Method for identifying abnormity of online car-hailing driver order structure

Abstract

The invention discloses a method for identifying abnormity of an online car-hailing driver order structure, and the method comprises the steps: S1, carrying out the statistics of orders completed in the past n days; s2, respectively calculating an order X1 of which the driver order preferential amount proportion is too high, an order X2 of which the driver order amount exceeds m, an order quantity X3 of which each driver order placing city is inconsistent with a working city, an order quantity X4 of which the driver order service mileage is smaller than n, and an order quantity X5 of which the driver order is in a to-be-paid state, calculating the order quantity X6 of the first order of the user in the driver order; through calculating the overall order structure condition of the driver, whether the driver has an abnormal cheating condition is reversely judged, the condition that the driver risk behavior is identified only through order granularity is supplemented, and the capability of identifying the abnormal risk of the driver by the online car-hailing platform is expanded; order abnormal scenes can be expanded and supplemented according to different operation conditions of the platform, flexible configuration is supported, and the method is suitable for identification of various abnormal scenes.

Description

Technical Field

[0001] The present invention belongs to the technical field of online car-hailing platforms, and specifically relates to a method for identifying abnormalities in the order structure of online car-hailing drivers. Background Art

[0002] During the operation of online ride-hailing platforms, drivers often cheat or harm the interests of the platform or users in various ways. These cheating behaviors are often difficult to identify through a single driver's order, but the order structure and data characteristics of cheating drivers and risky drivers are often very different from the data performance of normal drivers. The current problems that are prone to occur include:

[0003] 1. Currently, online ride-hailing platforms identify drivers’ risky behaviors mainly through the various characteristics of individual orders, which makes it easy for drivers to evade penalties and risk control strategies through targeted confrontation;

[0004] 3. There are many abnormal scenarios, and various cheating channels and methods. It is difficult to identify the abnormal causes and control of a single order;

[0005] 3. Lack of solutions and functions to identify driver cheating based on the driver's overall order structure and data characteristics;

[0006] To this end, the present invention designs a method for identifying abnormalities in the order structure of online car-hailing drivers. Summary of the invention

[0007] The purpose of the present invention is to provide a method for identifying abnormalities in the order structure of online car-hailing drivers, so as to solve the problems raised in the above-mentioned background technology.

[0008] To achieve the above-mentioned purpose, the present invention provides the following technical solution: a method for identifying abnormalities in the order structure of online car-hailing drivers, the specific steps comprising: S1: start, count the orders completed in the past n days;

[0009] S2: Calculate the number of orders with too high a percentage of discount amount in driver orders X1, calculate the number of orders with a driver order amount exceeding m X2, calculate the number of orders with inconsistent order cities and working cities for each driver order X3, calculate the number of orders with service mileage less than n in driver orders X4, calculate the number of orders in the driver order that are pending payment X5, and calculate the number of first orders of users in the driver order X6;

[0010] S3: Remove duplicates from the above abnormal orders and calculate X1+X2+..._X6 to get the number of abnormal orders Y from the driver;

[0011] S4: Determine whether the number of abnormal driver orders Y / the total number of driver orders Y2>a. If not, the determination ends. If so, it is considered that the driver's order structure is abnormal.

[0012] S5: further judge whether X2 / Y2>b. If so, it is considered that the driver's large orders account for too much, the abnormality is high, and it is a severe abnormality;

[0013] S6: Determine if X5 / Y2>c. If so, it means that the driver has too many pending orders, which is a serious abnormality.

[0014] S7: Risk screening is carried out according to the abnormality level, and drivers with severe abnormalities enter the risk control process;

[0015] S8: Other abnormal drivers are under continuous observation;

[0016] S9: End.

[0017] Preferably, in step S2, the abnormal type of orders is not limited to the above-mentioned types, but can be increased and adjusted according to the specific situation of the platform.

[0018] Preferably, in step S4, a is a set threshold value, and the threshold value of a can be adjusted according to the platform conditions.

[0019] Preferably, in step S5, b is a set threshold value, and the threshold value of b can be adjusted according to the platform conditions.

