CN111881375B

CN111881375B - Method and device for distributing forward order, electronic equipment and readable storage medium

Info

Publication number: CN111881375B
Application number: CN202010739812.3A
Authority: CN
Inventors: 周苗艺; 丁永涛
Original assignee: Beijing Didi Infinity Technology and Development Co Ltd
Current assignee: Beijing Didi Infinity Technology and Development Co Ltd
Priority date: 2020-07-28
Filing date: 2020-07-28
Publication date: 2024-09-06
Anticipated expiration: 2040-07-28
Also published as: CN111881375A

Abstract

The application provides a forward order distribution method, a forward order distribution device, electronic equipment and a readable storage medium, wherein the forward order distribution method comprises the following steps: acquiring forward preference information of a service provider for various forward historical orders, order information and route information of each order to be allocated; aiming at each order to be distributed, determining the type of the order to be distributed according to the order information and the route information of the order to be distributed; determining the forward route degree between each order to be allocated and the service provider based on forward route preference information of various forward route historical orders and the type of each order to be allocated; and determining a matching result between each order to be distributed and the service provider according to the forward road degree. Therefore, the order receiving preference of the service provider and the route information when providing the service can be considered, the matching degree between the to-be-allocated order and the service provider can be improved, the probability of canceling the order by the service provider can be reduced, and the experience of the user and the service provider can be improved.

Description

Method and device for distributing forward order, electronic equipment and readable storage medium

Technical Field

The present application relates to the field of information processing technologies, and in particular, to a forward order allocation method, apparatus, electronic device, and readable storage medium.

Background

With the development of internet technology, travel services based on internet technology bring a lot of convenience to people, and in order to save travel cost, more and more people prefer a travel mode, such as a forward road vehicle, etc., in the internet.

At present, a corresponding road-going vehicle is usually matched for an order according to the starting position and the end position of the order, or a corresponding road-going vehicle is closely matched for the order according to the starting position of the order, but the matching mode is single in consideration, and the matching result according to the starting position and/or the end position of the user is inaccurate, so that inconvenience can be caused to a road-going vehicle driver, the canceling probability of the order is high, and the travel of the user is influenced.

Disclosure of Invention

Accordingly, the present application is directed to a forward order allocation method, apparatus, electronic device, and readable storage medium, which can add forward preference information of a service provider, order time for an order to be allocated, and order position into consideration, so as to improve matching degree between the order to be allocated and the service provider, reduce probability of canceling the order by the service provider, and improve experience of both users and the service provider.

The application mainly comprises the following aspects:

in a first aspect, an embodiment of the present application further provides a forward order allocation method, where the forward order allocation method includes:

Acquiring forward preference information of a service provider for various forward historical orders, order information and route information of each order to be allocated, wherein the order information comprises any one or more of the following: order time and order location;

aiming at each order to be distributed, determining the type of the order to be distributed according to the order information and the route information of the order to be distributed;

Determining the forward route degree between each order to be allocated and the service provider based on forward route preference information of various forward route historical orders and the type of each order to be allocated;

And determining a matching result between each order to be distributed and the service provider according to the forward road degree.

In one possible implementation manner, the determining the forward path degree between each order to be allocated and the service provider based on the forward path preference information of each type of forward path historical order and the type of each order to be allocated includes:

Converting forward preference information of various forward historical orders into corresponding preference feature vectors, and converting the type of each order to be allocated into corresponding order feature vectors;

And inputting the preference feature vector and the order feature vector into a trained matching model, and determining the forward path degree between each order to be distributed and the service provider.

In one possible implementation, the matching model is trained by:

acquiring a plurality of sample service providers and a plurality of sample history service orders of each sample service provider;

For each sample service provider, determining a sample history service order for the sample service provider as a forward training sample and a sample history service order for the sample service provider as a non-forward training sample;

acquiring a first forward path degree corresponding to each positive training sample and a second forward path degree corresponding to each negative training sample, wherein the first forward path degree is greater than the second forward path degree;

And training the initial matching model based on the plurality of positive training samples, the plurality of negative training samples, the first forward path degree corresponding to each positive training sample and the second forward path degree corresponding to each negative training sample to obtain a trained matching model.

In one possible implementation, the forward preference information for the forward history order is generated by:

acquiring a plurality of forward road vehicle history orders of the service provider;

For each forward road vehicle history order, matching the planned order distance in the forward road vehicle history order with the driving route of the service provider, and determining the forward road vehicle history order with the forward road degree larger than a preset forward road threshold value by the service provider as an effective history order;

And generating forward preference information of the service provider for various forward historical orders based on the determined effective historical orders.

In one possible implementation manner, after the matching result between each to-be-allocated order and the service provider is determined according to the forward path degree, the forward path order allocation method further includes:

for each order to be distributed, determining a cancelling state corresponding to the service provider when the service provider cancels the order to be distributed according to the forward path degree between the service provider and the order to be distributed;

And determining the order allocation priority of the service provider after the to-be-allocated order is cancelled based on the cancellation state.

In a possible implementation manner, the determining, according to the degree of forward path between the service provider and each order to be allocated, a cancellation state corresponding to the service provider when the service provider cancels each order to be allocated includes:

When the forward road degree is larger than a preset matching threshold, determining a cancel state corresponding to the service provider as abnormal cancel when the service provider cancels an order to be allocated corresponding to the forward road degree;

And when the forward path degree is smaller than or equal to a preset matching threshold, determining the cancellation state corresponding to the service provider as normal cancellation when the service provider cancels the order to be distributed corresponding to the forward path degree.

