Track jump cheating scene analysis system and storage medium thereof

Abstract

The invention provides a trajectory jump cheating scene analysis system and a storage medium thereof, the system comprises a data processing unit, a calculation unit, a result output unit and a feedback processing unit, the data processing unit is connected with the calculation unit, the calculation unit is connected with the result output unit, and the result output unit is connected with the feedback processing unit; according to the method, the data processing unit is used for obtaining online car-hailing order trajectory path data, then data initialization, point speed recording, position direction recording and abnormal point elimination processing are carried out, then the calculation unit is used for calculating the path repetition degree according to the processed data by using the OWD algorithm, and meanwhile, the repetition starting point and the repetition ending point are recorded; and then the difference value between the total length of the non-direct-connection fragment data and the repeated path is solved, so that whether a track jump cheating phenomenon occurs can be directly judged according to a calculation result, the protection on the rights and interests of consumers is increased, the fair competition environment of online car hailing is maintained, and the protection on the overall reputation of an online car hailing platform is increased.

Description

Technical Field

[0001] The present invention relates to an analysis system, in particular to a track jumping cheating scenario analysis system, and belongs to the technical field of online car-hailing systems. Background Art

[0002] Online car-hailing, which is the abbreviation of online taxi booking service, refers to the business activities of building a service platform based on Internet technology, integrating supply and demand information, using qualified vehicles and drivers, and providing non-cruising taxi booking services.

[0003] With the continuous development of online car-hailing, the vitality of the industry has gradually increased, and more and more people have joined the industry of online car-hailing, and the industry prospects are thriving. In recent years, due to the saturation of online car-hailing drivers, the overall income of drivers is relatively low. In addition, since the billing rules of online car-hailing are related to the mileage, some drivers have begun to use cheating software to cheat the driving trajectory in order to increase their income, so that the final mileage of an order will be greater than the actual mileage. The principle of cheating software is to simulate the jump back of the originally normally recorded trajectory points, thereby increasing the mileage and improving the final revenue. This not only damages the rights and interests of consumers, but also destroys the fair competition environment of online car-hailing, and affects the overall reputation of the online car-hailing platform. For this reason, a trajectory jump cheating scenario analysis system and its storage medium are proposed. Summary of the invention

[0004] In view of this, the present invention provides a track jumping cheating scenario analysis system and a storage medium thereof to solve or alleviate the technical problems existing in the prior art and at least provide a beneficial choice.

[0005] The technical solution of the embodiment of the present invention is implemented as follows: a track jumping cheating scene analysis system includes a data processing unit, a calculation unit, a result output unit and a feedback processing unit, the data processing unit is connected to the calculation unit, the calculation unit is connected to the result output unit, and the result output unit is connected to the feedback processing unit;

[0006] Wherein, the data processing unit includes a data initialization module, a point speed recording module, a point direction recording module and an abnormal point elimination module;

[0007] Among them, the computing unit has a built-in OWD algorithm module;

[0008] The data processing unit is used to obtain the trajectory path data of the online car-hailing order and perform preliminary analysis and processing on the data;

[0009] The calculation unit is used to calculate the path repetition degree according to the data after preliminary processing by using the OWD algorithm, record the repetition starting point and ending point at the same time, and then calculate the difference between the total length of the non-directly connected segment data and the repeated path.

[0010] Further preferably, the result output unit is used to transmit the calculation result of the calculation unit to the feedback processing unit.

[0011] Further preferably, the feedback processing unit is used to set whether to perform direct connection calculation;

[0012] Among them, no direct connection calculation is the default value, and the received data is directly output through the feedback processing unit;

[0013] In which, direct connection calculation is performed, the direct connection section is calculated by the feedback processing unit, and then the maximum value of the direct connection and the indirect connection is taken and output.

[0014] Further preferably, the calculation of the directly connected road section is performed by intercepting the normal path from the starting point of the current path to the starting point of the speed anomaly as the current path, directly connecting the segments without anomalies, and calculating the remaining part.

[0015] Further preferably, the data initialization module is used to obtain the trajectory path data of the online car-hailing order, initialize the data into a point object, and store x, y, time data;

[0016] Among them, x and y are coordinates, and time is time data.

