Method, device, equipment and medium for determining starting stability degree of vehicle

Abstract

The present application relates to the field of transportation technologies, and particularly to a method, device, equipment and medium for determining the starting point stability degree of a vehicle. The method includes: obtaining a plurality of first travel trajectories corresponding to a preset morning / evening peak period within a historical time period for each first vehicle, thereby obtaining a plurality of first starting point hash values and a plurality of second starting point hash values corresponding to each first vehicle, determining a first target hash value and a second target hash value from the plurality of first starting point hash values, determining a third target hash value from the plurality of second starting point hash values, comparing the third target hash value with the first target hash value and the second target hash value, and adopting a corresponding calculation method for the starting point stability degree value according to the comparison situation of the hash values, so as to obtain a more accurate and reasonable starting point stability degree value.

Description

Technical Field

[0001] The present invention relates to the technical field of transportation, and particularly to a method, device, equipment and medium for determining the starting point stability degree of a vehicle. Background Art

[0002] With the development of social economy, the per capita ownership of private cars in China has been continuously increasing. People are more inclined to commute by self-driving, which brings great pressure to the road traffic during peak hours. The commuting problem not only involves everyone's travel, but also reflects the traffic management level of the whole city. Therefore, it is crucial to screen out commuting private cars in the peak traffic flow, which is also beneficial to adopting corresponding control strategies for peak traffic. When screening private cars, various data need to be collected according to the vehicle travel situation. Among them, the starting point during travel is an important indicator. Therefore, it is very meaningful to evaluate the stability degree of the starting point. Summary of the Invention

[0003] The purpose of the present invention is to provide a method, device, equipment and medium for determining the starting point stability degree of a vehicle. By collecting different situations of the starting point and adopting different calculation methods for the starting point stability degree values, the starting point stability degree can be evaluated more accurately and reasonably.

[0004] According to the first aspect of the present invention, a method for determining the starting point stability degree of a vehicle is provided, including the following steps:

[0005] For any first vehicle in a given first vehicle set, obtain a plurality of first travel trajectories corresponding to the preset morning / evening peak period within the historical time period of the first vehicle.

[0006] According to the plurality of first travel trajectories, obtain a plurality of first starting point hash values and a plurality of second starting point hash values corresponding to the first vehicle; the first starting point hash value refers to the first geohash value corresponding to a 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 the second geohash value corresponding to a plurality of vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory.

[0007] Determine the first target hash value and the second target hash value as the first starting point hash values with the largest and second largest number of the same ones respectively among the plurality of first starting point hash values, and determine the third target hash value as the second starting point hash value with the largest number of the same ones among the plurality of second starting point hash values.

[0008] When the first target hash value or the second target hash value is the same as the third target hash value, determine 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 as the starting point stability value of the first vehicle corresponding to the preset morning / evening peak period; otherwise, determine the ratio of the quantity corresponding to the first target hash value to the given number of days as the starting point stability value of the first vehicle corresponding to the preset morning / evening peak period.

[0009] Further, the method obtains a plurality of first travel trajectories of the first vehicle corresponding to the preset morning / evening peak period within the historical time period through the following steps:

[0010] Receive a plurality of vehicle position information reported by the GPS device of the first vehicle within the historical time period.

[0011] Divide the plurality of vehicle position information into a plurality of vehicle position information sets; the reporting times of the vehicle position information within each vehicle position information set are continuous and the reporting time intervals are not greater than the preset time threshold; the time interval between every two adjacent vehicle position information sets is greater than the preset time threshold.

[0012] According to the plurality of vehicle position information within each vehicle position information set, obtain the initial travel trajectory corresponding to each vehicle position information set.

[0013] When the travel time corresponding to the initial travel trajectory overlaps with the preset morning / evening peak period, obtain the initial travel trajectory itself as the first travel trajectory of the first vehicle corresponding to the preset morning / evening peak period within the historical time period.

[0014] Further, the method further includes the following steps:

[0015] According to the plurality of first travel trajectories, obtain a plurality of first end hash values and a plurality of second end hash values corresponding to the first vehicle; the first end 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 end 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.

[0016] Determine the first end hash value with the largest number of identical values and the second largest number of identical values among the plurality of first end hash values as the fourth target hash value and the fifth target hash value respectively, and determine the second end hash value with the largest number of identical values among the plurality of second end hash values as the sixth target hash value.

[0017] When there is a situation where the fourth target hash value or the fifth target hash value is the same as the sixth target hash value, determine 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 as the end - point stability value of the first vehicle during the preset morning / evening peak period; otherwise, determine the ratio of the quantity corresponding to the fourth target hash value to the given number of days as the end - point stability value of the first vehicle during the preset morning / evening peak period.

[0018] Further, the method further includes the following steps:

[0019] Obtain 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 morning peak period 1 D 1 and 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 and 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 and 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 .

[0020] According to O 1 D 1 and O 1 D 2 and O 2 D 1 and O 2 D 2 , obtain the distance matrix of the starting and ending points.

[0021] According to O 1 D 1 and O 1 D 2 and O 2 D 1 and O 2 D 2 and the distance matrix of the starting and ending points, calculate to obtain the spatial stability coefficient corresponding to the first vehicle.

[0022] Further, the method further includes the following steps:

[0023] Using factor analysis method, dimensionality reduction processing is performed on the spatial stability coefficient corresponding to each first vehicle, the starting point stability degree values and the ending point stability degree values corresponding to the preset morning peak period respectively, the starting point stability degree values and the ending point stability degree values corresponding to the preset evening peak period respectively, as well as the peak travel frequency, total travel frequency, non-peak period average travel frequency, and non-peak period travel frequency deviation coefficient corresponding to each first vehicle obtained in advance, to obtain the target travel feature value vector corresponding to each first vehicle; the dimension of each target travel feature value vector is the dimension obtained after dimensionality reduction processing.

[0024] According to the target travel feature value vector corresponding to each first vehicle, the first vehicles are clustered into a preset number of initial vehicle clusters by using a k-means clustering model.

[0025] According to the given maximum merging number, initial iteration number, initial splitting coefficient, and several target parameters obtained based on the preset number of initial vehicle clusters, an iterative clustering model is used to perform iterative clustering on the preset number of initial vehicle clusters to obtain several final vehicle clusters.

[0026] According to the preset screening conditions, the corresponding final vehicle clusters are screened out from several final vehicle clusters, and each first vehicle in the screened final vehicle clusters is determined to be a target vehicle with given travel characteristics.

[0027] Furthermore, the given number of days refers to the number of days that belong to working days within the historical time period.

[0028] According to the second aspect of the present invention, a device for determining the starting point stability degree of a vehicle is provided, and the device includes:

[0029] A first acquisition module, configured to acquire several first travel trajectories corresponding to a given first vehicle within a first vehicle set during a preset morning / evening peak period within a historical time period.

[0030] A second acquisition module, configured to acquire several first starting point hash values and several second starting point hash values corresponding to the first vehicle according to the several first travel trajectories; the first starting point hash value refers to the first geohash value corresponding to 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 several vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory.

[0031] A first determination module, configured to respectively determine the first target hash value and the second target hash value from among a plurality of first starting hash values as the ones with the largest and the second largest identical quantities, and determine the second starting hash value with the largest identical quantity among a plurality of second starting hash values as the third target hash value.

[0032] A second determination module, configured to, when there is a situation where the first target hash value or the second target hash value is the same as the third target hash value, determine 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 as the starting stability value of the first vehicle corresponding to the preset morning / evening peak period; otherwise, determine the ratio of the quantity corresponding to the first target hash value to the given number of days as the starting stability value of the first vehicle corresponding to the preset morning / evening peak period.

