CN111832869A

CN111832869A - Vehicle scheduling method and device, electronic equipment and storage medium

Info

Publication number: CN111832869A
Application number: CN201910722692.3A
Authority: CN
Inventors: 陈旋; 李敏; 王瑜; 卢宇鹏
Original assignee: Beijing Didi Infinity Technology and Development Co Ltd
Current assignee: Beijing Didi Infinity Technology and Development Co Ltd
Priority date: 2019-08-06
Filing date: 2019-08-06
Publication date: 2020-10-27

Abstract

The present application relates to the field of vehicle scheduling technologies, and in particular, to a vehicle scheduling method, an apparatus, an electronic device, and a storage medium, where the method includes: acquiring first attribute information of a charging station where a target vehicle is located, and second attribute information and supply and demand service information of each candidate parking lot station; determining a service scheduling score from the charging station where the target vehicle is located to each candidate parking lot station according to the first attribute information of the charging station where the target vehicle is located, and the second attribute information and the supply and demand service information of each candidate parking lot station; determining the candidate parking station with the highest service scheduling score as a target parking station; and sending an instruction for dispatching the target vehicle to the target parking station. By adopting the scheme, the reasonable dispatching station can be determined for the target vehicle based on the service dispatching score, and the utilization rate of vehicle resources is improved on the premise of meeting the vehicle using requirements.

Description

Vehicle scheduling method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of vehicle scheduling technologies, and in particular, to a vehicle scheduling method, an apparatus, an electronic device, and a storage medium.

Background

With the rapid development of vehicle manufacturing technology and internet technology, shared electric vehicles are receiving more and more attention as a new low-carbon travel mode, and more users select the shared electric vehicle as a vehicle for travel. The charging station is an infrastructure necessary for ensuring the continuation of the journey of the electric vehicle, and the parking station can provide convenience conditions for a user to take and return the vehicle, so that the electric vehicle can be dispatched to the parking station for the user to use after the charging station finishes charging.

However, the number of vehicles required by users in different regions also varies, which results in that electric vehicles which can be provided by currently deployed parking stations are either not in demand and cannot meet the vehicle demand of users, or are in demand and waste a large amount of parking resources.

Therefore, the current scheme has the problem that the resource utilization rate of the vehicle is low or the vehicle using requirement cannot be met.

Disclosure of Invention

In view of the above, an object of the present application is to provide a vehicle scheduling method, an apparatus, an electronic device and a storage medium, which can implement reasonable scheduling of vehicle resources.

Mainly comprises the following aspects:

in a first aspect, the present application provides a vehicle scheduling method, including:

acquiring first attribute information of a charging station where a target vehicle is located, and second attribute information and supply and demand service information of each candidate parking lot station;

determining a service scheduling score from the charging station where the target vehicle is located to each candidate parking lot station according to the first attribute information of the charging station where the target vehicle is located, and the second attribute information and the supply and demand service information of each candidate parking lot station;

determining the candidate parking station with the highest service scheduling score as a target parking station;

and sending an instruction for dispatching the target vehicle to the target parking station.

In one embodiment, the first attribute information of the charging station includes charging station location information, and the second attribute information of the parking candidate includes station location information; the supply and demand service information comprises vehicle supply service information and charging demand service information; the determining a service scheduling score from the charging station where the target vehicle is located to each candidate parking lot station according to the first attribute information of the charging station where the target vehicle is located, and the second attribute information and the supply and demand service information of each candidate parking lot station includes:

for each candidate parking station, determining a distance value from a charging station where the target vehicle is located to the candidate parking station according to the charging station position information and the station position information;

and determining a service scheduling score from the charging station where the target vehicle is located to each parking candidate station based on the determined distance value, the vehicle supply service information and the charging demand service information of the parking candidate stations, and preset respective service scheduling parameter values.

