

[0062] In the above, according to the situation that the third target hash value is the same as the first target hash value or the second target hash value, different calculation methods of the stability values ​​of the starting points are adopted. That is, when the third target hash value is the same as the first target hash value or the second target hash value, it means that the travel trajectory is consistent. It may be that the error in reporting time of the GPS device causes the inconsistent starting point. When the third target hash value is different from the first target hash value and the second target hash value, it means that the travel trajectory is inconsistent, and thus the travel starting point is inconsistent. Therefore, through the above calculation method, the stability value of the starting point obtained is more accurate and reasonable.

[0063] Specifically, Figure 3 As shown, the method obtains the stability value of the first vehicle at the destination corresponding to the preset morning / evening peak period through the following steps: S102, based on several first travel trajectories, obtain several first destination hash values ​​and several second destination hash values ​​corresponding to the first vehicle; the first destination hash value refers to the last geohash value corresponding to the several vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory, and the second destination hash value refers to the second to last geohash value corresponding to the several vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory; in a specific implementation, the geohash values ​​corresponding to the first to last hash block and the second to last hash block are both seven digits.

[0064] As mentioned above, by obtaining several first terminal hash values, the terminal position of each trip of the first vehicle corresponding to several preset morning / evening peak periods can be known, and then whether each terminal position is the same can be known, which is conducive to determining the stability of subsequent terminal points, and at the same time can provide an important reference for the screening of vehicles with morning / evening peak travel characteristics.

[0065] S104, determining the largest and second largest first destination hash values ​​among the plurality of first destination hash values ​​as the fourth target hash value and the fifth target hash value respectively, and determining the largest second destination hash value among the plurality of second destination hash values ​​as the sixth target hash value.

[0066] S106, when there is a fourth target hash value or the fifth target hash value is the same as the sixth target hash value, the ratio of the sum of the quantities corresponding to the fourth target hash value and the fifth target hash value to the given number of days is determined as the stability value of the destination corresponding to the preset morning / evening peak period of the first vehicle; otherwise, the ratio of the quantity corresponding to the fourth target hash value to the given number of days is determined as the stability value of the destination corresponding to the preset morning / evening peak period of the first vehicle; it can be understood that: the stability value of the destination corresponding to the preset evening peak period of the first vehicle is obtained in the same way as the stability value of the destination corresponding to the preset morning peak period.

[0067] As described above, in the process of obtaining the endpoint stability value, the fourth target hash value, the fifth target hash value and the sixth target hash value are determined by reverse deduction. According to the situation that the sixth target hash value is the same as the fourth target hash value or the fifth target hash value, different methods of calculating the endpoint stability value are adopted. Similarly, the obtained endpoint stability value is more accurate and reasonable.

[0068] Specifically, the peak travel frequency corresponding to the first vehicle is the ratio of the number of working days with peak travel in the historical time period to the given number of days.

[0069] Specifically, the total travel frequency corresponding to the first vehicle is the ratio of the number of working days for travel in the historical time period to the given number of days.

[0070] Specifically, the off-peak average travel frequency P corresponding to the first vehicle meets the following conditions: P=(∑ n j=1 (a j / A j )) / n, where n is the total number of days in the historical period, a j is the number of non-peak trips on the jth day in the historical time period, A j is the total number of trips on the jth day in the historical time period.

[0071] Specifically, the off-peak travel frequency deviation coefficient σ corresponding to the first vehicle meets the following conditions: σ=sqrt((∑ n j=1 (a j / A j -P) 2 ) / n), where sqrt() is the square root function.

[0072] Furthermore, the method obtains the spatial stability coefficient corresponding to the first vehicle through the following steps: S10, obtaining a spatial distance between a first target hash value corresponding to a preset morning rush hour period and a fourth target hash value corresponding to a preset morning rush hour period. 1 D 1 , the spatial distance O between the first target hash value corresponding to the preset morning peak period and the fourth target hash value corresponding to the preset evening peak period 1 D 2 , the spatial distance O between the first target hash value corresponding to the preset evening peak period and the fourth target hash value corresponding to the preset morning peak period 2 D 1 , the spatial distance O between the first target hash value corresponding to the preset evening peak period and the fourth target hash value corresponding to the preset evening peak period 2 D 2 .

[0073] S20, according to O 1 D 1 , O 1 D 2 , O 2 D 1 and O 2 D 2 , and get the distance matrix D of the starting and ending points.

[0074] Specifically, the distance matrix D of the start and end points meets the following conditions: .

[0075] S30, according to O 1 D 1 , O 1 D 2 , O 2 D 1 , O 2 D 2 The distance matrix of the starting and ending points is used to calculate the spatial stability coefficient η corresponding to the first vehicle.

[0076] Specifically, the space stability coefficient η corresponding to the first vehicle meets the following conditions: η=|D| / (max{O 1 D 1 , O 2 D 2}) 2 -(O 1 D 2 +O 2 D 1 ) / max{O 1 D 1, O 2 D 2}.

[0077] As mentioned above, the calculation of the spatial stability coefficient has changed the meaning of the starting point and the end point on the basis of the existing spatial stability coefficient formula. Through the calculation of the spatial stability coefficient, it can reflect the changes in the starting point and the end point of the vehicle during peak hours and the stability of the travel trajectory during peak hours. The spatial stability coefficient, as a subsequent parameter, is conducive to screening out vehicles with peak travel characteristics.

