Online car-hailing order pushing method and system, electronic equipment and storage medium

Abstract

The invention provides an online car-hailing order pushing method and system, electronic equipment and a storage medium. The method comprises the following steps: acquiring car-hailing order information; establishing a driver list based on to-be-dispatched drivers in a region range corresponding to the car order information; sorting according to the distance of the to-be-dispatched driver in the driver list and the order grabbing probability to obtain a driver sequence; sequentially adding the to-be-dispatched drivers in the driver sequence into a pushing sequence, and calculating an uncompleted order probability of the pushing sequence; wherein the uncompleted order probability is used for representing a joint probability that the order is not received or canceled after the order is pushed to each to-be-dispatched driver in the sequence; and when the change curve corresponding to the incomplete order probability has an inflection point, taking the corresponding push sequence as a target push sequence to push the order of the current batch. The method can effectively improve the matching between the order and the driver, and improves the order watching experience of the driver.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and particularly to a method, system, electronic device and storage medium for pushing online car-hailing orders. Background Art

[0002] During the process of dispatching online car-hailing orders, orders are usually pushed based on the user order information collected at the user side. However, in the existing solutions, there is usually no differential dispatching for drivers. Even if the actual transport capacity of the vehicle does not meet the user's needs, there may still be a situation where drivers grab orders; in addition, when drivers at a long distance join the order grabbing, it will greatly affect the order grabbing experience of the closer drivers, resulting in the closer drivers not having enough time to view the corresponding orders, and the matching degree between the drivers and the user orders is not high. Orders with low matching degree will affect the completion rate to a certain extent, bringing a bad experience to the platform and users. Summary of the Invention

[0003] In view of the above-mentioned disadvantages of the video stabilization technology, this application provides a method, system, electronic device and storage medium for pushing online car-hailing orders to solve the problem that the existing solutions do not fully consider the differences between drivers, resulting in low matching degree of order pushing and affecting the experience of drivers and users.

[0004] This application provides a method for pushing online car-hailing orders. The method includes: obtaining vehicle use order information; forming a driver list for the to-be-dispatched drivers within the range of the area corresponding to the vehicle use order information; sorting according to the distances and order-grabbing probabilities of the to-be-dispatched drivers in the driver list to obtain a driver sequence; sequentially adding the to-be-dispatched drivers in the driver sequence to a push sequence, and calculating the non-completion probability of the push sequence; where the non-completion probability is used to represent the joint probability that the order is not accepted or cancelled after being pushed to each to-be-dispatched driver in the sequence; when an inflection point appears in the change curve corresponding to the non-completion probability, using the corresponding push sequence as the target push sequence to push the current batch of orders.

[0005] In an embodiment of this application, the step of sorting according to the distances and order-grabbing probabilities of the to-be-dispatched drivers in the driver list includes: obtaining the location information in the vehicle use order information; sorting according to the distances from the to-be-dispatched drivers to the location information from near to far to obtain the driver sequence; where, if there are multiple to-be-dispatched drivers with equal distances, then sorting in descending order according to the order-grabbing probability, and the order-grabbing probability is determined according to the historical order data of the corresponding to-be-dispatched drivers.

[0006] In an embodiment of the present application, the method for determining the order snatching probability includes: obtaining the historical order data of the driver to whom an order is to be assigned, where the historical order data includes historical order information, order completion information after order snatching, driver vehicle type information, and pick-up distance; inputting the historical order data into a willingness model to predict the order snatching probability of the driver to whom an order is to be assigned for the vehicle use order information; wherein, the willingness model is pre-trained based on the historical order data of each driver.

[0007] In an embodiment of the present application, the steps for calculating the non-completion probability of the push sequence include: obtaining the completion probability of each driver to whom an order is to be assigned in the push sequence for snatching and completing an order; determining the cumulative probability of the order not being completed after snatching for each driver to whom an order is to be assigned in the push sequence according to the order snatching probability and the completion probability; determining the non-snatching probability that none of the drivers to whom an order is to be assigned in the push sequence snatch the order according to the order snatching probability; and obtaining the non-completion probability based on the cumulative probability and the non-snatching probability.