In some embodiments, the determining a service scheduling score from the charging station where the target vehicle is located to each parking candidate based on the determined distance value, the vehicle supply service information and the charging demand service information of the parking candidate, and preset respective service scheduling parameter values includes:

when the current scheduling time information of the target vehicle is determined to fall into a first time interval range, performing weighted summation operation on the determined distance value, a service scheduling parameter value preset for the distance value, vehicle supply service information of the candidate parking lot station, a service scheduling parameter value preset for the vehicle supply service information, charging demand service information of the candidate parking lot station and a service scheduling parameter value preset for the charging demand service information to obtain a service scheduling score from a charging station where the target vehicle is located to each candidate parking lot station;

and when the current scheduling time information of the target vehicle is determined to fall into a second time interval range, performing weighted summation operation on the vehicle supply service information of the candidate parking lot station, the service scheduling parameter value preset for the vehicle supply service information, the determined distance value, the charging demand service information of the candidate parking lot station and the service scheduling parameter value preset for the product of the distance value and the charging demand service information to obtain a service scheduling score from the charging station where the target vehicle is located to each candidate parking lot station.

In some embodiments, the service scheduling parameter value may be determined as follows:

determining a distance value from each charging station where the reference vehicle is located to each candidate parking station, vehicle supply service information and charging demand service information of each candidate parking station, and an actual service scheduling score from the charging station where the reference vehicle is located to each candidate parking station;

taking the distance value from each charging station where the reference vehicle is located to each candidate parking station, the vehicle supply service information and the charging demand service information of each candidate parking station as independent variables of a service scheduling relation function to be constructed, and taking the service scheduling score from the charging station where the reference vehicle is located to each candidate parking station as a dependent variable of the service scheduling relation function to be constructed to construct the service scheduling relation function;

and performing iterative operation on the constructed service scheduling relation function based on the initial value of the service scheduling parameter until the difference value between the service scheduling score obtained by the iterative operation and the actual service scheduling score is smaller than a preset difference value, and stopping the iteration to obtain the service scheduling parameter.

In some embodiments, the second attribute information of the candidate parking lot further includes a current number of free vehicles in a parking space set by the candidate parking lot; the vehicle supply service information includes a vehicle supply number; determining vehicle service provision information as follows:

for each candidate parking station, determining a historical vehicle order in which the distance between the vehicle using position and the station position of the candidate parking station is smaller than a preset distance based on the station position information of the candidate parking station and the vehicle using position information carried in each historical vehicle order;

determining the vehicle demand quantity corresponding to the candidate parking lot station based on the determined historical vehicle order, the historical travel condition information corresponding to the historical vehicle order and the current travel condition information;

and determining the vehicle supply number of the candidate parking lot station based on the vehicle demand number and the current idle vehicle number.

In some embodiments, the charging demand service information includes a charging demand amount; determining charging demand service information according to the following steps:

for each candidate parking station, acquiring charging work order information generated for a vehicle to be charged parked in the candidate parking station;

determining a number of charging demands of the candidate parking lot based on a number of charging work orders.

In another embodiment, the determining a service scheduling score from the charging station where the target vehicle is located to each parking lot candidate according to the first attribute information of the charging station where the target vehicle is located, and the second attribute information and the supply and demand service information of each parking lot candidate includes:

and inputting the first attribute information of the charging station where the target vehicle is located, the second attribute information of each candidate parking lot station and the supply and demand service information into a pre-trained service scheduling model, and determining a service scheduling score from the charging station where the target vehicle is located to each candidate parking lot station.

In some embodiments, the service scheduling model may be trained as follows:

constructing a service scheduling model to be trained based on the model initial parameters;

for each vehicle sample, inputting the acquired first attribute information of the charging station where the vehicle sample is located, and the second attribute information and supply and demand service information of each candidate parking lot station into the service scheduling model to be trained, and determining a service scheduling score from the vehicle sample to each candidate parking lot station, which is output by the model, based on model initial parameters;

and comparing a scheduling result output by the model and corresponding to the service scheduling score from the vehicle sample to each candidate parking lot with scheduling result marking information of the vehicle sample, if the comparison result is inconsistent, adjusting the initial parameters of the model until the comparison result is consistent, and training to obtain the model parameters of the service scheduling model.