[0078] S200, according to the target travel characteristic value vector corresponding to each first vehicle, the k-means clustering model is used to cluster the first vehicle set into a preset number of initial vehicle clusters; it can be understood as: using the k-means clustering model to cluster the m target travel characteristic value vectors, and according to the clustering results and the first vehicle corresponding to each target travel characteristic value, an initial vehicle cluster corresponding to each cluster is obtained; for example, when there are three dimensions after dimensionality reduction, the target travel characteristic value vector corresponding to each first vehicle is a vector composed of three dimensions, and based on the target travel characteristic value vector corresponding to each first vehicle, the k-means clustering model is used to cluster several target travel characteristic value vectors. Those skilled in the art are aware of the specific implementation of the k-means clustering model, which will not be repeated here.

[0079] As mentioned above, since the k-means clustering model has the advantages of fast convergence speed and few parameters that need to be adjusted, the k-means clustering model is used for pre-clustering processing. The clustering speed is fast and several target parameters in the subsequent self-iterative clustering can be obtained, reducing the operational complexity of the self-iterative clustering.

[0080] S300, according to the given maximum number of merges, the initial number of iterations, the initial splitting coefficient and several target parameters obtained based on the preset number of initial vehicle clusters, the preset number of initial vehicle clusters are iteratively clustered using a self-iterative clustering model to obtain several final vehicle clusters; those skilled in the art are aware of the specific implementation of the self-iterative clustering model, which will not be described in detail here; the maximum number of merges, the initial number of iterations and the initial splitting coefficient are all required parameters in the self-iterative clustering model, which will not be explained in detail here.

[0081] Preferably, the method determines the maximum number of merging by the following steps: S301, obtaining a distance Y between travel feature vectors corresponding to any two initial vehicles in any initial vehicle cluster.

[0082] S302, when Y≤ρ, merge any two initial vehicles and divide them into one initial vehicle group, where ρ is a preset distance threshold; it can be understood that: each initial vehicle group has a number of initial vehicles, and the distance between the travel feature vectors corresponding to any two initial vehicles in the group is not greater than the preset distance threshold.

[0083] S303, obtaining a target vehicle group corresponding to each initial vehicle cluster; the target vehicle group corresponding to each initial vehicle cluster refers to an initial vehicle group containing the most initial vehicles among a plurality of initial vehicle groups corresponding to the initial vehicle cluster itself.

[0084] S304, obtaining the initial number of vehicles in each target vehicle group, and determining the minimum initial number of vehicles as the maximum merging number.

[0085] As mentioned above, based on the clustering results of the first clustering, the maximum merger number corresponding to each initial vehicle cluster is calculated according to the dispersion of several initial vehicles in each initial vehicle cluster in the clustering results, that is, the distance between several travel characteristic value vectors corresponding to the initial vehicles. Using it as the initial parameter of the self-iterative clustering model can reduce the number of iterations of the secondary clustering, accelerate convergence, and improve the reliability of clustering.

[0086] Preferably, the method obtains the initial splitting coefficient ζ by the following steps: Among them, the initial splitting coefficient ζ meets the following conditions: ζ=∑ h g=1 ((∑ Zg v=1 (L gv / λ g )) / Z g ) / h, where L gv is the distance between the travel feature value vector corresponding to the vth initial vehicle in the gth initial vehicle cluster and the center point vector of the gth initial vehicle cluster, λ g is the maximum distance between the travel feature value vectors corresponding to all initial vehicles in the g-th initial vehicle cluster and the center point vector of the g-th initial vehicle cluster, Z g is the number of initial vehicles in the gth initial vehicle cluster, h is the number of initial vehicle clusters; the travel feature vector corresponding to each initial vehicle is a vector composed of several initial travel feature values ​​corresponding to the initial vehicle itself.

[0087] As mentioned above, the initial split coefficient is the difference between the self-iterative clustering model and the k-means clustering model. On the basis of the clustering results of the k-means clustering model, the initial split coefficient corresponding to the self-iterative clustering model is obtained according to the dispersion of several initial vehicles in each initial vehicle cluster in the clustering results, that is, the distance between the travel feature value vector corresponding to the initial vehicle and the center point vector of the initial vehicle cluster. Using it as an initial parameter of the self-iterative clustering model is conducive to the reasonable splitting of samples within the cluster, and accelerates the convergence of the self-iterative clustering model, thereby improving the efficiency and reliability of secondary clustering.

[0088] Specifically, the several target parameters include the number of clusters, the center point vector corresponding to each cluster, the initial number of samples corresponding to each cluster, the sample standard deviation threshold corresponding to each cluster and the initial shortest distance between clusters; it can be understood that: the number of clusters corresponding to the self-iterative clustering model is the number of initial vehicle clusters obtained after clustering by the k-means clustering model, the center point vector corresponding to each cluster is the center point vector corresponding to each initial vehicle cluster, the initial number of samples corresponding to each cluster is the minimum number of samples among all initial vehicle clusters, the sample standard deviation threshold corresponding to each cluster is not greater than the standard deviation of each initial vehicle cluster, and the initial shortest distance between clusters is not greater than the shortest distance between any two initial vehicle clusters among all initial vehicle clusters.

[0089] As mentioned above, based on the k-means clustering model, the self-iterative clustering model adds three parameters: the maximum number of merges, the initial number of iterations, and the initial split coefficient. It also adds the operations of merging and splitting the clustering results and iterates them to make the sample features in each cluster more similar, thereby obtaining more accurate classification results.

[0090] S400, screening out a corresponding final vehicle cluster from a plurality of final vehicle clusters according to a preset screening condition, and determining each first vehicle in the screened final vehicle cluster as a target vehicle having a given travel characteristic.

