CN114266631A

CN114266631A - Order scheduling method and computer storage medium

Info

Publication number: CN114266631A
Application number: CN202111660731.5A
Authority: CN
Inventors: 魏文鹏; 谷骞; 张旸
Original assignee: Alibaba Singapore Holdings Pte Ltd
Current assignee: Alibaba Innovation Co
Priority date: 2021-12-30
Filing date: 2021-12-30
Publication date: 2022-04-01

Abstract

The embodiment of the application provides an order scheduling method and a computer storage medium, wherein the method comprises the steps of receiving travel order information, and obtaining service provider information and historical travel service information of at least two candidate service providers corresponding to the travel order information; determining expected income according to the travel order information, the service provider information and the historical travel service information; and allocating orders for at least two candidate service providers according to the expected income to obtain an order scheduling result. The expected income represents the comprehensive income condition, and the comprehensive income not only comprises the short-term income corresponding to the travel order, but also comprises the probability of providing travel service in a future period through the candidate service provider, and reflected medium-term income and long-term income. Considering from the perspective of comprehensive benefits, the number of travel services provided by the service provider in a future predetermined time period is increased, and travel experience is improved.

Description

Order scheduling method and computer storage medium

Technical Field

The embodiment of the application relates to the technical field of computers, in particular to an order scheduling method and a computer storage medium.

Background

With the popularization of intelligent devices and the development of mobile internet technologies, the internet car booking service becomes more and more popular at present. A service requester (e.g., a passenger) may send an order for a requested vehicle while traveling through an online taxi service platform, which distributes the order for the requested vehicle to a service provider (e.g., a driver) according to a certain distribution strategy.

Different order scheduling modes influence the condition that a service provider provides service next time, and are related to the number of available vehicles of the online taxi service platform, and the number of the available vehicles is directly related to the passenger travel experience and the order income of the online taxi service platform. The order scheduling method not only affects the overall scheduling efficiency of the order scheduling platform, but also affects the sustainable development of the order scheduling platform, so that it is urgently needed to provide an order scheduling method, so that the online taxi calling service platform can better perform order scheduling.

Disclosure of Invention

In view of the above, the present disclosure provides an order scheduling scheme to at least partially solve the above problem.

According to a first aspect of an embodiment of the present application, there is provided an order scheduling method, including: the method comprises the steps of receiving travel order information, and obtaining service provider information and historical travel service information of at least two candidate service providers corresponding to the travel order information; determining expected income according to the travel order information, the service provider information and the historical travel service information; and distributing orders for at least two candidate service providers according to the expected income to obtain an order scheduling result.

According to a second aspect of the embodiments of the present application, there is provided another order scheduling method, including: the method comprises the steps that travel order information sent by a service requester is received through an order scheduling platform, wherein the order scheduling platform is an aggregation platform with a plurality of travel platforms; sending the travel order information to the plurality of travel platforms, and receiving feedback information fed back by the plurality of travel platforms, wherein the feedback information carries service provider information and historical travel service information of at least two candidate service providers corresponding to the travel order information; determining expected income according to the travel order information, the service provider information and the historical travel service information; and distributing orders for at least two candidate service providers according to the expected income to obtain an order scheduling result.

According to a third aspect of the embodiments of the present application, there is provided yet another order scheduling method, including: sending current position information of a service providing terminal and current service state information of the service providing terminal to a trip platform, so that the trip platform determines at least two candidate service providers according to the plurality of current position information, the plurality of current service state information and trip order information received from an order scheduling platform, generates feedback information and sends the feedback information to the order scheduling platform; determining expected revenue through the order scheduling platform according to the trip order information, the service provider information of at least two candidate service providers carried by the feedback information and historical trip service information, distributing orders for the at least two candidate service providers according to the expected revenue to obtain an order scheduling result, wherein the order scheduling result represents the service provider matched with each trip order information; and receiving matched travel order information sent by the order scheduling platform through a travel platform corresponding to the matched service provider and expected revenue corresponding to the matched travel order information.

According to a fourth aspect of the embodiments of the present application, there is provided another order scheduling method, including: receiving a travel request initiated by a service requester, and generating travel order information according to the travel request; sending the travel order information to an order scheduling platform, enabling the order scheduling platform to send the travel order information to a plurality of travel platforms, determining expected revenue by combining the travel order information based on service provider information and historical travel service information of at least two candidate service providers fed back by the plurality of travel platforms, and distributing orders for the at least two candidate service providers according to the expected revenue to obtain an order scheduling result; and receiving the service provider information distributed in the order scheduling result sent by the order scheduling platform.

According to a fifth aspect of embodiments of the present application, there is provided an electronic apparatus, including: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus; the memory is configured to store at least one executable instruction, where the executable instruction causes the processor to perform an operation corresponding to the order scheduling method according to any one of the first aspect to the fourth aspect.

According to a sixth aspect of embodiments of the present application, there is provided a computer storage medium having stored thereon a computer program which, when executed by a processor, implements the order scheduling method according to any one of the first to fourth aspects.

According to the order scheduling scheme provided by the embodiment of the application, trip order information is received, and service provider information and historical trip service information of at least two candidate service providers corresponding to the trip order information are obtained; determining expected income according to the travel order information, the service provider information and the historical travel service information; and allocating orders for at least two candidate service providers according to the expected income to obtain an order scheduling result. According to the method and the device for allocating the travel orders, when the orders are allocated, not only is single information corresponding to travel order information considered, but also service provider information corresponding to at least two candidate service providers capable of providing travel services for the travel orders and historical travel service information of the candidate service providers are considered, so that the determined expected income can represent a comprehensive income condition, the comprehensive income not only comprises short-term income corresponding to the travel orders, but also comprises probability of providing the travel services in a future period through the candidate service providers, and middle-term income and long-term income are reflected. Considering from the perspective of comprehensive benefits, the number of travel services provided by a service provider in a future preset time period is increased, the number of available vehicles of the order scheduling platform is ensured, the global optimization of the travel scheduling services is realized, the sustainable development of the order scheduling platform is improved, and the travel experience is improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the embodiments of the present application, and other drawings can be obtained by those skilled in the art according to the drawings.

Fig. 1 is a flowchart illustrating steps of an order scheduling method according to an embodiment of the present application;

fig. 2 is a schematic structural diagram of an order scheduling system according to an embodiment of the present application;

fig. 3 is a schematic view of an application scenario of an order scheduling method according to an embodiment of the present application;

fig. 4 is a block diagram of an order scheduling platform and a trip platform provided in the embodiment of the present application;

FIG. 5 is a flowchart illustrating steps of another method for scheduling orders according to an embodiment of the present disclosure;

FIG. 6 is a flowchart illustrating steps of a further method for scheduling orders according to an embodiment of the present disclosure;

FIG. 7 is a flowchart illustrating steps of another method for scheduling orders according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, but not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application shall fall within the scope of the protection of the embodiments in the present application.