In yet another embodiment, the method further comprises:

obtaining scheduling result verification information fed back by a vehicle dispatcher;

and when the scheduling result verification information is determined to be inconsistent with the scheduling result marking information, updating the scheduling result marking information based on the scheduling result verification information to obtain updated scheduling result marking information.

In some embodiments, the first attribute information of the charging station includes one or more of charging station identification information, charging station location information, an idle number of fast charging heads and an idle number of slow charging heads provided within the charging station; the second attribute information of the candidate parking lot station comprises one or more of lot identification information, lot position information, the number of occupied parking spaces in the parking spaces set by the candidate parking lot station and the number of free vehicles; the supply and demand service information of the candidate parking lot includes one or more of vehicle supply service information and charging demand service information.

In a second aspect, the present application further provides a vehicle dispatching device, comprising:

the information acquisition module is used for acquiring first attribute information of a charging station where the target vehicle is located, and second attribute information and supply and demand service information of each candidate parking station;

the score determining module is used for determining a service scheduling score from the charging station where the target vehicle is located to each candidate parking station according to the first attribute information of the charging station where the target vehicle is located, and the second attribute information and the supply and demand service information of each candidate parking station;

the parking lot scheduling system comprises a station determining module, a parking lot scheduling module and a parking lot scheduling module, wherein the station determining module is used for determining a candidate parking station with the highest service scheduling score as a target parking station;

and the vehicle dispatching module is used for sending an instruction for dispatching the target vehicle to the target parking lot station.

In one embodiment, the first attribute information of the charging station includes charging station location information, and the second attribute information of the parking candidate includes station location information; the supply and demand service information comprises vehicle supply service information and charging demand service information; the score determination module is configured to determine a service dispatch score from the charging station at which the target vehicle is located to each candidate parking station according to the following steps:

In some embodiments, the score determination module is configured to determine a service dispatch score from the charging station on which the target vehicle is located to each candidate parking lot station according to the following steps:

In some embodiments, the score determination module is configured to determine the service scheduling parameter value as follows:

In some embodiments, the second attribute information of the candidate parking lot further includes a current number of free vehicles in a parking space set by the candidate parking lot; the vehicle supply service information includes a vehicle supply number; the information acquisition module is used for determining vehicle supply service information according to the following steps:

In some embodiments, the charging demand service information includes a charging demand amount; the information acquisition module is used for determining the charging demand service information according to the following steps:

In another embodiment, the score determination module is configured to determine a service dispatch score from the charging station at which the target vehicle is located to each candidate parking lot station as follows:

In some embodiments, the score determination module is configured to train the service scheduling model according to the following steps:

In yet another embodiment, the apparatus further comprises:

the label updating module is used for acquiring the scheduling result verification information fed back by the vehicle dispatcher;

In a third aspect, the present application further provides an electronic device, including: the vehicle scheduling method comprises a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, when an electronic device runs, the processor and the storage medium communicate through the bus, and the processor executes the machine-readable instructions to execute the steps of the vehicle scheduling method according to the first aspect and any one of the implementation manners of the first aspect.

In a fourth aspect, the present application further provides a computer-readable storage medium, having a computer program stored thereon, where the computer program is executed by a processor to perform the steps of the vehicle scheduling method according to any one of the first aspect and the embodiments of the first aspect.

According to the scheme, firstly, the service scheduling score from the charging station where the target vehicle is located to each candidate parking lot station is determined according to the acquired first attribute information of the charging station where the target vehicle is located, the second attribute information of each candidate parking lot station and the supply and demand service information, then the candidate parking lot station with the highest service scheduling score is determined as the target parking lot station, and finally the target vehicle is scheduled to the target parking lot station. That is, by adopting the above-mentioned scheme, the attribute information of the charging station and the candidate parking station and the supply and demand service information of the candidate parking station can be comprehensively considered to determine the service scheduling score from the charging station where the target vehicle is located to each candidate parking station, and since the service scheduling score comprehensively considers the supply service information (such as vehicle supply quantity) and the demand service information (such as charging demand quantity) of the parking station, a reasonable scheduling station can be determined for the target vehicle based on each service scheduling score, and the vehicle resource utilization rate is also improved on the premise of meeting the vehicle demand.