[0091] Specifically, Figure 4 As shown, step S400 specifically includes the following steps: S401, according to the number of vehicles in each final vehicle cluster, obtain the total number of vehicles corresponding to several final vehicle clusters; for example: when there are three final vehicle clusters, and the number of vehicles in the clusters is 100, 150, and 200 respectively, the total number of vehicles is 100+150+200=450.

[0092] S402, obtaining a first spatial stability coefficient average value η according to the total number of vehicles and a number of initial travel characteristics corresponding to each first vehicle 1 , the average value of the first peak travel frequency F1 , the first total travel frequency average Q 1 , the average travel frequency during the first non-peak period K 1 , the average value of the deviation coefficient of the first non-peak travel frequency θ 1 , the average stability level S of the first starting point corresponding to the preset morning peak period 1 and the average stability of the first endpoint E 1 , the average stability level S of the first starting point corresponding to the preset evening peak period 0 1 and the average stability of the first endpoint E 0 1 .

[0093] Specifically, η 1 is the average value calculated based on the spatial stability coefficients of all first vehicles, F 1 , Q 1 , K 1 ,θ 1 , S 1 、E 1 , S 0 1 and E 0 1 The method of obtaining is the same as η 1 , I will not go into details here.

[0094] S403, according to the number of vehicles in each final vehicle cluster and a number of initial travel characteristics corresponding to each first vehicle in each final vehicle cluster, obtaining an average value η of the second spatial stability coefficient corresponding to each final vehicle cluster 2 , the average travel frequency of the second peak F 2 , the second total travel frequency average Q 2 , the average travel frequency during the second non-peak period K 2 , the average value of the deviation coefficient of the second non-peak travel frequency θ 2 , the average stability level S of the second starting point corresponding to the preset morning peak period 2 and the average stability of the second endpoint E 2 , the average stability level S of the second starting point corresponding to the preset evening peak period 0 2 and the average stability of the second endpoint E 0 2 .

[0095] Specifically, η 2 is the average value calculated from the spatial stability coefficients of all first vehicles in any final vehicle cluster, F 2 , Q 2 , K 2 ,θ2 , S 2 、E 2 , S 0 2 and E 0 2 The method of obtaining is the same as η 2 , which will not be elaborated here; it can be understood that each final vehicle cluster corresponds to 9 indicators.

[0096] S404, select from all final vehicle clusters those that satisfy η 2 >η 1 、F 2 >F 1 , Q 2 >Q 1 , K 2 <K 1 ,θ 2 <θ 1 , S 2 >S 1 、E 2 >E 1 , S 0 2 >S 0 1 and E 0 2 >E 0 1 The final vehicle cluster.

[0097] Above, F 2 and Q 2 Used to reflect the travel situation during peak hours, K 2 and θ 2 It is used to reflect the travel situation during non-peak hours, and the remaining five indicators are used to reflect the stability of the starting and ending points and the spatial stability. Therefore, through the above screening method, the final vehicle cluster that meets the conditions can be screened out more comprehensively and accurately. At the same time, vehicles that meet the peak travel conditions and have relatively stable starting and ending points during peak travel are screened out, that is, the required commuter vehicles are screened out, which is conducive to the subsequent management and planning of traffic in the region.

[0098] Embodiment 2 like Figure 5 As shown, this second embodiment provides a target vehicle screening device, including: The processing module 100 is used to use the factor analysis method to perform dimensionality reduction processing on a number of initial travel feature values ​​in the initial travel feature set corresponding to each first vehicle in the given first vehicle set, so as to obtain a target travel feature value vector corresponding to each first vehicle; the dimension of each target travel feature value vector is the dimension obtained after the dimensionality reduction processing.

[0099] Specifically, the first vehicle is any one of several randomly selected vehicles.

[0100] Specifically, performing dimensionality reduction processing on the initial travel characteristic values ​​refers to reducing the dimension of the vector composed of the initial travel characteristic values ​​corresponding to each first vehicle to a preset number of dimensions; for ease of understanding, the following explanation is made: When factor analysis is used for dimensionality reduction, a multidimensional vector composed of several initial travel characteristic values ​​is input into the factor analysis model, and the number of output factors can be actively set. In the present embodiment, the number of output factors is set to three, that is, the vector composed of several initial travel characteristic values ​​is reduced to three dimensions. Since the present application directly adopts the factor analysis method of the prior art, its specific implementation process will not be described in detail.

[0101] Specifically, the initial travel feature set corresponding to the first vehicle includes the spatial stability coefficient, peak travel frequency, total travel frequency, off-peak average travel frequency, off-peak travel frequency deviation coefficient of the first vehicle in the historical time period, and the pre-acquired stability values ​​of the starting point and the stability values ​​of the end point of the first vehicle corresponding to the preset morning peak period of the historical time period, and the stability values ​​of the starting point and the stability values ​​of the end point corresponding to the preset evening peak period of the historical time period; in a specific implementation, the preset morning peak period is 7:00-9:00, and the preset evening peak period is 18:00-20:00.

[0102] As described above, by using the factor analysis method to perform dimensionality reduction processing on several initial travel characteristic values ​​of the first vehicle, some linear relationships between multiple indicators can be eliminated, the dimension of the vector can be reduced, and clustering can be performed using the vector after dimensionality reduction, which can reduce the clustering complexity and thus improve the reliability of clustering.

[0103] Specifically, Figure 6 As shown, the processing module 100 includes: The fourth acquisition module 101 is used to obtain, for any first vehicle in a given first vehicle set, a number of first travel trajectories corresponding to a preset morning / evening peak period of the first vehicle within a historical time period; it can be understood that: the number of first travel trajectories corresponding to the preset morning peak period of the first vehicle within the historical time period are obtained in the same manner as the number of first travel trajectories corresponding to the preset evening peak period of the first vehicle within the historical time period.

