WO2019237694A1

WO2019237694A1 - Reservation order processing

Info

Publication number: WO2019237694A1
Application number: PCT/CN2018/121232
Authority: WO
Inventors: 吴鑫; 顾昊; 刘广权
Original assignee: 北京三快在线科技有限公司
Priority date: 2018-06-15
Filing date: 2018-12-14
Publication date: 2019-12-19
Also published as: CN108960976B; CN108960976A

Abstract

The present application provides a method and apparatus for processing a reservation order, and a storage medium. According to one embodiment of the method, after a vehicle reservation order is received, an order dispatch success rate corresponding to each preset time period among a plurality of preset time periods after the receiving time of the vehicle reservation order and before the reserved vehicle use time indicated by the vehicle reservation order may be determined; and order dispatch time of the vehicle reservation order is determined according to the order dispatch success rates in the plurality of preset time periods; and in this way, if the order dispatch time is reached, the vehicle reservation order is sent to online booking vehicles within a preset region with the departure place as the center.

Description

Processing reservations

Cross-reference to related applications

This patent application claims priority from a Chinese patent application filed on June 15, 2018, with an application number of 201810621873.2 and an invention name of "a method, device, and storage medium for processing reservation orders". The entire text of the application is incorporated by reference. The way is incorporated in this article.

Technical field

The present application relates to the field of Internet technologies, and in particular, to the processing of appointment forms.

Background technique

When the server receives the car reservation form sent by the user terminal, it will immediately broadcast the car reservation form to wait for the driver to accept the order. In this case, if the current time is longer than the user's car reservation time, the driver receiving the order may not be able to provide passenger services in a timely manner due to some reasons (such as unexpected conditions, etc.), which will reduce the user's travel efficiency and affect the user. Experience.

Summary of the Invention

In view of this, the present application provides a method, a device, and a storage medium for processing a reservation order, which can improve the travel efficiency of a user and the user experience.

Specifically, the present application is implemented through the following technical solutions.

According to the first aspect of the present application, a method for processing a reservation order is provided, including: receiving a car reservation form, the car reservation form including a reserved car time and a departure place; and determining a time before the reserved car time Among multiple preset time periods, the dispatch success rate corresponding to each preset time period; determining the dispatch time of the car reservation order according to the dispatch success rates within the plurality of preset time periods; At the dispatching time, the car booking order is sent to a network-booking car in a preset area centered on the departure place.

In an embodiment, the determining a success rate of order allocation corresponding to each preset time period among a plurality of preset time periods before the scheduled car use time includes: determining each of the preset time periods The characteristic value of the dispatch success rate in the preset area; inputting the characteristic value of the dispatch success rate into a pre-trained dispatch success rate model to obtain the dispatch success rate in each of the preset time periods.

In an embodiment, the method further includes pre-training the dispatch success rate model according to the following steps: obtaining a sample dispatch success rate characteristic value of a target area in a plurality of preset time periods, the target area including the preset Area; calibrate the sample success rate corresponding to the sample order success rate characteristic value in each preset time period; compare the sample order success rate characteristic value and the sample order success in each preset time period The dispatch success rate corresponding to the rate eigenvalue is used as the training set to train the dispatch success rate model.

In one embodiment, the characteristics of the dispatch success rate include at least one of an average speed of the vehicle, a capacity density, and a probability that the driver will not cancel the order.

In an embodiment, the plurality of preset time periods are a plurality of end-to-end time periods starting from the reserved car time; and the dispatch is successful according to the plurality of preset time periods. The rate determining the dispatch time of the car use reservation order includes: starting from the first preset time period starting from the car use reservation time, accumulating the success rate of order allocation corresponding to each of the preset time periods one by one. Until the currently accumulated total dispatch success rate meets the success rate condition; the dispatch time of the car reservation order is determined according to the difference between the car reservation time and each of the preset time periods currently accumulated.

In an embodiment, the total dispatch success rate meets a success rate condition, including that the total dispatch success rate is greater than or equal to a preset dispatch success rate threshold.

In one embodiment, the formula for calculating the overall dispatch success rate is:

Among them, P is the overall order success rate, Pi is the order success rate corresponding to the i-th preset time period, and n is the number of currently accumulated preset time periods.

In an embodiment, the sending the vehicle reservation order to a network-booking car in a preset area centered on the departure place includes: determining a network-booking car in the preset area that meets the dispatch condition. ; Sending the car reservation order to the online ride-hailing.

According to the second aspect of the present application, a device for processing reservation orders is provided, which includes: a reservation order receiving module for receiving a car reservation order, the car reservation order including a reserved car time and a departure place; a success rate A determining module is configured to determine a success rate of order allocation corresponding to each preset time period among a plurality of preset time periods before the scheduled car use time; a dispatch time determining module is configured to The success rate of dispatch within the time period determines the dispatch time of the car booking order; the booking sending module is configured to, when the dispatch time is reached, send a message to a preset area centered on the departure place. The ride-hailing service sends the car reservation form.