In a possible implementation manner, the determining, based on the cancellation status, an order allocation priority of the service provider after canceling the to-be-allocated order includes:

when the cancellation state is abnormal cancellation, determining an abnormal grade corresponding to the service provider according to the forward path degree;

and calculating the order allocation priority of the service provider after canceling the order to be allocated based on the priority reduction index corresponding to the abnormal grade.

when the forward road degree is smaller than or equal to a preset matching threshold, determining an incentive level corresponding to the service provider according to the forward road degree after the service provider finishes an order to be allocated corresponding to the forward road degree;

And adjusting the order allocation priority of the service provider based on the priority rising index corresponding to the incentive level.

In one possible embodiment, the forward preference information includes at least one of a historical order taking rate, a historical order cancellation rate, a driver activity area, a driver online time period, an early peak order taking probability, a late peak order taking probability, a driver service evaluation, historical order information, and self-feature information.

In one possible embodiment, the route information includes at least one of an origin, a destination, route information, and a departure time.

In one possible implementation, the order time of each to-be-allocated order is determined by:

Acquiring order departure time and estimated completion time of an order to be allocated from order information of the order to be allocated;

and determining the order time of the order to be distributed based on the order departure time and the estimated completion time.

In one possible implementation, the order location of each to-be-allocated order is determined by:

acquiring a starting position and a terminating position of an order to be distributed from order information of the order to be distributed;

and determining the order position of the order to be distributed based on the starting position and the ending position.

In a second aspect, an embodiment of the present application further provides a forward order allocation method, where the forward order allocation method includes:

acquiring order information and route information of each order to be allocated, wherein the order information comprises any one or more of the following: order time and order location;

Determining the forward path degree between each order to be distributed and the service provider based on the type of each order to be distributed;

In one possible implementation manner, the determining the degree of forward path between each to-be-allocated order and the service provider based on the type of each to-be-allocated order includes:

converting order information of each order to be allocated into corresponding order feature vectors;

and inputting the order feature vectors into a trained matching model, and determining the forward path degree between each order to be distributed and the service provider.

In one possible implementation, the matching model is trained by:

the service provider is determined to be a forward history service order as a positive training sample, the service provider is determined to be a non-forward history service order as a negative training sample, and a first forward degree corresponding to each positive training sample and a second forward degree corresponding to each negative training sample are obtained;

And training the initial matching model based on the plurality of positive training samples, the plurality of negative training samples, the first forward-path degree corresponding to each positive training sample and the second forward-path degree corresponding to each negative training sample, and obtaining a trained matching model corresponding to the service provider.

In a third aspect, an embodiment of the present application further provides a forward order allocation apparatus, where the forward order allocation apparatus includes:

The system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring forward preference information of a service provider for various forward historical orders, order information and route information of each order to be allocated, and the order information comprises any one or more of the following: order time and order location;

The first type determining module is used for determining the type of each order to be distributed according to the order information and the route information of the order to be distributed;

the first degree determining module is used for determining the forward route degree between each order to be distributed and the service provider based on forward route preference information of various forward route historical orders and the type of each order to be distributed;

And the first matching module is used for determining a matching result between each order to be distributed and the service provider according to the forward path degree.

In one possible implementation manner, the first degree determining module is configured to, when determining a forward road degree between each order to be allocated and the service provider based on forward road preference information of each type of forward road historical order and a type of each order to be allocated,:

In a possible implementation manner, the forward order allocation device further comprises a first model training module, wherein the first model training module is used for:

In one possible implementation manner, the forward order allocation device further comprises an information generating module, wherein the information generating module is used for:

In a possible implementation manner, the forward order allocation device further comprises a priority determining module, wherein the priority determining module is used for:

In a possible implementation manner, the priority determining module is configured to determine, according to a degree of forward path between the service provider and each order to be allocated, a cancel state corresponding to the service provider when the service provider cancels each order to be allocated, where the priority determining module is configured to:

In a possible implementation manner, the priority determining module, when configured to determine, based on the cancellation status, an order allocation priority of the service provider after canceling the order to be allocated, is configured to:

In one possible implementation, the forward order allocation apparatus further includes an incentive module for:

In a possible implementation manner, the forward order allocation device further comprises a time determining module, wherein the time determining module is used for:

In a possible implementation manner, the forward order allocation device further comprises a position determining module, wherein the position determining module is used for:

In a fourth aspect, an embodiment of the present application further provides a forward order allocation apparatus, where the forward order allocation apparatus includes:

the second acquisition module is used for acquiring order information and route information of each order to be distributed, wherein the order information comprises any one or more of the following: order time and order location;

The second type determining module is used for determining the type of each order to be distributed according to the order information and the route information of the order to be distributed;

The second degree determining module is used for determining the forward-path degree between each order to be distributed and the service provider based on the type of each order to be distributed;

and the second matching module is used for determining a matching result between each order to be distributed and the service provider according to the forward path degree.

In one possible implementation manner, the second degree determining module is used for determining the forward path degree between each order to be allocated and the service provider based on the type of each order to be allocated, where the second degree determining module is used for:

In a possible implementation manner, the forward order allocation device further comprises a second model training module, wherein the second model training module is used for:

In a fifth aspect, an embodiment of the present application further provides an electronic device, including: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory in communication via the bus when the electronic device is running, the machine-readable instructions when executed by the processor performing the steps of the forward order allocation method as described above.

Embodiments of the present application also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the forward order allocation method as described above.