[0104] The fifth acquisition module 103 is used to obtain several first starting point hash values ​​and several second starting point hash values ​​corresponding to the first vehicle according to several first travel trajectories; the first starting point hash value refers to the first geohash value corresponding to the several vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory, and the second starting point hash value refers to the second geohash value corresponding to the several vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory; it can be understood as: the first geohash hash block and the second geohash hash block passed in the first travel trajectory; in a specific implementation, the geohash values ​​corresponding to the first hash block and the second hash block are both seven bits.

[0105] As mentioned above, by obtaining several first starting point hash values, the starting position of each trip of the first vehicle corresponding to several preset morning / evening peak periods can be known, and then whether each starting point position is the same can be known, which is conducive to determining the stability of subsequent starting points, and at the same time can provide an important reference for the screening of vehicles with morning / evening peak travel characteristics.

[0106] The first determining module 105 is used to determine the first starting point hash values ​​with the largest number and the second largest number among the plurality of first starting point hash values ​​as the first target hash value and the second target hash value respectively, and to determine the second starting point hash value with the largest number among the plurality of second starting point hash values ​​as the third target hash value.

[0107] For better understanding, the following explanation is made: for example, there are a total of ten first starting point hash values, five of which represent the first area, four of which represent the second area, and one first starting point hash value represents the third area. Then the first starting point hash value corresponding to the first area is used as the first target hash value, and the first starting point hash value corresponding to the second area is used as the second target hash value.

[0108] The second determination module 107 is used to determine the ratio of the sum of the quantities corresponding to the first target hash value and the second target hash value to a given number of days as the stability value of the starting point of the first vehicle corresponding to the preset morning / evening peak period when there is a first target hash value or the second target hash value is the same as the third target hash value; otherwise, determine the ratio of the quantity corresponding to the first target hash value to the given number of days as the stability value of the starting point of the first vehicle corresponding to the preset morning / evening peak period; it can be understood that: the stability value of the starting point of the first vehicle corresponding to the preset evening peak period is obtained in the same manner as the stability value of the starting point corresponding to the preset morning peak period.

[0109] Specifically, the given number of days refers to the number of working days in the historical time period; in a specific implementation, the historical time period is generally selected from the past month, and the working days are Monday to Friday of each week.

[0110] In the above, according to the situation that the third target hash value is the same as the first target hash value or the second target hash value, different calculation methods of the stability values ​​of the starting points are adopted. That is, when the third target hash value is the same as the first target hash value or the second target hash value, it means that the travel trajectory is consistent. It may be that the error in reporting time of the GPS device causes the inconsistent starting point. When the third target hash value is different from the first target hash value and the second target hash value, it means that the travel trajectory is inconsistent, and thus the travel starting point is inconsistent. Therefore, through the above calculation method, the stability value of the starting point obtained is more accurate and reasonable.

[0111] Specifically, Figure 7 As shown, the processing module 100 also includes: The sixth acquisition module 102 is used to obtain several first destination hash values ​​and several second destination hash values ​​corresponding to the first vehicle based on several first travel trajectories; the first destination hash value refers to the last geohash value corresponding to the several vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory, and the second destination hash value refers to the second to last geohash value corresponding to the several vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory; in a specific implementation, the geohash values ​​corresponding to the first to last hash block and the second to last hash block are both seven bits.

[0112] As mentioned above, by obtaining several first terminal hash values, the terminal position of each trip of the first vehicle corresponding to several preset morning / evening peak periods can be known, and then whether each terminal position is the same can be known, which is conducive to determining the stability of subsequent terminal points, and at the same time can provide an important reference for the screening of vehicles with morning / evening peak travel characteristics.

[0113] The third determining module 104 is configured to determine the largest and second largest first destination hash values ​​among the plurality of first destination hash values ​​as the fourth target hash value and the fifth target hash value, respectively, and to determine the largest second destination hash value among the plurality of second destination hash values ​​as the sixth target hash value.

[0114] The fourth determination module 106 is used to determine the stability value of the terminal point of the first vehicle corresponding to the preset morning / evening peak period by the ratio of the sum of the quantities corresponding to the fourth target hash value and the fifth target hash value to the given number of days when there is a fourth target hash value or the fifth target hash value is the same as the sixth target hash value; otherwise, determine the stability value of the terminal point of the first vehicle corresponding to the preset morning / evening peak period by the ratio of the quantity corresponding to the fourth target hash value to the given number of days; it can be understood that: the stability value of the terminal point of the first vehicle corresponding to the preset evening peak period is obtained in the same way as the stability value of the terminal point corresponding to the preset morning peak period.

[0115] As described above, in the process of obtaining the endpoint stability value, the fourth target hash value, the fifth target hash value and the sixth target hash value are determined by reverse deduction. According to the situation that the sixth target hash value is the same as the fourth target hash value or the fifth target hash value, different methods of calculating the endpoint stability value are adopted. Similarly, the obtained endpoint stability value is more accurate and reasonable.

[0116] Specifically, the peak travel frequency corresponding to the first vehicle is the ratio of the number of working days with peak travel in the historical time period to the given number of days.

[0117] Specifically, the total travel frequency corresponding to the first vehicle is the ratio of the number of working days for travel in the historical time period to the given number of days.

[0118] Specifically, the off-peak average travel frequency P corresponding to the first vehicle meets the following conditions: P=(∑ n j=1 (a j / A j )) / n, where n is the total number of days in the historical period, a j is the number of non-peak trips on the jth day in the historical time period, A j is the total number of trips on the jth day in the historical time period.