In an embodiment, the success rate determining module includes: a feature value determining unit, configured to determine a feature value of order success rate of the preset area in each of the preset time periods; a success rate determining unit, It is used to input the feature value of the dispatch success rate into a pre-trained dispatch success rate model to obtain the dispatch success rate in each of the preset time periods.

According to a third aspect of the present application, a device for processing a reservation order is provided, including: a processor; a memory configured to store processor-executable instructions; wherein the processor is configured to execute any one of the foregoing Method of processing reservations.

According to a fourth aspect of the present application, a computer-readable storage medium is provided. The storage medium stores a computer program, and the computer program is used to execute any one of the methods for processing a reservation order.

As can be seen from the above technical solution, the present application receives a car booking order and determines a success rate of order allocation corresponding to each preset time period among a plurality of preset time periods before the scheduled car booking time, and then according to the The dispatch success rate corresponding to each of a plurality of preset time periods determines the dispatch time of the car reservation order, and the dispatch time can be determined relatively accurately, and when the dispatch time is reached, the appointment order is performed as an instant order. Processing so that when determining whether to accept an order, the driver can more accurately predict whether the passenger service can be provided in a timely manner according to the current situation, which can effectively reduce the probability of the driver receiving an incorrect order, increase the success rate of the appointment, and thus improve the user experience .

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a flowchart of a method for processing a reservation order, according to an exemplary embodiment of the present application.

Fig. 2 is a flowchart illustrating how to determine a success rate of dispatching for each preset time period according to an exemplary embodiment of the present application.

FIG. 3 is a flowchart illustrating how to determine a success rate of dispatching for each preset time period, according to another exemplary embodiment of the present application.

Fig. 4A is a flowchart showing how to determine a dispatch time of a car reservation order according to an exemplary embodiment of the present application.

FIG. 4B is a schematic diagram illustrating a search range of a network-aid car in each time period during a process of processing a car booking order according to an exemplary embodiment of the present application.

Fig. 4C is a schematic diagram showing a search range of a network-aid car in each time period in the process of processing a car booking order according to another exemplary embodiment of the present application.

Fig. 5A is a flow chart showing how to send a car reservation order according to an exemplary embodiment of the present application.

FIG. 5B is a schematic diagram illustrating a search range of a network-aid car in each time period in the process of processing a car booking order according to an exemplary embodiment of the present application.

Fig. 6 is a structural diagram of an apparatus for processing a reservation order, according to an exemplary embodiment of the present application.

Fig. 7 is a structural diagram of a device for processing a reservation order, according to another exemplary embodiment of the present application.

Fig. 8 is a structural diagram of a device for processing a reservation order, according to an exemplary embodiment of the present application.

detailed description

Exemplary embodiments will be described in detail here, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with this application. Rather, they are merely examples of devices and methods consistent with certain aspects of the application as detailed in the appended claims.

The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to limit the application. As used in this application and the appended claims, the singular forms "a", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

It should be understood that although the terms first, second, third, etc. may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein can be interpreted as "at" or "when" or "in response to determination".

FIG. 1 is a flowchart of a method for processing a reservation order, according to an exemplary embodiment of the present application; this embodiment can be used for a terminal device (such as a smart phone, a tablet computer, a desktop notebook, and the like) having a function of processing a reservation order for a car. ) Or server (including one or more servers, etc.). As shown in FIG. 1, the method includes steps S101-S103.

S101: Receive a car reservation form, where the car reservation form includes a reserved car time and a departure place.

When booking a vehicle, a passenger will send a car reservation form to the server that contains information on the time of the reserved car and the place of departure.

The above-mentioned car booking order includes the reserved car time and departure place, and may also include other related information, such as a destination, which is not limited in this embodiment. In an embodiment, the above-mentioned reserved car use time may be a certain time in the future. For example, when the passenger sends a reservation order at 9:00 am on May 1, 2018, the reserved car use time may be May 2, 2018. Sunday at 15:00.

It is worth noting that the above-mentioned form of the reserved car use time is only for illustrative purposes. In actual implementation, other forms such as a time stamp may be adopted as needed, which is not limited in this embodiment.

The starting point may be a boarding point recommended by the server based on the passenger's location (the location of the user automatically recognized by the terminal device of the passenger), or a boarding point manually input by the user, which is not limited in this embodiment.

S102: Determine a success rate of order allocation corresponding to each preset time period in a plurality of preset time periods after the reception time of the car use reservation order and before the reserved car use time.

In one embodiment, the plurality of preset time periods may be a time period from the end of the car reservation time to the reception time of the car use reservation order starting from the car reservation time.

For example, if a passenger sends an appointment order at 9:00 am on May 1, 2018, and the scheduled appointment is at 15:00 pm on May 2, 2018, multiple preset time periods may be 2018 14: 00 ～ 15: 00 on May 2nd, 13: 00 ～ 14: 00 on May 2nd, 2018,…, 9: 00 ～ 10: 00 a.m. on May 1, 2018.

