Contribution degree driver classification method

Abstract

The invention discloses a contribution degree driver classification method. The method comprises the following steps: S1, collecting travel order data; s2, calculating the contribution degree of a driver; s3, classifying drivers according to contribution degrees; and S4, applying driver classification marking. According to the contribution degree driver classification method provided by the invention, classification is carried out according to the contribution degree of the drivers to enterprise profit, subsidy increase and order dispatching priority adjustment are carried out on the drivers with high contribution degree, the problem of effective subsidy of travel enterprises to the drivers can be solved, and benign development and profit increase of the enterprises can be promoted.

Description

Technical Field

[0001] The present invention relates to travel fields such as online car-hailing and taxis, and in particular to a driver classification method based on contribution. Background Art

[0002] For travel companies to achieve healthy development, they need to achieve a win-win situation between passenger subsidies, driver subsidies, and corporate profits. The travel industry generally uses rewards to encourage drivers to accept orders. The traditional method is to use fixed rules to encourage drivers to complete more orders and adjust the priority of driver dispatch based on passenger evaluations. If drivers are classified according to their contribution to the company's profits, it can promote better development of drivers and companies. To this end, a new technology is needed to solve this problem. Summary of the invention

[0003] The present invention is aimed at the deficiencies in the prior art. The present invention provides a method for classifying drivers based on their contribution. The method classifies drivers according to their contribution to corporate profits, increases subsidies and adjusts dispatch priorities for drivers with high contribution. This can solve the problem of effective subsidies for drivers by travel companies, promote healthy development and profit growth of companies, and meet actual usage requirements.

[0004] To solve the above problems, the technical solutions adopted by the present invention are as follows:

[0005] A driver classification method based on contribution includes the following steps:

[0006] S1. Collect travel order data

[0007] It is necessary to collect order data within 7 days. Each order data includes: driver ID, order number, order amount orderFee, passenger subsidy amount couponFee, passenger payment amount payFee, driver share amount driverFee, and driver travel time workTime;

[0008] The driver's driving time includes the pick-up time and the time the driver waits for the passenger to get on the car. The profit entProfit of the order is calculated as follows: entProfit = orderFee-couponFee-payFee-driverFee;

[0009] S2. Calculate driver contribution

[0010] Assuming that the driver has n orders within the data collection period (7 days), the driver's profit driverEntProfit for n orders is calculated as: driverEntProfit = ∑orderFee - ∑couponFee - ∑payFee - ∑driverFee; the driver's total working time for n orders driverWorkTime = ∑worktime;

[0011] The driver's contribution p = driverEntProfit / driverWorkTime, where p represents the profit contributed by the driver per unit time;

[0012] S3. Classify drivers by contribution

[0013] Drivers with p≥0 are put into set S1, and drivers with p<0 are put into set S2, S1 is the positive contribution set, and S2 is the negative contribution set;

[0014] The classification method for positive contribution sets is:

[0015] Sort the drivers in S1 by contribution from greatest to smallest, i.e. the drivers with greatest contribution are at the front and the drivers with least contribution are at the back;

[0016] The top 20% of drivers are marked as important contributing drivers, the middle 20%-50% are marked as medium contributing drivers, and the last 50%-100% are marked as ordinary contributing drivers;

[0017] The classification method for negative contribution sets is:

[0018] (1) Sort the drivers in S2 by their contribution from greatest to least, i.e., drivers with greater contribution are ranked first and drivers with less contribution are ranked last;

[0019] (2) The top 95% of drivers are marked as negative contribution drivers, and the bottom 5% of drivers are marked as risky drivers;

[0020] S4. Apply driver classification tags

[0021] After the driver classification is completed, the five categories of drivers are marked in order: important contribution drivers, medium contribution drivers, ordinary contribution drivers, negative contribution drivers, and risky drivers;

[0022] Here is how to apply the driver contribution classification:

[0023] The application method for driver dispatch is that the dispatch priority of important contribution drivers is higher than that of medium contribution drivers, medium contribution drivers are higher than ordinary contribution drivers, and so on, negative contribution drivers are higher than risk drivers;

[0024] The application method of the reward activity is to screen the number of completed orders, amount, region, etc. of important contribution drivers, medium contribution drivers, and ordinary contribution drivers, and formulate unified reward rules accordingly to ensure that the formulated rules can give priority to these drivers to receive rewards; in addition, in order to avoid discrimination against drivers, negative contribution drivers and risky drivers can also participate in the unified reward rules; however, some of these two types of drivers may not meet the reward participation rules or reward acquisition rules such as the number of completed orders, amount, region, etc., and some cannot get rewards;

[0025] The application method for driver risks is that for drivers classified as risky drivers, stricter rules for determining fake orders will be set to detect whether the driver and passengers are jointly committing fake orders.

