A method for dispatching online car-hailing capacity

Abstract

The present invention relates to a method for dispatching the transport capacity of online car-hailing vehicles. The method calculates the regional space-time value A according to the expected income of drivers in each area every ten minutes to one hour in the future; calculates the expected income of idle drivers in each area in each time slice within one hour in the future at a specific moment; and calculates the net income of drivers going to a specific area according to the expected income of idle drivers in each time slice within one hour in the future at a specific moment. The beneficial effect is that online car-hailing drivers do not need to rely on experience and luck, but can use the platform's prediction of the area where order demand occurs to find orders and take jobs.

Description

Technical Field

[0001] The present invention relates to the field of online car-hailing, and in particular to a method for dispatching the transportation capacity of online car-hailing. Background Art

[0002] Under the current online car-hailing operation model, drivers are required to find orders and pick up jobs based on historical experience and understanding of the city. There are obvious differences in the efficiency of finding orders and income levels among drivers of different levels.

[0003] The capacity dispatch notifications issued by some leading companies are generally not accepted by drivers, and drivers are unwilling to perform dispatch tasks, resulting in ineffective capacity dispatch. Therefore, the prior art lacks a capacity dispatch system for online car-hailing services to dispatch the capacity of online car-hailing services. Summary of the invention

[0004] In view of the above problems, the present invention is proposed to provide a method for dispatching online car-hailing capacity that overcomes the above problems or at least partially solves the above problems.

[0005] According to one aspect of the present invention, a method for dispatching online car-hailing capacity is provided.

[0006] A method for dispatching online car-hailing capacity, the method comprising:

[0007] Predict and obtain the probability of drivers accepting orders in the six time slices after the time slice at time T. The probability of accepting orders in area i in the time slice at time T and in the next five time slices is P t1 i ,P t2 i ,P t3 i ,P t4 i ,P t5 i ,P t6 i ;

[0008] In the time slice of time t and the next five time slices, the probability of receiving an order from area i to area j is P t1 ij ,P t2 ij ,P t3 ij ,P t4 ij ,P t5 ij ,P t6 ij , the average order prices are Price t1 ij,Price t2 ij ,Price t3 ij ,Price t4 ij ,Price t5 ij ,Price t6 ij , the average migration time of orders is ΔT t1 ij ,ΔT t2 ij ,ΔT t3 ij ,ΔT t4 ij ,ΔT t5 ij ,ΔT t6 ij , after time t, the arrival time slots of each time slot from region i to region j are respectively time_slot t1 ij ,time_slot t2 ij ,time_slot t3 ij ,time_slot t4 ij ,time_slot t5 ij ,time_slot t6 ij ;

[0009] Calculate the regional spatiotemporal value A based on the expected income of drivers in each area every ten minutes to one hour in the future;

[0010] Calculate the expected income of idle drivers in each time slice in each zone within the next hour at a specific time;

[0011] The net benefit for drivers traveling to a specific area is calculated based on the expected earnings of idle drivers in each area in each time slice within the next hour at a specific time.

[0012] Optionally, the calculation of the regional spatiotemporal value A according to the expected income of drivers in each area every ten minutes to one hour in the future specifically includes:

[0013] Recursively calculate from the sixth time slice onwards;

[0014] The regional value of region i in the sixth time slice in the future at time t is determined by the probability of idle drivers accepting orders in this region, the distribution of order destinations departing from this region, and the corresponding price distribution, expressed as:

[0015]

[0016] The regional value of region i to the driver in the next 1 to 5 time slices consists of two parts. The first part is that if an order is accepted in the current time slice, it is determined by the probability of accepting an order in the time slice, the distribution of the destinations and prices of the orders departing from the region, and the regional value of the order destination. The second part is that if no order is accepted in the current time slice and the empty driving state continues to the next time slice, the regional value is:

[0017]

[0018] Optionally, the calculation of the net income of a driver going to a specific area based on the expected income of an idle driver in each area in each time slice within one hour from a specific time specifically includes:

[0019] The zone value of the driver’s initial location in the next hour;

[0020] the value of a particular area after the driver has traveled to that area;

[0021] Let o be the initial area where the idle driver h is located. The expected profit of the driver staying in the initial area in the next hour is

[0022] The cost C of a driver going to a specific area i is determined by the driver's estimated mileage and estimated time to go to area i, that is:

[0023] C hi =Cost(dura hi ,dist hi )

[0024] C stands for Cost, which is the driver's cost, dura stands for estimated time, and dist stands for estimated distance.