[0017] Further preferably, the point speed recording module is used to record each point of the point object and calculate the speed between two adjacent points;

[0018] The calculation threshold is 140-160, and points greater than the threshold are abnormal points. The abnormal points are counted through the point speed recording module to generate an abnormal point set.

[0019] Further preferably, the point direction recording module is used to calculate the direction of two vectors according to three consecutive points of the point object;

[0020] Among them, the angle less than 90° is an abnormal direction point. The abnormal direction points are counted through the point direction recording module to generate a set of abnormal direction points.

[0021] Further preferably, the outlier removal module adopts a Gaussian noise reduction algorithm to calculate the Euclidean distance between a single point of the point object and its surrounding adjacent points, calculates the mean standard deviation to establish an equation, and then uses a single discrete point through a credibility range;

[0022] The equation is:

[0023]

[0024] Among them, p1 and p2 are two adjacent points in the point object, x1 and y1 represent the coordinates corresponding to point p1, and x2 and y2 represent the coordinates corresponding to point p2.

[0025] Further preferably, the OWD algorithm module has a built-in OWD algorithm for calculating the distance between the point p and the closest point on the path R, and then calculating the average in reverse order to calculate the repeatability;

[0026] Among them, the distance from point p to path R is Dp, which is expressed as:

[0027] Dp(p,R)=min p2∈R d(p1,p2);

[0028] Among them, d(p1,p2) represents the Euclidean distance between points p1 and p2;

[0029] Among them, the one-way distance from path R1 to path R2 is Do, and the expression is:

[0030]

[0031] The calculation formula for repeatability is:

[0032]

[0033] A computer-readable storage medium stores thereon: a computer program for implementing a track jumping cheating scenario analysis system.

[0034] The embodiment of the present invention has the following advantages due to the adoption of the above technical solution:

[0035] 1. The present invention obtains the trajectory path data of the online car-hailing order by utilizing a data processing unit, and then initializes the data, records the point speed, the position direction and removes abnormal points. Then, the calculation unit uses the OWD algorithm to calculate the path repetition based on the processed data, and records the repeated starting point and the end point at the same time. Then, the difference between the total length of the non-directly connected segment data and the repeated path is calculated, so that whether the trajectory jumping cheating phenomenon occurs can be directly judged according to the calculation result, thereby increasing the protection of consumer rights and interests, maintaining a fair competition environment for online car-hailing, and increasing the protection of the overall reputation of the online car-hailing platform.

[0036] 2. The present invention uses a feedback processing unit to set whether to perform direct calculation, and then sets the direct calculation to intercept the normal path from the starting point of the current path to the starting point of the speed abnormality as the current path, directly connects the segments without abnormalities, and calculates the remaining parts to correct the driving trajectory.

[0037] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 It is a schematic block diagram of the system of the present invention;

[0040] Figure 2 is a system block diagram of a data processing unit of the present invention;

[0041] Figure 3 is a system block diagram of a computing unit of the present invention;

[0042] Figure 4 It is a schematic diagram of the process of the present invention;

[0043] Figure 5 This is a cheating track diagram of the first embodiment of the present invention;

[0044] Figure 6 This is a trajectory coordinate analysis diagram of the first embodiment of the present invention;

[0045] Figure 7 This is a cheating track diagram of the second embodiment of the present invention;

[0046] Figure 8 This is a trajectory coordinate analysis diagram of the second embodiment of the present invention;

[0047] Fig. 9 This is a cheating track diagram of the third embodiment of the present invention;

[0048] Fig.10 This is a trajectory coordinate analysis diagram of embodiment 3 of the present invention. DETAILED DESCRIPTION

[0049] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0050] It should be noted that the terms "first", "second", "symmetrical", "array", etc. are only used to distinguish between description and position description purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the definition of "first", "symmetrical", etc. can explicitly or implicitly include one or more of these features; similarly, when the number of certain features is not limited in the form of words such as "two" or "three", it should be noted that this feature also explicitly or implicitly includes one or more feature quantities.