[0026] Compared with the prior art, the implementation effects of the present invention are as follows:

[0027] The present invention provides a driver classification method based on contribution to solve the problem of selecting which drivers to reward and screening reward rules. The advantage of this method is that it can classify drivers, formulate more favorable reward rules for drivers with positive contribution, and limit the number of dispatch orders. For drivers with negative contribution, the dispatch priority is reduced, and risky drivers are given special attention to prevent fraudulent order behavior. This method can effectively improve corporate profits and promote drivers to contribute to travel companies. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0029] The content of the present invention will be described below with reference to specific embodiments.

[0030] The present invention provides a method for classifying drivers according to their contribution to corporate profits. The method classifies drivers according to their contribution to corporate profits, increases subsidies for drivers with high contribution and adjusts dispatch priorities. This can solve the problem of effective subsidies for drivers by travel companies and promote healthy development and profit growth of companies.

[0031] like Figure 1 As shown: A driver classification method based on contribution, comprising the following steps:

[0032] S1. Collect travel order data

[0033] It is necessary to collect order data within 7 days. Each order data includes: driver ID, order number, order amount orderFee, passenger subsidy amount couponFee, passenger payment amount payFee, driver share amount driverFee, and driver travel time workTime;

[0034] The driver's driving time includes the pick-up time and the time the driver waits for the passenger to get on the car. The profit entProfit of the order is calculated as follows: entProfit = orderFee-couponFee-payFee-driverFee;

[0035] S2. Calculate driver contribution

[0036] Assuming that the driver has n orders within the data collection period (7 days), the driver's profit driverEntProfit for n orders is calculated as: driverEntProfit = ∑orderFee - ∑couponFee - ∑payFee - ∑driverFee; the driver's total working time for n orders driverWorkTime = ∑worktime;

[0037] The driver's contribution p = driverEntProfit / driverWorkTime, where p represents the profit contributed by the driver per unit time;

[0038] S3. Classify drivers by contribution

[0039] Drivers with p≥0 are put into set S1, and drivers with p<0 are put into set S2, S1 is the positive contribution set, and S2 is the negative contribution set;

[0040] The classification method for positive contribution sets is:

[0041] Sort the drivers in S1 by contribution from greatest to smallest, i.e. the drivers with greatest contribution are at the front and the drivers with least contribution are at the back;

[0042] The top 20% of drivers are marked as important contributing drivers, the middle 20%-50% are marked as medium contributing drivers, and the last 50%-100% are marked as ordinary contributing drivers;

[0043] The classification method for negative contribution sets is:

[0044] (1) Sort the drivers in S2 by their contribution from greatest to least, i.e., drivers with greater contribution are ranked first and drivers with less contribution are ranked last;

[0045] (2) The top 95% of drivers are marked as negative contribution drivers, and the bottom 5% of drivers are marked as risky drivers;

[0046] S4. Apply driver classification tags

[0047] After the driver classification is completed, the five categories of drivers are marked in order: important contribution drivers, medium contribution drivers, ordinary contribution drivers, negative contribution drivers, and risky drivers;

[0048] Here is how to apply the driver contribution classification:

[0049] The application method for driver dispatch is that the dispatch priority of important contribution drivers is higher than that of medium contribution drivers, medium contribution drivers are higher than ordinary contribution drivers, and so on, negative contribution drivers are higher than risk drivers;

[0050] The application method of the reward activity is to screen the number of completed orders, amount, region, etc. of important contribution drivers, medium contribution drivers, and ordinary contribution drivers, and formulate unified reward rules accordingly to ensure that the formulated rules can give priority to these drivers to receive rewards; in addition, in order to avoid discrimination against drivers, negative contribution drivers and risky drivers can also participate in the unified reward rules; however, some of these two types of drivers may not meet the reward participation rules or reward acquisition rules such as the number of completed orders, amount, region, etc., and some cannot get rewards;

[0051] The application method for driver risks is that for drivers classified as risky drivers, stricter rules for determining fake orders will be set to detect whether the driver and passengers are jointly committing fake orders.