In an embodiment, the plurality of preset time periods may also be a plurality of non-end-to-end time periods spaced between the reserved car use time and the reception time of the car use reservation order. For example, if the passenger sends the booking order at 9:00 am on May 1, 2018, and the scheduled appointment time is at 15:00 pm on May 2, 2018, the multiple preset time periods may be May 2018. 13:30 to 14:30 pm on May 2nd, 12:00 to 13:00 pm on May 2, 2018, ..., and 10:00 to 11:00 am on May 1, 2018.

In one embodiment, based on the historical data collected and stored by the server in the past, it can calculate the success rate of dispatching for each preset time period in multiple preset time periods before the reserved car time, such as one in advance. Order success rate for hourly orders, order success rate two hours in advance, order success rate N hours in advance. Among them, N can be calculated according to the difference between the time when the reservation order is received and the time for the reserved car. In an embodiment, if the difference is not an integer, the difference may be rounded down.

It is worth noting that the length of each of the above preset time periods is selected as an example for illustrative purposes only. In actual implementation, each time period can be set to 5 minutes, 10 minutes, 30 minutes, and 2 hours as required. Etc. Alternatively, the lengths of the respective time periods may be set to be different, which is not limited in this embodiment.

After determining the reserved car use time and the length of each preset time period, each of a plurality of preset time periods after the reception time of the car use reservation form and before the reserved car use time may be calculated. Set the dispatch success rate for the time period. For the calculation method of the dispatch success rate for each preset time period, refer to the embodiment shown in FIG. 2 below, which will not be described in detail here.

S103: Determine the dispatch time of the car reservation order according to the dispatch success rate in the multiple preset time periods.

In one embodiment, after determining the dispatch success rate in a plurality of preset time periods, the advance dispatch time in the plurality of preset time periods may be used to calculate a preset time period and two reservation times in advance, respectively. The success rate of the single car booking for the car booking as described in the segment to multiple time periods until the demand for the order success rate is met; then the total need for advance ordering can be determined based on the sum of multiple preset time periods required to meet the order success rate. The length of time can be calculated. For example, if it is calculated that the order needs to be dispatched 4 hours in advance, and the appointment time is 15:00 PM on May 2, 2018, then the order dispatch time can be determined to be 11:00 AM on May 2, 2018.

For a manner of determining the dispatch time of the vehicle reservation order, reference may be made to the embodiment shown in FIG. 4A below, which will not be described in detail here.

S104: If the dispatch time is reached, send the car reservation order to a network-booked car in a preset area centered on the departure place.

When the dispatch time is determined, when the dispatch time is reached, the car reservation order may be sent to a network-booking car in a preset area centered on the departure place.

It is worth noting that the dispatch mode can achieve a higher success rate than the rush order mode. The reason is that under the rush order mode, the driver knows very little information when deciding whether to rush to order, based only on his own position. , Willingness, and time to book a car, departure and destination, and other factors, but less knowledge of real-time road conditions, supply and demand, and other drivers and passengers. In the dispatch mode, in addition to considering the driver's location, the driver's willingness to take orders (based on the results of big data analysis), the time of the reserved car, the departure and destination, and other factors, the server can also integrate road conditions, supply and demand, and drivers And the distribution of passengers ’conditions determine the best driver for dispatching, which can reduce the probability of no driver snatching orders, improve the success rate of passenger appointments, and give drivers comprehensive consideration of road conditions, capacity, and bill of lading distribution. Make sure to make an appointment for subsidies to achieve the purpose of improving the experience of both the driver and the driver.

For a manner of sending the car reservation order, reference may be made to the embodiment shown in FIG. 5A below, which is not described in detail here.

It can be known from the foregoing description that, compared with the technology of broadcasting immediately after obtaining a car reservation form, this embodiment may be based on multiple preset times after the time of obtaining the car reservation form and before the time of the reserved car use. In the segment, the dispatch success rate corresponding to each preset time period determines the dispatch time of the car reservation order. The dispatch time can be calculated relatively accurately, and when the dispatch time is reached, the appointment order can be regarded as instant. The order is processed so that the driver can more accurately predict whether the passenger service can be provided in a timely manner according to the current situation when judging whether to accept the order, reduce the probability of the driver receiving a wrong order, increase the success rate of the appointment, and thereby improve the user experience.

Fig. 2 is a flow chart showing how to determine the dispatch success rate of each preset time period according to an exemplary embodiment of the present application; based on the above embodiment, how to determine the dispatch of each preset time period in this embodiment The single success rate is exemplified for example. As shown in FIG. 2, in step S102, determining a success rate of order allocation corresponding to each preset time period among a plurality of preset time periods before the scheduled car use time may include the following steps S201-S202.

S201: Determine the characteristic value of the dispatch success rate of the preset area in each of the preset time periods.

A characteristic value of the success rate of dispatching in a preset area centered on the departure place within each of the preset time periods may be determined.