[0051] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0052] Embodiment 1

[0053] like Figure 1-6 As shown, an embodiment of the present invention provides a track jumping cheating scenario analysis system, including a data processing unit, a calculation unit, a result output unit and a feedback processing unit, the data processing unit is connected to the calculation unit, the calculation unit is connected to the result output unit, and the result output unit is connected to the feedback processing unit;

[0054] Among them, the data processing unit includes a data initialization module, a point speed recording module, a point direction recording module and an abnormal point elimination module;

[0055] Among them, the computing unit has a built-in OWD algorithm module;

[0056] The data processing unit is used to obtain the trajectory path data of the online car-hailing order and perform preliminary analysis and processing on the data;

[0057] The calculation unit is used to calculate the path repetition degree according to the data after preliminary processing by using the OWD algorithm, record the repetition starting point and ending point at the same time, and then calculate the difference between the total length of the non-directly connected segment data and the repeated path.

[0058] In one embodiment, the result output unit is used to transmit the calculation result of the calculation unit to the feedback processing unit, and the feedback processing unit is used to set whether to perform direct connection calculation;

[0059] Among them, no direct connection calculation is the default value, and the received data is directly output through the feedback processing unit;

[0060] Among them, direct connection calculation is performed, the direct connection section is calculated by the feedback processing unit, and then the maximum value of the direct connection and the non-direct connection is taken and output;

[0061] The calculation of the directly connected section is to intercept the normal path from the starting point of the current path to the starting point of the speed anomaly as the current path, directly connect the segments without anomalies, and calculate the remaining part.

[0062] The output unit is used to obtain the settlement result of the calculation unit, and the calculation result is fed back to the feedback processing unit;

[0063] When the feedback processing unit is set not to perform direct connection calculation, the received data is directly output through the feedback processing unit;

[0064] When the feedback processing unit is set to perform direct connection calculation, the feedback processing unit intercepts the normal path from the starting point of the current path to the starting point of the speed abnormality as the normal path of the current path, directly connects the segments without abnormalities, calculates the remaining parts, and uses them to calculate the direct connection sections, and then takes the maximum value of the direct connection and the non-direct connection for output;

[0065] Among them, the point coordinates in the abnormal point set and the directional abnormal point set need to be removed during the calculation process.

[0066] In one embodiment, Figure 5-6 As shown, the data initialization module is used to obtain the trajectory path data of the online car-hailing order, initialize the data into a point object, and store x, y, and time data;

[0067] Among them, x and y are coordinates, and time is time data.

[0068] Initialize the data to facilitate subsequent calculations;

[0069] Among them, the point object is an object with x and y coordinates, which is used to represent the position of the two-dimensional space coordinates. It uses the Cartesian coordinate system to represent the position, and time represents the time corresponding to the point.

[0070] In one embodiment, the point speed recording module is used to record each point of the point object and calculate the speed between two adjacent points;

[0071] The calculation threshold is 140-160, and points greater than the threshold are abnormal points. The abnormal points are counted through the point speed recording module to generate an abnormal point set.

[0072] The point speed recording module uses the coordinates of the midpoint of the point object and the time corresponding to the coordinates to calculate the speed between the two points. When the calculation result is greater than 140, the two points are marked as abnormal points. Then the abnormal points are counted to generate an abnormal point set, so that the trajectory route can be corrected by removing the abnormal points in the subsequent direct connection calculation.

[0073] In one embodiment, the point direction recording module is used to calculate the direction of two vectors according to three consecutive points of the point object;

[0074] Among them, the angle less than 90° is an abnormal direction point. The abnormal direction points are counted through the point direction recording module to generate a direction abnormal point set.

[0075] By using the coordinates of the midpoint of the point object in the point position and direction recording module, the vector directions of three consecutive points are calculated. When the direction angle is less than 90°, the two points are marked as abnormal direction points. Then, the abnormal direction points are counted to generate an abnormal direction point set, so that the trajectory route can be corrected by removing the abnormal direction points in the subsequent direct connection calculation.