[0033] Further, the first acquisition module includes:

[0034] A receiving module, configured to receive a plurality of vehicle position information reported by the GPS device of the first vehicle within a historical time period.

[0035] A partitioning module, configured to partition the plurality of vehicle position information into a plurality of vehicle position information sets; the reporting times of the vehicle position information within each vehicle position information set are continuous and the reporting time intervals are not greater than a preset time threshold; the time interval between every two adjacent vehicle position information sets is greater than the preset time threshold.

[0036] A third acquisition module, configured to obtain an initial travel trajectory corresponding to each vehicle position information set according to the plurality of vehicle position information within each vehicle position information set.

[0037] A fourth acquisition module, configured to, when the travel time corresponding to the initial travel trajectory overlaps with the preset morning / evening peak period, obtain the initial travel trajectory itself as the first travel trajectory of the first vehicle corresponding to the preset morning / evening peak period within the historical time period.

[0038] Further, the device further includes an end stability determination module, and the end stability determination module includes:

[0039] A fifth acquisition module, configured to obtain a plurality of first end hash values and a plurality of second end hash values corresponding to the first vehicle according to the plurality of first travel trajectories; the first end 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 end hash value refers to the penultimate geohash value corresponding to the plurality of vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory.

[0040] A third determination module, configured to determine the fourth target hash value and the fifth target hash value respectively from the first end hash values with the largest and the second largest number of identical ones among a plurality of first end hash values, and determine the sixth target hash value from the second end hash values with the largest number of identical ones among a plurality of second end hash values.

[0041] A fourth determination module, configured to, when there is a same value between the fourth target hash value or the fifth target hash value and the sixth target hash value, 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 end point stability degree value of the first vehicle corresponding to a preset morning / evening rush hour period; otherwise, determine the ratio of the quantity corresponding to the fourth target hash value to a given number of days as the end point stability degree value of the first vehicle corresponding to a preset morning / evening rush hour period.

[0042] Further, the apparatus further includes a spatial stability coefficient acquisition module, and the spatial stability coefficient acquisition module includes:

[0043] A sixth acquisition module, configured to acquire the spatial distance O 1 D 1 between the first target hash value corresponding to a preset morning rush hour period and the fourth target hash value corresponding to the preset morning rush hour period, 1 D 2 the spatial distance O 2 D 1 between the first target hash value corresponding to a preset morning rush hour period and the fourth target hash value corresponding to a preset evening rush hour period, 2 D 2 .

[0044] A first processing module, configured to obtain a distance matrix of the starting and ending points according to O 1 D 1 , O 1 D 2 , O 2 D 1 and O 2 D 2 .

[0045] A calculation module, configured to calculate the spatial stability coefficient corresponding to the first vehicle according to O 1 D 1 , O 1 D 2 , O 2 D 1 , O 2 D 2 and the distance matrix of the starting and ending points.

[0046] Further, the device further includes a target vehicle screening module, and the target vehicle screening module includes:

[0047] A second processing module, configured to perform dimensionality reduction processing on the spatial stability coefficient corresponding to each first vehicle, the starting point stability degree values and the ending point stability degree values respectively corresponding to the preset morning rush hour, the starting point stability degree values and the ending point stability degree values respectively corresponding to the preset evening rush hour, as well as the peak travel frequency, total travel frequency, non-peak period average travel frequency, and non-peak period travel frequency deviation coefficient corresponding to each first vehicle obtained in advance, 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.

[0048] A first clustering module, configured to cluster the first vehicles into a preset number of initial vehicle clusters by using a k-means clustering model according to the target travel feature value vector corresponding to each first vehicle.

[0049] A second clustering module, configured to perform iterative clustering on the preset number of initial vehicle clusters by using a self-iterative clustering model according to a given maximum merging number, initial iteration number, initial splitting coefficient, and several target parameters obtained based on the preset number of initial vehicle clusters, to obtain several final vehicle clusters.

[0050] A screening module, configured to screen out the corresponding final vehicle clusters from the several final vehicle clusters according to preset screening conditions, and determine each first vehicle in the screened final vehicle clusters as a target vehicle with given travel characteristics.

[0051] Further, the given number of days refers to the number of days that are weekdays within the historical time period.

[0052] According to a third aspect of the present invention, there is provided an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where when the processor executes the computer program, the method for determining the starting point stability degree of the vehicle as described above is implemented.

[0053] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium storing a computer program, where when the computer program is executed by a processor, the method for determining the starting point stability degree of the vehicle as described above is implemented.

[0054] The present invention has at least the following beneficial effects compared with the prior art:

[0055] When implementing the method for determining the starting point stability degree of a vehicle according to the present invention, first, a plurality of first travel trajectories corresponding to a preset morning rush hour or a preset evening rush hour within a historical time period are obtained for each first vehicle. Then, a plurality of first starting point hash values and a plurality of second starting point hash values corresponding to the first vehicle itself are obtained according to the plurality of first travel trajectories corresponding to each first vehicle. A first target hash value and a second target hash value are determined from the plurality of first starting point hash values, and a third target hash value is determined from the plurality of second starting point hash values. The third target hash value is compared with the first target hash value and the second target hash value. When the third target hash value is the same as one of the target hash values, it indicates that the travel trajectories are consistent, and it may be a situation where the starting points obtained are inconsistent due to errors in the reporting time of the GPS device or other circumstances. It can be considered that the actual starting points of travel are the same. When the third target hash value is not the same as any of the target hash values, it indicates that the travel trajectories are inconsistent, and thus it is considered that the actual starting points of travel are inconsistent. The present application re - determines the starting point based on the comparison of hash values, and adopts different calculation methods for the starting point stability degree value according to different situations of the starting point, so as to more accurately and reasonably evaluate the starting point stability degree during the preset morning rush hour or the preset evening rush hour. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0057] Figure 1 It is a flowchart of the method for determining the starting point stability degree of a vehicle provided in Embodiment 1 of the present invention;

[0058] Figure 2 It is a flowchart of step S100 provided in Embodiment 1 of the present invention;

[0059] Figure 3 It is a flowchart of the method for determining the ending point stability degree of a vehicle provided in Embodiment 1 of the present invention;

[0060] Figure 4 It is a flowchart of the step for obtaining the spatial stability coefficient provided in Embodiment 1 of the present invention;

[0061] Figure 5 It is a flowchart of the step for screening target vehicles provided in Embodiment 1 of the present invention;

[0062] Figure 6 It is a schematic structural diagram of the device for determining the starting point stability degree of a vehicle provided in Embodiment 2 of the present invention;

[0063] Figure 7 This is a schematic structural diagram of the first acquisition module 100 provided in the second embodiment of the present invention;

[0064] Figure 8 This is a schematic structural diagram of the end point stability determination module provided in the second embodiment of the present invention;

[0065] Figure 9 This is a schematic structural diagram of the spatial stability coefficient acquisition module provided in the second embodiment of the present invention;

[0066] Figure 10 This is a schematic structural diagram of the target vehicle screening module provided in the second embodiment of the present invention. Detailed implementation manners

[0067] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0068] Embodiment 1

[0069] As Figure 1 shown, Embodiment 1 of the present invention provides a method for determining the starting point stability of a vehicle, including the following steps:

[0070] S100. For any first vehicle in a given first vehicle set, obtain a plurality of first travel trajectories corresponding to the preset morning / evening peak period within the historical time period; it can be understood that: the method for obtaining a plurality of first travel trajectories corresponding to the preset morning peak period within the historical time period of the first vehicle is the same as the method for obtaining a plurality of first travel trajectories corresponding to the preset evening peak period within the historical time period of the first vehicle; 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.