It should be noted that the first and second embodiments are only used for distinguishing names, do not represent sequential relationships, and are not understood to indicate or imply relative importance or implicitly indicate the number of indicated technical features, such as the first benefit and the second benefit.

The following further describes specific implementations of embodiments of the present application with reference to the drawings of the embodiments of the present application.

The first embodiment,

As shown in fig. 1, fig. 1 is a flowchart of an order scheduling method provided in an embodiment of the present application.

To facilitate the description of the order scheduling scheme provided in the embodiment of the present application, first, a system architecture and an application scenario to which the scheme is applicable are respectively exemplarily described below.

As shown in fig. 2, fig. 2 is a schematic structural diagram of an order scheduling system according to an embodiment of the present disclosure. In fig. 2, the order scheduling platform is an aggregation platform, which has access to a plurality of travel platforms (illustrated as travel platforms 1 and 2 … … N), and each of the travel platforms may be considered as a sub-platform of the order scheduling platform. For each travel platform, it may have access to one or more (two or more) travel service providers (three are shown as an example), each of which has a certain number of service providers (drivers) (n are shown in the figure), so that the order scheduling platform can aggregate more service providers, on one hand, providing faster and better service for the service requesters (travel users), and on the other hand, providing more travel service opportunities for the service providers (drivers). In addition, the implementation cost of the travel platform can be effectively reduced, the travel platform does not need to have complex functions, such as expected income prediction, service provider retention rate prediction, single order income prediction, order income prediction in a preset time period, order income prediction in a future preset time period and the like, and the travel service with quality guarantee can be provided for the outside.

The order scheduling method relates to interaction among an order scheduling platform, a trip platform, a service request terminal and a service providing terminal, for a service requester, when the service requester needs to trip, the service request terminal can operate an interface (such as an application interface and the like) provided by the order scheduling platform to send a trip request, and the service request terminal generates trip order information according to the trip request; after receiving the travel order information, the order scheduling platform sends the travel order information to a plurality of aggregated travel platforms.

Each trip platform receives current position information and current service state information of each signed service provider sent by the trip service provider signed with the trip platform, determines at least two candidate service providers according to the current position information, the current service state information and the trip order information, and generates feedback information, wherein the feedback information carries the service provider information of the at least two candidate service providers corresponding to the trip order information and historical trip service information of the at least two candidate service providers, and the feedback information is sent to the order scheduling platform.

And finally, selecting a service provider matched with each travel order message from at least two candidate service providers by the order scheduling platform to obtain an order scheduling result, and feeding back the order scheduling result to the service requester.

It should be noted that, in practical application, the order scheduling platform may be deployed on a server or a server cluster, and in this case, the server or the server cluster may also be considered as the order scheduling platform. But not limited thereto, the order scheduling platform may also be deployed in a cloud, and in this case, the cloud software and hardware configuration having the functions implemented by the order scheduling platform may also be regarded as the order scheduling platform. Similarly, each travel platform may also be deployed in a server or a server cluster or a cloud, and the corresponding software and hardware settings may be considered as a travel platform. The travel order processing scheme based on the above architecture is explained in the following through a plurality of embodiments.

For example, a server deployed by a travel platform may be used to process information and/or data related to a network appointment order, and the server stores historical travel service information of a plurality of service providers. In an actual travel scene, after receiving travel order information sent by the order scheduling platform, the travel platform obtains service provider information of at least two candidate service providers within a preset range of a taking starting point, wherein the distance between the travel platform and the taking starting point is less than a preset distance (for example, 3km and 8km), and/or the predicted order taking time between the travel platform and the taking starting point is less than a preset time (for example, 5 minutes and 10 minutes). And then, screening out the historical trip service information of the at least two candidate service providers from the historical trip service information pre-stored in the server according to the service provider information of the at least two candidate service providers.

The preset range, the preset distance and the preset time may be set appropriately by those skilled in the art according to actual needs, or determined by analyzing a large number of range thresholds, distance thresholds and time thresholds used in a process of determining at least two candidate service providers according to orders.

In the embodiment of the present application, the number of orders is not limited, and may be one, or two or more. Taking a plurality of orders as an example, the plurality of orders may be orders received by the order scheduling platform at a certain time or within a certain time period (e.g., 5 seconds, 10 seconds, 20 seconds), for example, the plurality of orders may be orders located in a certain area, the starting point of the taking a bus of the plurality of orders is located in a certain area, and the area may be a preset regular or irregular shape such as a rectangle, a hexagon, a circle, etc., which is not limited in this embodiment of the present application. In the embodiment of the present application, the number of the service providers is at least two, the service providers may be multiple drivers to receive orders in a certain area, and taking multiple travel orders as an example, the multiple drivers to receive orders may be the same as the area where the multiple travel orders are located.

As shown in fig. 3, fig. 3 is a schematic view of an application scenario of an order scheduling method according to an embodiment of the present application. The application scene comprises the following steps: the service scheduling method includes the steps that a service request terminal, a service providing terminal and an order scheduling platform are shown in fig. 3, wherein 2 service request terminals and 4 service providing terminals are used for distributing an order a to a service provider (4) and distributing an order B to a service provider (2).

Based on the application scenarios of the order scheduling system in fig. 2 and the order scheduling method in fig. 3, the order scheduling method includes the following steps, as shown in fig. 1.

Step S101, receiving travel order information, and acquiring service provider information and historical travel service information of at least two candidate service providers corresponding to the travel order information.

The travel order in the embodiment of the application may be an order initiated by a service requester (e.g., a passenger) to an order scheduling platform, where the travel order information is used to represent relevant information of the service requester on travel demand, and includes a service requester identifier, a travel (taking a bus) starting point, a travel distance between the travel (taking a bus) starting point and the travel (taking a bus) ending point, and a travel time corresponding to the order (e.g., whether to weekend, whether to night, whether to go to work, and whether to peak work).

The trip starting point is related to nearby vehicles capable of providing services and is used for screening candidate service providers; the travel distance is related to the single order income corresponding to the order; the travel time corresponding to the order is closely related to the available vehicles, and the order profit corresponding to the order is greatly related, for example, the number of available vehicles corresponding to the travel in the peak time of commuting is less than that in the ordinary time period, the travel time in the same route is longer than that in the ordinary time period, and correspondingly, the travel time and the vehicle call both affect the order profit.

It will be appreciated that, in addition to the above-mentioned comparative critical information, the travel order information may also include at least one of: the travel (riding) terminal, whether the travel (riding) starting point and/or the travel (riding) terminal is a business block, whether the travel (riding) starting point and/or the travel (riding) terminal is a traffic hub, an order origination city, a vehicle type, a number of passengers, an expected order price, an expected travel time, an expected travel distance, an expected arrival time, a weather condition, a traffic condition (e.g., whether a road toll is generated, whether a congested area is crossed, etc.).