In this way, the application obtains the forward preference information of the service provider for various forward vehicle historical orders and the order information and route information of each order to be allocated, determines the type of the order to be allocated based on the order information and route information of the order to be allocated, and then determines the forward extent between each order to be allocated and the service provider according to the forward preference information of the service provider for various forward vehicle historical orders and the type of each order to be allocated, thereby determining the matching result between each order to be allocated and the service provider according to the forward extent, and being capable of adding the forward preference information of the service provider, the order time for the order to be allocated and the order position into the consideration range, improving the matching degree between the order to be allocated and the service provider, being beneficial to reducing the probability of canceling the order by the service provider, and simultaneously improving the experience of users and service providers.

In order to make the above objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram of an embodiment of a forward order distribution system;

FIG. 2 is a flow chart of a forward order distribution method according to an embodiment of the present application;

FIG. 3 is a flow chart illustrating a method for forward order allocation according to another embodiment of the present application;

FIG. 4 is a flowchart illustrating another method for forward order allocation according to an embodiment of the present application;

FIG. 5 is a schematic diagram of a forward order distribution device according to an embodiment of the present application;

FIG. 6 is a second schematic diagram of a forward order distribution device according to an embodiment of the present application;

FIG. 7 is a schematic diagram of another forward order distribution device according to an embodiment of the present application;

FIG. 8 is a second schematic diagram of another forward order distribution device according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Description of main reference numerals:

In the figure: 110-a server; 120-network; 130-service requestor; 140-service provider; 150-a database; 500-forward order distribution device; 501-a first acquisition module; 502-a first type determination module; 503-a first degree determination module; 504-a first matching module; 505-a first model training module; 506-an information generation module; 507-a priority determination module; 508-an excitation module; 509-a time determination module; 510-a position determination module; 700-forward order distribution device; 701-a second acquisition module; 702-a second type determination module; 703-a second degree determination module; 704-a second matching module; 705-a second model training module; 900-an electronic device; 910-a processor; 920-memory; 930-bus.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. Based on the embodiments of the present application, every other embodiment obtained by a person skilled in the art without making any inventive effort falls within the scope of protection of the present application.

In order to enable those skilled in the art to make use of the present disclosure, the following embodiments are presented in connection with a specific application scenario "forward order distribution". It will be apparent to those having ordinary skill in the art that the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the application. While the present application is primarily described in terms of forward order allocation, it should be understood that this is but one exemplary embodiment.

It should be noted that the term "comprising" will be used in embodiments of the application to indicate the presence of the features stated hereafter, but not to exclude the addition of other features.

The terms "passenger," "requestor," "service requestor," and "customer" are used interchangeably herein to refer to a person, entity, or tool that may request or subscribe to a service. The terms "driver," "provider," "service provider," and "provider" are used interchangeably herein to refer to a person, entity, or tool that can provide a service. The term "user" in the present application may refer to a person, entity or tool requesting, subscribing to, providing or facilitating the provision of a service. For example, the user may be a passenger, driver, operator, etc., or any combination thereof. In the present application, "passenger" and "passenger terminal" may be used interchangeably, and "driver" and "driver terminal" may be used interchangeably.

The terms "service request" and "order" are used interchangeably herein to refer to a request initiated by a passenger, service requester, driver, service provider, or vendor, etc., or any combination thereof. Accepting the "service request" or "order" may be a passenger, a service requester, a driver, a service provider, a vendor, or the like, or any combination thereof. The service request may be either fee-based or free.

The positioning techniques used in the present application may be based on global positioning system (Global Positioning System, GPS), global navigation satellite system (Global Navigation SATELLITE SYSTEM, GLONASS), COMPASS navigation system (COMPASS), galileo positioning system, quasi Zenith satellite system (Quasi-Zenith SATELLITE SYSTEM, QZSS), wireless fidelity (WIRELESS FIDELITY, WIFI) positioning techniques, or the like, or any combination thereof. One or more of the above-described positioning systems may be used interchangeably in the present application.

One aspect of the application relates to a forward order distribution system. The system can determine the forward route degree between each to-be-allocated order and the service provider based on the acquired forward route preference information of the service provider for various forward route historical orders, the order information of each to-be-allocated order and the scene information in the travel time period of each to-be-allocated order, so that the allocation between each to-be-allocated order and the service provider is determined according to the forward route degree between each to-be-allocated order and the service provider, the forward route degree between the forward route order and the service provider can be improved, the probability of canceling the order by the service provider is reduced, and the experience of users and the service provider can be improved simultaneously.

It should be noted that, before the application of the present application is performed, a corresponding road vehicle is usually matched for an order according to a starting position and an ending position of the order, or a corresponding road vehicle is closely matched for the order according to the starting position of the order, but the matching manner is considered to be single, and the matching result according to the starting position and/or the ending position of the user is not accurate enough, which may cause inconvenience to a driver of the road vehicle, so that the probability of canceling the order is high, and the trip of the user is affected.

Aiming at the problems, in the embodiment of the application, the forward preference information of the service provider for various forward vehicle historical orders and the order information and the route information of each to-be-allocated order are obtained, the type of the to-be-allocated order is determined based on the order information and the route information of each to-be-allocated order, and then the forward extent between each to-be-allocated order and the service provider is determined according to the forward preference information of the service provider for various forward vehicle historical orders and the type of each to-be-allocated order, so that the matching result between each to-be-allocated order and the service provider is determined according to the forward extent, the forward preference information of the service provider, the order time of each to-be-allocated order and the order position are added into the consideration range, the matching degree between each to-be-allocated order and the service provider can be improved, the probability of canceling the order by the service provider can be reduced, and the experience of users and the service provider can be improved simultaneously.