[0076] The calculation principle is: in two-dimensional space, the vector between two points (x1, y1) and (x2, y2) can be expressed as (x2-x1, y2-y1). The direction of the vector can be expressed as the ratio of these two coordinates, that is, θ = arctan2(y2-y1, x2-x1), where the arctan2 function returns the angle from the positive direction of the x-axis to the direction of the vector;

[0077] Take out three consecutive points, assuming they are point P1(x1, y1), point P2(x2, y2), and point P3(x3, y3);

[0078] Calculate the vector V1 from P1 to P2, whose direction is θ1 = arctan2(y2-y1, x2-x1);

[0079] Calculate the vector V2 from P2 to P3, whose direction is θ2=arctan2(y3-y2,x3-x2), then the angle θ between them can be obtained by cos(θ)=(V1·V2) / (|V1||V2|).

[0080] In one embodiment, the outlier removal module uses a Gaussian noise reduction algorithm to calculate the Euclidean distance between a single point of the point object and its surrounding adjacent points, calculates the mean standard deviation to establish an equation, and then uses a single discrete point through a credibility range;

[0081] The equation is:

[0082]

[0083] Among them, p1 and p2 are two adjacent points in the point object, x1 and y1 represent the coordinates corresponding to point p1, and x2 and y2 represent the coordinates corresponding to point p2.

[0084] The Euclidean distance between the object point and the surrounding adjacent points is calculated through the outlier removal module;

[0085] Among them, the credibility range can be set according to actual needs.

[0086] In one embodiment, the OWD algorithm module has a built-in OWD algorithm for calculating the distance between point p and the closest point on path R, and then performing reverse averaging to calculate the repeatability;

[0087] Among them, the distance from point p to path R is Dp, which is expressed as:

[0088] Dp(p,R)=min p2∈R d(p1,p2);

[0089] Among them, d(p1,p2) represents the Euclidean distance between points p1 and p2;

[0090] Among them, the one-way distance from path R1 to path R2 is Do, and the expression is:

[0091]

[0092] The calculation formula for repeatability is:

[0093]

[0094] The outgoing path repetition is calculated by using the OWD algorithm, and the calculation result is transmitted to the result output unit by using the calculation unit.

[0095] pass Figure 5 It can be seen that the original continuous trajectory is destroyed due to the abnormal jump point. This system extracts and analyzes the trajectory points to obtain Figure 6 ,like Figure 6 The trajectory shown has become a two-segment trajectory. When the final mileage is calculated traditionally, since the abnormal point is on the original trajectory path, the extra mileage is the overlapping mileage of the two trajectories, which increases the final mileage and improves the income of the cheating driver. The final calculation result of this system is that the original trajectory mileage is 55.35 kilometers and the cheating mileage is 62.07 kilometers.

[0096] Embodiment 2

[0097] like Figure 1-4 and Figure 7-8 As shown, an embodiment of the present invention provides a track jumping cheating scenario analysis system, including a data processing unit, a calculation unit, a result output unit and a feedback processing unit, the data processing unit is connected to the calculation unit, the calculation unit is connected to the result output unit, and the result output unit is connected to the feedback processing unit;

[0098] Among them, the data processing unit includes a data initialization module, a point speed recording module, a point direction recording module and an abnormal point elimination module;

[0099] Among them, the computing unit has a built-in OWD algorithm module;

[0100] The data processing unit is used to obtain the trajectory path data of the online car-hailing order and perform preliminary analysis and processing on the data;

[0101] The calculation unit is used to calculate the path repetition degree according to the data after preliminary processing by using the OWD algorithm, record the repetition starting point and ending point at the same time, and then calculate the difference between the total length of the non-directly connected segment data and the repeated path.

[0102] In one embodiment, the result output unit is used to transmit the calculation result of the calculation unit to the feedback processing unit, and the feedback processing unit is used to set whether to perform direct connection calculation;

[0103] Among them, no direct connection calculation is the default value, and the received data is directly output through the feedback processing unit;

[0104] Among them, direct connection calculation is performed, the direct connection section is calculated by the feedback processing unit, and then the maximum value of the direct connection and the non-direct connection is taken and output;

[0105] The calculation of the directly connected section is to intercept the normal path from the starting point of the current path to the starting point of the speed anomaly as the current path, directly connect the segments without anomalies, and calculate the remaining part.