[0008] In an embodiment of the present application, the method for determining the inflection point of the change curve corresponding to the non-completion probability includes: if, for each newly added driver to whom an order is to be assigned in the push sequence, the slope of the change curve exceeds a preset amplitude of the slope before the addition, then the newly added driver to whom an order is to be assigned is taken as the inflection point.

[0009] In an embodiment of the present application, when no driver snatches the order after the current batch of orders is pushed, the next inflection point of the change curve corresponding to the non-completion probability is determined according to the remaining drivers to whom an order is to be assigned in the driver sequence, so as to intercept a corresponding number of drivers to whom an order is to be assigned from the driver sequence based on the next inflection point as the target push sequence for the next batch.

[0010] In an embodiment of the present application, after all the drivers to whom an order is to be assigned in the driver sequence are pushed and no driver snatches the order, the vehicle use order information is pushed to the target push sequence of the first batch again after a preset time interval.

[0011] The present application also provides a system for pushing online car-hailing orders, the system includes: an order collection module for obtaining vehicle use order information; a driver selection module for forming a driver list based on the drivers to whom an order is to be assigned within the area range corresponding to the vehicle use order information; a sorting module for sorting according to the distance and order snatching probability of the drivers to whom an order is to be assigned in the driver list to obtain a driver sequence; a non-completion prediction module for sequentially adding the drivers to whom an order is to be assigned in the driver sequence to the push sequence and calculating the non-completion probability of the push sequence; wherein the non-completion probability is used to represent the joint probability that the order is not accepted or cancelled after being pushed to each driver in the sequence; and a push module for, when an inflection point appears in the change curve corresponding to the non-completion probability, taking the corresponding push sequence as the target push sequence to perform the current batch of order pushing.

[0012] The present application also provides an electronic device, which includes: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the electronic device implements the online car-hailing order pushing method described above.

[0013] The present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor of a computer, the computer executes the online car-hailing order pushing method described above.

[0014] An online car-hailing order pushing method, system, electronic device and storage medium provided by the present application have the following beneficial effects:

[0015] The present application fully considers the distance of the driver and the order grabbing probability, and preferentially pushes orders to drivers who are closer and have a higher order grabbing rate, so that drivers who are closer can view the corresponding orders first, avoiding the problem of being unable to obtain matching orders due to operation efficiency. And it fully considers the order fulfillment situations of the drivers and users, calculates the cumulative non-acceptance probability of each driver in the push sequence, optimizes the matching degree between the order and the driver and the order pushing process, and enhances the experience of the users and drivers.

[0016] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of an implementation environment of a video stabilization method shown in an exemplary embodiment of the present application.

[0018] Figure 2 It is a schematic diagram of a change curve of the non-fulfillment probability in an embodiment of the present application.

[0019] Figure 3 It is a schematic diagram of the overall process of the online car-hailing order pushing method in an embodiment of the present application.

[0020] Figure 4 It is a block diagram of an online car-hailing order pushing system shown in an exemplary embodiment of the present application.

[0021] Figure 5 It shows a schematic diagram of the structure of a computer system of an electronic device suitable for implementing the embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] The embodiments of the present application will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for explaining the present application and not for limiting the protection scope of the present application.

[0023] In the present application, "first", "second", etc. are only used to distinguish similar objects, and are not intended to limit the order or sequence of similar objects. The described "including", "having", etc. are in a modified form, indicating that the scope covered by the subject of the word does not exclude other examples in addition to the examples shown by the word.

[0024] It can be understood that the various numerical numbers, step numbers, etc. recorded in the present application are for the convenience of description and do not limit the scope of the present application. The size of the labels in the present application does not mean the order of execution. The execution order of each process should be determined by its function and internal logic.