[0119] Specifically, the off-peak travel frequency deviation coefficient σ corresponding to the first vehicle meets the following conditions: σ=sqrt((∑ n j=1 (a j / A j -P) 2 ) / n), where sqrt() is the square root function.

[0120] Furthermore, the processing module 100 is also used for: Obtain the spatial distance O between the first target hash value corresponding to the preset morning rush hour period and the fourth target hash value corresponding to the preset morning rush hour period 1D 1 , the spatial distance O between the first target hash value corresponding to the preset morning peak period and the fourth target hash value corresponding to the preset evening peak period 1 D 2 , the spatial distance O between the first target hash value corresponding to the preset evening peak period and the fourth target hash value corresponding to the preset morning peak period 2 D 1 , the spatial distance O between the first target hash value corresponding to the preset evening peak period and the fourth target hash value corresponding to the preset evening peak period 2 D 2 .

[0121] According to O 1 D 1 , O 1 D 2 , O 2 D 1 and O 2 D 2 , and get the distance matrix D of the starting and ending points.

[0122] Specifically, the distance matrix D of the start and end points meets the following conditions: .

[0123] According to O 1 D 1 , O 1 D 2 , O 2 D 1 , O 2 D 2 The distance matrix of the starting and ending points is used to calculate the spatial stability coefficient η corresponding to the first vehicle.

[0124] Specifically, the spatial stability coefficient η corresponding to the first vehicle meets the following conditions: η=|D| / (max{O 1 D 1 , O 2 D 2}) 2 -(O 1 D 2 +O 2 D 1 ) / max{O 1 D 1 , O 2 D 2}.

[0125] As mentioned above, the calculation of the spatial stability coefficient has changed the meaning of the starting point and the end point on the basis of the existing spatial stability coefficient formula. Through the calculation of the spatial stability coefficient, it can reflect the changes in the starting point and the end point of the vehicle during peak hours and the stability of the travel trajectory during peak hours. The spatial stability coefficient, as a subsequent parameter, is conducive to screening out vehicles with peak travel characteristics.

[0126] The first clustering module 200 is used to cluster the first vehicle set into a preset number of initial vehicle clusters using a k-means clustering model according to the target travel characteristic value vector corresponding to each first vehicle; it can be understood as: using the k-means clustering model to cluster the m target travel characteristic value vectors, and obtaining the initial vehicle cluster corresponding to each cluster according to the clustering results and the first vehicle corresponding to each target travel characteristic value; for example, when there are three dimensions after dimensionality reduction, the target travel characteristic value vector corresponding to each first vehicle is a vector composed of three dimensions, and based on the target travel characteristic value vector corresponding to each first vehicle, a k-means clustering model is used to cluster several target travel characteristic value vectors. Those skilled in the art are aware of the specific implementation of the k-means clustering model, which will not be repeated here.

[0127] As mentioned above, since the k-means clustering model has the advantages of fast convergence speed and few parameters that need to be adjusted, the k-means clustering model is used for pre-clustering processing. The clustering speed is fast and several target parameters in the subsequent self-iterative clustering can be obtained, reducing the operational complexity of the self-iterative clustering.

[0128] The second clustering module 300 is used to iteratively cluster the preset number of initial vehicle clusters using a self-iterative clustering model according to a given maximum number of merges, an initial number of iterations, an initial split coefficient and a number of target parameters obtained based on the preset number of initial vehicle clusters, so as to obtain a number of final vehicle clusters; those skilled in the art are aware of the specific implementation of the self-iterative clustering model, which will not be described in detail here; the maximum number of merges, the initial number of iterations and the initial split coefficient are all required parameters in the self-iterative clustering model, which will not be explained in detail here.

[0129] Specifically, the several target parameters include the number of clusters, the center point vector corresponding to each cluster, the initial number of samples corresponding to each cluster, the sample standard deviation threshold corresponding to each cluster and the initial shortest distance between clusters; it can be understood that: the number of clusters corresponding to the self-iterative clustering model is the number of initial vehicle clusters obtained after clustering by the k-means clustering model, the center point vector corresponding to each cluster is the center point vector corresponding to each initial vehicle cluster, the initial number of samples corresponding to each cluster is the minimum number of samples among all initial vehicle clusters, the sample standard deviation threshold corresponding to each cluster is not greater than the standard deviation of each initial vehicle cluster, and the initial shortest distance between clusters is not greater than the shortest distance between any two initial vehicle clusters among all initial vehicle clusters.

[0130] As mentioned above, based on the k-means clustering model, the self-iterative clustering model adds three parameters: the maximum number of merges, the initial number of iterations, and the initial split coefficient. It also adds the operations of merging and splitting the clustering results and iterates them to make the sample features in each cluster more similar, thereby obtaining more accurate classification results.

[0131] The first screening module 400 is used to screen out a corresponding final vehicle cluster from a plurality of final vehicle clusters according to a preset screening condition, and determine each first vehicle in the screened final vehicle cluster as a target vehicle with a given travel characteristic.

[0132] Specifically, Figure 8 As shown, the first screening module 400 includes: The first acquisition module 401 is used to acquire the total number of vehicles corresponding to several final vehicle clusters according to the number of vehicles in each final vehicle cluster; for example, when there are three final vehicle clusters, and the number of vehicles in the clusters is 100, 150, and 200 respectively, the total number of vehicles is 100+150+200=450.