[0106] The output unit is used to obtain the settlement result of the calculation unit, and the calculation result is fed back to the feedback processing unit;

[0107] When the feedback processing unit is set not to perform direct connection calculation, the received data is directly output through the feedback processing unit;

[0108] When the feedback processing unit is set to perform direct connection calculation, the feedback processing unit intercepts the normal path from the starting point of the current path to the starting point of the speed abnormality as the normal path of the current path, directly connects the segments without abnormalities, calculates the remaining parts, and uses them to calculate the direct connection sections, and then takes the maximum value of the direct connection and the non-direct connection for output;

[0109] Among them, the point coordinates in the abnormal point set and the directional abnormal point set need to be removed during the calculation process.

[0110] In one embodiment, Figure 7-8 As shown, the data initialization module is used to obtain the trajectory path data of the online car-hailing order, initialize the data into a point object, and store x, y, and time data;

[0111] Among them, x and y are coordinates, and time is time data.

[0112] Initialize the data to facilitate subsequent calculations;

[0113] Among them, the point object is an object with x and y coordinates, which is used to represent the position of the two-dimensional space coordinates. It uses the Cartesian coordinate system to represent the position, and time represents the time corresponding to the point.

[0114] In one embodiment, the point speed recording module is used to record each point of the point object and calculate the speed between two adjacent points;

[0115] The calculation threshold is 150, and points greater than the threshold are abnormal points. The abnormal points are counted through the point speed recording module to generate an abnormal point set.

[0116] The point speed recording module uses the coordinates of the midpoint of the point object and the time corresponding to the coordinates to calculate the speed between the two points. When the calculation result is greater than 150, the two points are marked as abnormal points. Then the abnormal points are counted to generate an abnormal point set, so that the trajectory route can be corrected by removing the abnormal points in the subsequent direct connection calculation.

[0117] In one embodiment, the point direction recording module is used to calculate the direction of two vectors according to three consecutive points of the point object;

[0118] Among them, the angle less than 90° is an abnormal direction point. The abnormal direction points are counted through the point direction recording module to generate a direction abnormal point set.

[0119] By using the coordinates of the midpoint of the point object in the point position and direction recording module, the vector directions of three consecutive points are calculated. When the direction angle is less than 90°, the two points are marked as abnormal direction points. Then, the abnormal direction points are counted to generate an abnormal direction point set, so that the trajectory route can be corrected by removing the abnormal direction points in the subsequent direct connection calculation.

[0120] The calculation principle is: in two-dimensional space, the vector between two points (x1, y1) and (x2, y2) can be expressed as (x2-x1, y2-y1). The direction of the vector can be expressed as the ratio of these two coordinates, that is, θ = arctan2(y2-y1, x2-x1), where the arctan2 function returns the angle from the positive direction of the x-axis to the direction of the vector;

[0121] Take out three consecutive points, assuming they are point P1(x1, y1), point P2(x2, y2), and point P3(x3, y3);

[0122] Calculate the vector V1 from P1 to P2, whose direction is θ1 = arctan2(y2-y1, x2-x1);

[0123] Calculate the vector V2 from P2 to P3, whose direction is θ2=arctan2(y3-y2,x3-x2), then the angle θ between them can be obtained by cos(θ)=(V1·V2) / (|V1||V2|).

[0124] In one embodiment, the outlier removal module uses a Gaussian noise reduction algorithm to calculate the Euclidean distance between a single point of the point object and its surrounding adjacent points, calculates the mean standard deviation to establish an equation, and then uses a single discrete point through a credibility range;

[0125] The equation is:

[0126]

[0127] Among them, p1 and p2 are two adjacent points in the point object, x1 and y1 represent the coordinates corresponding to point p1, and x2 and y2 represent the coordinates corresponding to point p2.

[0128] The Euclidean distance between the object point and the surrounding adjacent points is calculated through the outlier removal module;

[0129] Among them, the credibility range can be set according to actual needs.