The service provider (e.g., driver, operator) in an embodiment of the present application receives the order through an order dispatch platform. The service provider information is used for representing service capability information of the service provider within a preset range from the starting point of the travel, and comprises vehicle state information (such as whether the vehicle is in an idle state, is about to be in an idle state, and is loaded with passengers but not fully loaded) and current position information. The vehicle state information reflects that the vehicle can provide services in the next period of time, the current position information reflects the area where the vehicle is located, and candidate service providers can be screened according to the current position information and the travel order information.

It will be appreciated that in addition to the more critical information described above, the service provider information may include at least one of: vehicle information (e.g., model, grade, license plate number, number of seats), current travel speed, distance from the start of an order ride, time expected to reach the start of an order ride, driver information (e.g., name, age, service score, occupation).

The historical travel service information is used for representing service capability information of a service provider when the service provider provides travel service in the past, and comprises an average value of the number of historical rejected orders in a preset time period (for example, daily, weekly, monthly, quarterly and yearly), an average time length of the historical travel service provided in the preset time period, a corresponding time period (for example, morning, afternoon, evening, night, working day and weekend) when the service provider provides travel service in the history, a corresponding area (for example, a place where drivers tend to be more familiar) when the service provider provides travel service in the history and an average value of historical order earnings in the preset time period.

The refusal order, the service duration, the service area and the service time period reflect the service habit of the service provider in the past when the service is provided, and the order receiving quantity and the service duration of the service provider in the next period of time can be estimated according to the service habit; the historical order revenue averages over the predetermined time period may be used to predict order revenue over the predetermined time period. It will be appreciated that, in addition to the above-mentioned comparative critical information, the historical travel service information may also include at least one of: historical rejected order to historical received order ratios, historical completed order quantity averages over a predetermined time period, areas corresponding to a service provider stopping receiving orders over a historical predetermined time period (e.g., drivers tend to stop receiving orders relatively close to home).

And S102, determining expected income according to the travel order information, the service provider information and the historical travel service information.

In the embodiment of the application, when the order is distributed, expected income is determined according to the travel order information, the service provider information corresponding to at least two candidate service providers capable of providing travel service for the travel order and the historical travel service information of the service providers, the expected income comprises the comprehensive income of each candidate service provider corresponding to each travel order, and the comprehensive income not only comprises the income brought by the travel order but also comprises the probability of providing the travel service by the candidate service providers in a period of time in the future. The profit brought by the current travel order can be understood as a short-term profit, the probability that the candidate service provider provides travel service in a future period can be reflected by a medium-term profit and a long-term profit, and both the medium-term profit and the long-term profit represent whether the travel order is distributed to a certain candidate service provider or not, and influence is exerted on whether the candidate service provider provides travel service in the future period, so that the profit brought by the candidate service provider in the future period is influenced.

Optionally, in an embodiment of the present application, the step S102 may include steps S1021 to S1023.

And S1021, predicting the retention rate of the service provider according to the travel order information, the service provider information and the historical travel service information.

Wherein the service provider retention rate is used for characterizing the probability that the candidate service provider provides travel service within a predetermined period of time in the future.

And taking the time corresponding to the order as the current time, wherein the time of the future scheduled time period is later than the current time. Illustratively, the time corresponding to the order is the current day and the predetermined time period in the future may be the next day.

In this example, for a driver who has a history that the average number of received orders per day is 8 and the time period corresponding to the history of providing travel service is daytime, if the driver receives only two orders before 17:00 pm on the day, the driver may not provide travel service any more on the next day, which can be understood as that the driver is not very aggressive.

According to the embodiment of the application, the service provider retention rate of each service provider is predicted according to the travel order information, the service provider information and the historical travel service information. For example, if the number of orders is M and the number of service providers is N, then M × N service provider retention rates are predicted. The method and the device predict the retention rate of the service provider through the travel order information, the service provider information and the historical travel service information, so that how to distribute the order to the service provider is determined according to the retention rate of the service provider, the positivity of the service provider is improved, and the order income of the order scheduling platform is improved.

And S1022, predicting the order income in a future preset time period according to the historical travel service information and the service provider retention rate.

The historical travel service information in this example includes the historical average value of the order profit in the predetermined time period, the historical average value of the number of completed orders in the predetermined time period, and the average time length for providing travel service in the history in the predetermined time period. The order income in a future preset time period can be estimated by combining the historical travel service information and the service provider retention rate, taking the preset time period as one day as an example, the order income brought by the next day is estimated according to the average value of the number of finished orders and the service provider retention rate in the history of one day in the historical travel service information. Or estimating the order income brought by the next day according to the average value of the historical order income of one day in the historical trip service information and the retention rate of the service provider. Or estimating the order income brought by the next day according to the average time length of the travel service in one day in the historical travel service information and the retention rate of the service provider. The revenue of the order within the future predetermined time period in the embodiment of the present application may also be understood as the long-term revenue.

And S1023, according to the order income in the future preset time period, combining the order income corresponding to each piece of predetermined travel order information and the order income in the preset time period, and determining the expected income.

The time of the preset time period is earlier than that of the future preset time period, the time of the preset time period comprises order time corresponding to the travel order information, and the future preset time period is adjacent to the preset time period in terms of time.

In the embodiment of the application, the order income corresponding to each predetermined travel order information and the order income within a predetermined time period may be determined by the order scheduling platform according to the travel order information, the service provider information and the historical travel service information, or may be obtained from other related servers. The embodiments of the present application are not limited thereto.

In this example, the single order revenue corresponding to the travel order information may be understood as the short-term revenue. Illustratively, the intrinsic value of an order, may also be understood as the price of the order. The individual order revenue corresponding to the individual travel order information may represent the intrinsic value of each order. The price of the order may be referenced to the projected order price, and the final transaction price of the order may not be the same as the projected order price during the actual trip. In a feasible manner, the price of the order can be determined according to at least one factor of a riding starting point, a riding terminal, an order starting time, a predicted arrival time, a predicted travelling distance, a weather condition, a traffic condition, a supply and demand relationship between a driver and the order, and the like. It will be appreciated that the order revenue may also include other revenue associated with the order, such as passenger tip, return trip allowance for empty, etc. In a travel scenario, the price for the order may be the fare paid by the service requester for the order.

In this example, taking the predetermined time period as one day as an example, the order revenue within the predetermined time period may represent the order revenue within one day. Whether the current order is assigned to a service provider has a large impact on the revenue of the order from the subsequent service provider, for example, if the start point of the ride of the current order is located in an area with high service demand (e.g., a downtown area) and the end point of the ride of the order is located in an area with low service demand (e.g., a suburban area), the driver may not reach the order for a long time after completing the order, or the driver may need to return empty to the area with high service demand after completing the order to receive the order. Even if the intrinsic value of the order is calculated, the driver's total order revenue over a future period of time (e.g., an hour, hours, a day, etc.) may be reduced by taking the order.