[0020] Preferably, in step S6, c is a set threshold value, and the threshold value of c can be adjusted according to the platform conditions.

[0021] Compared with the prior art, the beneficial effects of the present invention are: by calculating the overall order structure of the driver, it is possible to reversely judge whether the driver has any abnormal cheating situation, which supplements the situation of identifying the driver's risky behavior only through the order granularity, and expands the ability of the online car-hailing platform to identify the abnormal risks of drivers; the order abnormality scenarios can be expanded and supplemented according to the different operating conditions of the platform, supports flexible configuration, and is suitable for the identification of various abnormal scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] See also Figure 1 ,The present invention provides a technical solution: a method for identifying abnormal order structure of online ride-hailing ,drivers, S1: start and count the completed orders in the past n days;

[0025] S2: Calculate the number of orders with too high a percentage of discount amount in driver orders X1, calculate the number of orders with a driver order amount exceeding m X2, calculate the number of orders with inconsistent order cities and working cities for each driver order X3, calculate the number of orders with service mileage less than n in driver orders X4, calculate the number of orders in the driver order that are pending payment X5, and calculate the number of first orders of users in the driver order X6;

[0026] S3: Remove duplicates from the above abnormal orders and calculate X1+X2+..._X6 to get the number of abnormal orders Y from the driver;

[0027] S4: Determine whether the number of abnormal driver orders Y / the total number of driver orders Y2>60%. If not, the determination is terminated. If so, it is considered that the driver's order structure is abnormal.

[0028] S5: Further determine if X2 / Y2>60%. If so, it is considered that the driver's large orders account for too many and the abnormality is high, which is a severe abnormality;

[0029] S6: Determine if X5 / Y2>60%. If so, it means that the driver has too many pending orders, which is a serious abnormality.

[0030] S7: Risk screening is carried out according to the abnormality level, and drivers with severe abnormalities enter the risk control process;

[0031] S8: Other abnormal drivers are under continuous observation;

[0032] S9: End.

[0033] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for identifying abnormalities in the order structure of online car-hailing drivers, characterized by: The specific steps include: S1: Start by counting the orders completed in the past n days; S2: Calculate the number of orders with too high a percentage of discount amount in driver orders X1, calculate the number of orders with a driver order amount exceeding m X2, calculate the number of orders with inconsistent order cities and working cities for each driver order X3, calculate the number of orders with service mileage less than n in driver orders X4, calculate the number of orders in the driver order that are pending payment X5, and calculate the number of first orders of users in the driver order X6; S3: Remove duplicates from the above abnormal orders and calculate X1+X2+..._X6 to get the number of abnormal orders Y from the driver; S4: Determine whether the number of abnormal driver orders Y / the total number of driver orders Y2>a. If not, the determination ends. If so, it is considered that the driver's order structure is abnormal. S5: further judge whether X2 / Y2>b. If so, it is considered that the driver's large orders account for too much, the abnormality is high, and it is a severe abnormality; S6: Determine if X5 / Y2>c. If so, it means that the driver has too many pending orders, which is a serious abnormality. S7: Risk screening is carried out according to the abnormality level, and drivers with severe abnormalities enter the risk control process; S8: Other abnormal drivers are under continuous observation; S9: End.

2. A method for identifying abnormalities in the order structure of online car-hailing drivers according to claim 1, characterized in that: In step S2, the abnormal type of orders is not limited to the above types, but can be increased and adjusted according to the specific situation of the platform.

3. A method for identifying abnormalities in the order structure of online car-hailing drivers according to claim 1, characterized in that: In step S4, a is a set threshold value, and the threshold value of a can be adjusted according to the platform conditions.

4. A method for identifying abnormalities in the order structure of online car-hailing drivers according to claim 1, characterized in that: In step S5, b is a set threshold value, and the threshold value of b can be adjusted according to the platform conditions.

5. The method for identifying abnormalities in the order structure of online car-hailing drivers according to claim 1, characterized in that: In step S6, c is a set threshold value, and the threshold value of c can be adjusted according to the platform conditions.

Images