Fig. 1 is a schematic diagram of an architecture of a forward order distribution system according to an embodiment of the present application. For example, the forward order distribution system may be an online transportation service platform for transportation services such as taxis, ride-on services, express, carpools, bus services, driver leases, or airliner services, or any combination thereof. The forward order distribution system may include one or more of a server 110, a network 120, a service requester 130, a service provider 140, and a database 150.

In some embodiments, server 110 may include a processor. The processor may process information and/or data related to the service request to perform one or more of the functions described in the present application. For example, the processor may determine the target vehicle based on a service request obtained from the service requester 130. In some embodiments, a processor may include one or more processing cores (e.g., a single core processor (S) or a multi-core processor (S)). By way of example only, the Processor may include a central processing unit (Central Processing Unit, CPU), application Specific Integrated Circuit (ASIC), special instruction set Processor (Application Specific Instruction-set Processor, ASIP), graphics processing unit (Graphics Processing Unit, GPU), physical processing unit (Physics Processing Unit, PPU), digital signal Processor (DIGITAL SIGNAL Processor, DSP), field programmable gate array (Field Programmable GATE ARRAY, FPGA), programmable logic device (Programmable Logic Device, PLD), controller, microcontroller unit, reduced instruction set computer (Reduced Instruction Set Computing, RISC), microprocessor, or the like, or any combination thereof.

In some embodiments, the device type corresponding to the service requester 130 and the service provider 140 may be a mobile device, such as may include a smart home device, a wearable device, a smart mobile device, a virtual reality device, or an augmented reality device, etc., as well as a tablet computer, a laptop computer, or a built-in device in a motor vehicle, etc.

In some embodiments, database 150 may be connected to network 120 to communicate with one or more components in the forward order distribution system (e.g., server 110, service requester 130, service provider 140, etc.). One or more components in the forward order distribution system may access data or instructions stored in database 150 via network 120. In some embodiments, the database 150 may be directly connected to one or more components in the forward order distribution system, or the database 150 may be part of the server 110.

The following describes the forward order allocation method according to the embodiment of the present application in detail with reference to the description of the forward order allocation system shown in fig. 1.

Referring to fig. 2, fig. 2 is a flow chart of a forward order allocation method according to an embodiment of the present application, where the method may be executed by a processor in a forward order allocation system, and the specific execution process is as follows:

S201, acquiring forward preference information of a service provider for various forward historical orders, order information and route information of each order to be allocated, wherein the order information comprises any one or more of the following: order time and order location.

In the step, before determining the forward road degree between each order to be allocated and the service provider, forward road preference information of the service provider for various forward road vehicle historical orders, and order information and route information of each order to be allocated are obtained.

Wherein the order information includes any one or more of the following: order time and order location.

The forward preference information comprises at least one of a historical order taking rate, a historical order cancellation rate, a driver activity area, a driver on-line time length, an early peak order taking probability, a late peak order taking probability, a driver service evaluation, historical order information and self characteristic information.

The self-characteristic information may include high value driver probability, driver home address characteristics, accumulated online time, age, subsidy sensitivity, 30 days online time on the driver, proportion of peak travel of the driver in the past week, proportion of peak travel of the driver in the past day, time of driver attendance (days), and number of days of driver registration time interval.

The order information also includes at least one of origin, destination, line information, and departure time.

S202, aiming at each order to be distributed, determining the type of the order to be distributed according to the order information and the route information of the order to be distributed.

In the step, for each order to be distributed, the type of the order to be distributed is determined according to the order information and the route information of the order to be distributed.

Specifically, the type of the order to be allocated may be determined according to the order time in the order information, for example, the early peak, the late peak, the common time period, etc., for example, the order to be allocated is an early peak order, etc.

The type of the order to be allocated may also be determined according to the order location in the order information, for example, a city, a county, a town, etc., for example, the order to be allocated is a city order.

Or the type of the order to be allocated may be determined according to route information of the order to be allocated, for example, an on-bridge route, an off-bridge route, or an expressway route, etc., for example, the order to be allocated is an expressway order, etc.

Or the type of the order to be distributed can be determined according to the order information and the route information at the same time.

S203, determining the forward route degree between each order to be allocated and the service provider based on forward route preference information of various forward route history orders and the type of each order to be allocated.

In the step, after the forward preference information of various forward historical orders of the service provider is obtained and the type of each order to be allocated is determined, the forward degree between each order to be allocated and the service provider is determined based on the obtained forward preference information of various forward historical orders and the type of each order to be allocated.

Therefore, when the order to be distributed of the road going vehicle is distributed, subjective willingness of the service provider, road condition information and the like can be considered, and further the order to be distributed of the road going vehicle which is more suitable for the service provider can be recommended to the service provider, so that the probability of canceling the order by the service provider is reduced.

S204, according to the forward path degree, determining a matching result between each order to be distributed and the service provider.

In the step, a matching result between each to-be-allocated order and the service provider is determined according to the determined forward path degree between each to-be-allocated order and the service provider.

Specifically, the order to be distributed, of which the forward-road degree is located at a preset position, can be matched with the service provider according to the forward-road degree between each order to be distributed and the service provider; or matching the order to be distributed with the forward path degree being greater than a preset degree threshold to the service provider.