[0052] The present invention provides a driver classification method based on contribution to solve the problem of selecting which drivers to reward and screening reward rules. The advantage of this method is that it can classify drivers, formulate more favorable reward rules for drivers with positive contribution, and limit the number of dispatch orders. For drivers with negative contribution, the dispatch priority is reduced, and risky drivers are given special attention to prevent fraudulent order behavior. This method can effectively improve corporate profits and promote drivers to contribute to travel companies.

[0053] In summary, compared with the traditional classification method, this method has the advantages of classification by contribution, identifying risky drivers, and rewarding drivers with high contribution. It can enhance the enthusiasm of drivers with high contribution, promote the efficiency of enterprise driver subsidies, reduce losses, and achieve sustainable development.

[0054] The above content is a detailed description of the present invention in combination with specific embodiments, and it cannot be determined that the specific implementation of the present invention is limited to these descriptions. For those skilled in the art of the present invention, without departing from the concept of the present invention, several simple deductions or substitutions can be made, which should be regarded as falling within the scope of protection of the present invention.

Claims

1. A driver classification method based on contribution, characterized by: The following steps are involved: S1. Collect travel order data It is necessary to collect order data within 7 days. Each order data includes: driver ID, order number, order amount orderFee, passenger subsidy amount couponFee, passenger payment amount payFee, driver share amount driverFee, and driver travel time workTime; The driver's driving time includes the pick-up time and the time the driver waits for the passenger to get on the car. The profit entProfit of the order is calculated as follows: entProfit = orderFee-couponFee-payFee-driverFee; S2. Calculate driver contribution Assuming that the driver has n orders within the data collection period (7 days), the driver's profit driverEntProfit for n orders is calculated as: driverEntProfit = ∑orderFee - ∑couponFee - ∑payFee - ∑driverFee; the driver's total working time for n orders driverWorkTime = ∑worktime; The driver's contribution p = driverEntProfit / driverWorkTime, where p represents the profit contributed by the driver per unit time; S3. Classify drivers by contribution Drivers with p≥0 are put into set S1, and drivers with p<0 are put into set S2. S1 is the positive contribution set, and S2 is the negative contribution set. The classification method for positive contribution sets is: Sort the drivers in S1 by contribution from greatest to least, i.e. the drivers with greatest contribution are at the front and the drivers with least contribution are at the back; The top 20% of drivers are marked as important contributing drivers, the middle 20%-50% are marked as medium contributing drivers, and the last 50%-100% are marked as ordinary contributing drivers; The classification method for negative contribution sets is: (1) Sort the drivers in S2 by their contribution from greatest to least, i.e., drivers with greater contribution are ranked first and drivers with less contribution are ranked last; (2) The top 95% of drivers are marked as negative contribution drivers, and the bottom 5% of drivers are marked as risky drivers; S4. Apply driver classification tags After the driver classification is completed, the five categories of drivers are marked in order: important contribution drivers, medium contribution drivers, ordinary contribution drivers, negative contribution drivers, and risky drivers; Here is how to apply the driver contribution classification: The application method for driver dispatch is that the dispatch priority of important contribution drivers is higher than that of medium contribution drivers, medium contribution drivers are higher than ordinary contribution drivers, and so on, negative contribution drivers are higher than risk drivers; The application method of the reward activity is to screen the number of completed orders, amount, region, etc. of important contribution drivers, medium contribution drivers, and ordinary contribution drivers, and formulate unified reward rules accordingly to ensure that the formulated rules can give priority to these drivers to receive rewards; in addition, in order to avoid discrimination against drivers, negative contribution drivers and risky drivers can also participate in the unified reward rules; however, some of these two types of drivers may not meet the reward participation rules or reward acquisition rules such as the number of completed orders, amount, region, etc., and some cannot get rewards; The application method for driver risks is that for drivers classified as risky drivers, stricter rules for determining fake orders will be set to detect whether the driver and passengers are jointly committing fake orders.

Images