When the expected income is calculated, the current single order income and the order income in the preset time period are considered, and the order income in the future preset time period is also considered comprehensively, namely the order income in the short-term (single order income), the medium-term (order income in the preset time period) and the long-term (order income in the future preset time period) are considered respectively, so that when the order distribution is carried out according to the expected income subsequently, the quantity of travel services provided by a service provider in the future preset time period is increased, the order income is also ensured, and the travel experience is improved.

Alternatively, in an embodiment of the present application, the single order revenue and the order revenue within the predetermined time period in S1023 above may be obtained in the following manner. Acquiring current travel road information; performing road condition analysis on the current travel road information to obtain a road condition analysis result; and according to the road condition analysis result, predicting the single order income and the order income within a preset time period respectively by combining the current position information in the service provider information and the travel starting point position information and the travel ending point position information in the travel order information.

The current travel road information includes, but is not limited to, a current travel road condition, a geographic position corresponding to the current travel road, and a current travel vehicle condition, and the current travel road information affects a completion time of a current order and a quantity of orders capable of providing services in a next preset time period, that is, the current travel road information affects not only a benefit brought by the current order but also a benefit brought by the orders capable of providing services in the preset time period. The order income and the order income in a preset time period can be respectively estimated according to the road condition analysis result of the current travel road information, the service provider information, the travel order information and the historical travel service information.

In the embodiment of the application, the road condition analysis is carried out on the current road information, and the current position information, the trip starting point position information, the trip end point position information, the trip distance, the trip time point corresponding to the trip order of the service provider, the service information, the service duration, the service time period and the service area which are not provided in the historical trip service information are combined to predict the income brought by the trip order, so that the prediction accuracy of the income of the single order is improved; when the order income in the preset time period is predicted, the number of the travel orders corresponding to the travel time point is combined, the service number and the service duration of the service provider in the next preset time period can be predicted, so that the order income in the preset time period is predicted, and the prediction accuracy of the order income in the preset time period is improved.

And step S103, distributing orders for at least two candidate service providers according to the expected income to obtain an order scheduling result.

In the embodiment of the present application, the expected revenue includes a comprehensive revenue of each candidate service provider corresponding to each travel order, and may be understood as forming an order matching pair by each candidate service provider and each travel order, and distributing the travel orders by comprehensively considering the comprehensive revenue of each order matching pair. The preset income comprehensively considers the short-term income and the income in a future period of time, so the order distribution is carried out according to the preset income, the accuracy of the order scheduling result is improved, and the remaining quantity of the service provider in the future period of time, namely the quantity of travel service is ensured.

According to the order scheduling scheme provided by the embodiment of the application, not only is single information corresponding to the trip order information considered, but also service provider information corresponding to at least two candidate service providers capable of providing trip services for the trip order and historical trip service information thereof are considered, so that the determined expected profit can represent a comprehensive profit condition, the comprehensive profit not only comprises short-term profit corresponding to the trip order, but also comprises the probability of providing trip services in a future period through the candidate service providers, and reflected medium-term profit and long-term profit. Considering from the perspective of comprehensive benefits, the number of travel services provided by a service provider in a future preset time period is increased, the number of available vehicles of the order scheduling platform is ensured, the global optimization of the travel scheduling services is realized, the sustainable development of the order scheduling platform is improved, and the travel experience is improved.

The order scheduling method of the embodiment of the present application may be executed by any suitable electronic device with data processing capability, including but not limited to: server, mobile terminal (such as mobile phone, PAD, etc.), PC, etc.

Example II,

In an achievable order scheduling method, an order scheduling platform matches a travel order with a candidate service provider. The order scheduling model, which may include a cancellation rate model and a spatiotemporal value model, implements order scheduling by selecting either an optimization near term objective (e.g., optimizing current completion rate using the cancellation rate model) or a medium term objective (e.g., optimizing current completion amount on the day using the spatiotemporal value model) according to an order scheduling model, given a row order matching service provider. However, the following problems may occur in this scheme: the order is intensively distributed to the active head service providers (such as drivers), on one hand, the workload of the head drivers is increased, on the other hand, the working habits of the low-activity drivers are not easy to develop, and the retention and the travel service providing time of the low-activity drivers are difficult to improve.

The travel platform provides drivers with travel services, and the different types of drivers have different days for providing services every week, different service time periods for providing services every day and different corresponding time periods for providing services every day. The number of available vehicles of the travel platform aggregated by the order calling platform is directly related to the important travel experience of whether a platform passenger can take the vehicle or not and whether the platform passenger can take the vehicle quickly or not. The embodiment of the application provides an order scheduling method, which can improve the retention rate of a service provider, so that the number of days for a driver to provide travel service and the number of available vehicles of an order scheduling platform are increased, and travel experience is improved. The details are as follows.

As shown in fig. 4, fig. 4 is a block diagram of an order scheduling platform and a trip platform provided in the embodiment of the present application. The travel platform comprises a historical travel service information storage part 402 and a historical travel service information inquiry part 403; the order scheduling platform includes a supply and demand information input section 401, a service provider retention prediction section 404, a short term profit calculation section 405, a medium term profit calculation section 406, a long term profit calculation section 407, a matching problem solving section 408, and an order scheduling result output section 409. The order scheduling platform aggregates a plurality of trip platforms, and data and information interaction can be carried out between the order scheduling platform and the trip platforms.

With reference to the parts in fig. 4, the second embodiment of the present application is based on the solution of the first embodiment, and optionally, the second embodiment of the present application may include the following steps S201 to S208.

Step S201, obtaining the trip order information, and service provider information and historical trip service information of at least two candidate service providers corresponding to the trip order information.

The supply and demand information input part 401 is configured to receive travel order information sent by a service provider terminal, the travel platform determines at least two candidate service providers according to the travel order information sent by the supply and demand information input part 401, and according to the service provider information of the at least two candidate service providers, the historical travel service information query part 403 is configured to query historical travel service information of the at least two candidate service providers in the historical travel service information storage part 402. The supply and demand information input part 401 is further configured to receive service provider information and historical travel service information of at least two candidate service providers sent by the travel platform.

Step S202, inputting the travel order information, the service provider information and the historical travel service information into a retention rate prediction model which is trained in advance, and obtaining the retention rate of the service provider.

The service provider retention prediction section 404 is configured to predict a retention rate of the service provider after an order is allocated to the service provider and a retention rate of the service provider after an order is not allocated to the service provider, according to the travel order information, the service provider information, and the queried historical travel service information.

The retention prediction model in this example is used to predict the retention probability of the service provider, and the retention prediction model may be any appropriate Neural Network (NN) model that can be used to predict the retention according to the travel order information, the service provider information, and the historical travel service information. The embodiment of the present application does not limit the specific structure of the retention rate prediction model, for example: a Convolutional Recurrent Neural Network (CRNN), a Convolutional Neural Network (CNN), and the like.