[0071] Specifically, the first vehicle is any vehicle randomly selected from a plurality of vehicles.

[0072] Specifically, as Figure 2 shown, step S100 includes the following steps:

[0073] S101. Receive a plurality of vehicle position information reported by the GPS device of the first vehicle within the historical time period; it can be understood that: the vehicle position information refers to the longitude and latitude information of the vehicle reported by the GPS device in real time.

[0074] S102. Divide the several vehicle position information into several vehicle position information sets; the reporting times of the vehicle position information within each vehicle position information set are continuous and the reporting time intervals are not greater than a preset time threshold; the time interval between every two adjacent vehicle position information sets is greater than the preset time threshold.

[0075] For better understanding, the following explanation is made: For example, if the preset time threshold is 15 minutes, and the times when the GPS device reports the vehicle position information three times in succession are 6:50, 7:10, and 7:11 respectively, then the vehicle position information reported at 6:50 is divided into the previous vehicle position information set, and the vehicle position information reported at 7:10 and 7:11 is jointly divided into the subsequent vehicle position information set.

[0076] S103. According to the several vehicle position information within each vehicle position information set, obtain the corresponding initial travel trajectory for each vehicle position information set; in a specific implementation, the GPS device usually uploads the vehicle position information every few seconds, and the several vehicle position information within the vehicle position information set are concatenated to obtain the corresponding initial travel trajectory.

[0077] S104. When the travel time corresponding to the initial travel trajectory overlaps with the preset morning / evening rush hour period, obtain that the initial travel trajectory itself is the first travel trajectory corresponding to the first vehicle during the preset morning / evening rush hour period within the historical time period.

[0078] As described above, when obtaining the first travel trajectories corresponding to the morning / evening rush hour periods of the vehicle over multiple days, first obtain the travel time of each first travel trajectory. Without considering the overlap size between the travel time and the morning / evening rush hour period, as long as there is an overlap, it is determined as the first travel trajectory corresponding to the morning / evening rush hour period. In this way, considering the different work start times of different people, the different distances between home and company, etc., which lead to inconsistent travel times, it is possible to more comprehensively and reasonably determine several vehicles with morning / evening rush hour travel characteristics.

[0079] S200. According to the 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 through 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 digits.

[0080] As described above, by obtaining a number of first starting point hash values, it is possible to know the starting point position of the first vehicle for each trip corresponding to a number of preset morning / evening rush hour periods, and then to know whether each starting point position is the same, which is beneficial to the subsequent determination of the starting point stability, and at the same time can provide an important reference for the screening of vehicles with morning / evening rush hour travel characteristics.

[0081] S300, determine the first target hash value and the second target hash value respectively as the first starting point hash values with the largest and second largest number of the same ones among a number of first starting point hash values, and determine the third target hash value as the second starting point hash value with the largest number of the same ones among a number of second starting point hash values.

[0082] For better understanding, the following description is made: for example, there are a total of ten first starting point hash values, among which five first starting point hash values all represent the first area, four first starting point hash values all 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.

[0083] S400, when there is a first target hash value or a second target hash value that is the same as the third target hash value, determine 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 as the starting point stability value of the first vehicle corresponding to the preset morning / evening rush hour period; otherwise, determine the ratio of the quantity corresponding to the first target hash value to the given number of days as the starting point stability value of the first vehicle corresponding to the preset morning / evening rush hour period; it can be understood that: the method for obtaining the starting point stability value of the first vehicle corresponding to the preset evening rush hour period is the same as that for the preset morning rush hour period.

[0084] Specifically, the given number of days refers to the number of days that belong to working days within the historical time period; in a specific implementation, the historical time period is generally selected as the past month, and the working days are from Monday to Friday every week.

[0085] As described above, according to the same situation between the third target hash value and the first target hash value or the second target hash value, different calculation methods for the starting point stability value 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 trajectories are the same, and it may be the situation that the starting points obtained are inconsistent due to errors in the reporting time of the GPS device. When the third target hash value is not the same as both the first target hash value and the second target hash value, it means that the travel trajectories are different, and thus the starting points of travel are different. Therefore, through the above calculation method, the obtained starting point stability value is more accurate and reasonable.

[0086] Further, as Figure 3 shown, the method further includes the following steps:

[0087] S10. Obtain a number of first end hash values and a number of second end hash values corresponding to the first vehicle according to a number of first travel trajectories; the first end hash value refers to the last geohash value corresponding to a number of vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory, and the second end hash value refers to the penultimate geohash value corresponding to a number of 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 last hash block and the penultimate hash block are both seven digits.

[0088] As described above, by obtaining a number of first end hash values, it is possible to know the end position of each trip of the first vehicle corresponding to a number of preset morning / evening rush hour periods, and then to know whether each end position is the same, which is beneficial to the determination of the subsequent end stability degree, and at the same time can provide an important reference for the screening of vehicles with morning / evening rush hour travel characteristics.

[0089] S20. Determine the first end hash value with the largest number of identical ones and the second largest number of identical ones among a number of first end hash values as the fourth target hash value and the fifth target hash value respectively, and determine the second end hash value with the largest number of identical ones among a number of second end hash values as the sixth target hash value.

[0090] S30. When there is a situation where the fourth target hash value or the fifth target hash value is the same as the sixth target hash value, determine 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 as the end stability degree value of the first vehicle corresponding to the preset morning / evening rush hour period; otherwise, determine the ratio of the quantity corresponding to the fourth target hash value to the given number of days as the end stability degree value of the first vehicle corresponding to the preset morning / evening rush hour period; it can be understood that: the method for obtaining the end stability degree value corresponding to the preset evening rush hour period of the first vehicle is the same as that for the preset morning rush hour period.

[0091] As described above, in the process of obtaining the end degree stability value, the fourth target hash value, the fifth target hash value and the sixth target hash value are determined by a backward deduction method. According to the same situation between the sixth target hash value and the fourth target hash value or the fifth target hash value, different calculation methods for the end stability degree value are adopted. Similarly, the obtained end stability degree value is more accurate and reasonable.

[0092] Further, as Figure 4 shown, the method further includes the following steps:

[0093] S40. 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 rush hour and the fourth target hash value corresponding to the preset evening rush hour 1 D 2 The spatial distance O between the first target hash value corresponding to the preset evening rush hour and the fourth target hash value corresponding to the preset morning rush hour 2 D 1 The spatial distance O between the first target hash value corresponding to the preset evening rush hour and the fourth target hash value corresponding to the preset evening rush hour 2 D 2 .

[0094] S50. According to O 1 D 1 、O 1 D 2 、O 2 D 1 and O 2 D 2 , the distance matrix D of the starting and ending points is obtained.

[0095] Specifically, the distance matrix D of the starting and ending points meets the following conditions:

[0096] .

[0097] S60. According to O 1 D 1 、O 1 D 2 、O 2 D 1 、O 2 D 2 and the distance matrix of the starting and ending points, the spatial stability coefficient η corresponding to the first vehicle is calculated.

[0098] Specifically, the spatial stability coefficient η corresponding to the first vehicle meets the following conditions:

[0099] 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 .