In order to make the aforementioned 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 required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

FIG. 1 is a flow chart illustrating a vehicle dispatching method according to an embodiment of the present application;

FIG. 2 is a flowchart illustrating a vehicle dispatching method according to a second embodiment of the present disclosure;

FIG. 3 is a flowchart illustrating a further vehicle dispatching method provided in the second embodiment of the present application;

FIG. 4 is a flowchart illustrating a further vehicle dispatching method provided in the second embodiment of the present application;

FIG. 5 is a flowchart illustrating a further vehicle dispatching method provided in the second embodiment of the present application;

FIG. 6 is a flowchart illustrating a vehicle dispatching method according to a third embodiment of the present application;

fig. 7 is a schematic structural diagram illustrating a vehicle dispatching device according to a fourth embodiment of the present application;

fig. 8 shows a schematic structural diagram of an electronic device provided in the fifth embodiment of the present application.

Detailed Description

In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for illustrative and descriptive purposes only and are not used to limit the scope of protection of the present application. Additionally, it should be understood that the schematic drawings are not necessarily drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be performed out of order, and steps without logical context may be performed in reverse order or simultaneously. One skilled in the art, under the guidance of this application, may add one or more other operations to, or remove one or more operations from, the flowchart.

In addition, the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.

To enable those skilled in the art to use the present disclosure, the following embodiments are presented in conjunction with a specific application scenario "shared vehicle dispatch". It will be apparent to those skilled 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. Although the present application is primarily described in the context of shared vehicle dispatch, it should be understood that this is merely one exemplary embodiment.

It should be noted that the vehicle in the embodiment of the present application mainly refers to an electric vehicle with electric drive, and the vehicle may be a bicycle, a tricycle, a car, or other electric vehicles, and the electric vehicle may be exemplified below in view of wide application of the electric vehicle in the field of shared vehicle technology.

Furthermore, the term "comprising" will be used in the embodiments of the present application to indicate the presence of the features hereinafter claimed, but not to exclude the addition of further features.

It is noted that, before the application is filed, in consideration of the difference of the number of vehicles required by users in different regions in the related art, the electric vehicles that can be provided by the currently deployed parking lot station may not meet the demand of the vehicle due to insufficient supply, or waste a lot of parking resources due to supply of the vehicle greater than the demand. However, according to the vehicle scheduling method, the vehicle scheduling device, the electronic device, and the storage medium provided by the application, the service scheduling score from the charging station where the target vehicle is located to each candidate parking lot can be determined according to the acquired attribute information of the charging station where the target vehicle is located, the attribute information of each candidate parking lot, and the supply and demand service information, so that the target vehicle can be scheduled to a reasonable parking lot according to the service scheduling score, and the vehicle resource utilization rate is improved on the premise that the vehicle demand is met. The following examples are provided for the purpose of illustration.

Example one

As shown in fig. 1, a flowchart of a vehicle scheduling method provided in an embodiment of the present application is provided, where an execution subject of the method may be a server, and the vehicle scheduling method includes the following steps:

s101, acquiring first attribute information of a charging station where the target vehicle is located, and second attribute information and supply and demand service information of each candidate parking station.

Here, to facilitate understanding of the vehicle scheduling method provided in the embodiment of the present application, first, an application scenario provided in the embodiment of the present application is briefly described. The user can get the car at the parking lot station and use the car, also can return the car to the parking lot station after accomplishing to use the car, to the electric automobile who parks to the parking lot station, need in time charge for it in order to satisfy user's the needs of using the car. Therefore, when the residual electric quantity of the electric vehicle is smaller than the preset electric quantity value, the charging work order information can be generated for the electric vehicle, and a vehicle dispatcher can drive the electric vehicle to a charging station to charge after receiving the charging work order. After the vehicle is fully charged, the vehicle dispatcher may return the fully charged vehicle to the parking lot. In view of the fact that currently deployed parking lots are either low in vehicle resource utilization rate due to supply or demand or incapable of meeting vehicle demand due to supply or demand, in order to better perform integrated scheduling on all parking lot resources at present, the embodiment of the present application may perform vehicle scheduling on fully charged target vehicles at charging stations.