The retention rate prediction model in this example may be pre-trained in the following manner. The method comprises the steps of obtaining a training sample comprising travel order sample information, service provider sample information and historical travel service sample information, inputting the training sample into an initial retention rate prediction model to obtain a retention prediction probability, training the initial retention rate prediction model according to the difference between the retention prediction probability of the training sample and the retention marking probability of the training sample to obtain a trained retention rate prediction model, wherein the retention marking probability corresponds to the training sample. When a sample is used for training the initial retention rate prediction model, model parameters of the retention rate prediction model are continuously adjusted, iterative updating is carried out until a training termination condition is reached, and the trained retention rate prediction model is obtained, wherein the training termination condition is that the training times reach a preset number, or the prediction result of the retention rate prediction model is in a preset deviation range.

It should be noted that the retention rate prediction model in the embodiment of the present application is not limited to the retention rate prediction model trained in advance in the present application, and the present application does not limit the specific structure of the retention rate prediction model, that is, the existing model trained by other people only needs to have the function of predicting the retention rate, and can be adapted to the scheme of the present application. The retention rate prediction model with the retention rate prediction function provided in the embodiment of the application is an optional improvement scheme, and is not a necessary scheme.

In the example, the retention rate is predicted according to the trip order information, the service provider information and the historical trip service information through the retention rate prediction model trained in advance, and the accuracy of the retention rate of the service provider is improved.

Optionally, in an embodiment of the present application, the service provider retention rate includes an assigned retention rate for characterizing the order being assigned to the service provider and an unassigned retention rate for characterizing the order being unassigned to the service provider.

In the present example, the predetermined time period is a day, and whether to allocate an order to a driver on the day directly affects the enthusiasm of the driver, and has a great influence on the probability that the driver will provide travel service the next day. The service provider retention rate in the embodiment of the application comprises two parts, wherein one part is the probability that the service provider provides travel service the next day when the order is allocated to the service provider, and the other part is the probability that the service provider provides travel service the next day when the order is not allocated to the service provider.

And S203, predicting the order income in a future preset time period according to the historical travel service information and the service provider retention rate.

The long-term profit calculation section 407 is configured to calculate a long-term profit after an order is allocated to the service provider according to the queried historical travel service information and service provider retention rates of the at least two candidate service providers.

Step S203 is the same as step S1022 in the first embodiment, and is not described herein again.

Alternatively, in an embodiment of the present application, when predicting the order revenue in the future predetermined time period in step S203, the following two examples may be specifically implemented.

Example one, a first benefit is determined according to the average value of the number of historical completed orders in the historical trip service information within a preset time period and the distribution retention rate; determining a second benefit according to the historical finished order quantity average value in the historical trip service information within a preset time period and the unallocated retention rate; and determining the order revenue in the future preset time period according to the difference value of the first revenue and the second revenue.

In the example, the predetermined time period is one day, and the first profit is determined according to the average value of the number of the orders completed in the history of one day in the history travel service information and the distribution retention rate of the orders distributed to the service provider. Optionally, the product of the two is taken as the first benefit. And determining a second profit according to the average value of the number of the orders which are finished in the history of one day in the historical trip service information and the unallocated retention rate of the orders which are not allocated to the service provider. Optionally, the product of the two is taken as the second benefit. And then determining the difference value of the first profit and the second profit as the profit of the order on the next day.

And example two, according to the difference value of the distributed retention rate and the unallocated retention rate and the average value of the number of the historical completed orders in the historical trip service information within the preset time period, the order income in the future preset time period is determined.

Optionally, the product of the difference between the allocated retention rate and the unallocated retention rate and the average value of the number of historical completed orders in the historical travel service information within the predetermined time period is determined as the order profit in the future predetermined time period.

Example two and example one are two specific different ways of calculating the revenue for an order. Specifically, according to the average value of the number of the historical completed orders in the historical travel service information within the preset time period, the distribution retention rate and the unallocated retention rate, the order income within the future preset time period is determined, and the accuracy of predicting the order income is improved.

And S204, inputting the travel order information, the service provider information and the historical travel service information into a pre-trained completion rate prediction model to obtain the income of the order.

The short-term profit calculating part 405 is configured to calculate a short-term profit after the order is allocated to the service provider according to the received travel order information, the service providing information of the at least two candidate service providers, and the inquired historical travel service information of the at least two candidate service providers.

The revenue of the order, i.e. the revenue generated by the current order, can be understood as short term revenue. In the present example, the completion rate prediction model is used for predicting order completion probability, and the completion rate prediction model may be understood as a cancellation rate model, and in a travel scene, an order may be cancelled by a passenger or an order may be cancelled by a driver, and the cancellation rate model may be used for predicting whether a current order is completed or not, so as to generate a benefit or not. In the example, the travel order information, the service provider information and the historical travel service information are input into a cancellation rate model, and the income of the order is output.

It should be noted that the completion rate prediction model in this example is similar to the retention rate prediction model in step S202, and both can be understood as machine learning models, but training samples are different and implemented functions are different, and the specific training process of the completion rate prediction model in this example may refer to step S202, and is not described herein again.

Step S205, inputting the travel order information, the service provider information and the historical travel service information into a pre-trained finished quantity prediction model, and obtaining the allocated order income within a preset time period after representing that the order is allocated to the service provider and the unallocated order income within a preset time period after representing that the order is not allocated to the service provider; and determining the order income in the preset time period according to the difference value between the allocated order income in the preset time period and the unallocated order income in the preset time period.

The medium term profit calculation section 406 is configured to calculate a medium term profit after the order is allocated to the service provider according to the received travel order information, the service provider information of the at least two candidate service providers, and the inquired historical travel service information of the at least two candidate service providers.

In this example, the completion quantity prediction model is used for predicting the completion quantity of the order within a predetermined time period, and the completion quantity prediction model may be understood as a spatio-temporal value model, and considering from time and space, whether the current order is allocated to the service provider or not may affect the order revenue brought by the subsequent service provider.

The spatio-temporal distribution of orders is considered in this example and includes, but is not limited to, at least one of the number of orders at the time point corresponding to the order origination (e.g., a greater number of orders originated at the same time point during the morning rush hour), the area of the start of ride, the area of the end of ride, the order origination time, and the length of the service provider's empty drive time. In the example, by inputting travel order information, service provider information and historical travel service information into a spatio-temporal value model, the income of an order distributed within a preset time period after the order is distributed to a service provider is represented, and the income of an order not distributed within the preset time period after the order is not distributed to the service provider is represented; the difference value between the income of the distributed order in the preset time period and the income of the unallocated order in the preset time period is determined as the income of the order in the preset time period, so that the accuracy of the income of the order in the preset time period is improved.

The revenue of the order within the predetermined time period may be understood as the medium term revenue, and taking the predetermined time period as one day as an example, the revenue of the order within the predetermined time period represents the revenue of the order within one day.