[0133] The second acquisition module 402 is used to obtain the first spatial stability coefficient average value η according to the total number of vehicles and a number of initial travel characteristics corresponding to each first vehicle. 1 , the average value of the first peak travel frequency F 1 , the first total travel frequency average Q 1 , the average travel frequency during the first non-peak period K 1 , the average value of the deviation coefficient of the first non-peak travel frequency θ 1 , the average stability level S of the first starting point corresponding to the preset morning peak period 1 and the average stability of the first endpoint E 1 , the average stability level S of the first starting point corresponding to the preset evening peak period 01 and the average stability of the first endpoint E 0 1 .

[0134] Specifically, η 1 is the average value calculated based on the spatial stability coefficients of all first vehicles, F 1 , Q 1 , K 1 ,θ 1 , S 1 、E 1 , S 0 1 and E 0 1 The method of obtaining is the same as η 1 , I will not go into details here.

[0135] The third acquisition module 403 is used to obtain the second spatial stability coefficient average value η corresponding to each final vehicle cluster according to the number of vehicles in each final vehicle cluster and a number of initial travel characteristics corresponding to each first vehicle in each final vehicle cluster. 2 , the average travel frequency of the second peak F 2 , the second total travel frequency average Q 2 , the average travel frequency during the second non-peak period K 2 , the average value of the deviation coefficient of the second non-peak travel frequency θ 2 , the average stability level S of the second starting point corresponding to the preset morning peak period 2 and the average stability of the second endpoint E 2 , the average stability level S of the second starting point corresponding to the preset evening peak period 0 2 and the average stability of the second endpoint E 0 2 .

[0136] Specifically, η 2 is the average value calculated from the spatial stability coefficients of all first vehicles in any final vehicle cluster, F 2 , Q 2 , K 2 ,θ 2 , S 2 、E 2 , S 0 2 and E 0 2 The method of obtaining is the same as η 2 , which will not be elaborated here; it can be understood that each final vehicle cluster corresponds to 9 indicators.

[0137] The second screening module 404 is used to screen out a corresponding final vehicle cluster from the plurality of final vehicle clusters, and determine each first vehicle in the screened final vehicle cluster as a target vehicle with a given travel characteristic.

[0138] Above, F 2 and Q 2 Used to reflect the travel situation during peak hours, K 2 and θ 2 It is used to reflect the travel situation during non-peak hours, and the remaining five indicators are used to reflect the stability of the starting and ending points and the spatial stability. Therefore, through the above screening method, the final vehicle cluster that meets the conditions can be screened out more comprehensively and accurately. At the same time, vehicles that meet the peak travel conditions and have relatively stable starting and ending points during peak travel are screened out, that is, the required commuter vehicles are screened out, which is conducive to the subsequent management and planning of traffic in the region.

[0139] Embodiment 3 This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: The factor analysis method is used to perform dimensionality reduction processing on several initial travel characteristic values ​​in the initial travel characteristic set corresponding to each first vehicle in the given first vehicle set to obtain a target travel characteristic value vector corresponding to each first vehicle; the dimension of each target travel characteristic value vector is the dimension obtained after the dimensionality reduction processing.

[0140] According to the target travel feature value vector corresponding to each first vehicle, the first vehicle set is clustered into a preset number of initial vehicle clusters using a k-means clustering model.

[0141] According to a given maximum number of merges, an initial number of iterations, an initial split coefficient and a number of target parameters obtained based on the preset number of initial vehicle clusters, a self-iterative clustering model is used to iteratively cluster the preset number of initial vehicle clusters to obtain a number of final vehicle clusters.

[0142] According to a preset screening condition, a corresponding final vehicle cluster is screened out from a plurality of final vehicle clusters, and each first vehicle in the screened final vehicle cluster is determined as a target vehicle with a given travel characteristic.

[0143] Embodiment 4 This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: The factor analysis method is used to perform dimensionality reduction processing on several initial travel characteristic values ​​in the initial travel characteristic set corresponding to each first vehicle in the given first vehicle set to obtain a target travel characteristic value vector corresponding to each first vehicle; the dimension of each target travel characteristic value vector is the dimension obtained after the dimensionality reduction processing.

[0144] According to the target travel feature value vector corresponding to each first vehicle, the first vehicle set is clustered into a preset number of initial vehicle clusters using a k-means clustering model.

[0145] According to a given maximum number of merges, an initial number of iterations, an initial split coefficient and a number of target parameters obtained based on the preset number of initial vehicle clusters, a self-iterative clustering model is used to iteratively cluster the preset number of initial vehicle clusters to obtain a number of final vehicle clusters.

[0146] According to a preset screening condition, a corresponding final vehicle cluster is screened out from a plurality of final vehicle clusters, and each first vehicle in the screened final vehicle cluster is determined as a target vehicle with a given travel characteristic.

[0147] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0148] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0149] Although some specific embodiments of the present invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It will also be appreciated by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.

Claims

1. A target vehicle screening method, characterized in that: The following steps are involved: A factor analysis method is used to perform dimensionality reduction processing on a number of initial travel characteristic values ​​in an initial travel characteristic set corresponding to each first vehicle in a given first vehicle set, so as to obtain a target travel characteristic value vector corresponding to each first vehicle; the dimension of each target travel characteristic value vector is the dimension obtained after the dimensionality reduction processing; According to the target travel feature value vector corresponding to each first vehicle, clustering the first vehicle set into a preset number of initial vehicle clusters using a k-means clustering model; Iteratively clustering the preset number of initial vehicle clusters using a self-iterative clustering model according to a given maximum merging number, an initial number of iterations, an initial splitting coefficient, and a number of target parameters obtained based on the preset number of initial vehicle clusters to obtain a number of final vehicle clusters; According to a preset screening condition, a corresponding final vehicle cluster is screened out from a plurality of final vehicle clusters, and each first vehicle in the screened final vehicle cluster is determined as a target vehicle with a given travel characteristic.