[0130] In one embodiment, the OWD algorithm module has a built-in OWD algorithm for calculating the distance between point p and the closest point on path R, and then performing reverse averaging to calculate the repeatability;

[0131] Among them, the distance from point p to path R is Dp, which is expressed as:

[0132] Dp(p,R)=min p2∈R d(p1,p2);

[0133] Among them, d(p1,p2) represents the Euclidean distance between points p1 and p2;

[0134] Among them, the one-way distance from path R1 to path R2 is Do, and the expression is:

[0135]

[0136] The calculation formula for repeatability is:

[0137]

[0138] The outgoing path repetition is calculated by using the OWD algorithm, and the calculation result is transmitted to the result output unit by using the calculation unit.

[0139] pass Figure 7Although the generated trajectory jump point is on the original trajectory, the subsequent trajectory is slightly different from the original trajectory. This system extracts and analyzes the trajectory points to obtain Figure 8 ,like Figure 8 The jump point of the shown trajectory is on the original trajectory, but the two-segment trajectory formed is obviously different. In addition to the overlapping part, the extra mileage also includes extra trajectories. The final calculation result is that the original trajectory mileage is 41.94 kilometers and the cheating mileage is 67.26 kilometers.

[0140] Embodiment 3

[0141] like Figure 1-4 and Figure 9-10 As shown, an embodiment of the present invention provides a track jumping cheating scenario analysis system, including a data processing unit, a calculation unit, a result output unit and a feedback processing unit, the data processing unit is connected to the calculation unit, the calculation unit is connected to the result output unit, and the result output unit is connected to the feedback processing unit;

[0142] Among them, the data processing unit includes a data initialization module, a point speed recording module, a point direction recording module and an abnormal point elimination module;

[0143] Among them, the computing unit has a built-in OWD algorithm module;

[0144] The data processing unit is used to obtain the trajectory path data of the online car-hailing order and perform preliminary analysis and processing on the data;

[0145] The calculation unit is used to calculate the path repetition degree according to the data after preliminary processing by using the OWD algorithm, record the repetition starting point and ending point at the same time, and then calculate the difference between the total length of the non-directly connected segment data and the repeated path.

[0146] In one embodiment, the result output unit is used to transmit the calculation result of the calculation unit to the feedback processing unit, and the feedback processing unit is used to set whether to perform direct connection calculation;

[0147] Among them, no direct connection calculation is the default value, and the received data is directly output through the feedback processing unit;

[0148] Among them, direct connection calculation is performed, the direct connection section is calculated by the feedback processing unit, and then the maximum value of the direct connection and the non-direct connection is taken and output;

[0149] The calculation of the directly connected section is to intercept the normal path from the starting point of the current path to the starting point of the speed anomaly as the current path, directly connect the segments without anomalies, and calculate the remaining part.

[0150] The output unit is used to obtain the settlement result of the calculation unit, and the calculation result is fed back to the feedback processing unit;

[0151] When the feedback processing unit is set not to perform direct connection calculation, the received data is directly output through the feedback processing unit;

[0152] When the feedback processing unit is set to perform direct connection calculation, the feedback processing unit intercepts the normal path from the starting point of the current path to the starting point of the speed abnormality as the normal path of the current path, directly connects the segments without abnormalities, calculates the remaining parts, and uses them to calculate the direct connection sections, and then takes the maximum value of the direct connection and the non-direct connection for output;

[0153] Among them, the point coordinates in the abnormal point set and the directional abnormal point set need to be removed during the calculation process.

[0154] In one embodiment, Figure 9-10 As shown, the data initialization module is used to obtain the trajectory path data of the online car-hailing order, initialize the data into a point object, and store x, y, and time data;

[0155] Among them, x and y are coordinates, and time is time data.

[0156] Initialize the data to facilitate subsequent calculations;

[0157] Among them, the point object is an object with x and y coordinates, which is used to represent the position of the two-dimensional space coordinates. It uses the Cartesian coordinate system to represent the position, and time represents the time corresponding to the point.