[0025] In the following description, a large number of details are explored to provide a more thorough explanation of the embodiments of the present application. However, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present application difficult to understand.

[0026] After research by the inventor, it is found that: currently, online car-hailing usually conducts dynamic order distribution based on grid supply-demand data. The dynamic order distribution strategy will be dynamically adjusted according to the driver density: in areas with low driver density, the number of drivers pushed in the first round of dynamic order distribution is more than the established strategy of the overall order distribution; while in areas with high driver density, the number of drivers pushed in the first round of dynamic order distribution is significantly less than the established strategy of the overall order distribution.

[0027] However, the application of grid supply-demand data has certain limitations. First, limited by the grid granularity, when orders are located at different positions in the same grid, their actual supply-demand situations may be different, but all orders of the same vehicle type falling in the grid within the same period use the same grid supply-demand data, which reduces the differences between orders to a certain extent. Second, the number of drivers in the grid supply-demand data cannot accurately reflect the true effective transport capacity. For example, there are complex situations such as drivers of different vehicle types accepting or rejecting orders upwards or downwards.

[0028] In a scenario where supply exceeds demand, if both the supply and demand densities are at relatively high levels, a shrinking broadcast strategy should be adopted to achieve nearby order distribution as much as possible, considering optimizing the driver experience and operation efficiency, so as to prompt drivers to accept nearby orders. In a scenario where supply is less than demand, it is usually understood as the peak period. However, it should be noted that in the case where both the supply and demand densities are relatively low, the phenomenon of supply being less than demand may also occur. At this time, obviously, an expanding broadcast strategy should be adopted to improve the order matching efficiency.

[0029] Based on the problems existing in the existing solutions, this application proposes a method, system, electronic device, and storage medium for pushing online car-hailing orders. The technical solutions of this application will be elaborated in detail below in combination with specific embodiments.

[0030] Please refer to Figure 1 , Figure 1 , which is a flowchart of the method for pushing online car-hailing orders in an embodiment of this application. The method includes the following steps:

[0031] Step S100, obtain vehicle usage order information.

[0032] In an embodiment, the user (the relevant person in need of a vehicle) can access the online car-hailing order information collection application through a mobile phone or other terminal devices. This application can be a WeChat mini-program, a terminal APP, or a web page. The vehicle usage order information can be filled in the corresponding application. The vehicle usage order information can include the starting point, ending point, vehicle usage time, required vehicle type, etc. After the server receives the vehicle usage order information, it can calculate the mileage and route information of the current order based on the starting point and ending point of the vehicle usage order, associate all the information with the vehicle usage order information or the user, and record the historical vehicle usage order information of the corresponding user, so as to predict the probability of the user completing the order subsequently and obtain the user's performance information.

[0033] Step S110, form a driver list based on the drivers waiting for orders within the area range corresponding to the vehicle usage order information.

[0034] In an embodiment, a range of areas can be delimited according to the starting point in the vehicle usage order information or a specified location point (such as the location point where the user initiates the order), and all the drivers waiting for orders within this area range can be incorporated into a list to form a driver list. The drivers waiting for orders here refer to those who are currently in an idle state or are about to complete an order and choose to continue accepting orders. Of course, the specific range of drivers waiting for orders can also be set and adjusted according to actual needs, and there is no limitation here. The area range can be a circular area centered on the specified location point, or an irregular area delimited according to the geographical location (such as avoiding some mountainous areas or impassable areas). The specific size of the area range can be set and adjusted according to actual application needs, and there is no limitation here.

[0035] Step S120: Sort the drivers waiting for orders in the driver list according to their distances and order-grabbing probabilities to obtain a driver sequence.

[0036] In one embodiment, the distance of the driver waiting for an order here refers to the straight-line distance or the navigation-planned driving distance between the current location of the driver waiting for an order and the specified location information in the car-hailing order information.

[0037] In one embodiment, the step of sorting the drivers waiting for orders in the driver list according to their distances and order-grabbing probabilities includes:

[0038] Step S121: Obtain the location information in the car-hailing order information.