In order to implement the vehicle scheduling, in the embodiment of the present application, first attribute information of a charging station where a target vehicle is located, and second attribute information and supply and demand service information of each candidate parking lot station need to be acquired. Here, the first attribute information of the charging station may mainly include charging station location information, and may also include information owned by other charging stations, such as charging station identification information, information such as the number of charging piles set in the charging station, and similarly, the second attribute information of the parking lot candidate may also mainly include station location information, and may also include information owned by other parking lot stations, such as station identification information, information such as the number of parking spaces set in the parking lot station, and the supply and demand service information of the parking lot candidate mainly includes two parts of information, one part of which is derived from vehicle supply service information that satisfies vehicle demand of the user, and the other part of which is derived from charging demand service information that satisfies the charging demand of the user.

Since the charging station and the parking station where the target vehicle is located can be preset, the actual geographic location (such as charging station location information and station location information) can be predetermined, and the information about the supply and demand service can be determined by comprehensively considering the current vehicle environment and the historical vehicle environment. In addition, the target vehicle may be any one of a group of electric vehicles to be currently scheduled.

S102, determining a service scheduling score from the charging station where the target vehicle is located to each parking candidate according to the first attribute information of the charging station where the target vehicle is located, and the second attribute information and the supply and demand service information of each parking candidate.

Here, for the acquired first attribute information of the charging station where the target vehicle is located, and the second attribute information and the supply and demand service information of each parking lot candidate, in the embodiment of the present application, on one hand, a service scheduling score from the charging station where the target vehicle is located to each parking lot candidate may be determined based on a weighting manner (that is, the information is weighted based on a weighting policy), and on the other hand, the service scheduling score may be determined based on a model training manner (that is, the acquired information is input into a service scheduling model trained in advance) so as to meet the requirements of different application scenarios.

S103, determining the candidate parking station with the highest service scheduling score as the target parking station.

Here, after it is determined that the service scheduling score of the target vehicle to each of the candidate parking lots is obtained, the candidate parking lot having the highest service scheduling score may be selected as the target parking lot.

And S104, sending an instruction for dispatching the target vehicle to the target parking lot station.

Here, based on the selected target parking lot, the target vehicle may be dispatched to the target parking lot. The target parking station is selected by comprehensively considering the attribute information, the supply and demand service information, the attribute information of the target vehicle and other various information of each candidate parking station in the scheduling process, so that the reasonable scheduling of vehicle resources is realized, and the utilization rate of the vehicle resources can be improved under the condition of meeting the vehicle using requirements.

In practical applications, a batch of electric vehicles to be currently scheduled may be scheduled, and the batch of electric vehicles may be a set of electric vehicles that have completed charging determined at a current time point or a smaller time period within a preset scheduling range. In this way, vehicle scheduling can be performed for each target vehicle according to the vehicle scheduling method described above. It should be noted that, when vehicle scheduling is performed, for a candidate parking lot, the number of target vehicles scheduled to the candidate parking lot should be smaller than the maximum number of return vehicles of the candidate parking lot, where the maximum number of return vehicles may be determined based on the information about the number of remaining parking spaces of the candidate parking lot and the predicted number of orders for vehicles.

The determination of the service scheduling score is a key step in the vehicle scheduling method provided in the embodiment of the present application, and considering that the embodiment of the present application may determine the service scheduling score in a weighting manner and may also determine the service scheduling score based on a model training manner, the following two determination manners are specifically described in the following two embodiments and three embodiments, respectively.