2. The target vehicle screening method according to claim 1, characterized in that: The initial travel feature set corresponding to the first vehicle includes the spatial stability coefficient, peak travel frequency, total travel frequency, off-peak average travel frequency, off-peak travel frequency deviation coefficient of the first vehicle in the historical time period, and the pre-acquired stability values ​​of the starting point and the stability values ​​of the end point of the first vehicle corresponding to the preset morning peak period of the historical time period, and the pre-acquired stability values ​​of the starting point and the stability values ​​of the end point corresponding to the preset evening peak period of the historical time period.

3. The target vehicle screening method according to claim 2, characterized in that: The method of selecting a corresponding final vehicle cluster from a plurality of final vehicle clusters according to a preset screening condition comprises the following steps: According to the number of vehicles in each final vehicle cluster, obtaining the total number of vehicles corresponding to several final vehicle clusters; According to the total number of vehicles and the initial travel characteristics corresponding to each first vehicle, the first spatial stability coefficient average value η1, the first peak travel frequency average value F1, the first total travel frequency average value Q1, the first non-peak average travel frequency average value K1, the first non-peak travel frequency deviation coefficient average value θ1, the first starting point stability average value S1 and the first end point stability average value E1 corresponding to the preset morning peak period, and the first starting point stability average value S1 corresponding to the preset evening peak period are obtained. 0 1 and the average stability of the first endpoint E 0 1; According to the number of vehicles in each final vehicle cluster and the initial travel characteristics corresponding to each first vehicle in each final vehicle cluster, the second spatial stability coefficient average value η2, the second peak travel frequency average value F2, the second total travel frequency average value Q2, the second off-peak average travel frequency average value K2, the second off-peak travel frequency deviation coefficient average value θ2, the second starting point stability average value S2 and the second end point stability average value E2 corresponding to the preset morning peak period, and the second starting point stability average value S2 corresponding to the preset evening peak period are obtained. 0 2 and the average stability of the second endpoint E 0 2; Select from all the final vehicle clusters the ones that satisfy η2>η1, F2>F1, Q2>Q1, K2<K1, θ2<θ1, S2>S1, E2>E1, S 0 2>S 0 1 and E 0 2>E 0 1’s final vehicle cluster.

4. The target vehicle screening method according to claim 2, characterized in that: The method obtains the stability value of the starting point of the first vehicle corresponding to the preset morning / evening peak period by the following steps: For any first vehicle in a given first vehicle set, obtaining a plurality of first travel trajectories corresponding to a preset morning / evening peak period of the first vehicle in a historical time period; According to the plurality of first travel trajectories, a plurality of first starting point hash values ​​and a plurality of second starting point hash values ​​corresponding to the first vehicle are obtained; the first starting point hash value refers to a first geohash value corresponding to the plurality of vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory, and the second starting point hash value refers to a second geohash value corresponding to the plurality of vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory; Determine the first starting point hash values ​​with the largest number and the second largest number of the same among the plurality of first starting point hash values ​​as the first target hash value and the second target hash value, respectively, and determine the second starting point hash value with the largest number of the same among the plurality of second starting point hash values ​​as the third target hash value; When the first target hash value exists or the second target hash value is the same as the third target hash value, the ratio of the sum of the quantities corresponding to the first target hash value and the second target hash value to the given number of days is determined as the stability value of the starting point of the first vehicle corresponding to the preset morning / evening peak period; otherwise, the ratio of the quantity corresponding to the first target hash value to the given number of days is determined as the stability value of the starting point of the first vehicle corresponding to the preset morning / evening peak period.

5. The target vehicle screening method according to claim 4, characterized in that: The method obtains the stability value of the destination corresponding to the preset morning / evening peak period of the first vehicle by the following steps: According to the plurality of first travel trajectories, a plurality of first destination hash values ​​and a plurality of second destination hash values ​​corresponding to the first vehicle are obtained; the first destination hash value refers to the last geohash value corresponding to the plurality of vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory, and the second destination hash value refers to the second to last geohash value corresponding to the plurality of vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory; Determine the largest and second largest first destination hash values ​​among the plurality of first destination hash values ​​as the fourth target hash value and the fifth target hash value, respectively, and determine the largest second destination hash value among the plurality of second destination hash values ​​as the sixth target hash value; When there is a fourth target hash value or the fifth target hash value is the same as the sixth target hash value, the ratio of the sum of the quantities corresponding to the fourth target hash value and the fifth target hash value to the given number of days is determined as the stability value of the destination corresponding to the preset morning / evening peak period of the first vehicle; otherwise, the ratio of the quantity corresponding to the fourth target hash value to the given number of days is determined as the stability value of the destination corresponding to the preset morning / evening peak period of the first vehicle.

6. The target vehicle screening method according to claim 1, characterized in that: The target parameters include the number of clusters, the center point vector corresponding to each cluster, the initial number of samples corresponding to each cluster, the sample standard deviation threshold corresponding to each cluster and the initial shortest distance between clusters.

7. A target vehicle screening device, characterized in that: The device comprises: a processing module, configured to perform dimensionality reduction processing on a plurality of initial travel characteristic values ​​in an initial travel characteristic set corresponding to each first vehicle in a given first vehicle set by using a factor analysis method, so as to obtain a target travel characteristic value vector corresponding to each first vehicle; the dimension of each target travel characteristic value vector is the dimension obtained after the dimensionality reduction processing; A first clustering module, configured to cluster the first vehicle set into a preset number of initial vehicle clusters using a k-means clustering model according to the target travel feature value vector corresponding to each first vehicle; A second clustering module is used to iteratively cluster the preset number of initial vehicle clusters using a self-iterative clustering model according to a given maximum merging number, an initial number of iterations, an initial splitting coefficient, and a number of target parameters obtained based on the preset number of initial vehicle clusters, so as to obtain a number of final vehicle clusters; The first screening module is used to screen out a corresponding final vehicle cluster from a plurality of final vehicle clusters according to a preset screening condition, and determine each first vehicle in the screened final vehicle cluster as a target vehicle with a given travel characteristic.