[0158] In one embodiment, the point speed recording module is used to record each point of the point object and calculate the speed between two adjacent points;

[0159] The calculation threshold is 160, and points greater than the threshold are abnormal points. The abnormal points are counted through the point speed recording module to generate an abnormal point set.

[0160] The point speed recording module uses the coordinates of the midpoint of the point object and the time corresponding to the coordinates to calculate the speed between the two points. When the calculation result is greater than 160, the two points are marked as abnormal points. Then the abnormal points are counted to generate an abnormal point set, so that the trajectory route can be corrected by removing the abnormal points in the subsequent direct connection calculation.

[0161] In one embodiment, the point direction recording module is used to calculate the direction of two vectors according to three consecutive points of the point object;

[0162] Among them, the angle less than 90° is an abnormal direction point. The abnormal direction points are counted through the point direction recording module to generate a direction abnormal point set.

[0163] By using the coordinates of the midpoint of the point object in the point position and direction recording module, the vector directions of three consecutive points are calculated. When the direction angle is less than 90°, the two points are marked as abnormal direction points. Then, the abnormal direction points are counted to generate an abnormal direction point set, so that the trajectory route can be corrected by removing the abnormal direction points in the subsequent direct connection calculation.

[0164] The calculation principle is: in two-dimensional space, the vector between two points (x1, y1) and (x2, y2) can be expressed as (x2-x1, y2-y1). The direction of the vector can be expressed as the ratio of these two coordinates, that is, θ = arctan2(y2-y1, x2-x1), where the arctan2 function returns the angle from the positive direction of the x-axis to the direction of the vector;

[0165] Take out three consecutive points, assuming they are point P1(x1, y1), point P2(x2, y2), and point P3(x3, y3);

[0166] Calculate the vector V1 from P1 to P2, whose direction is θ1 = arctan2(y2-y1, x2-x1);

[0167] Calculate the vector V2 from P2 to P3, whose direction is θ2=arctan2(y3-y2,x3-x2), then the angle θ between them can be obtained by cos(θ)=(V1·V2) / (|V1||V2|).

[0168] In one embodiment, the outlier removal module uses a Gaussian noise reduction algorithm to calculate the Euclidean distance between a single point of the point object and its surrounding adjacent points, calculates the mean standard deviation to establish an equation, and then uses a single discrete point through a credibility range;

[0169] The equation is:

[0170]

[0171] Among them, p1 and p2 are two adjacent points in the point object, x1 and y1 represent the coordinates corresponding to point p1, and x2 and y2 represent the coordinates corresponding to point p2.

[0172] The Euclidean distance between the object point and the surrounding adjacent points is calculated through the outlier removal module;

[0173] Among them, the credibility range can be set according to actual needs.

[0174] In one embodiment, the OWD algorithm module has a built-in OWD algorithm for calculating the distance between point p and the closest point on path R, and then performing reverse averaging to calculate the repeatability;

[0175] Among them, the distance from point p to path R is Dp, which is expressed as:

[0176] Dp(p,R)=min p2∈R d(p1,p2);

[0177] Among them, d(p1,p2) represents the Euclidean distance between points p1 and p2;

[0178] Among them, the one-way distance from path R1 to path R2 is Do, and the expression is:

[0179]

[0180] The calculation formula for repeatability is:

[0181]

[0182] The outgoing path repetition is calculated by using the OWD algorithm, and the calculation result is transmitted to the result output unit by using the calculation unit.

[0183] like Fig. 9 As shown in the figure, the track jump point is on the original track and is completely covered. It is not difficult to find that the original track is already a complete driving track. The cheating track jump point is to perform a cheating jump simulation at the final moment of the trip, so as to achieve the effect of increasing the final mileage. Fig.10 As shown, this system extracts and analyzes the trajectory points, and the final calculation result is that the original trajectory mileage is 17.54 kilometers and the cheating mileage is 22.44 kilometers.