[0100] For the above calculation of the spatial stability coefficient, based on the existing formula for the spatial stability coefficient, the meanings of the starting point and the ending point are changed. Through the calculation of the spatial stability coefficient, it is possible to reflect the changes in the starting point and the ending point of the vehicle during the peak period and the stability degree of the travel trajectory during the peak period. As a subsequent parameter, the spatial stability coefficient is conducive to screening out vehicles with peak travel characteristics.

[0101] Furthermore, as Figure 5 shown, the method further includes the following steps:

[0102] S001. Using factor analysis method to perform dimensionality reduction processing on the spatial stability coefficient corresponding to each first vehicle, the starting point stability degree value and the ending point stability degree value corresponding to the preset morning peak period respectively, the starting point stability degree value and the ending point stability degree value corresponding to the preset evening peak period respectively, and the peak travel frequency, total travel frequency, non-peak period average travel frequency, and non-peak period travel frequency deviation coefficient corresponding to each first vehicle obtained in advance, to obtain the target travel characteristic value vector corresponding to each first vehicle; the dimension of each target travel characteristic value vector is the dimension obtained after dimensionality reduction processing; it can be understood that: after dimensionality reduction processing of the multi-dimensional vector composed of the above nine indicators corresponding to each first vehicle, a target travel characteristic value vector with a preset number of dimensions is obtained; in this embodiment, the dimension after dimensionality reduction processing is three dimensions.

[0103] For easy understanding, the following explanations are made:

[0104] When performing dimensionality reduction processing using the factor analysis method, a number of initial travel characteristic values, that is, the multi-dimensional vector composed of the above nine indicators, are input into the factor analysis model, and the number of factors to be output can be actively set. In this embodiment, the number of factors to be output is set to three, that is, the vector composed of a number of initial travel characteristic values is reduced to three dimensions. Since this application directly uses the factor analysis method of the prior art, the specific implementation process thereof will not be elaborated herein.

[0105] For the above, by using the factor analysis method to perform dimensionality reduction processing on a number of initial travel characteristic values of the first vehicle, it is possible to eliminate part of the linear relationship between various indicators, reduce the dimension of the vector, and use the vector after dimensionality reduction for clustering, which can reduce the clustering complexity and thus improve the reliability of clustering.

[0106] 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.

[0107] Specifically, the total travel frequency corresponding to the first vehicle is the ratio of the number of working days with travel in the historical time period to the given number of days.

[0108] Specifically, the average off-peak travel frequency P of the first vehicle meets the following conditions:

[0109] P = (∑ n j=1 (a j / A j )) / n, where n is the total number of days in the historical time period, a j is the number of off-peak trips on the j-th day in the historical time period, and A j is the total number of trips on the j-th day in the historical time period.

[0110] Specifically, the off-peak travel frequency deviation coefficient σ of the first vehicle meets the following conditions:

[0111] σ = sqrt((∑ n j=1 (a j / A j -P) 2 ) / n), where sqrt() is the square root function.

[0112] S002. According to the target travel characteristic value vectors corresponding to each first vehicle, use the k-means clustering model to cluster the first vehicles into a preset number of initial vehicle clusters; it can be understood that: use the k-means clustering model to cluster m target travel characteristic value vectors, and according to the clustering results and the first vehicle corresponding to each target travel characteristic value, obtain the initial vehicle clusters corresponding to each cluster; 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. Based on the target travel characteristic value vectors corresponding to each first vehicle, use the k-means clustering model to cluster several target travel characteristic value vectors. Those skilled in the art know the specific implementation of the k-means clustering model and will not be elaborated here.

[0113] As mentioned above, since the k-means clustering model has the advantages of fast convergence speed and few parameters to be tuned, the k-means clustering model is used for pre-clustering processing. While the clustering speed is fast, several target parameters in the subsequent self-iterative clustering can be obtained, reducing the operation complexity of the self-iterative clustering.

[0114] S003. Based on the given maximum merging number, initial iteration number, initial splitting coefficient, and several target parameters obtained from the preset number of initial vehicle clusters, use the self-iterative clustering model to perform iterative clustering on the preset number of initial vehicle clusters to obtain several final vehicle clusters. Those skilled in the art are aware of the specific implementation of the self-iterative clustering model and will not be elaborated here. The maximum merging number, initial iteration number, and initial splitting coefficient are all required parameters in the self-iterative clustering model and will not be explained in detail here.

[0115] Preferably, the method determines the maximum merging number through the following steps:

[0116] S0031. Obtain the distance Y between the travel feature vectors corresponding to any two initial vehicles in any initial vehicle cluster.

[0117] S0032. When Y ≤ ρ, merge the two initial vehicles and divide them into an initial vehicle group, where ρ is a preset distance threshold. It can be understood that each initial vehicle group contains several initial vehicles, and the distance between the travel feature vectors corresponding to any two initial vehicles within the group is not greater than the preset distance threshold.

[0118] S0033. Obtain the target vehicle group corresponding to each initial vehicle cluster. The target vehicle group corresponding to each initial vehicle cluster refers to the initial vehicle group with the largest number of initial vehicles among the several initial vehicle groups corresponding to the initial vehicle cluster itself.

[0119] S0034. Obtain the number of initial vehicles in each target vehicle group and determine the smallest number of initial vehicles as the maximum merging number.

[0120] As described above, based on the clustering result of the first clustering, according to the dispersion of several initial vehicles within each initial vehicle cluster in the clustering result, that is, the distance between the several travel eigenvalue vectors corresponding to the initial vehicles, calculate the maximum merging number corresponding to each initial vehicle cluster and use it as the initial parameter of the self-iterative clustering model, which can reduce the number of iterations of the secondary clustering, accelerate convergence, and improve the reliability of clustering.

[0121] Preferably, the method obtains the initial splitting coefficient ζ through the following steps:

[0122] Among them, the initial splitting coefficient ζ meets the following conditions:

[0123] ζ = ∑ h g=1 ((∑ Zg v=1 (L gv / λ g )) / Z g ) / h, where Lgv is the distance between the travel eigenvalue vector corresponding to the v-th initial vehicle in the g-th initial vehicle cluster and the center point vector of the g-th initial vehicle cluster, λ g is the maximum distance among the distances between the travel eigenvalue vectors corresponding to all the 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 g-th initial vehicle cluster, and 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 eigenvalues corresponding to the initial vehicle itself.

[0124] As mentioned above, the initial splitting coefficient is the difference between the self-iterative clustering model and the k-means clustering model. Based on the clustering results of the k-means clustering model, according to the dispersion of several initial vehicles in each initial vehicle cluster in the clustering results, that is, the distance between the travel eigenvalue vector corresponding to the initial vehicle and the center point vector of the initial vehicle cluster, the initial splitting coefficient corresponding to the self-iterative clustering model is obtained and used as an initial parameter of the self-iterative clustering model, which is beneficial 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 the secondary clustering.

[0125] Specifically, the several target parameters include the number of clustering clusters, the center point vector corresponding to each clustering cluster, the initial number of samples corresponding to each clustering cluster, the sample standard deviation threshold corresponding to each clustering cluster, and the initial shortest distance between clustering clusters; it can be understood that: the number of clustering 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 clustering cluster is respectively the center point vector corresponding to each initial vehicle cluster, the initial number of samples corresponding to each clustering cluster is the minimum number of samples in all initial vehicle clusters, the sample standard deviation threshold corresponding to each clustering cluster is not greater than the standard deviation of each initial vehicle cluster, and the initial shortest distance between clustering clusters is not greater than the shortest distance among the distances between any two initial vehicle clusters in all initial vehicle clusters.