8. The target vehicle screening device according to claim 7, characterized in that: The initial travel feature set corresponding to the first vehicle includes the spatial stability coefficient, peak travel frequency, total travel frequency, off-peak average travel frequency, off-peak travel frequency deviation coefficient of the first vehicle in the historical time period, and the pre-acquired stability values ​​of the starting point and the stability values ​​of the end point of the first vehicle corresponding to the preset morning peak period of the historical time period, and the pre-acquired stability values ​​of the starting point and the stability values ​​of the end point corresponding to the preset evening peak period of the historical time period.

9. The target vehicle screening device according to claim 8, characterized in that: The first screening module comprises: A first acquisition module, used for acquiring the total number of vehicles corresponding to a number of final vehicle clusters according to the number of vehicles in each final vehicle cluster; The second acquisition module is used to obtain the first spatial stability coefficient average value η1, the first peak travel frequency average value F1, the first total travel frequency average value Q1, the first non-peak average travel frequency average value K1, the first non-peak travel frequency deviation coefficient average value θ1, the first starting point stability average value S1 and the first end point stability average value E1 corresponding to the preset morning peak period, and the first starting point stability average value S1 corresponding to the preset evening peak period, according to the total number of vehicles and the initial travel characteristics corresponding to each first vehicle. 0 1 and the average stability of the first endpoint E 0 1; The third acquisition module is used to obtain the second spatial stability coefficient average value η2, the second peak travel frequency average value F2, the second total travel frequency average value Q2, the second non-peak average travel frequency average value K2, the second non-peak travel frequency deviation coefficient average value θ2, the second starting point stability average value S2 and the second end point stability average value E2 corresponding to the preset morning peak period, and the second starting point stability average value S2 corresponding to the preset evening peak period, according to the number of vehicles in each final vehicle cluster and the initial travel characteristics corresponding to each first vehicle in each final vehicle cluster. 0 2 and the average stability of the second endpoint E 0 2; The second screening module is used to screen out from all the final vehicle clusters the vehicles that satisfy η2>η1, F2>F1, Q2>Q1, K2<K1, θ2<θ1, S2>S1, E2>E1, S 0 2>S 0 1 and E 0 2>E 0 1’s final vehicle cluster.

10. The target vehicle screening device according to claim 8, characterized in that: The processing module comprises: A fourth acquisition module is used to acquire, for any first vehicle in a given first vehicle set, a plurality of first travel trajectories corresponding to a preset morning / evening peak period of the first vehicle in a historical time period; A fifth acquisition module, configured to acquire a plurality of first starting point hash values ​​and a plurality of second starting point hash values ​​corresponding to the first vehicle according to the plurality of first travel trajectories; the first starting point hash value refers to a first geohash value corresponding to the plurality of vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory, and the second starting point hash value refers to a second geohash value corresponding to the plurality of vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory; A first determination module is used to determine the first starting point hash values ​​with the largest number and the second largest number of the same among the plurality of first starting point hash values ​​as the first target hash value and the second target hash value, respectively, and to determine the second starting point hash value with the largest number of the same among the plurality of second starting point hash values ​​as the third target hash value; The second determination module is used to determine the stability value of the starting point of the first vehicle corresponding to the preset morning / evening peak period by the ratio of the sum of the quantities corresponding to the first target hash value and the second target hash value to the given number of days when the first target hash value exists or the second target hash value is the same as the third target hash value; otherwise, determine the stability value of the starting point of the first vehicle corresponding to the preset morning / evening peak period by the ratio of the quantity corresponding to the first target hash value to the given number of days.

11. The target vehicle screening device according to claim 10, characterized in that: The processing module also includes: A sixth acquisition module, configured to acquire a plurality of first destination hash values ​​and a plurality of second destination hash values ​​corresponding to the first vehicle according to the plurality of first travel trajectories; the first destination hash value refers to the last geohash value corresponding to the plurality of vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory, and the second destination hash value refers to the second to last geohash value corresponding to the plurality of vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory; a third determination module, configured to determine the largest and second largest first destination hash values ​​among the plurality of first destination hash values ​​as the fourth target hash value and the fifth target hash value, respectively, and to determine the largest second destination hash value among the plurality of second destination hash values ​​as the sixth target hash value; The fourth determination module is used to determine the stability value of the first vehicle at the destination corresponding to the preset morning / evening peak period by the ratio of the sum of the quantities corresponding to the fourth target hash value and the fifth target hash value to the given number of days when there is a fourth target hash value or the fifth target hash value is the same as the sixth target hash value; otherwise, determine the stability value of the first vehicle at the destination corresponding to the preset morning / evening peak period by the ratio of the quantity corresponding to the fourth target hash value to the given number of days.

12. The target vehicle screening device according to claim 7, characterized in that: The target parameters include the number of clusters, the center point vector corresponding to each cluster, the initial number of samples corresponding to each cluster, the sample standard deviation threshold corresponding to each cluster and the initial shortest distance between clusters.

13. An electronic 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 computer program, the target vehicle screening method according to any one of claims 1 to 6 is implemented.

14. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the target vehicle screening method according to any one of claims 1 to 6 is implemented.

Images