[0025] After the driver goes to a specific area i, the value of the area is determined by the area i at time t+dura hi The value of the time slot is determined later. The time slot of driver h arriving at area j is called time_slot hi , then the value of the region to driver h is

[0026]

[0027] Based on the above information, the net profit of driver h going to area j can be calculated as:

[0028]

[0029] For a specific idle driver h, dispatch it to the net profit The largest area i*, corresponding to the maximum expected net profit Right now:

[0030]

[0031]

[0032] In order to increase the reliability of the scheduling, when the maximum expected net benefit Dispatch notifications are pushed to drivers only when certain conditions are met, i.e., dispatch notifications are pushed to idle drivers in the following set:

[0033]

[0034] The present invention provides a method for dispatching online car-hailing capacity, which calculates the regional spatiotemporal value A according to the expected income of drivers in each area every ten minutes to one hour in the future; calculates the expected income of idle drivers in each area in each time slice within one hour from a specific moment; and calculates the net income of drivers going to a specific area according to the expected income of idle drivers in each time slice within one hour from a specific moment. The beneficial effect is that online car-hailing drivers do not need to rely on experience and luck, but can use the platform's prediction of the area where order demand occurs to find orders and take jobs.

[0035] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0037] Figure 1 A flow chart of a method for dispatching online car-hailing capacity provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0039] The terms "comprises" and "having" and any variations thereof in the description embodiments, claims and drawings of the present invention are intended to cover non-exclusive inclusions, for example, including a series of steps or units.

[0040] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments.

[0041] like Figure 1 As shown, a method for dispatching the transportation capacity of online car-hailing vehicles comprises:

[0042] Step 100: Predict and obtain the probability of a driver accepting an order in the six time slots after the time slot at time T. The probability of accepting an order in the time slot at time T and in the next five time slots is P t1 i ,P t2 i ,P t3 i ,P t4 i ,P t5 i ,P t6 i ;

[0043] In the time slice of time t and the next five time slices, the probability of receiving an order from area i to area j is P t1 ij ,P t2 ij ,P t3 ij ,P t4 ij ,P t5 ij ,P t6 ij , the average order prices are Price t1 ij ,Price t2 ij ,Price t3 ij ,Price t4 ij ,Price t5 ij ,Price t6 ij , the average migration time of orders is ΔT t1 ij ,ΔT t2 ij ,ΔT t3 ij ,ΔTt4 ij ,ΔT t5 ij ,ΔT t6 ij , after time t, the arrival time slots of each time slot from region i to region j are respectively time_slot t1 ij ,time_slot t2 ij ,time_slot t3 ij ,time_slot t4 ij ,time_slot t5 ij ,time_slot t6 ij ;

[0044] Step 200: Calculate the regional spatiotemporal value A according to the expected income of drivers in each area every ten minutes to one hour in the future;

[0045] Step 300: recursively calculate from the sixth time slice onwards;

[0046] The regional value of region i in the sixth time slice in the future at time t is determined by the probability of idle drivers accepting orders in this region, the distribution of order destinations departing from this region, and the corresponding price distribution, expressed as:

[0047]

[0048] The regional value of region i to the driver in the next 1 to 5 time slices consists of two parts. The first part is that if an order is accepted in the current time slice, it is determined by the probability of accepting an order in the time slice, the distribution of the destinations and prices of the orders departing from the region, and the regional value of the order destination. The second part is that if no order is accepted in the current time slice and the empty driving state continues to the next time slice, the regional value is:

[0049]

[0050] Step 400: Calculate the expected income of idle drivers in each area in each time slice within one hour in the future at a specific time;

[0051] Step 500: Calculate the net income of a driver traveling to a specific area based on the expected income of idle drivers in each area in each time slice within one hour from a specific time.

[0052] The zone value of the driver’s initial location in the next hour;

[0053] the value of a particular area after the driver has traveled to that area;

[0054] Let o be the initial area where the idle driver h is located. The expected profit of the driver staying in the initial area in the next hour is

[0055] The cost C of a driver going to a specific area i is determined by the driver's estimated mileage and estimated time to go to area i, that is:

[0056] C hi =Cost(dura hi ,dist hi )

[0057] C stands for Cost, which is the driver's cost, dura stands for estimated time, and dist stands for estimated distance.