It should be noted that the number of completions prediction model in this example is similar to the retention rate prediction model in step S202, and both can be understood as machine learning models, but training samples are different and implemented functions are different, and the specific training process of the number of completions prediction model in this example may refer to step S202, and is not described herein again. In the embodiment of the present application, the execution sequence of step S203, step S204, and step S205 is not limited, and step S203, step S204, and step S205 may also be executed simultaneously.

And S206, determining three weights corresponding to the single order income, the order income in the preset time period and the order income in the future preset time period according to the income attention.

The interest degree of the profit includes interest degrees of the income of the single order, the order income in the predetermined time period and the order income in the future predetermined time period, and for example, in a general case, three weight weights corresponding to the income of the single order, the order income in the predetermined time period and the order income in the future predetermined time period are set to be 1, that is, the short-term income, the medium-term income and the long-term income are considered comprehensively, and a certain income is not considered with emphasis. The profit proportion can be adjusted by adjusting the weight value at a later stage, for example, if the order profit in the future predetermined time period is concerned, the third weight corresponding to the order profit in the future predetermined time period is set to be larger, for example, 1.5, 1.2, etc., that is, when the order is allocated, the order profit in the future predetermined time period is considered with emphasis; if the attention to the single order revenue decreases, the first weight setting corresponding to the single order revenue is smaller, for example, 0.8, 0.7, etc.

In this example, a first weight corresponding to the income of the order, a second weight corresponding to the income of the order within the predetermined time period, and a third weight corresponding to the income of the order within the future predetermined time period are determined according to the income attention, and the income ratio can be flexibly adjusted by adjusting the weights according to the income attention, so that the income is improved.

And step S207, determining a revenue function for representing the expected revenue according to the revenue of each order, the order revenue in the preset time period, the order revenue in the future preset time period and three weights corresponding to the revenue of each order, the order revenue in the preset time period and the order revenue in the future preset time period.

Illustratively, the revenue function is single order revenue x first weight + order revenue x second weight within a predetermined time period + order revenue x third weight within a future predetermined time period. The short-term income, the medium-term income and the long-term income are comprehensively considered through the income function, so that the accuracy of an order scheduling result is improved and the allocation effect is improved when orders are allocated to at least two candidate service providers according to the income function in the follow-up process.

And S208, distributing orders for at least two candidate service providers according to the revenue function to obtain an order scheduling result.

The matching problem solving section 408 is configured to calculate and solve the matching problem between the travel order and the service provider according to the short-term profit, the medium-term profit, the long-term profit, and the profit function determined by the weights corresponding thereto, and to obtain a better solution that maximizes the expected profit. The order scheduling result output part 409 is used for outputting the calculated order scheduling result.

Since the revenue function in this example comprehensively considers the short-term revenue, the medium-term revenue, and the long-term revenue, when performing order scheduling for at least two candidate service providers, not only the allocation effect when allocating orders is improved, but also the number of available vehicles of the order scheduling platform is ensured.

When the order is allocated in step S208, the following two examples may be specifically implemented.

Example one, if the number of the orders is one, the candidate service provider corresponding to the maximum function value of the revenue function is taken as the service provider matched with the order.

If the number of the orders is one, that is, one of the at least two candidate service providers is selected, in this example, the candidate service provider corresponding to the maximum function value of the revenue function is used as the service provider matched with the order, so that the distribution effect is improved.

Example two, if the number of the orders is at least two, obtaining a plurality of order matching pairs based on each trip order information and the service provider information, wherein one order matching pair comprises one order and one candidate service provider, and the corresponding revenue functions of different order matching pairs are different; and distributing orders to at least two candidate service providers according to a plurality of revenue functions corresponding to the plurality of order matching pairs to obtain an order scheduling result.

Optionally, if the number of the orders is at least two, obtaining a plurality of order matching pairs based on the order information of each trip and the service provider information, and distributing the orders to at least two candidate service providers according to a plurality of revenue functions corresponding to the plurality of order matching pairs by using a bipartite graph matching algorithm to obtain an order scheduling result.

The bipartite graph matching algorithm may include a maximum matching algorithm (e.g., hungarian algorithm, Hopcroft-Karp algorithm, etc.), a matching algorithm (e.g., mankras (Kuhn-Munkres, abbreviated KM) algorithm), and the like. Taking a KM matching algorithm as an example, order matching pairs correspond to revenue functions one by one, a KM matching algorithm can find out better matching under better time complexity, all travel orders and service providers are matched to obtain the service provider with the highest matching degree with the order, and an order scheduling platform allocates the order to a vehicle where the service provider with the highest matching degree with the order is located, so that the allocation effect is improved.

According to the method and the device, the influence of order allocation on the service provider retention is predicted, the service provider retention is used as a long-term income to be added into an optimization target when the order is allocated, so that the order is more prone to be allocated to the low-activity service provider to increase the retention rate of the service provider, namely the service providing time of the service provider is prolonged, the number of available vehicles of a travel platform aggregated by an order scheduling platform is increased, and the travel experience is improved.

It should be noted that, in the embodiment of the present application, mutual cooperation and information interaction between the travel platform and the order scheduling platform are used as an example for description, it can be understood that a plurality of travel platforms and order scheduling platforms may be integrated in the online taxi calling service platform, the online taxi calling service platform stores historical travel service information of a plurality of service providers, and the steps of obtaining travel order information, determining at least two candidate service providers, querying the historical travel service information, predicting a retention rate and predicting revenue are all completed by the online taxi calling service platform.

Example III,

An embodiment of the present application further provides an order scheduling method, as shown in fig. 5, fig. 5 is a flowchart illustrating steps of another order scheduling method provided in the embodiment of the present application.

Step S501, receiving travel order information sent by a service requester through an order scheduling platform, where the order scheduling platform is an aggregation platform aggregating a plurality of travel platforms.

Step S502, sending the trip order information to a plurality of trip platforms, and receiving feedback information fed back by the plurality of trip platforms, wherein the feedback information carries service provider information and historical trip service information of at least two candidate service providers corresponding to the trip order information.

And S503, determining expected income according to the travel order information, the service provider information and the historical travel service information.

Optionally, in this embodiment of the application, both the order scheduling platform and the trip platform may display expected revenue. So as to effectively intervene in the order scheduling process according to the expected revenue,

step S504, distributing orders for at least two candidate service providers according to the expected income to obtain an order scheduling result.

For specific implementation of the above processing of the order scheduling platform and the achieved technical effect thereof, reference may be made to the description of the corresponding parts in the foregoing first embodiment and second embodiment, and details are not described herein again.

Example four,

An embodiment of the present application further provides an order scheduling method, as shown in fig. 6, fig. 6 is a flowchart illustrating steps of another order scheduling method provided in the embodiment of the present application, and the order scheduling method provided in the embodiment of the present application is described from the perspective of a service providing terminal of a service provider in the embodiment.