[0126] As mentioned above, based on the k-means clustering model, the self-iterative clustering model adds three parameters: the maximum merging number, the initial number of iterations, and the initial splitting coefficient, adds operations of merging and splitting the clustering results, and performs iterations, making the sample features in each clustering cluster more similar, and thus obtaining a more accurate classification result.

[0127] S004, according to the preset screening conditions, screen out the corresponding final vehicle clusters from several final vehicle clusters, and determine each first vehicle in the screened final vehicle clusters as a target vehicle with a given travel feature.

[0128] Specifically, step S004 specifically includes the following steps:

[0129] S0041: Obtain 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 are 100, 150, and 200 respectively, the total number of vehicles is 100 + 150 + 200 = 450.

[0130] S0042: Obtain the average value η of the first spatial stability coefficient, the average value F of the first peak travel frequency, the average value Q of the first total travel frequency, the average value K of the first non-peak period average travel frequency, the average value θ of the first non-peak period travel frequency deviation coefficient, the average value S of the first starting point stability degree corresponding to the preset morning peak period, and the average value E of the first ending point stability degree according to the total number of vehicles and several initial travel characteristics corresponding to each first vehicle. 1 and the average value F of the first peak travel frequency 1 、the average value Q of the first total travel frequency 1 、the average value K of the first non-peak period average travel frequency 1 、the average value θ of the first non-peak period travel frequency deviation coefficient 1 、the average value S of the first starting point stability degree corresponding to the preset morning peak period 1 and the average value E of the first ending point stability degree 1 、the average value S of the first starting point stability degree corresponding to the preset evening peak period 0 1 and the average value E of the first ending point stability degree 0 1 .

[0131] Specifically, η 1 is the average value calculated according to the spatial stability coefficients of all first vehicles. The acquisition methods of F, Q, K, θ, S, E, S, and E are the same as that of η 1 、Q 1 、K 1 、θ 1 、S 1 、E 1 、S 0 1 and E 0 1 and will not be elaborated here. 1

[0132] S0043: Obtain the average value η of the second spatial stability coefficient, the average value F of the second peak travel frequency, the average value Q of the second total travel frequency, the average value K of the second non-peak period average travel frequency, the average value θ of the second non-peak period travel frequency deviation coefficient, the average value S of the second starting point stability degree corresponding to the preset morning peak period for each final vehicle cluster according to the number of vehicles in each final vehicle cluster and several initial travel characteristics corresponding to each first vehicle in each final vehicle cluster. 2 、the average value F of the second peak travel frequency 2 、the average value Q of the second total travel frequency 2 、the average value K of the second non-peak period average travel frequency 2 、the average value θ of the second non-peak period travel frequency deviation coefficient 2 、the average value S of the second starting point stability degree corresponding to the preset morning peak period2 and the average value E of the stability degree of the second end point 2 and the average value S of the stability degree of the second starting point corresponding to the preset evening rush hour 0 2 and the average value E of the stability degree of the second end point 0 2 .

[0133] Specifically, η 2 is the average value calculated based on the spatial stability coefficients of all the first vehicles in any one of the final vehicle clusters, F 2 , Q 2 , K 2 , θ 2 , S 2 , E 2 , S 0 2 and E 0 2 are obtained in the same way as η 2 , which will not be elaborated here; it can be understood that each final vehicle cluster corresponds to 9 indicators.

[0134] S0044, select from all the final vehicle clusters those that simultaneously 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 of the final vehicle clusters.

[0135] As mentioned above, F 2 and Q 2 are used to reflect the travel situation during the peak period, K 2 and θ 2One is used to reflect the off-peak travel situation, and the remaining five indicators are used to reflect the stability degree of the starting and ending points and the spatial stability degree. Therefore, through the above screening method, the final vehicle clusters that meet the conditions can be screened out more comprehensively and accurately. At the same time, the vehicles that meet the peak travel situation and have relatively stable starting and ending points during peak travel are screened out, that is, the required commuting vehicles are screened out, which is beneficial to the subsequent management and planning of the traffic in the area.

[0136] Embodiment 2

[0137] As Figure 6 shown, Embodiment 2 of the present invention provides a device for determining the stability degree of a vehicle starting point, including:

[0138] The first acquisition module 100 is used to acquire a plurality of first travel trajectories corresponding to a preset morning / evening peak period within a historical time period for any first vehicle in a given first vehicle set; it can be understood that: the acquisition methods of a plurality of first travel trajectories corresponding to the preset morning peak period within the historical time period for the first vehicle and a plurality of first travel trajectories corresponding to the preset evening peak period within the historical time period for the first vehicle are the same; 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.

[0139] Specifically, the first vehicle is any vehicle randomly selected from a plurality of vehicles.

[0140] Specifically, as Figure 7 shown, the first acquisition module 100 includes:

[0141] The receiving module 101 is used to receive 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 longitude and latitude information of the vehicle reported by the GPS device in real time.

[0142] The partitioning module 102 is used to partition the plurality of vehicle position information into a plurality of vehicle position information sets; the reporting times of the vehicle position information within each vehicle position information set are continuous and the reporting time intervals are not greater than a preset time threshold; the time interval between every two adjacent vehicle position information sets is greater than the preset time threshold.

[0143] For better understanding, the following description is made: for example, the preset time threshold is 15 min. If the times when the GPS device reports the vehicle position information three times in succession are 6:50, 7:10, and 7:11, then the vehicle position information reported at 6:50 is partitioned into the previous vehicle position information set, and the vehicle position information reported at 7:10 and 7:11 is jointly partitioned into the subsequent vehicle position information set.

[0144] The third acquisition module 103 is configured to obtain an initial travel trajectory corresponding to each set of vehicle position information according to a plurality of vehicle position information in each set of vehicle position information; in a specific implementation, the GPS device usually uploads vehicle position information every few seconds, and the plurality of vehicle position information in the set of vehicle position information are concatenated to obtain the corresponding initial travel trajectory.

[0145] The fourth acquisition module 104 is configured to, when the travel time corresponding to the initial travel trajectory overlaps with a preset morning / evening rush hour period, obtain the initial travel trajectory itself as the first travel trajectory corresponding to the first vehicle during the preset morning / evening rush hour period within a historical time period.

[0146] As described above, when obtaining the first travel trajectory corresponding to the morning / evening rush hour period of the vehicle over multiple days, first obtain the travel time of each first travel trajectory, regardless of the overlap size between the travel time and the morning / evening rush hour period. As long as there is an overlap, it is determined as the first travel trajectory corresponding to the morning / evening rush hour period. In this way, considering the different work start times of different people and the different distances between home and company, etc., which result in inconsistent travel times, it is possible to more comprehensively and reasonably determine a number of vehicles with morning / evening rush hour travel characteristics.

[0147] The second acquisition module 200 is configured to obtain a plurality of first starting hash values and a plurality of second starting hash values corresponding to the first vehicle according to the plurality of first travel trajectories; the first starting hash value refers to the first geohash value corresponding to a plurality of vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory, and the second starting hash value refers to the second geohash value corresponding to a plurality of 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 through 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 digits.

[0148] As described above, by obtaining a plurality of first starting hash values, it is possible to know the starting position of each travel of the first vehicle corresponding to a plurality of preset morning / evening rush hour periods, and then know whether each starting position is the same, which is beneficial to the subsequent determination of the starting stability degree, and at the same time can provide an important reference for the screening of vehicles with morning / evening rush hour travel characteristics.

[0149] The first determination module 300 is configured to respectively determine the first starting hash value with the largest number of the same and the second largest number of the same among the plurality of first starting hash values as the first target hash value and the second target hash value, and determine the second starting hash value with the largest number of the same among the plurality of second starting hash values as the third target hash value.