The above distribution success rate characteristics can be selected and set by developers according to actual business needs. For example, the distribution success rate feature may be set to at least one of the average vehicle speed, the capacity density, and the probability that the driver will not cancel the order (used to reflect the driver's willingness to take orders) in the above-mentioned preset areas during each preset time period. This embodiment is not limited to this.

S202: Input the feature value of the dispatch success rate into a pre-trained dispatch success rate model to obtain the dispatch success rate in each of the preset time periods.

The dispatch success rate model can be trained according to the sample data in advance. The input of the model is the feature value of the dispatch success rate, such as the average speed of the vehicle, the capacity density, and the probability of the driver not canceling the order within the preset time period in the above-mentioned area At least one item is output as a success rate of dispatch within each of the preset time periods.

After obtaining the distribution success rate characteristic value of the preset area in each of the preset time periods, the distribution success rate characteristic value may be input to a pre-trained distribution success rate model to obtain each of the Order success rate within a preset time period.

For the training method of the above-mentioned dispatch success rate model, reference may be made to the embodiment shown in FIG. 3 below, which will not be described in detail here.

It can be known from the foregoing description that in this embodiment, by determining the characteristic value of the distribution success rate of the preset area in each of the preset time periods, and inputting the characteristic value of the distribution success rate into the pre-trained distribution success Rate model to obtain the dispatch success rate in each of the preset time periods, which can provide a basis for determining the dispatch time of the car reservation order based on the dispatch success rate in each preset time period to ensure the dispatch time Accuracy.

Fig. 3 is a flow chart showing how to determine the success rate of dispatching for each preset time period according to another exemplary embodiment of the present application; this embodiment describes how to determine the success rate of dispatching for each preset time period. As shown in FIG. 3, in step S102, it is determined that the dispatch order corresponding to each preset time period is in a plurality of preset time periods after the reception time of the car use reservation order and before the reserved car use time. The success rate may include the following steps S301-S305.

S301: Acquire a sample distribution success rate characteristic value of a target area in a plurality of preset time periods, where the target area includes the preset area.

In order to train the dispatch success rate model, multiple target regions can be set in advance, and the sample dispatch success rate characteristic values of each target region within multiple preset time periods can be obtained.

The above target area can be divided according to actual business needs, for example, the target environment can be divided into multiple areas of 10-20 square kilometers in size according to streets, business districts, office buildings, and the like. The preset area is an area for searching for an available car rental centered at the departure place, so the preset area is smaller than the target area.

The above target environment can be selected by the developer according to the needs of the actual distribution service. For example, the country, province, city, or town where the service is located can be selected, which is not limited in this embodiment.

S302: Calibrate the distribution success rate corresponding to the sample distribution success rate characteristic value in each preset time period.

After obtaining the sample dispatch success rate characteristic value of the target area in multiple preset time periods, the dispatch success rate corresponding to the sample dispatch success rate characteristic value in each preset time period may be calibrated. A manual method (that is, a supervised method) or a machine learning method (semi-supervised method) can be used to calibrate the sample delivery success rate corresponding to the sample delivery success rate characteristic value within each preset time period. This embodiment The comparison is not limited.

S303: Use the sample dispatch success rate feature value and the sample dispatch success rate feature value corresponding to the sample dispatch success rate feature value in the target area within each preset time period as a training set to train a dispatch success rate model.

After obtaining the above-mentioned sample order success rate characteristic value and the target order success rate corresponding to the sample order success rate characteristic value in the target area within each preset time period, the sample order success rate characteristic may be Value and the sample success rate corresponding to the sample dispatch success rate feature value are used as training sets to train the dispatch success rate model.

The above dispatch success rate model may be a support vector machine, a convolutional neural network (CNN) model, or the developer may select other models for training according to actual business needs, which is not limited in this embodiment.

S304: Determine the characteristic value of the dispatch success rate of the preset area in each of the preset time periods.

S305: The feature value of the dispatch success rate is input into the dispatch success rate model trained in advance to obtain the dispatch success rate in each of the preset time periods.

For related explanations and descriptions of steps S304-S305, refer to the foregoing embodiments, and details are not described herein again.

The above steps S301 to S303 may be performed in advance, that is, the dispatch success rate model is trained according to the sample data in advance.

As can be seen from the above description, in this embodiment, by acquiring sample feature success rate characteristic values of target regions in multiple preset time periods, and calibrating the corresponding order value of the sample order success rate characteristic values in each preset time period The success rate, and further uses the sample dispatch success rate feature value and the sample dispatch success rate feature value corresponding to the sample dispatch success rate feature value in the target region within each preset time period as a training set to train the dispatch success rate model So that the subsequent success rate can be calculated based on the trained success rate model in each of the preset time periods, and then the car booking order can be determined based on the success rate of dispatch in each preset time period. The dispatch time provides a basis to ensure the accuracy of the dispatch time.