[0039] Specifically, the location information can be the starting point of the order, or can be specified by the user or the server side, and can be specifically set and adjusted according to actual application requirements. After the server side receives the car-hailing order information fed back by the user terminal, the corresponding location information can be parsed.

[0040] Step S122: Sort the drivers waiting for orders in ascending order of their distances to the location information to obtain a driver sequence; among them, if there are multiple drivers waiting for orders with equal distances, they are sorted in descending order according to the order-grabbing probabilities, and the order-grabbing probability is determined based on the historical order data of the corresponding drivers waiting for orders.

[0041] In one embodiment, the drivers waiting for orders in the driver list can be preferentially sorted in ascending order of distance. In the case where the distances of two or more drivers waiting for orders are equal, the order-grabbing probabilities of the drivers with equal distances can be calculated and sorted in descending order based on the order-grabbing probabilities. Combining the dual sorting rules of distance and order-grabbing probability, a driver sequence can be obtained. Among them, when the distance deviation of the driver is within a set range (such as within 100 meters), the drivers within the range can also be determined to have equal distances. It can be specifically set and adjusted according to actual application situations, and there is no limitation here.

[0042] In one embodiment, the method for determining the order snatching probability includes: obtaining the historical order data of the driver to whom the order is to be assigned, where the historical order data includes historical order information, order completion information after order snatching, driver vehicle type information, and pick-up distance; inputting the historical order data into a willingness model to predict the order snatching probability of the driver to whom the order is to be assigned for the vehicle use order information; wherein, the willingness model is pre-trained based on the historical order data of each driver. Specifically, the willingness model can be constructed based on network architectures such as recurrent neural networks and multi-layer perceptrons, such as using a long short-term memory neural network architecture, etc. Collect the order information of users and the historical order data of drivers over a period of time. Predict the order snatching probability of the currently assigned driver through supervised learning. The willingness model is used to evaluate the fit between the order and the driver, specifically manifested as the probability that the driver is willing to snatch the order after the order is pushed to the driver. The architecture and training process of the specific model are conventional methods in this field and will not be elaborated here. After determining the order snatching probability based on the willingness model, sort the drivers with equal distances in descending order of the order snatching probability. Of course, the order snatching probability of the corresponding driver can also be calculated for the drivers sorted based on distance, and the order snatching probability is associated with the driver to whom the order is to be assigned.

[0043] Step S130, sequentially add the drivers to whom the order is to be assigned in the driver sequence to the push sequence, and calculate the non-completion probability of the push sequence; wherein the non-completion probability is used to represent the joint probability that the order is not accepted or cancelled after being pushed to each driver in the sequence.

[0044] In one embodiment, the initial state of the push sequence is an empty set, or a specified number of drivers to whom the order is to be assigned can be directly intercepted from the driver sequence and included in the push sequence. Then calculate the cumulative non-completion probability of each driver to whom the order is to be assigned in the push sequence. Alternatively, add the drivers to whom the order is to be assigned to the push sequence one by one in the order of the driver sequence. For each newly added driver to whom the order is to be assigned, calculate the cumulative non-completion probability of each driver in the current push sequence.

[0045] In one embodiment, the steps for calculating the non-completion probability of the push sequence include:

[0046] Step S131, obtain the completion probability of each driver to whom the order is to be assigned in the push sequence for snatching and completing the order.

[0047] The driver's order completion rate model can be constructed based on the way of constructing the willingness degree model, and this driver's order completion rate model is used to evaluate the fit degree among orders, users and drivers. Specifically, it refers to the probability that neither the driver nor the user cancels the order after the driver accepts the order. Specifically, the model will use the method of supervised learning to predict the non-cancellation probability of the driver after accepting the order according to information such as order information (starting and ending points, time price, vehicle type, mileage), user's historical performance information, driver's historical performance information, driver's vehicle type information, and pick-up distance. The specific architecture and training method of the driver's order completion rate model can be selected and adjusted according to actual application requirements, and no restrictions are imposed here. The order completion probability of each driver to be dispatched in the push sequence can be predicted through the four-level order completion rate model, and the order completion probability is associated with the corresponding driver to be dispatched in the push sequence.