Step S601, sending current position information of a service providing terminal and current service state information of the service providing terminal to a trip platform, so that the trip platform sends feedback information to an order scheduling platform according to a plurality of current position information, a plurality of current service state information and trip order information received from the order scheduling platform; and determining expected income through the order scheduling platform according to the trip order information, the service provider information of at least two candidate service providers carried by the feedback information and the historical trip service information, distributing orders for the at least two candidate service providers according to the expected income to obtain an order scheduling result, wherein the order scheduling result represents the service providers matched with the trip order information.

The service providing terminal sends current position information and current service state information (such as whether the service providing terminal is in an idle state, is about to be in an idle state, and is loaded with passengers but not fully loaded) to a corresponding travel platform, and the plurality of travel platforms receive the current position information and the current service state information of the plurality of service providing terminals. For specific implementation of the above processing of the order scheduling platform, reference may be made to the descriptions of corresponding parts in the foregoing first embodiment and second embodiment, and details are not described here again. The candidate service provider may be assigned a travel order that matches it, or the candidate service provider may not be assigned a travel order.

Step S602, receiving the travel order information sent by the order scheduling platform through the travel platform corresponding to the matched service provider, and the expected revenue corresponding to the matched travel order information.

Optionally, in this embodiment of the present application, the service providing terminal (e.g., a terminal corresponding to the driver end) may display the expected revenue, so that the service provider (e.g., the driver) knows the possible revenue obtained, and the enthusiasm of the service provider is improved.

The trip order distribution process does not need the participation of the service provider, the service provider does not know a specific distribution strategy, and the service provider distributed to the trip order can receive the matched trip order information through the corresponding trip platform. If the service provider is determined to be the matched service provider, the service providing terminal receives and displays the travel order information sent by the order scheduling platform through the travel platform and the travel service provider. Meanwhile, the service providing terminal may also receive expected revenue, such as the revenue of the order, the revenue of the order within a predetermined time period, and the revenue of the order within a future predetermined time period, so that the service provider (e.g., the driver) can know the revenue that may be obtained, thereby improving the experience and the enthusiasm of the service provider.

Example V,

An embodiment of the present application further provides an order scheduling method, as shown in fig. 7, fig. 7 is a flowchart illustrating steps of another order scheduling method provided in the embodiment of the present application, and the order scheduling method provided in the embodiment of the present application is described from the perspective of a service request terminal of a service requester in the embodiment, where the order scheduling method of the embodiment of the present application includes the following steps.

Step S701, a travel request initiated by a service requester is received, and travel order information is generated according to the travel request.

The order scheduling platform or the travel platform provides a corresponding interface, such as a corresponding application program, to the service request terminal of the service provider, so that the service requester can initiate a travel request through the application program in the service request terminal.

It should be noted that in practical applications, the contract with the travel platform may be a travel service provider, and therefore, this step may also be considered that the travel platform receives a travel request initiated by a service requester through the travel service provider, but the interface may still be provided by the order scheduling platform or the travel platform. Of course, it may also be provided by an travel service provider. But no matter which party provides it, timely interaction among the above parties can be achieved.

Step S702, the travel order information is sent to an order scheduling platform, so that the order scheduling platform sends the travel order information to a plurality of travel platforms, and based on the service provider information and the historical travel service information of at least two candidate service providers fed back by the plurality of travel platforms, expected revenue is determined by combining the travel order information, and orders are distributed to the at least two candidate service providers according to the expected revenue to obtain an order scheduling result.

As mentioned above, the order scheduling platform is aggregated with a plurality of travel platforms. After receiving the travel order information sent by the service request terminal, the order scheduling platform distributes the travel order information to a plurality of travel platforms, determines candidate service providers capable of serving the current travel order through each travel platform, the travel service provider signed with each travel platform and the service provider signed with each travel service provider, and feeds back the candidate service providers to the order scheduling platform step by step. Further, the order scheduling platform performs revenue prediction based on the feedback information and the travel order information, thereby realizing order allocation to at least two candidate service providers.

For the specific implementation of the service provider determined by the order scheduling platform for the travel order information and the technical effect achieved by the service provider, reference may be made to the description of the corresponding parts in the foregoing first embodiment and second embodiment, which are not described herein again.

Step S703, receiving the service provider information of the service provider allocated in the order scheduling result sent by the order scheduling platform.

As previously described, the order scheduling platform determines the service provider that matches the travel order information. Then, the service provider information of the service provider matching thereto is fed back to the service request terminal. Further, the service request terminal may present the service provider information to the service requester.

Example six,

Based on any order scheduling method described in the first to fifth embodiments, an embodiment of the present application provides an electronic device, and it should be noted that the order scheduling method in the embodiment of the present application may be executed by any appropriate electronic device with an order scheduling capability, including but not limited to: server, mobile terminal (such as mobile phone, PAD, etc.), PC, etc. As shown in fig. 8, fig. 8 is a structural diagram of an electronic device according to an embodiment of the present application. The specific embodiments of the present application do not limit the specific implementation of the electronic device. The electronic device 80 may include: a processor (processor)802, a Communications Interface 804, a memory 806, and a communication bus 808.

Wherein: the processor 802, communication interface 804, and memory 806 communicate with one another via a communication bus 808.

A communication interface 804 for communicating with other electronic devices or servers.

The processor 802 is configured to execute the computer program 810, and may specifically perform the relevant steps in the above-described order scheduling method embodiment.

In particular, the computer program 810 may comprise computer program code comprising computer operating instructions.

The processor 802 may be a processor CPU, or an application Specific Integrated circuit (asic), or one or more Integrated circuits configured to implement embodiments of the present application. The intelligent device comprises one or more processors which can be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.

A memory 806 for storing a computer program 810. The memory 806 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.

For specific implementation of each step in the program 810, reference may be made to corresponding steps and corresponding descriptions in units in the above embodiment of the order scheduling method, which are not described herein again. It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described devices and modules may refer to the corresponding process descriptions in the foregoing method embodiments, and are not described herein again.

Example seven,

Based on the order scheduling methods described in the first to fifth embodiments, an embodiment of the present application provides a computer storage medium, which stores a computer program, and the computer program, when executed by a processor, implements the order scheduling methods described in the first to fifth embodiments.

It should be noted that, according to the implementation requirement, each component/step described in the embodiment of the present application may be divided into more components/steps, and two or more components/steps or partial operations of the components/steps may also be combined into a new component/step to achieve the purpose of the embodiment of the present application.