In this way, the application obtains the forward preference information of the service provider for various forward vehicle historical orders and the order information and route information of each to-be-allocated order, determines the type of the to-be-allocated order based on the order information and route information of the to-be-allocated order, and then determines the forward extent between each to-be-allocated order and the service provider according to the forward preference information of the service provider for various forward vehicle historical orders and the type of each to-be-allocated order, thereby determining the matching result between each to-be-allocated order and the service provider according to the forward extent, and adding the forward preference information of the service provider, the order time of the to-be-allocated order and the order position into the consideration range, thereby improving the matching degree between the to-be-allocated order and the service provider, being beneficial to reducing the probability of the service provider canceling the order, and simultaneously improving the experience of users and service providers.

Referring to fig. 3, fig. 3 is a flowchart illustrating a forward order allocation method according to another embodiment of the application. As shown in fig. 3, the forward order allocation method provided by the embodiment of the present application includes:

S301, acquiring forward preference information of a service provider for various forward historical orders, order information and route information of each order to be allocated, wherein the order information comprises any one or more of the following: order time and order location.

S302, aiming at each order to be distributed, determining the type of the order to be distributed according to the order information and the route information of the order to be distributed.

S303, converting forward preference information of various forward historical orders into corresponding preference feature vectors, and converting the type of each order to be allocated into corresponding order feature vectors.

In the step, forward preference information of various forward historical orders is converted into corresponding preference feature vectors, and the type of each order to be distributed is converted into corresponding order feature vectors.

Specifically, a convertible preference feature is extracted from the forward preference information, and the extracted preference features are converted into corresponding preference feature vectors; similarly, a convertible type feature is extracted from each type of order to be allocated, and the extracted type feature is converted into a corresponding order feature vector.

S304, inputting the preference feature vector and the order feature vector into a trained matching model, and determining the forward path degree between each order to be distributed and the service provider.

In the step, the preference feature vector and the order feature vector obtained through conversion are input into a pre-trained matching model, and the forward path degree between each order to be distributed and the service provider is determined through the matching model.

The matching model can be obtained based on any one of deep learning models or deep neural network training.

And S305, determining a matching result between each order to be distributed and the service provider according to the forward-road degree.

The descriptions of S301, S302, and S305 may refer to the descriptions of S201, S202, and S204, and the same technical effects can be achieved, which will not be described in detail.

Further, the matching model is trained by: acquiring a plurality of sample service providers and a plurality of sample history service orders of each sample service provider; for each sample service provider, determining a sample history service order for the sample service provider as a forward training sample and a sample history service order for the sample service provider as a non-forward training sample; acquiring a first forward path degree corresponding to each positive training sample and a second forward path degree corresponding to each negative training sample, wherein the first forward path degree is greater than the second forward path degree; and training the initial matching model based on the plurality of positive training samples, the plurality of negative training samples, the first forward path degree corresponding to each positive training sample and the second forward path degree corresponding to each negative training sample to obtain a trained matching model.

In the step, a plurality of sample service providers and a plurality of sample history service orders of each sample service provider are obtained, for each sample service provider, the sample history service order of the sample service provider determined to be forward is used as a positive training sample, and the sample history service order of the sample service provider determined to be non-forward is used as a negative training sample; meanwhile, a first forward path degree corresponding to each positive training sample and a second forward path degree corresponding to each negative training sample are obtained, wherein the first forward path degree is greater than the second forward path degree.

And training the constructed initial matching model based on the obtained positive training samples, negative training samples and the first forward path degree corresponding to each positive training sample and the second forward path degree corresponding to each negative training sample to obtain a trained matching model.

Further, the forward preference information of the forward history order is generated by: acquiring a plurality of forward road vehicle history orders of the service provider; for each forward road vehicle history order, matching the planned order distance in the forward road vehicle history order with the driving route of the service provider, and determining the forward road vehicle history order with the forward road degree larger than a preset forward road threshold value by the service provider as an effective history order; and generating forward preference information of the service provider for various forward historical orders based on the determined effective historical orders.

In the step, a plurality of forward road historical orders of a service provider are obtained, an order planning distance of the forward road historical order is determined for each forward road historical order, an actual running route of the service provider is compared with the actual running route when the forward road historical order is provided with service, whether the order planning distance of the forward road historical order accords with the running route is determined, meanwhile, whether the forward road degree of the forward road historical order is greater than a preset forward road threshold value is determined by the service provider after the forward road historical order is completed, and if the order planning distance of the forward road historical order accords with the running route, and the forward road historical order is determined by the service provider to be a valid historical order; and generating forward preference information of the service provider for various forward historical orders based on the determined multiple effective historical orders.

Further, after step S304, the forward order allocation method further includes: for each order to be distributed, determining a cancelling state corresponding to the service provider when the service provider cancels the order to be distributed according to the forward path degree between the service provider and the order to be distributed; and determining the order allocation priority of the service provider after the to-be-allocated order is cancelled based on the cancellation state.

In the step, for each order to be allocated, determining a cancelling state corresponding to the service provider when the service provider cancels the order to be allocated according to the determined forward path degree between the service provider and the order to be allocated; and then, determining the corresponding order allocation priority of the service provider when receiving the order next time after canceling the order to be allocated according to the cancellation state.

In the allocation process of the order to be allocated of the forward road vehicle, when the service provider takes the order and cancels the order, the order allocation priority of the service provider in the next order taking process is properly reduced after the service provider cancels the order to be allocated according to the forward road degree between the service provider and the order to be allocated.