[0048] Step S132, determine the cumulative probability of the uncompleted orders after the drivers to be dispatched in the push sequence grab the orders according to the order grab probability and the order completion probability.

[0049] In one embodiment, the cumulative probability can be expressed as:

[0050] represents the probability that any driver among the drivers numbered from 1 to k grabs the order and does not complete the order. p i represents the order grab probability that the order is grabbed after being pushed to the i-th driver; q i represents the order completion probability if the i-th driver to be dispatched grabs the order. Assume p i and q i (i ∈ [1, n]) represent the corresponding probabilities of each driver in the driver sequence sorted by the push distance from near to far; and represent the order grab probability and the order completion probability corresponding to the sequence obtained by intercepting the first k drivers sorted by the push distance and then sorting them continuously by the order grab probability, and it is agreed that the driver with a high order grab probability grabs the order first.

[0051] Step S133, determine the non-grab probability that none of the drivers to be dispatched in the push sequence grabs the order according to the order grab probability.

[0052] In one embodiment, represents the probability that none of the drivers numbered from 1 to k grabs the order. In the order distribution scenario, each driver has an order grab probability and an order completion probability. The system generates a driver sequence through a two-dimensional sorting strategy - first sort by the push distance from near to far, and then sort the drivers with the same distance in descending order of the order grab probability. To determine the optimal number of push drivers, the system generates an incomplete order probability sequence based on a dynamic calculation model that intercepts the first K drivers. In the calculation formula, the first term represents the cumulative probability that any driver among the first K drivers grabs the order but does not complete the order, and the second term is the probability that none of all the drivers grabs the order.

[0053] Step S134: Obtain the probability of an incomplete order based on the cumulative probability and the probability of not snatching an order.

[0054] In one embodiment, the probability of an incomplete order can be expressed as:

[0055]

[0056] where p i represents the probability of snatching an order after the order is pushed to the i-th driver; q i represents the probability of completing the order if the i-th driver waiting for an assigned order snatches the order. Assume that p i and q i (i ∈ [1, n]) represent the corresponding probabilities of each driver in the driver sequence sorted by the distance from near to far; and represent the probability of snatching an order and the probability of completing an order corresponding to the sequence obtained by intercepting the first k drivers sorted by the distance and then sorting them continuously by the probability of snatching an order. It is agreed that the driver with a higher probability of snatching an order will snatch the order first. Then, the probability of an incomplete order for the first k drivers is R k .

[0057] Step S140: When an inflection point appears in the change curve corresponding to the probability of an incomplete order, use the corresponding push sequence as the target push sequence to push the current batch of orders.

[0058] In one embodiment, by iteratively calculating the (R_k) values when (k = 1, 2,..., N), construct the change curve of the probability of an incomplete order.

[0059] In one embodiment, when no driver snatches the order after pushing the current batch of orders, determine the next inflection point of the change curve of the corresponding probability of an incomplete order according to the remaining drivers waiting for an assigned order in the driver sequence, so as to intercept the corresponding number of drivers waiting for an assigned order from the driver sequence based on the next inflection point as the target push sequence for the next batch. Please refer to Figure 2 , Figure 2 which is a schematic diagram of the change curve of the probability of an incomplete order in an embodiment of the present application. In the figure, the abscissa is the number of intercepted drivers, and the ordinate is the probability of an incomplete order. 1, 2, and 3 in the figure respectively represent the three inflection points corresponding to the change curve. For the push sequence formed by pre-intercepting k drivers, the drivers in the push sequence can be divided into multiple batches based on the inflection point, and each inflection point is used as the interception point for one batch. As Figure 2 shown, four batches of target push sequences can be obtained. Use the target push sequence intercepted at inflection point 1 as the first batch to push the order. In the case that no one snatches the order in the first batch, push the order for the target push sequence of the next batch after a set time interval.