[0150] For better understanding, the following description is provided: For example, there are a total of ten first starting point hash values, among which five first starting point hash values all represent the first area, four first starting point hash values all 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.

[0151] A second determination module 400, configured to, when there is a situation where the first target hash value or the second target hash value is the same as the third target hash value, determine 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 as the starting point stability value of the first vehicle corresponding to the preset morning / evening peak period; otherwise, determine the ratio of the quantity corresponding to the first target hash value to the given number of days as the starting point stability value of the first vehicle corresponding to the preset morning / evening peak period; it can be understood that: the method for obtaining the starting point stability value of the first vehicle corresponding to the preset evening peak period is the same as that corresponding to the preset morning peak period.

[0152] Specifically, the given number of days refers to the number of days that belong to working days within the historical time period; in a specific implementation, the historical time period is generally selected as the past month, and the working days are from Monday to Friday every week.

[0153] As described above, according to the same situation between the third target hash value and the first target hash value or the second target hash value, different calculation methods for the starting point stability value 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 indicates that the travel trajectories are the same, and it may be the case that the starting points obtained are inconsistent due to errors in the reporting time of the GPS device. When the third target hash value is different from both the first target hash value and the second target hash value, it indicates that the travel trajectories are different, and thus the starting points of travel are different. Therefore, through the above calculation method, the obtained starting point stability value is more accurate and reasonable.

[0154] Furthermore, as Figure 8 shown, the device further includes an end point stability determination module, and the end point stability determination module includes:

[0155] The fifth acquisition module 10 is configured to obtain a plurality of first end hash values and a plurality of second end hash values corresponding to the first vehicle according to a plurality of first travel trajectories; the first end hash value refers to the last geohash value corresponding to a plurality of vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory, and the second end hash value refers to the penultimate geohash value corresponding to a plurality of 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 last hash block and the penultimate hash block are both seven digits.

[0156] As described above, by obtaining a plurality of first end hash values, it is possible to know the end position of each trip of the first vehicle corresponding to a plurality of preset morning / evening rush hour periods, and further to know whether each end position is the same, which is beneficial to the determination of the subsequent end stability degree, and at the same time can provide an important reference for the screening of vehicles with morning / evening rush hour travel characteristics.

[0157] The third determination module 20 is configured to respectively determine the first end hash value with the largest number of identical values and the second largest number of identical values among the plurality of first end hash values as the fourth target hash value and the fifth target hash value, and determine the second end hash value with the largest number of identical values among the plurality of second end hash values as the sixth target hash value.

[0158] The fourth determination module 30 is configured to, when there is an identical value between the fourth target hash value or the fifth target hash value and the sixth target hash value, determine 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 as the end stability degree value of the first vehicle corresponding to the preset morning / evening rush hour period; otherwise, determine the ratio of the quantity corresponding to the fourth target hash value to the given number of days as the end stability degree value of the first vehicle corresponding to the preset morning rush hour period; it can be understood that: the method for obtaining the end stability degree value of the first vehicle corresponding to the preset evening rush hour period is the same as that for the preset morning rush hour period.

[0159] As described above, in the process of obtaining the end degree stability value, the fourth target hash value, the fifth target hash value, and the sixth target hash value are determined by a backward deduction method. According to the identical situation between the sixth target hash value and the fourth target hash value or the fifth target hash value, different calculation methods for the end stability degree value are adopted. Similarly, the obtained end stability degree value is more accurate and reasonable.

[0160] Further, as Figure 9 shown, the device further includes a spatial stability coefficient acquisition module, and the spatial stability coefficient acquisition module includes:

[0161] The sixth acquisition module 40 is configured to acquire the spatial distance O between the first target hash value corresponding to the preset morning rush hour and the fourth target hash value corresponding to the preset morning rush hour. 1 D 1 and the spatial distance O between the first target hash value corresponding to the preset morning rush hour and the fourth target hash value corresponding to the preset evening rush hour. 1 D 2 and the spatial distance O between the first target hash value corresponding to the preset evening rush hour and the fourth target hash value corresponding to the preset morning rush hour. 2 D 1 and the spatial distance O between the first target hash value corresponding to the preset evening rush hour and the fourth target hash value corresponding to the preset evening rush hour. 2 D 2 .

[0162] The first processing module 50 is configured to obtain the distance matrix D of the starting and ending points according to 1 D 1 , 1 D 2 , 2 D 1 and 2 D 2 .

[0163] Specifically, the distance matrix D of the starting and ending points meets the following conditions:

[0164] .

[0165] The calculation module 60 is configured to calculate the spatial stability coefficient η corresponding to the first vehicle according to 1 D 1 , 1 D 2 , 2 D 1 , 2 D 2 and the distance matrix of the starting and ending points.

[0166] Specifically, the spatial stability coefficient η corresponding to the first vehicle meets the following conditions:

[0167] η = |D| / (max{ 1 D 1 , 2 D 2 ) 2 - ( 1 D 2 + 2 D 1 ) / max{ 1 D 1 , 2 D2}.

[0168] In the above, for the calculation of the spatial stability coefficient, based on the existing formula for the spatial stability coefficient, the meanings of the starting point and the ending point are changed. Through the calculation of the spatial stability coefficient, it is possible to reflect the changes in the starting point and the ending point of the vehicle during the peak period and the stability degree of the travel trajectory during the peak period. As a subsequent parameter, the spatial stability coefficient is conducive to screening out vehicles with peak travel characteristics.

[0169] Furthermore, as Figure 10 shown, the device further includes a target vehicle screening module, and the target vehicle screening module includes:

[0170] The second processing module 001 is configured to perform dimensionality reduction processing on the spatial stability coefficient corresponding to each first vehicle, the starting point stability degree values and the ending point stability degree values corresponding to the preset morning peak period respectively, the starting point stability degree values and the ending point stability degree values corresponding to the preset evening peak period respectively, and the peak travel frequency, total travel frequency, non-peak period average travel frequency, and non-peak period travel frequency deviation coefficient corresponding to each first vehicle obtained in advance, 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; it can be understood that: after dimensionality reduction processing on the multi-dimensional vector composed of the above nine indicators corresponding to each first vehicle, a target travel characteristic value vector with a preset number of dimensions is obtained; in this embodiment, the dimension after the dimensionality reduction processing is three dimensions.

[0171] For the convenience of understanding, the following explanations are made:

[0172] When performing dimensionality reduction processing using the factor analysis method, a number of initial travel characteristic values, that is, the multi-dimensional vector composed of the above nine indicators, are input into the factor analysis model, and the number of output factors can be actively set. In this embodiment, the number of output factors is set to three, that is, the vector composed of a number of initial travel characteristic values is reduced to three dimensions. Since the present application directly uses the factor analysis method of the existing technology, the specific implementation process thereof will not be elaborated herein.

[0173] In the above, by performing dimensionality reduction processing on a number of initial travel characteristic values of the first vehicle using the factor analysis method, it is possible to eliminate some linear relationships between multiple indicators, reduce the dimension of the vector, and use the vector after dimensionality reduction for clustering, which can reduce the clustering complexity and thus improve the reliability of clustering.

[0174] 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.

[0175] Specifically, the total travel frequency corresponding to the first vehicle is the ratio of the number of working days of travel within the historical time period to the given number of days.