For example, when the service provider a receives the order B to be allocated, the order taking is cancelled, it is determined that the forward path degree between the service provider a and the order B to be allocated is 90%, and after the service provider a cancels the order taking according to the forward path degree, it is determined that the order allocation priority of the order needs to be reduced by two levels.

Further, the determining, according to the degree of forward path between the service provider and each order to be allocated, a cancel state corresponding to the service provider when the service provider cancels each order to be allocated includes: when the forward road degree is larger than a preset matching threshold, determining a cancel state corresponding to the service provider as abnormal cancel when the service provider cancels an order to be allocated corresponding to the forward road degree; and when the forward path degree is smaller than or equal to a preset matching threshold, determining the cancellation state corresponding to the service provider as normal cancellation when the service provider cancels the order to be distributed corresponding to the forward path degree.

In the step, when the determined forward path degree between the service provider and the order to be allocated is greater than a preset matching threshold, it can be determined that the cancellation state corresponding to the service provider is abnormal cancellation after the service provider cancels the order to be allocated; in contrast, when the determined forward path degree between the service provider and the order to be allocated is less than or equal to the preset matching threshold, it may be determined that the cancellation state corresponding to the service provider is normal cancellation after the service provider cancels the order to be allocated.

Thus, the method is beneficial to avoiding the random cancellation of the taken orders by the service provider, and can improve the service experience of the user.

Further, the determining, based on the cancellation status, the order allocation priority of the service provider after canceling the to-be-allocated order includes: when the cancellation state is abnormal cancellation, determining an abnormal grade corresponding to the service provider according to the forward path degree; and calculating the order allocation priority of the service provider after canceling the order to be allocated based on the priority reduction index corresponding to the abnormal grade.

In the step, when the cancellation state of the service provider when canceling the order to be distributed is determined to be abnormal cancellation, determining an abnormal grade corresponding to the service provider according to the forward path degree between the service provider and the order to be distributed.

And determining a preset priority descending index corresponding to the abnormal grade, and calculating the order allocation priority of the service provider after canceling the order to be allocated based on the current order allocation priority of the service provider and the priority descending index.

Corresponding to the above embodiment, the current order allocation priority of the service provider is 6, according to the degree of forward path between the service provider and the order to be allocated being 90%, it is determined that the corresponding anomaly level of the service provider after the order is cancelled is 4, and it is determined that the priority drop index is 3 when the anomaly level is 4, then after the service provider cancels the order to be allocated, the order allocation priority is dropped by 3, that is, the order allocation priority of the service provider becomes 3.

Further, after step S304, the forward order allocation method further includes: when the forward road degree is smaller than or equal to a preset matching threshold, determining an incentive level corresponding to the service provider according to the forward road degree after the service provider finishes an order to be allocated corresponding to the forward road degree; and adjusting the order allocation priority of the service provider based on the priority rising index corresponding to the incentive level.

In the step, when the forward-path degree between the service provider and the order to be allocated is smaller than or equal to a preset matching threshold, after the service provider finishes the order to be allocated, determining an incentive level corresponding to the service provider according to the forward-path degree, and simultaneously, adjusting the order allocation priority of the service provider when the order is received next time according to a preset priority rising index corresponding to the incentive level.

For example, the current order allocation priority of the service provider is 6, according to the forward path degree 40% between the service provider and the order to be allocated, it is determined that the corresponding incentive level of the service provider after the order is cancelled is 2, and the priority rising index is 1 when the incentive level is 2, then after the service provider completes the order to be allocated, the order allocation priority is raised by 1, that is, the order allocation priority of the service provider is changed to 7.

Further, the order time of each to-be-allocated order is determined by the following steps: acquiring order departure time and estimated completion time of an order to be allocated from order information of the order to be allocated; and determining the order time of the order to be distributed based on the order departure time and the estimated completion time.

In this step, the order departure time of each order to be allocated and the estimated completion time of the order to be allocated are obtained from the order information of each order to be allocated, and the order time of the order to be allocated is determined based on the obtained order departure time and the estimated completion time, that is, the order time may include the order departure time, the estimated completion time, the travel time period for completing the order to be allocated, and the like, and any time information obtained by calculating according to the order departure time and the estimated completion time can be obtained.

Further, the order location of each to-be-allocated order is determined by: acquiring a starting position and a terminating position of an order to be distributed from order information of the order to be distributed; and determining the order position of the order to be distributed based on the starting position and the ending position.

In the step, from order information of each order to be allocated, a starting position and a final position of the order to be allocated are obtained, and based on the obtained starting position and final position, a journey planning journey route for providing service for the order to be allocated is determined, the starting position of the order to be allocated belongs to a city, the final position of the order to be allocated belongs to the city and other order position information.

The order position also comprises the condition that whether road congestion exists in the journey planned route in the journey time period.

Referring to fig. 4, fig. 4 is a flowchart of another forward order allocation method according to an embodiment of the present application. As shown in fig. 4, the forward order allocation method provided by the embodiment of the present application includes:

s401, acquiring order information and route information of each order to be distributed, wherein the order information comprises any one or more of the following: order time and order location.

In the step, order information and route information of each order to be distributed are acquired before the forward path degree between each order to be distributed and the service provider is determined.

S402, aiming at each order to be distributed, determining the type of the order to be distributed according to the order information and the route information of the order to be distributed.

S403, determining the forward path degree between each order to be distributed and the service provider based on the type of each order to be distributed.

In the step, after determining the type of each order to be allocated, determining the forward path degree between each order to be allocated and the service provider based on the type of each order to be allocated.