[0060] In one embodiment, the method for determining the inflection point of the incomplete order probability corresponding change curve includes: if, for each newly added driver to be assigned an order in the push sequence, the slope of the change curve exceeds a preset range of the slope before the addition, then the newly added driver to be assigned an order is regarded as the inflection point. Specifically, when the addition of the new driver causes the decline rate of the incomplete order probability to slow down significantly or rise in the opposite direction, it is determined as the optimal cut-off point for the current round (for example Figure 2 the position 2 in). The specific change range of the slope for judging the inflection point can be set and adjusted according to actual application requirements, and no limitation is imposed here.

[0061] In one embodiment, after pushing all the drivers to be assigned orders in the driver sequence and no driver grabs the order, the car-hailing order information is pushed to the target push sequence of the first batch again after a preset time interval.

[0062] Please refer to Figure 3 , Figure 3 which is the overall flowchart of the car-hailing order push method in an embodiment of the present application. First, the user fills in the pick-up and drop-off addresses at the passenger end of the car-hailing platform and places an order. The order system creates an order and sends the order information to the order assignment system. At the order push level, the order assignment system selects drivers according to the order information and filters out the drivers who do not meet the distance strategy requirements and status requirements. The status requirements here can be to exclude the drivers with a driver order-grabbing rate lower than a set threshold, or to exclude the drivers with a completed order rate lower than a set threshold. The specific status requirements can be set and adjusted according to the actual situation, and no limitation is imposed here. The filtered final driver data is input into the driver sequence for sorting, and the push driver list for this round (i.e., the target push sequence) is output. After the order is distributed to the driver in the order assignment system, the passenger end gives corresponding prompts to the passenger, and the driver end timely displays the relevant information of the pushed order on the interface, leaving a broadcast duration for one round as the decision-making time for the driver to decide whether to grab the order. The specific broadcast duration for one round can be set and adjusted according to actual application requirements. If multiple push drivers of the order grab the order, then at the order-grabbing level, the order assignment system inputs the order-grabbing driver list into the order-grabbing PK strategy algorithm, and the algorithm layer executes the driver order-grabbing PK strategy, and finally outputs 1 driver who obtains the order. The specific PK strategy can be to comprehensively consider the distance, order-grabbing probability, and completed order probability, and compare to obtain a driver as the order-receiving driver. Of course, when the PK cannot obtain a unique result, a driver can also be randomly selected from multiple drivers as the order-receiving driver.

[0063] In one embodiment, after a round of order broadcasting time, if the order is not grabbed by any driver waiting to be dispatched, the next round of order push will begin. In particular, in the new round of push, the drivers who have been pushed in the previous round will be filtered. If after multiple rounds of push (determined by analyzing the waiting patience data of users on the online car-hailing platform), there is still no driver to grab the order, then the order distribution system will re-initiate the order broadcasting process for the drivers around the order, and re-push the order according to the aforementioned batches until the order expires. Alternatively, re-circle the driver component driver list, re-determine the target push sequence according to the aforementioned process, and perform multiple rounds of order push. This ensures that new idle drivers can be included in the circled range after joining, ensuring the order success rate and push efficiency.

[0064] Based on the technical solutions of the above embodiments of the present application, by introducing an order incomplete probability model based on the order grabbing willingness model and the cancellation rate model, it is ensured that drivers who are close and have a high probability of completing orders have more time to view orders and make decisions, thereby significantly improving the fairness and rationality of order allocation; dynamically adjusting the order broadcast range and the number of drivers pushed, reasonably controlling the number of orders pushed by a single driver, effectively reducing the screen swiping and order explosion phenomena, improving the driver's order viewing experience, and improving operational efficiency; it can effectively improve order response, order completion and driver experience.