[0184] Trajectory continuity: Trajectory continuity means that the cosine value of the angle between the vector of the previous point and the point and the vector of the point and the next point in the trajectory is infinitely close to 1;

[0185] Two-segment trajectory: The trajectory refers to the continuous points from the starting point to the end point. The two-segment trajectory is composed of two trajectories from the starting point to the end point, and the two trajectories are non-continuous;

[0186] Trajectory jump: Trajectory jump refers to the abnormal trajectory point appearing in the originally continuous trajectory, which destroys the trajectory continuity and makes the trajectory become a two-segment trajectory;

[0187] Trajectory jump point: The abnormal trajectory point where the trajectory jump occurs becomes the trajectory jump point;

[0188] Original trajectory: the original normal continuous trajectory.

[0189] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of various changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A track jumping cheating scenario analysis system, comprising a data processing unit, a calculation unit, a result output unit and a feedback processing unit, characterized in that: The data processing unit is connected to the calculation unit, the calculation unit is connected to the result output unit, and the result output unit is connected to the feedback processing unit; Wherein, the data processing unit includes a data initialization module, a point speed recording module, a point direction recording module and an abnormal point elimination module; Among them, the computing unit has a built-in OWD algorithm module; The data processing unit is used to obtain the trajectory path data of the online car-hailing order and perform preliminary analysis and processing on the data; The calculation unit is used to calculate the path repetition degree according to the data after preliminary processing by using the OWD algorithm, record the repetition starting point and ending point at the same time, and then calculate the difference between the total length of the non-directly connected segment data and the repeated path.

2. The track jumping cheating scenario analysis system according to claim 1, characterized in that: The result output unit is used to transmit the calculation result of the calculation unit to the feedback processing unit.

3. The track jumping cheating scenario analysis system according to claim 1, characterized in that: The feedback processing unit is used to set whether to perform direct connection calculation; Among them, no direct connection calculation is the default value, and the received data is directly output through the feedback processing unit; In which, direct connection calculation is performed, the direct connection section is calculated by the feedback processing unit, and then the maximum value of the direct connection and the indirect connection is taken and output.

4. The track jumping cheating scenario analysis system according to claim 3 is characterized by: The direct-connected road section calculation is to intercept the normal path from the starting point of the current path to the starting point of the speed anomaly as the current path, directly connect the segments without anomalies, and calculate the remaining parts.

5. The track jumping cheating scenario analysis system according to claim 1, characterized in that: The data initialization module is used to obtain the trajectory path data of the online car-hailing order, initialize the data into a point object, and store x, y, and time data; Among them, x and y are coordinates, and time is time data.

6. The track jumping cheating scenario analysis system according to claim 5, characterized in that: The point speed recording module is used to record each point of the point object and calculate the speed between two adjacent points; The calculation threshold is 140-160, and points greater than the threshold are abnormal points. The abnormal points are counted through the point speed recording module to generate an abnormal point set.

7. The track jumping cheating scenario analysis system according to claim 6, characterized in that: The point direction recording module is used to calculate the direction of two vectors according to three consecutive points of the point object; Among them, the angle less than 90° is an abnormal direction point. The abnormal direction points are counted through the point direction recording module to generate a set of abnormal direction points.

8. The track jumping cheating scenario analysis system according to claim 7, characterized in that: The outlier removal module adopts Gaussian noise reduction algorithm to calculate the Euclidean distance between the single point of the point object and the surrounding adjacent points, calculates the mean standard deviation to establish an equation, and then uses the credibility range to separate the single discrete points; The equation is: Among them, p1 and p2 are two adjacent points in the point object, x1 and y1 represent the coordinates corresponding to point p1, and x2 and y2 represent the coordinates corresponding to point p2.

9. The track jumping cheating scenario analysis system according to claim 8, characterized in that: The OWD algorithm module has a built-in OWD algorithm for calculating the distance between point p and the closest point on path R, and then calculating the average in reverse order to calculate the repeatability; Among them, the distance from point p to path R is Dp, which is expressed as: Dp(p,R)=min p2∈R d(p1,p2); Among them, d(p1,p2) represents the Euclidean distance between points p1 and p2; Among them, the one-way distance from path R1 to path R2 is Do, and the expression is: The calculation formula for repeatability is:

10. A computer-readable storage medium, characterized in that: Stored thereon is: a computer program for implementing the track jumping cheating scenario analysis system as described in any one of claims 1-9.

Images