FIG. 4A is a flowchart showing how to determine a dispatch time of a car reservation order according to an exemplary embodiment of the present application; FIG. 4B is a network in each time period during a process of car reservation order processing according to an exemplary embodiment of the present application 4C is a schematic diagram of a search range of a network of car appointments in each time period during the process of a car booking reservation process according to another exemplary embodiment of the present application.

Based on the above embodiment, this embodiment describes how to determine the dispatch time of the car reservation order. As shown in FIG. 4A, in step S103, the dispatch time of the car reservation order is determined according to the dispatch success rate in the multiple preset time periods, and includes the following steps S401-S402.

S401: Starting from the first preset time period starting from the reserved car use time, accumulating the dispatch success rate corresponding to each of the preset time periods one by one, until the total cumulative success rate of the current dispatch is consistent with success Rate conditions. The "cumulative" operation is implemented by a related algorithm of probability calculation, which will be described below.

S402: Determine a dispatch time of the car reservation order according to a difference between the car reservation time and each of the preset time periods currently accumulated.

A three-dimensional model as shown in FIG. 4B can be established, and the model is used to more clearly and intuitively explain the search range of the online car rental in each time period from the time and space in the processing of the car booking order. As shown in FIG. 4B, the x and y axes are used to represent geographic coordinates, and the T axis is used to represent time. Assume that the reserved car time is T = 0. In order to ensure that passengers can get on the car on time, the server can determine the online appointment for the ride some time in advance. Theoretically, the longer the advance time is, the larger the range of the network-reserved car used for searching for the pickup can be (assuming that the network-reserved car's traveling speed is uniform in time and space). For example, assuming that the driver starts to pick up at T = -t (that is, the pick-up time is t), and the average speed of the network-reserved car is v, the range of the network-reserved car used to search for the driver can be calculated. A circle with a radius of R = v * t, centered on the departure point of the passenger. That is, assuming that the traveling speed of the ride-hailing car is uniform in time and space, a cone model can be constructed starting from the time T = 0 and centered on the starting point to the negative direction of the time axis. The tangent function of the vertex angle θ of the cone The value of is v (that is, tanθ = v), the height is t, and the circular section at time t can be used to indicate the range of the search for a ride-hailing car when the pickup time is t.

On this basis, if the pick-up time is increased from t to (t + dt), that is, by adding a preset time period, the height of the cone becomes (t + dt), and a round table with a height of dt (that is, the figure) Middle thick line). It can be seen from FIG. 4B that the larger the time t, the larger the circular cut surface, which means that the range used for searching for a car about the network is also larger.

The above-mentioned total dispatch success rate meets the success rate condition, and may include: the total dispatch success rate is greater than or equal to a preset dispatch success rate threshold. The preset success rate threshold can be set by a developer or user according to actual needs, such as 95% or 99%.

As shown in FIG. 4C, starting from the first preset time period (that is, the small cone with a height of t) as the starting point of the reserved vehicle time T = 0, the success rate of order allocation corresponding to each preset time period (i.e., Increasing the order success rate corresponding to the dt round table one by one), until the total accumulated order success rate currently reached the preset order success rate threshold, and then the pick-up time can be determined according to the current accumulated time period, that is, the time of advance order .

Starting from T = 0, n round tables are sequentially numbered as 1, 2, ..., n (where the round table with number 1 is a cone with a height of t). Assume that the probability that a network-booking vehicle that meets the dispatch conditions is found in n round tables and the order is successful is P, and the probability that a network-booking vehicle that meets the dispatch conditions is searched in the i-th stage is successful and the order is Pi , The corresponding failure probability is (1-Pi). Assuming that the online booking car that meets the dispatch conditions is searched in n round platforms and the successful events are independent of each other, the probability that no online booking car that meets the dispatch conditions is found in all n round platforms is

which is

Thus, the problem of calculating the probability P can be converted into the problem of calculating the probability Pi of each round table, and then the probability P can be calculated by calculating the probability Pi of each round table, that is,

For example, if the round-table car number 1 is found and the probability of successful dispatch is P1: if the probability P1 is greater than or equal to the preset success rate threshold of 95%, the dispatch time can be determined to be T =- t; If the probability P1 is less than the preset success rate threshold of 95%, the probability of the round table of number 2 is accumulated on the basis of the round table of number 1, that is, the number of round tables of number 1 and number 2 is calculated and a car is searched and dispatched Probability of success P ₁₂ = 1- (1-P ₁ ) (1-P ₂ ). If the probability P _{12 is} greater than or equal to the preset success rate threshold of 95%, it can be determined that the dispatch time is T =-(t + dt1); if the probability P _{12 is} less than the preset success rate threshold of 95%, the number is 1 On the basis of the round tables of No. 2 and No. 2, the probability of continuing to accumulate the round table of No. 3 is calculated, that is, the probability of successful search for an online car from the round tables of No. 1, No. 2, and No. 3 is calculated. P ₁₂₃ = 1- (1-P ₁ ) (1-P ₂ ) (1-P ₃ ), if the probability P ₁₂₃ value is greater than or equal to the preset success rate threshold 95%, then it can be determined that the dispatch time is T =-(t + dt1 + dt2) ; If the value of the probability P ₁₂₃ is less than the preset success rate threshold of 95%, the probability of the round table of number 4 is continued to be accumulated on the basis of the round tables of number 1, 2, and 3, until the obtained probability is greater than or equal to the preset The success rate threshold is 95%.