[0065] See also Figure 4 , Figure 4 It is a block diagram of a system for pushing online car-hailing orders as shown in an exemplary embodiment of the present application. The system includes: an order collection module 40, which is used to obtain car order information; a driver selection module 41, which is used to form a driver list based on the drivers to be dispatched in the area corresponding to the car order information; a sorting module 42, which is used to sort the drivers to be dispatched in the driver list according to their distance and the probability of grabbing orders to obtain a driver sequence; an unfinished order prediction module 43, which is used to sequentially add the drivers to be dispatched in the driver sequence to the push sequence, and calculate the unfinished order probability of the push sequence; wherein the unfinished order probability is used to characterize the joint probability of not accepting the order or being cancelled after the order is pushed to each driver to be dispatched in the sequence; a push module 44, which is used to use the corresponding push sequence as the target push sequence to push the current batch of orders when an inflection point appears in the corresponding change curve of the unfinished order probability.

[0066] The online car-hailing order push system provided in the above embodiment and the online car-hailing order push method provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs the operation has been described in detail in the method embodiment and will not be repeated here. In actual application, the online car-hailing order push system provided in the above embodiment can allocate the above functions to different functional modules as needed, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0067] This embodiment also provides an electronic device, including: one or more processors; a storage device for storing one or more programs, which, when executed by the one or more processors, cause the electronic device to implement the online car-hailing order pushing method provided in each of the above embodiments.

[0068] Please refer to Figure 5 , Figure 5 which shows a schematic structural diagram of a computer system of an electronic device suitable for implementing the embodiments of the present application. Figure 5 The computer system 600 of the electronic device shown is only an example and should not impose any limitation on the functions and scope of use of the embodiments of the present application.

[0069] As Figure 5 shown, the computer system 600 includes a central processing unit 601, which can perform various appropriate actions and processes according to the program stored in the read-only memory 602 or the program loaded from the storage section 608 into the random access memory 603, such as executing the method in the above embodiments. In the random access memory 603, various programs and data required for system operation are also stored. The central processing unit 601, the read-only memory 602, and the random access memory 603 are connected to each other via a bus 604. The input / output interface 605 is also connected to the bus 604.

[0070] The following components are connected to the input / output interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including, for example, a CRT (Cathode Ray Tube), an LCD (Liquid Crystal Display), etc. and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the input / output interface 605 as required. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as required so that a computer program read from it can be installed into the storage section 608 as required.

[0071] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication section 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit 601, various functions defined in the system of the present application are executed.

[0072] The computer-readable medium shown in the embodiments of the present application may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may, for example, be an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a RAM (Random Access Memory), a ROM (Read Only Memory), an EPROM (Erasable Programmable Read Only Memory), a flash memory, an optical fiber, a CD-ROM (Compact Disc Read-Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program included on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

[0073] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of devices, methods, and computer program products according to various embodiments of the present application. Among them, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the above-mentioned module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order from that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, as well as the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0074] The units involved in the embodiments described in the present application can be implemented in software or in hardware, and the described units can also be provided in a processor. Among them, the names of these units do not, in some cases, constitute a limitation on the unit itself.

[0075] On the other hand, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor of the computer, the computer is caused to execute the online car-hailing order pushing method as described above. The computer-readable storage medium may be included in the electronic device described in the above embodiments, or may exist separately without being assembled into the electronic device.

[0076] On the other hand, the present application also provides a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the video stabilization method provided in the above various embodiments.

[0077] The above embodiments are only used to exemplarily illustrate the principles and effects of the present application, rather than to limit the present application. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by those with ordinary knowledge in the technical field without departing from the spirit and technical idea disclosed by the present application should still be covered by the claims of the present application.

Claims

1. A method for pushing online car-hailing orders, characterized in that, The method includes: Obtaining vehicle usage order information; Forming a driver list based on the drivers waiting for orders within the corresponding area range of the vehicle usage order information; Sorting according to the distances and order grabbing probabilities of the drivers waiting for orders in the driver list to obtain a driver sequence; Sequentially adding the drivers waiting for orders in the driver sequence to the push sequence and calculating the non-completion probability of the push sequence; wherein the non-completion probability is used to represent the joint probability that the order is not accepted or cancelled after being pushed to each driver waiting for orders in the sequence; When an inflection point appears in the change curve corresponding to the non-completion probability, using the corresponding push sequence as the target push sequence to push the current batch of orders.