[0058] After the driver goes to a specific area i, the value of the area is determined by the area i at time t+dura hi The value of the time slot is determined later. The time slot of driver h arriving at area j is called time_slot hi , then the value of the region to driver h is

[0059]

[0060] Based on the above information, the net profit of driver h going to area j can be calculated as:

[0061]

[0062] For a specific idle driver h, dispatch it to the net profit The largest area i*, corresponding to the maximum expected net profit Right now:

[0063]

[0064]

[0065] In order to increase the reliability of the scheduling, when the maximum expected net benefit Dispatch notifications are pushed to drivers only when certain conditions are met, i.e., dispatch notifications are pushed to idle drivers in the following set:

[0066]

[0067] The above specific implementation methods further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above are only specific implementation methods of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for dispatching online car-hailing capacity, characterized in that: The scheduling method comprises: Predict and obtain the probability of drivers accepting orders in the six time slices after time t. The probability of accepting orders in area i in the time slice of time t and in the next five time slices is P t1 i ,P t2 i ,P t3 i ,P t4 i ,P t5 i ,P t6 i ; In the time slice of time t and the next five time slices, the probability of receiving an order from area i to area j is P t1 ij ,P t2 ij ,P t3 ij ,P t4 ij ,P t5 ij ,P t6 ij , the average order prices are Price t1 ij ,Price t2 ij ,Price t3 ij ,Price t4 ij ,Price t5 ij ,Price t6 ij , the average migration time of orders is ΔT t1 ij ,ΔT t2 ij ,ΔT t3 ij ,ΔT t4 ij ,ΔT t5 ij ,ΔT t6 ij , after time t, the arrival time slots of each time slot from region i to region j are respectively time_slot t1 ij ,time_slot t2 ij ,time_slot t3 ij ,time_slot t4 ij ,time_slot t5 ij ,time_slot t6 ij ; Calculate the regional spatiotemporal value A based on the expected income of drivers in each area every ten minutes to one hour in the future; Calculate the expected income of idle drivers in each time slice in each zone within the next hour at a specific time; Calculate the net benefit of drivers traveling to a specific area based on the expected earnings of idle drivers in each area in each time slice within the next hour at a specific time; The zone value of the driver’s initial location in the next hour; the value of a particular area after the driver has traveled to that area; Let o be the initial area where the idle driver h is located. The expected profit of the driver staying in the initial area in the next hour is The cost C of a driver going to a specific area i is determined by the driver's estimated mileage and estimated time to go to area i, that is: C hi =Cost(dura hi ,dist hi ) C stands for Cost, which is the driver's cost, dura stands for estimated time, and dist stands for estimated distance. After the driver goes to a specific area i, the value of the area is determined by the area i at time t+dura hi The value of the time slot is determined later. The time slot of driver h arriving at area j is called time_slot hi , then the value of the region to driver h is Based on the above information, the net profit of driver h going to area j can be calculated as: For a specific idle driver h, dispatch it to the net profit The largest area i*, corresponding to the maximum expected net profit Right now: In order to increase the reliability of the scheduling, when the maximum expected net benefit Dispatch messages are pushed to drivers only when certain conditions are met, that is, dispatch notifications are pushed to idle drivers in the following set:

2. A method for dispatching online car-hailing capacity according to claim 1, characterized in that: The calculation of the regional spatiotemporal value A according to the expected income of drivers in each area every ten minutes to one hour in the future specifically includes: Recursively calculate from the sixth time slice onwards; The regional value of region i in the sixth time slice in the future at time t is determined by the probability of idle drivers accepting orders in this region, the distribution of order destinations departing from this region, and the corresponding price distribution, expressed as: The regional value of region i to the driver in the next 1 to 5 time slices consists of two parts. The first part is that if an order is accepted in the current time slice, it is determined by the probability of accepting an order in the time slice, the distribution of the destinations and prices of the orders departing from the region, and the regional value of the order destination. The second part is that if no order is accepted in the current time slice and the empty driving state continues to the next time slice, the regional value is:

Images