It is worth noting that if the traveling speed of the net-ride car is not uniform in time or space, the apex angles of each round table may not be equal. If it is desired to indicate that the traveling speed is uneven in time or space, the cross section of the circular table can be set as an irregular plane, that is, an irregular cone derived from a cone. However, this type of irregular cones derived from cones has the common feature that the closer the time is to the departure time of T = 0, the smaller the time and space range of the search network about the car. This feature is the opposite of an instant order, so for the booking order of a given car time, the server must strictly consider the pick-up time. And the processing method of the instant order is: after the passenger issues a car reservation order, the passenger's location or the nearest pick-up point position is used as the center to search for a network appointment within a certain search range. After a period of time, if the search fails, Then the search scope is expanded, and the pick-up time is likely to be longer after the search scope is expanded. Passengers can choose whether to wait. The server does not need to guarantee the pick-up time for the immediate order.

As can be seen from the above description, this embodiment starts by accumulating the success rate of order allocation corresponding to each of the preset time periods starting from the first preset time period starting from the reserved car use time, until the current cumulatively obtained The total dispatch success rate meets the success rate condition, and then the dispatch time of the car reservation order is determined based on the difference between the reserved car time and each of the preset time periods currently accumulated, and the dispatch can be calculated relatively accurately Single time, and then the appointment order can be processed as an instant order when the order arrives later, so that the driver can more accurately predict whether the passenger service can be provided in a timely manner according to the current situation, and reduce the probability of the driver receiving the order by mistake. Increasing the success rate of car hire can improve user experience.

Fig. 5A is a flow chart showing how to send a car reservation form according to an exemplary embodiment of the present application; based on the above embodiment, this embodiment describes how to send a car reservation form. As shown in FIG. 5A, the step of sending the car reservation order to a network-booked car in a preset area centered on the departure place as described in step S104 may include the following steps S501-S502.

S501: Determining a network-aid car in the preset area that meets the ordering conditions.

When the dispatch time is determined, a preset area for searching for an online car can be determined according to the dispatch time. For example, as shown in FIG. 5B, if the dispatch time is T = -t, the preset area of the corresponding search network for a car is the cone section corresponding to the dispatch time T = -t, that is, as shown in FIG. 5B. Area corresponding to a circle with a radius R = v * t.

The corresponding areas described above can be used to characterize the "feasible areas" used to search for network rides. The closer the pick-up distance, the shorter the time required for pick-up, and the stronger the driver ’s willingness to pick up (that is, the willingness not to cancel the order after being dispatched), it can be within the corresponding “feasible area” A smaller area (such as a circular area indicated by a dashed line in FIG. 5B) is determined as a "preferred area" for searching for an online car. It is worth noting that the size of the preferred area can be determined by developers based on experience or related algorithms, for example, it is set to 80%, 60%, etc. of the size of the "feasible area", which is not limited in this embodiment.

For example, you can first lock a ride-hailing car A in the "feasible area", and then look for a better ride-hailing vehicle B in the "preferred area". If you find a ride-hailing vehicle B, replace A; and If the network-aid car A is about to leave the "feasible area" and no better network-aid car B is found in the "preferred area", the car reservation will be sent to the network-aid car A. For a manner of determining a more optimal ride-hailing vehicle B, refer to related technologies, which is not limited in this embodiment.

After the preset area is determined, among the available network rental cars in the preset area, the online rental cars that meet the dispatch conditions can be filtered.

The above-mentioned available network-aid cars may include the currently-available network-aid cars that are already available in a preset area, or may be network-aid cars that stop at a preset time or pass through the preset area and can take orders.

The above-mentioned dispatch conditions can be set in advance by a developer or a user, for example, it can be set as a distance from a departure place, a driver's rating, and the number of services, which is not limited in this embodiment. For example, the dispatch condition may be set to the ride-hailing service closest to the departure place.

S502: Send the car reservation order to the online car rental.

When it is determined that the online appointment car in the preset area meets the dispatching conditions, the above-mentioned car reservation order may be sent to the online appointment car.

It can be known from the foregoing description that, in this embodiment, by determining the online appointment car that meets the dispatch condition in the preset area, and sending the car reservation order to the online appointment car, it is possible to accurately determine the Compared with the order-buying mode, online booking can reduce the probability of driver-less order-buying, increase the success rate of passenger booking, and improve the experience of both the driver and the passenger.

Corresponding to the foregoing method embodiments, this application also provides embodiments of corresponding devices.