[0176] Specifically, the average off-peak travel frequency P corresponding to the first vehicle meets the following conditions:

[0177] P = (∑ n j=1 (a j / A j )) / n, where n is the total number of days within the historical time period, a j is the number of off-peak trips on the j-th day within the historical time period, and A j is the total number of trips on the j-th day within the historical time period.

[0178] Specifically, the off-peak travel frequency deviation coefficient σ corresponding to the first vehicle meets the following conditions:

[0179] σ = sqrt((∑ n j=1 (a j / A j -P) 2 ) / n), where sqrt() is the square root function.

[0180] The first clustering module 002 is configured to cluster the first vehicles into a preset number of initial vehicle clusters according to the target travel feature value vectors corresponding to each first vehicle; it can be understood that: using the k-means clustering model to cluster m target travel feature value vectors, and obtaining the initial vehicle clusters corresponding to each cluster according to the clustering result and the first vehicle corresponding to each target travel feature value; for example, when there are three dimensions after dimensionality reduction, the target travel feature value vector corresponding to each first vehicle is a vector composed of three dimensions. Based on the target travel feature value vectors corresponding to each first vehicle, using the k-means clustering model to cluster a number of target travel feature value vectors. Those skilled in the art are aware of the specific implementation manner of the k-means clustering model and will not be elaborated here.

[0181] As mentioned above, since the k-means clustering model has advantages such as fast convergence speed and few parameters to be tuned, the k-means clustering model is used for pre-clustering processing. It can not only achieve fast clustering speed but also obtain several target parameters in the subsequent self-iterative clustering, reducing the operation complexity of the self-iterative clustering.

[0182] The second clustering module 003 is used to perform iterative clustering on the preset number of initial vehicle clusters by using a self-iterative clustering model according to the given maximum merging number, initial iteration number, initial splitting coefficient, and several target parameters obtained based on the preset number of initial vehicle clusters. Those skilled in the art are aware of the specific implementation of the self-iterative clustering model, which will not be elaborated here. The maximum merging number, initial iteration number, and initial splitting coefficient are all required parameters in the self-iterative clustering model and will not be explained in detail here.

[0183] Specifically, the several target parameters include the number of clustering clusters, the center point vector corresponding to each clustering cluster, the initial number of samples corresponding to each clustering cluster, the sample standard deviation threshold corresponding to each clustering cluster, and the initial shortest distance between clustering clusters. It can be understood that: the number of clustering 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 clustering cluster is the center point vector corresponding to each initial vehicle cluster respectively, the initial number of samples corresponding to each clustering cluster is the minimum number of samples in all initial vehicle clusters, the sample standard deviation threshold corresponding to each clustering cluster is not greater than the standard deviation of each initial vehicle cluster respectively, and the initial shortest distance between clustering clusters is not greater than the shortest distance among the distances between any two initial vehicle clusters in all initial vehicle clusters.

[0184] As described above, based on the k-means clustering model, the self-iterative clustering model adds three parameters: the maximum merging number, the initial iteration number, and the initial splitting coefficient, adds operations of merging and splitting the clustering results, and performs iteration, making the sample features in each clustering cluster more similar, and thus obtaining a more accurate classification result.

[0185] The screening module 004 is used to screen out the corresponding final vehicle clusters from several final vehicle clusters according to preset screening conditions, and determine each first vehicle in the screened final vehicle clusters as a target vehicle with given travel characteristics.

[0186] Specifically, the screening module 004 is specifically used for:

[0187] 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 are 100, 150, and 200 respectively, then the total number of vehicles is 100 + 150 + 200 = 450.

[0188] According to the total number of vehicles and several initial travel characteristics corresponding to each first vehicle, obtain the average value η of the first spatial stability coefficient 1 、the average value F of the first peak travel frequency 1 、the average value Q of the first total travel frequency 1, the average value K of the average travel frequency during the first off-peak period 1 , the average value θ of the deviation coefficient of the travel frequency during the first off-peak period 1 , the average value S of the stability degree of the first starting point corresponding to the preset morning peak period 1 and the average value E of the stability degree of the first ending point 1 , the average value S of the stability degree of the first starting point corresponding to the preset evening peak period 0 1 and the average value E of the stability degree of the first ending point 0 1 .

[0189] Specifically, η 1 is the average value calculated based on the spatial stability coefficients of all the first vehicles, F 1 , Q 1 , K 1 , θ 1 , S 1 , E 1 , S 0 1 and E 0 1 are obtained in the same way as η 1 , and will not be elaborated here.

[0190] 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, obtain the average value η of the second spatial stability coefficient corresponding to each final vehicle cluster 2 , the average value F of the second peak travel frequency 2 , the average value Q of the second total travel frequency 2 , the average value K of the average travel frequency during the second off-peak period 2 , the average value θ of the deviation coefficient of the travel frequency during the second off-peak period 2 , the average value S of the stability degree of the second starting point corresponding to the preset morning peak period 2 and the average value E of the stability degree of the second ending point 2 , the average value S of the stability degree of the second starting point corresponding to the preset evening peak period 0 2 and the average value E of the stability degree of the second ending point 0 2 .

[0191] Specifically, η 2 is the average value calculated based on the spatial stability coefficients of all the 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 acquisition methods of and E are the same as those of η 2 , which will not be elaborated here; it can be understood that each final vehicle cluster corresponds to 9 indicators.

[0192] Select from all the final vehicle clusters those that simultaneously 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 final vehicle clusters.

[0193] As mentioned above, F 2 and Q 2 are used to reflect the travel conditions during peak hours, K 2 and θ 2 are used to reflect the travel conditions during off-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, it is possible to more comprehensively and accurately screen out the final vehicle clusters that meet the conditions, and at the same time screen out the vehicles that meet the peak travel conditions and have relatively stable starting and ending points during peak travel, that is, screen out the required commuting vehicles, which is beneficial to the subsequent management and planning of the traffic in the area.

[0194] Embodiment 3

[0195] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented:

[0196] For any first vehicle in a given first vehicle set, obtain a plurality of first travel trajectories corresponding to the preset morning / evening peak hours within the historical time period of the first vehicle.

[0197] According to a number of first travel trajectories, a number of first starting hash values and a number of second starting hash values corresponding to the first vehicle are obtained; the first starting hash value refers to the first geohash value corresponding to a number of vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory, and the second starting hash value refers to the second geohash value corresponding to a number of vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory.

[0198] Determine the first target hash value and the second target hash value respectively as the first starting hash values with the largest and second largest number of identical ones among the number of first starting hash values, and determine the third target hash value as the second starting hash value with the largest number of identical ones among the number of second starting hash values.

[0199] When there is a situation where the first target hash value or the second target hash value is the same as the third target hash value, determine 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 as the starting stability value of the first vehicle corresponding to the preset morning / evening rush hour period; otherwise, determine the ratio of the quantity corresponding to the first target hash value to the given number of days as the starting stability value of the first vehicle corresponding to the preset morning / evening rush hour period; the method for obtaining the starting stability value of the first vehicle corresponding to the preset evening rush hour period is the same as that for the preset morning rush hour period.

[0200] Embodiment 4

[0201] 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:

[0202] For any first vehicle in a given set of first vehicles, obtain a number of first travel trajectories corresponding to the first vehicle during a historical time period for the preset morning / evening rush hour period.

[0203] According to a number of first travel trajectories, a number of first starting hash values and a number of second starting hash values corresponding to the first vehicle are obtained; the first starting hash value refers to the first geohash value corresponding to a number of vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory, and the second starting hash value refers to the second geohash value corresponding to a number of vehicle position information reported by the GPS device of the first vehicle in the first travel trajectory.