Therefore, when the order to be distributed of the road-going vehicle is distributed, road condition information and the like when the order to be distributed is provided with service are considered, and further the order to be distributed of the road-going vehicle which is more suitable for the service provider can be recommended, and the probability of the service provider cancelling the order is reduced.

S404, determining a matching result between each order to be distributed and the service provider according to the forward-road degree.

Further, step S403 includes: converting order information of each order to be allocated into corresponding order feature vectors; and inputting the order feature vectors into a trained matching model, and determining the forward path degree between each order to be distributed and the service provider.

In the step, the determined order information of each order to be distributed is converted into a corresponding order feature vector; and inputting the obtained order feature vectors into a matching model corresponding to the trained service provider, and determining the forward path degree between each order to be distributed and the service provider.

The matching model is trained for the service provider according to the historical service orders of the service provider, that is to say, the matching model is suitable for the service provider, so that when matching an order to be distributed for the service provider, only order information and route information of the order to be distributed are acquired.

Further, the matching model is trained by:

(1) And taking the historical service order of which the service provider is determined to be forward as a positive training sample, taking the historical service order of which the service provider is determined to be non-forward as a negative training sample, and acquiring a first forward degree corresponding to each positive training sample and a second forward degree corresponding to each negative training sample.

In the step, a plurality of sample historical service orders of a sample service provider are obtained, for each sample service provider, the sample historical service order of the sample service provider determined to be forward is used as a positive training sample, and the sample historical service order of the sample service provider determined to be non-forward is used as a negative training sample; meanwhile, a first forward path degree corresponding to each positive training sample and a second forward path degree corresponding to each negative training sample are obtained, wherein the first forward path degree is greater than the second forward path degree.

(2) And training the initial matching model based on the plurality of positive training samples, the plurality of negative training samples, the first forward-path degree corresponding to each positive training sample and the second forward-path degree corresponding to each negative training sample, and obtaining a trained matching model corresponding to the service provider.

In the step, the constructed initial matching model is trained based on the acquired positive training samples, negative training samples and the first forward path degree corresponding to each positive training sample and the second forward path degree corresponding to each negative training sample, so as to obtain a trained matching model.

Therefore, the matching model trained according to the sample history service orders of the service provider is suitable for the service provider, and is trained according to the characteristic information of the service provider, so that the forward path degree between each to-be-allocated order and the service provider can be determined more accurately.

In this way, the application determines the type of the order to be distributed by acquiring the order information and the route information of each order to be distributed, and then determines the forward-route degree between each order to be distributed of the service provider according to the type of each order to be distributed, thereby determining the matching result between each order to be distributed and the service provider according to the forward-route degree, adding the order time and the order position of the order to be distributed into the consideration range, improving the matching degree between the order to be distributed and the service provider, helping to reduce the probability of canceling the order by the service provider, and improving the experience of users and service providers.

Referring to fig. 5 to 8, fig. 5 is a schematic diagram of a forward order distribution device according to an embodiment of the present application, fig. 6 is a schematic diagram of a forward order distribution device according to a second embodiment of the present application, fig. 7 is a schematic diagram of another forward order distribution device according to an embodiment of the present application, and fig. 8 is a schematic diagram of another forward order distribution device according to an embodiment of the present application. As shown in fig. 5, the forward order distribution device 500 includes:

A first obtaining module 501, configured to obtain forward preference information of a service provider for various forward historical orders, order information of each order to be allocated, and route information, where the order information includes any one or more of the following: order time and order location;

A first type determining module 502, configured to determine, for each order to be allocated, a type of the order to be allocated according to order information and route information of the order to be allocated;

a first degree determining module 503, configured to determine a forward degree between each order to be allocated and the service provider based on forward preference information of various forward historical orders and a type of each order to be allocated;

A first matching module 504, configured to determine a matching result between each to-be-allocated order and the service provider according to the forward path degree.

Further, as shown in fig. 6, the forward order allocation apparatus 500 further includes a first model training module 505, where the first model training module 505 is configured to:

Further, as shown in fig. 6, the forward order allocation apparatus 500 further includes an information generating module 506, where the information generating module 506 is configured to:

Further, as shown in fig. 6, the forward order allocation apparatus 500 further includes a priority determining module 507, where the priority determining module 507 is configured to:

Further, as shown in fig. 6, the forward order allocation apparatus 500 further includes an incentive module 508, where the incentive module 508 is configured to:

Further, as shown in fig. 6, the forward order allocation apparatus 500 further includes a time determining module 509, where the time determining module 509 is configured to:

Further, as shown in fig. 6, the forward order allocation apparatus 500 further includes a location determining module 510, where the location determining module 510 is configured to:

Further, when the first degree determining module 503 is configured to determine the degree of forward road between each order to be allocated and the service provider based on forward road preference information of each type of historical order of forward road vehicles and the type of each order to be allocated, the first degree determining module 503 is configured to:

Further, when the priority determining module 507 is configured to determine, according to the degree of forward path between the service provider and each order to be allocated, a cancel state corresponding to the service provider when the service provider cancels each order to be allocated, the priority determining module 507 is configured to:

In a possible implementation manner, when the priority determining module 507 is configured to determine, based on the cancellation status, an order allocation priority of the service provider after canceling the order to be allocated, the priority determining module 507 is configured to:

Further, the forward preference information includes at least one of a historical order taking rate, a historical order cancellation rate, a driver activity area, a driver on-line time length, an early peak order taking probability, a late peak order taking probability, a driver service evaluation, historical order information and self-feature information.