FIG. 6 is a structural diagram of a device for processing a reservation order shown in an exemplary embodiment of the present application; as shown in FIG. 6, the device includes: a reservation order receiving module 110, a success rate determination module 120, and a dispatch time determination module 130 and a reservation order sending module 140, where:

The booking order receiving module 110 is configured to receive a car booking order, the car booking order including a reserved car time and a departure place;

The success rate determination module 120 is configured to determine that after a time of receiving the car use reservation order and in a plurality of preset time periods before the car use reservation order, the order allocation corresponding to each preset time period is successful rate;

The dispatch time determining module 130 is configured to determine the dispatch time of the car reservation order according to the dispatch success rate corresponding to the multiple preset time periods;

A booking order sending module 140 is configured to send the car booking order to a network-booked car in a preset area centered on the departure place when the time of the order is reached.

It can be known from the foregoing description that, compared with the technology of broadcasting immediately after obtaining a car reservation form, this embodiment may be based on multiple preset times after the time of obtaining the car reservation form and before the time of the reserved car use. In the segment, the dispatch success rate corresponding to each preset time period determines the dispatch time of the car reservation order, so that the dispatch time can be calculated relatively accurately, and when the dispatch time is reached, the appointment order is regarded as instant Order processing, so that when determining whether to accept an order, the driver can more accurately foresee whether the passenger service can be provided in a timely manner according to the current situation, reducing the probability of the driver receiving a wrong order, increasing the success rate of the appointment, and thereby improving the user experience .

FIG. 7 is a structural diagram of a device for processing reservation orders, according to another exemplary embodiment of the present application; wherein, the reservation order receiving module 210, the success rate determination module 220, the dispatch time determination module 230, and the reservation order sending module 240 The functions of the reservation order receiving module 110, the success rate determination module 120, the dispatch time determination module 130, and the reservation order sending module 140 in the embodiment shown in FIG. 6 are the same, and details are not described herein. As shown in FIG. 7, the success rate determination module 220 may include:

A characteristic value determining unit 221, configured to determine a characteristic value of order success rate of the preset area in each of the preset time periods;

The success rate determining unit 222 is configured to input the dispatch success rate characteristic value into a pre-trained dispatch success rate model to obtain a dispatch success rate within each of the preset time periods.

In an embodiment, the apparatus may further include a model training module 250, and the model training module 250 may include:

A feature value acquisition unit 251 is configured to obtain a feature value of a sample order success rate of a target area in a plurality of preset time periods, where the target area includes the preset area;

The success rate calibration unit 252 is configured to calibrate an order success rate corresponding to the sample order success rate characteristic value within each preset time period;

A model training unit 253 is configured to use the sample dispatch success rate feature value corresponding to each preset time period and the sample dispatch success rate feature value corresponding to the sample dispatch success rate feature value as training sets to train the dispatch success rate model.

In an embodiment, the dispatch success rate characteristic may include at least one of an average speed of a vehicle, a capacity density, and a probability that the driver does not cancel the order.

In an embodiment, the plurality of preset time periods may be a plurality of end-to-end time periods starting from the reserved car time.

The dispatch time determination module 230 may include:

The success rate accumulating unit 231 is configured to start from the first preset time period starting from the reserved car use time period, and accumulate the success rate of order allocation corresponding to each of the preset time periods one by one, until the current total obtained total The dispatch success rate meets the success rate conditions;

The dispatching time determining unit 232 is configured to determine the dispatching time of the vehicle reservation order according to the difference between the reserved vehicle time and each of the preset time periods currently accumulated.

In an embodiment, the total dispatch success rate meets the success rate condition, and may include:

The total dispatch success rate is greater than or equal to a preset dispatch success rate threshold.

In an embodiment, the reservation order sending module 240 may include:

The network-booking-determining unit 241 is configured to determine a network-booking-ride in the preset area that meets the ordering conditions;

The booking order sending unit 242 is configured to send the car booking order to the online car rental.

It is worth noting that all of the above-mentioned optional technical solutions can be combined in any optional manner to form optional embodiments of the present disclosure, which will not be described in detail here.

The embodiment of the apparatus for processing a reservation ticket of the present disclosure may be applied to a network device. The device embodiments can be implemented by software, or by hardware or a combination of software and hardware. Taking software implementation as an example, as a logical device, it is formed by reading the corresponding computer program instructions in the non-volatile storage medium into the memory through the processor of the device in which the computer program is executed. The method for processing a reservation order provided by the embodiment shown in FIG. 1 to FIG. 5B. In terms of hardware, as shown in FIG. 8, the hardware structure diagram of the device for processing reservation orders in the present disclosure, except for the processor 801, the network interface 802, the memory 803, and the non-volatile storage medium 804 shown in FIG. 8. In addition to the internal bus 805, the device may also generally include other hardware, such as a forwarding chip responsible for processing messages, etc. In terms of hardware structure, the device may also be a distributed device, which may include multiple interface cards. In order to expand the message processing at the hardware level. On the other hand, the present application also provides a computer-readable storage medium. The storage medium stores a computer program, and the computer program is configured to execute the method for processing a reservation order provided by the embodiment shown in FIG. 1 to FIG. 5B.