[0204] Determine the first target hash value and the second target hash value respectively as the first starting hash values with the largest and second largest number of identical ones among the number of first starting hash values, and determine the third target hash value as the second starting hash value with the largest number of identical ones among the number of second starting hash values.

[0205] When the 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 starting point stability value 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 starting point stability value of the first vehicle corresponding to the preset morning / evening peak period; the method for obtaining the starting point stability value of the first vehicle corresponding to the preset evening peak period is the same as that corresponding to the preset morning peak period.

[0206] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. 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 methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can 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.

[0207] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the above division of each functional unit and module is used as an example. In practical applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above.

[0208] Although some specific embodiments of the present invention have been described in detail by way of examples, those skilled in the art should understand that the above examples are only for illustration and not for limiting the scope of the present invention. Those skilled in the art should also understand that various modifications can 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 method for determining the stability of a vehicle starting point, characterized in that: The following steps are involved: 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 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 starting point stability value corresponding to the first vehicle during 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 starting point stability value corresponding to the first vehicle during the preset morning / evening peak period; The method further comprises the following steps: A factor analysis method is used to perform dimensionality reduction processing on the spatial stability coefficient corresponding to each first vehicle obtained in advance, the starting point stability value and the terminal point stability value corresponding to the preset morning peak period, the starting point stability value and the terminal point stability value corresponding to the preset evening peak period, and the peak travel frequency, total travel frequency, off-peak average travel frequency, and off-peak travel frequency deviation coefficient corresponding to each first vehicle obtained in advance, to obtain a target travel eigenvalue vector corresponding to each first vehicle; the dimension of each target travel eigenvalue 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; According to the given maximum number of merges, the initial number of iterations, the initial splitting coefficient and the several target parameters obtained based on the preset number of initial vehicle clusters, the preset number of initial vehicle clusters are iteratively clustered using the self-iterative clustering model to obtain several final vehicle clusters; wherein 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; 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 having a given travel characteristic; 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, 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.

2. The method for determining the stability of a vehicle starting point according to claim 1, characterized in that: The method obtains a plurality of first travel trajectories corresponding to a preset morning / evening peak period of a first vehicle in a historical time period by the following steps: Receiving a plurality of vehicle location information reported by the GPS device of the first vehicle within a historical time period; Dividing the plurality of vehicle position information into a plurality of vehicle position information sets; The reporting time of the vehicle location information in each vehicle location information set is continuous and the reporting time interval is no greater than the preset time threshold; the time interval between each two adjacent vehicle location information sets is greater than the preset time threshold; According to a plurality of vehicle position information in each vehicle position information set, an initial travel trajectory corresponding to each vehicle position information set is obtained; 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 the first travel trajectory corresponding to the preset morning / evening peak period of the first vehicle in the historical time period.

3. The method for determining the stability of a vehicle starting point according to claim 1, characterized in that: The method further comprises 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 terminal stability value corresponding to the first vehicle during the preset morning / evening peak period; otherwise, the ratio of the quantity corresponding to the fourth target hash value to the given number of days is determined as the terminal stability value corresponding to the first vehicle during the preset morning / evening peak period.

4. The method for determining the stability of a vehicle starting point according to claim 3, characterized in that: The method further comprises the following steps: Obtain the spatial distance O1D1 between the first target hash value corresponding to the preset morning peak period and the fourth target hash value corresponding to the preset morning peak period, the spatial distance O1D2 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, the spatial distance O2D1 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, and the spatial distance O2D2 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; According to O1D1, O1D2, O2D1 and O2D2, the distance matrix of the starting and ending points is obtained; The spatial stability coefficient corresponding to the first vehicle is calculated based on O1D1, O1D2, O2D1, O2D2 and the distance matrix of the starting and ending points.

5. The method for determining the stability of a vehicle starting point according to claim 1, characterized in that: The given number of days refers to the number of working days in the historical time period.

6. A device for determining the stability of a vehicle starting point, characterized in that: The device comprises: A first 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 second acquisition module is used 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 a plurality of first travel trajectories; the first starting point hash value refers to a first geohash value corresponding to a 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 a 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; A second determination module 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 the given number of days as the starting point stability value corresponding to the first vehicle during 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 starting point stability value corresponding to the first vehicle during the preset morning / evening peak period; The device further comprises a target vehicle screening module, wherein the target vehicle screening module comprises: The second processing module is used to use the factor analysis method to perform dimensionality reduction processing on the spatial stability coefficient corresponding to each first vehicle in advance, the starting point stability value and the terminal stability value corresponding to the preset morning peak period, the starting point stability value and the terminal stability value corresponding to the preset evening peak period, and the peak travel frequency, total travel frequency, off-peak average travel frequency, and off-peak travel frequency deviation coefficient corresponding to each first vehicle in advance, so as to obtain a target travel eigenvalue vector corresponding to each first vehicle; the dimension of each target travel eigenvalue 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; 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 number of merges, 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; wherein 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; A screening module, used for screening 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 with a given travel characteristic; Among them, the screening module is specifically used for: 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.

7. The device for determining the stability of a vehicle starting point according to claim 6, characterized in that: The first acquisition module includes: A receiving module, used for receiving a plurality of vehicle position information reported by the GPS device of the first vehicle within a historical time period; A division module, used to divide the plurality of vehicle position information into a plurality of vehicle position information sets; the reporting time of the vehicle position information in each vehicle position 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 position information sets is greater than the preset time threshold; A third acquisition module is used to acquire an initial travel trajectory corresponding to each vehicle position information set according to a plurality of vehicle position information in each vehicle position information set; The fourth acquisition module is used to obtain the initial trip trajectory itself as the first trip trajectory corresponding to the preset morning / evening peak period of the first vehicle in the historical time period when the driving time corresponding to the initial trip trajectory overlaps with the preset morning / evening peak period.

8. The device for determining the stability of a vehicle starting point according to claim 6, characterized in that: The device further includes an endpoint stability determination module, wherein the endpoint stability determination module includes: a fifth acquisition module, configured to acquire, 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; 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 terminal stability value corresponding to the first vehicle in 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 terminal stability value corresponding to the first vehicle in 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.

9. The device for determining the stability of a vehicle starting point according to claim 8, characterized in that: The device further includes a spatial stability coefficient acquisition module, and the spatial stability coefficient acquisition module includes: A sixth acquisition module is used to acquire a spatial distance O1D1 between a first target hash value corresponding to a preset morning peak period and a fourth target hash value corresponding to the preset morning peak period, a spatial distance O1D2 between a first target hash value corresponding to a preset morning peak period and a fourth target hash value corresponding to a preset evening peak period, a spatial distance O2D1 between a first target hash value corresponding to a preset evening peak period and a fourth target hash value corresponding to a preset morning peak period, and a spatial distance O2D2 between a first target hash value corresponding to a preset evening peak period and a fourth target hash value corresponding to a preset evening peak period; The first processing module is used to obtain a distance matrix of the start and end points according to O1D1, O1D2, O2D1 and O2D2; The calculation module is used to calculate the spatial stability coefficient corresponding to the first vehicle according to O1D1, O1D2, O2D1, O2D2 and the distance matrix of the starting and ending points.

10. The device for determining the stability of a vehicle starting point according to claim 6, characterized in that: The given number of days refers to the number of working days in the historical time period.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for determining the degree of stability of a vehicle starting point as claimed in any one of claims 1 to 5 is implemented.

12. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for determining the degree of stability of a vehicle starting point as claimed in any one of claims 1 to 5 is implemented.

Images