The above-described methods according to embodiments of the present application may be implemented in hardware, firmware, or as software or computer code storable in a recording medium such as a CD ROM, a RAM, a floppy disk, a hard disk, or a magneto-optical disk, or as computer code originally stored in a remote recording medium or a non-transitory machine-readable medium downloaded through a network and to be stored in a local recording medium, so that the methods described herein may be stored in such software processes on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware such as an ASIC or FPGA. It will be appreciated that the computer, processor, microprocessor controller or programmable hardware includes memory components (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code that, when accessed and executed by the computer, processor or hardware, implements the order scheduling methods described herein. Further, when a general purpose computer accesses code for implementing the order scheduling methods illustrated herein, execution of the code transforms the general purpose computer into a special purpose computer for performing the order scheduling methods illustrated herein.

Those of ordinary skill in the art will appreciate that the various illustrative elements and method steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the embodiments of the present application.

The above embodiments are only used for illustrating the embodiments of the present application, and not for limiting the embodiments of the present application, and those skilled in the relevant art can make various changes and modifications without departing from the spirit and scope of the embodiments of the present application, so that all equivalent technical solutions also belong to the scope of the embodiments of the present application, and the scope of patent protection of the embodiments of the present application should be defined by the claims.

Claims

1. An order scheduling method, comprising:

the method comprises the steps of receiving travel order information, and obtaining service provider information and historical travel service information of at least two candidate service providers corresponding to the travel order information;

determining expected income according to the travel order information, the service provider information and the historical travel service information;

and distributing orders for at least two candidate service providers according to the expected income to obtain an order scheduling result.

2. The method of claim 1, wherein determining expected revenue from the travel order information, the service provider information, and the historical travel service information comprises:

predicting a service provider retention rate according to the travel order information, the service provider information and the historical travel service information, wherein the service provider retention rate is used for representing the probability that a candidate service provider provides travel service in a future preset time period;

predicting the order income in the future preset time period according to the historical travel service information and the retention rate of the service provider;

and according to the order income in the future preset time period, combining the predetermined order income corresponding to each piece of travel order information and the predetermined order income in the preset time period, and determining the expected income.

3. The method of claim 2, wherein the service provider retention rate comprises an allocated retention rate for characterizing allocation of an order to a service provider and an unallocated retention rate for characterizing unallocated allocation of an order to a service provider.

4. The method of claim 3, wherein said predicting the revenue of the order for the future predetermined period of time from the historical travel service information and the service provider retention rate comprises:

determining a first benefit according to the average value of the quantity of historical completed orders in the historical trip service information within a preset time period and the distribution retention rate;

determining a second benefit according to the historical finished order quantity average value in the historical trip service information within a preset time period and the unallocated retention rate;

and determining the order revenue in the future preset time period according to the difference value of the first revenue and the second revenue.

5. The method of claim 3, wherein said predicting the revenue of the order for the future predetermined period of time from the historical travel service information and the service provider retention rate comprises:

and determining the order income in the future preset time period according to the difference value between the distributed retention rate and the unallocated retention rate and the average value of the number of the historical completed orders in the preset time period in the historical trip service information.

6. The method according to claim 2, wherein determining expected revenue according to the order revenue in the future predetermined time period and by combining the predetermined order revenue corresponding to each piece of travel order information and the predetermined order revenue in the predetermined time period comprises:

and determining a revenue function for representing the expected revenue according to the single order revenue, the order revenue in the preset time period, the order revenue in the future preset time period and three weights corresponding to the single order revenue, the order revenue in the preset time period and the order revenue in the future preset time period.

7. The method of claim 6, wherein allocating orders for at least two of the candidate service providers based on the expected revenue, resulting in an order scheduling result, comprises:

if the number of the orders is one, taking the candidate service provider corresponding to the maximum function value of the revenue function as a service provider matched with the orders;

if the number of the orders is at least two, obtaining a plurality of order matching pairs based on the travel order information and the service provider information, wherein one order matching pair comprises one order and one candidate service provider, and the corresponding revenue functions of different order matching pairs are different;

and distributing orders to at least two candidate service providers according to a plurality of revenue functions corresponding to the plurality of order matching pairs to obtain an order scheduling result.

8. The method of claim 6, wherein the method further comprises:

and determining three weights corresponding to the single order income, the order income in the preset time period and the order income in the future preset time period according to the income attention degree.

9. The method of claim 2, wherein predicting a service provider retention rate from the travel order information, the service provider information, and the historical travel service information comprises:

inputting the travel order information, the service provider information and the historical travel service information into a retention rate prediction model trained in advance to obtain the retention rate of the service provider.

10. The method of claim 2, wherein the method further comprises:

inputting the travel order information, the service provider information and the historical travel service information into a pre-trained completion rate prediction model to obtain the single order income;

inputting the travel order information, the service provider information and the historical travel service information into a pre-trained finished quantity prediction model to obtain allocated order income within a preset time period after representing that the order is allocated to the service provider and unallocated order income within a preset time period after representing that the order is not allocated to the service provider;

and determining the order income in the preset time period according to the difference value between the allocated order income in the preset time period and the unallocated order income in the preset time period.

11. The method of claim 2, wherein the method further comprises:

acquiring current travel road information;

analyzing the road condition of the current travel road information to obtain a road condition analysis result;

and according to the road condition analysis result, predicting the order income and the order income within the preset time period respectively by combining the current position information in the service provider information and the travel starting point position information and the travel ending point position information in the travel order information.

12. An order scheduling method, comprising:

the method comprises the steps that travel order information sent by a service requester is received through an order scheduling platform, wherein the order scheduling platform is an aggregation platform with a plurality of travel platforms;

sending the travel order information to the plurality of travel platforms, and receiving feedback information fed back by the plurality of travel platforms, wherein the feedback information carries service provider information and historical travel service information of at least two candidate service providers corresponding to the travel order information;

13. An order scheduling method, comprising:

sending current position information of a service providing terminal and current service state information of the service providing terminal to a trip platform, so that the trip platform sends feedback information to an order scheduling platform according to the plurality of current position information, the plurality of current service state information and trip order information received from the order scheduling platform;

determining expected income through the order scheduling platform according to the trip order information, the service provider information of at least two candidate service providers carried by the feedback information and historical trip service information;

distributing orders for at least two candidate service providers according to the expected income to obtain an order scheduling result, wherein the order scheduling result represents the service providers matched with the trip order information;

and receiving matched travel order information sent by the order scheduling platform through a travel platform corresponding to the matched service provider and expected revenue corresponding to the matched travel order information.

14. An order scheduling method, comprising:

receiving a travel request initiated by a service requester, and generating travel order information according to the travel request;

sending the travel order information to an order scheduling platform, enabling the order scheduling platform to send the travel order information to a plurality of travel platforms, determining expected revenue by combining the travel order information based on service provider information and historical travel service information of at least two candidate service providers fed back by the plurality of travel platforms, and distributing orders for the at least two candidate service providers according to the expected revenue to obtain an order scheduling result;

and receiving the service provider information distributed in the order scheduling result sent by the order scheduling platform.

15. A computer storage medium having stored thereon a computer program which, when executed by a processor, implements the order scheduling method of any of claims 1-14.