As for the device embodiment, since it basically corresponds to the method embodiment, the relevant part may refer to the description of the method embodiment. The device embodiments described above are only schematic, and the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located One place, or it can be distributed across multiple network elements. Some or all of these modules can be selected according to actual needs to achieve the purpose of the solution of this application. Those of ordinary skill in the art can understand and implement without creative efforts.

Those skilled in the art will readily contemplate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application. These variations, uses, or adaptations follow the general principles of this application and include common general knowledge or conventional technical means in the technical field not disclosed in this application. . It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.

It should also be noted that the terms "including", "comprising" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, product, or device that includes a series of elements includes not only those elements, but also Other elements not explicitly listed, or those that are inherent to such a process, method, product, or device. Without more restrictions, the elements defined by the sentence "including a ..." do not exclude the existence of other identical elements in the process, method, product or equipment including the elements.

The above are only preferred embodiments of this application, and are not intended to limit this application. Any modification, equivalent replacement, or improvement made within the spirit and principle of this application shall be included in this application Within the scope of protection.

Claims

A method for processing an appointment form includes:

Receiving a car booking form, the car booking form including a reserved car time and a departure place;

Determining a success rate of order allocation corresponding to each preset time period among a plurality of preset time periods after the reception time of the car use reservation order and before the reserved car use time;

Determining a dispatch time of the car reservation order according to the dispatch success rate corresponding to the multiple preset time periods;

If the dispatch time is reached, the car booking order is sent to a network-booking car in a preset area centered on the departure place.
The method according to claim 1, determining a dispatch order corresponding to each preset time period among a plurality of preset time periods after the reception time of the car use reservation order and before the reserved car use time. Success rate, including:

Determining the characteristic value of the dispatch success rate of the preset area in each of the preset time periods;

The feature value of the dispatch success rate is input into a pre-trained dispatch success rate model to obtain the dispatch success rate corresponding to each of the preset time periods.
The method according to claim 2, further comprising:

Acquiring sample distribution success rate characteristic values of a target area in a plurality of preset time periods, the target area including the preset area;

Calibrating the distribution success rate corresponding to the characteristic value of the sample distribution success rate in each preset time period;

Use the sample dispatch success rate feature value corresponding to each preset time period and the sample dispatch success rate feature value corresponding to the sample dispatch success rate feature value as a training set to train the dispatch success rate model.
The method according to claim 2, wherein the dispatch success rate characteristic includes at least one of an average speed of the vehicle, a capacity density, and a probability that the driver does not cancel the order.
The method according to claim 1, wherein the plurality of preset time periods are a plurality of end-to-end time periods starting from the reserved car time;

Determining the dispatch time of the car booking order according to the dispatch success rate corresponding to the multiple preset time periods includes:

Starting from the first preset time period starting from the reserved car use time, accumulating the success rate of order allocation corresponding to each of the preset time periods toward the receiving time of the car use booking order, until the current cumulative The success rate of total dispatches meets the success rate conditions;

The dispatch time of the car reservation order is determined according to a difference between the reserved car use time and each of the preset time periods currently accumulated.
The method according to claim 5, wherein the total dispatch success rate meets a success rate condition, comprising:

The total dispatch success rate is greater than or equal to a preset dispatch success rate threshold.
The method according to claim 5, wherein the calculation formula of the total dispatch success rate is:

Among them, P is the overall order success rate, Pi is the order success rate corresponding to the i-th preset time period, and n is the number of currently accumulated preset time periods.
The method according to any one of claims 1 to 7, sending the car reservation order to a network-booked car in the preset area centered on the departure place, comprising:

Determining a network-booking car in the preset area that meets the dispatch conditions;

And sending the car reservation order to the online car rental.
The method according to claim 1, further comprising:

Approximately determine the size of the preset area according to the average vehicle speed and the dispatch time.
A device for processing a reservation order includes:

A reservation order receiving module for receiving a vehicle reservation order, wherein the vehicle reservation order includes a reservation time and a departure place;

A success rate determining module, configured to determine a success rate of order allocation corresponding to each preset time period in a plurality of preset time periods after the reception time of the car use reservation order and before the reserved car use time. ;

A dispatch time determination module, configured to determine the dispatch time of the car reservation order according to the dispatch success rate corresponding to the multiple preset time periods;

A reservation order sending module is configured to, when the dispatch time is reached, send the car reservation order to a network-booked car in a preset area centered on the departure place.
A device for processing reservation orders, including:

processor;

A storage medium configured to store processor-executable instructions;

The processor is configured to execute the method for processing a reservation order according to any one of claims 1-9.
A computer-readable storage medium stores a computer program, and the computer program is used to execute the method for processing a reservation order according to any one of claims 1-9.