Further, the route information includes at least one of an origin, a destination, route information, and a departure time.

Further, as shown in fig. 7, the forward order allocation apparatus 700 includes:

A second obtaining module 701, configured to obtain order information and route information of each to-be-allocated order, where the order information includes any one or more of the following: order time and order location;

a second type determining module 702, configured to determine, for each order to be allocated, a type of the order to be allocated according to order information and route information of the order to be allocated;

A second degree determining module 703, configured to determine a forward-path degree between each to-be-allocated order and the service provider based on the type of each to-be-allocated order;

and a second matching module 704, configured to determine a matching result between each to-be-allocated order and the service provider according to the forward path degree.

Further, as shown in fig. 8, the forward order allocation apparatus 700 further includes a second model training module 705, where the second model training module 705 is configured to:

Further, when the second degree determining module 703 is configured to determine a degree of forward path between each to-be-allocated order and the service provider based on the type of each to-be-allocated order, the second degree determining module 703 is configured to:

Referring to fig. 9, fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the application. As shown in fig. 9, the electronic device 900 includes a processor 910, a memory 920, and a bus 930.

The memory 920 stores machine-readable instructions executable by the processor 910, when the electronic device 900 is running, the processor 910 communicates with the memory 920 through the bus 930, and when the machine-readable instructions are executed by the processor 910, the steps of the forward order allocation method in the method embodiments shown in fig. 2, 3 and 4 may be executed, and detailed implementation manners may refer to method embodiments and are not repeated herein.

The embodiment of the present application further provides a computer readable storage medium, where a computer program is stored, where the computer program may execute the steps of the forward order allocation method in the method embodiments shown in fig. 2, fig. 3, and fig. 4 when the computer program is run by a processor, and the specific implementation manner may refer to the method embodiments and will not be repeated herein.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.

In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and there may be other manners of division in actual implementation, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

Finally, it should be noted that: the above examples are only specific embodiments of the present application, and are not intended to limit the scope of the present application, but it should be understood by those skilled in the art that the present application is not limited thereto, and that the present application is described in detail with reference to the foregoing examples: any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or perform equivalent substitution of some of the technical features, while remaining within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.

Claims

1. The forward order distribution method is characterized by comprising the following steps of:

Determining a matching result between each order to be distributed and the service provider according to the forward road degree;

the determining the forward route degree between each order to be allocated and the service provider based on forward route preference information of various forward route history orders and the type of each order to be allocated comprises the following steps:

And inputting the preference feature vector and the order feature vector into a trained matching model, determining the forward path degree between each order to be distributed and the service provider, wherein the matching model is trained according to a positive training sample and a negative training sample, the positive training sample is a sample historical service order determined to be forward by a sample service provider, and the negative training sample is a sample historical service order determined to be non-forward by the service provider.

2. The forward order allocation method according to claim 1, wherein the matching model is trained by:

3. The forward order allocation method according to claim 1, wherein forward preference information of the forward history order is generated by:

4. The forward order allocation method according to claim 1, further comprising, after said determining a matching result between each order to be allocated and the service provider according to the forward extent:

5. The forward order allocation method according to claim 4, wherein the determining the cancel status corresponding to the service provider when the service provider cancels each order to be allocated according to the forward extent between the service provider and each order to be allocated comprises:

6. The forward order allocation method according to claim 5, wherein said determining an order allocation priority of the service provider after canceling the order to be allocated based on the cancellation status comprises:

7. The forward order allocation method according to claim 1, further comprising, after said determining a matching result between each order to be allocated and the service provider according to the forward extent:

8. The forward order allocation method according to claim 1, wherein the forward preference information includes at least one of a historical order taking rate, a historical order cancellation rate, a driver activity area, a driver on-line time length, an early peak order taking probability, a late peak order taking probability, a driver service evaluation, historical order information, and self-feature information.

9. The forward order allocation method according to claim 1, wherein the route information includes at least one of an origin, a destination, route information, and a departure time.

10. The forward order allocation method according to claim 1, wherein the order time of each of the orders to be allocated is determined by:

11. The forward order allocation method according to claim 1, wherein the order location of each of the orders to be allocated is determined by:

12. The forward order distribution method is characterized by comprising the following steps of:

The determining the forward path degree between each to-be-allocated order and the service provider based on the type of each to-be-allocated order comprises the following steps:

Converting the type of each order to be allocated into a corresponding order feature vector;

And inputting the order feature vectors into a trained matching model, determining the forward path degree between each order to be distributed and the service provider, wherein the matching model is trained according to a positive training sample and a negative training sample, the positive training sample is a sample historical service order determined to be forward by the sample service provider, and the negative training sample is a sample historical service order determined to be non-forward by the service provider.

13. A forward order distribution device, characterized in that the forward order distribution device comprises:

The first matching module is used for determining a matching result between each order to be distributed and the service provider according to the forward-road degree;

the first degree determining module is specifically configured to:

14. A forward order distribution device, characterized in that the forward order distribution device comprises:

The second matching module is used for determining a matching result between each order to be distributed and the service provider according to the forward-road degree;

the second degree determining module is specifically configured to:

15. An electronic device, comprising: a processor, a storage medium and a bus, the storage medium storing machine-readable instructions executable by the processor, the processor and the storage medium communicating over the bus when the electronic device is running, the processor executing the machine-readable instructions to perform the steps of the forward order allocation method of any of claims 1 to 11 or 12.

16. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, performs the steps of the forward order allocation method according to any of claims 1 to 11 or 12.