2. The online car-hailing order pushing method according to claim 1, wherein The step of sorting according to the distances and order grabbing probabilities of the drivers waiting for orders in the driver list includes: Obtaining the location information in the vehicle usage order information; Sorting in ascending order according to the distances from the drivers waiting for orders to the location information to obtain the driver sequence; wherein, if there are multiple drivers waiting for orders with equal distances, then sorting in descending order according to the order grabbing probability, and the order grabbing probability is determined based on the historical order data of the corresponding drivers waiting for orders.

3. The online car-hailing order pushing method according to claim 2, wherein The determination method of the order grabbing probability includes: Obtaining the historical order data of the corresponding driver waiting for orders, and the historical order data includes historical order information, order completion information after grabbing the order, driver vehicle type information, and order receiving distance; Inputting the historical order data into a willingness model to predict the order grabbing probability of the corresponding driver waiting for orders for the vehicle usage order information; wherein, the willingness model is pre-trained based on the historical order data of each driver.

4. The online car-hailing order push method according to claim 1, wherein The step of calculating the non-completion probability of the push sequence includes: Obtaining the order completion probability of each driver waiting for orders in the push sequence to grab and complete the order; Determining the cumulative probability of the orders not being completed after each driver waiting for orders in the push sequence grabs the order according to the order grabbing probability and the order completion probability; Determining the non-order-grabbing probability that none of the drivers waiting for orders in the push sequence grab the order according to the order grabbing probability; Obtaining the non-completion probability based on the cumulative probability and the non-order-grabbing probability.

5. The online car-hailing order pushing method according to claim 1, wherein The determination method of the inflection point of the change curve corresponding to the non-completion probability includes: If for each newly added driver waiting for orders in the push sequence, the slope of the change curve exceeds a preset amplitude of the slope before the addition, then the newly added driver waiting for orders is used as the inflection point.

6. The online car-hailing order pushing method according to claim 1, wherein When no driver grabs the order after pushing the current batch of orders, determining the next inflection point of the change curve of the corresponding non-completion probability based on the remaining drivers waiting for orders in the driver sequence, so as to intercept the corresponding number of drivers waiting for orders from the driver sequence based on the next inflection point as the target push sequence for the next batch.

7. The online car-hailing order pushing method according to claim 6, characterized in that, After pushing all the drivers waiting for orders in the driver sequence and no driver grabs the order, pushing the vehicle usage order information to the target push sequence of the first batch again after a preset time interval.

8. A network car-hailing order push system, characterized in that The system includes: An order collection module for obtaining vehicle usage order information; A driver selection module for forming a driver list based on the drivers waiting for orders within the corresponding area range of the vehicle usage order information; A sorting module, configured to sort according to the distance and order snatching probability of the drivers to be assigned orders in the driver list to obtain a driver sequence; An incomplete order prediction module, configured to sequentially add the drivers to be assigned orders in the driver sequence to a push sequence and calculate the incomplete order probability of the push sequence; wherein the incomplete order probability is used to represent the joint probability that the order is not accepted or cancelled after being pushed to each driver to be assigned order in the sequence; A push module, configured to use the corresponding push sequence as a target push sequence for pushing the current batch of orders when an inflection point appears in the change curve corresponding to the incomplete order probability.

9. An electronic device, characterized in that, The electronic device includes: One or more processors; A storage device, configured to store one or more programs, which, when executed by the one or more processors, cause the electronic device to implement the online car-hailing order pushing method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, A computer program is stored thereon, which, when executed by a processor of a computer, causes the computer to execute the online car-hailing order pushing method according to any one of claims 1-7.

Images