Example two

As shown in fig. 2, a flowchart of a method for determining a service scheduling score based on a weighting manner according to an embodiment of the present application is provided, where the method for determining a service scheduling score includes the following steps:

s201, aiming at each candidate parking station, determining a distance value from a charging station where the target vehicle is located to the candidate parking station according to charging station position information and station position information;

s202, determining service scheduling scores from the charging station where the target vehicle is located to each parking lot candidate based on the determined distance values, the vehicle supply service information and the charging demand service information of the parking lot candidate and preset service scheduling parameter values.

Here, the vehicle scheduling method provided in the embodiment of the present application may determine, for each candidate parking lot, a distance value from the charging station where the target vehicle is located to each candidate parking lot according to the charging station location information and the lot location information, where the charging station location information and the lot location information may be respectively represented by corresponding longitude and latitude information, so that the distance value between two actual geographic locations may be determined based on a distance calculation formula. And determining the service scheduling score from the charging station where the target vehicle is located to each candidate parking station based on the distance value corresponding to each candidate parking station, the corresponding vehicle supply service information and charging demand service information and the preset service scheduling parameter values.

In the embodiment of the present application, as shown in fig. 3, the vehicle provision service information may be determined according to the following steps:

s301, aiming at each candidate parking station, determining a historical vehicle order in which the distance between the vehicle using position and the station position of the candidate parking station is smaller than a preset distance based on the station position information of the candidate parking station and the vehicle using position information carried in each historical vehicle order;

s302, determining the vehicle demand quantity corresponding to the candidate parking lot station based on the determined historical vehicle order, the historical travel condition information corresponding to the historical vehicle order and the current travel condition information;

and S303, determining the vehicle supply number of the candidate parking lot station based on the vehicle using demand number and the current idle vehicle number.

Here, in the embodiment of the present application, for each candidate parking lot, a historical vehicle order corresponding to the candidate parking lot may be determined first, and then the required vehicle quantity corresponding to the candidate parking lot may be determined based on the determined historical vehicle order and the historical travel condition information corresponding thereto, and the current travel condition information, that is, on the premise of determining the required vehicle quantity corresponding to the historical travel condition, the required vehicle quantity required by the user in the current travel condition, that is, the required vehicle quantity corresponding to the candidate parking lot may be determined. In this way, after the currently required number of vehicles is determined, the currently free number of vehicles in the parking spaces set by the parking lot candidates included in the second attribute information of the parking lot candidates may be based, where the currently free number of vehicles may be subtracted from the demanded number of vehicles, so that the vehicles currently required to be provided by the parking lot candidates, that is, the vehicle supply number, may be determined.

It should be noted that the current number of idle vehicles refers to the number of vehicles that are not currently ordered by the user and that have sufficient power to provide the user with vehicle service.

In the embodiment of the present application, as shown in fig. 4, the charging demand service information may be determined according to the following steps:

s401, acquiring charging work order information generated for vehicles to be charged parked in each candidate parking lot station;

s402, determining the quantity of the charging demands of the candidate parking lots based on the quantity of the charging work orders.

Here, in the embodiment of the present application, for each candidate parking lot, the charging work order information generated for the vehicle to be charged parked in the candidate parking lot may be first acquired, and then the charging demand number of the candidate parking lot may be determined based on the charging work order number. In addition to the charging work order that is generated in the parking lot candidate station and generated for the vehicle to be charged currently, that is, the charging work order that is not received by the vehicle dispatcher, the charging work order may also include the charging work order that is generated in the parking lot candidate station and generated for the vehicle to be charged currently, that is, the charging work order that has been received by the vehicle dispatcher but does not reach the charging station, so that the influence of all the charging work orders on the vehicle dispatching can be comprehensively considered.

In the embodiment of the application, the service scheduling parameter values may be obtained through verification of a plurality of test results, or may be obtained through analysis of related information of a plurality of reference vehicles in advance, that is, the service scheduling parameter values obtained based on the reference vehicles may be stored in advance, and when it is determined that the attribute information of the target vehicle is relatively related to the attribute information of each reference vehicle, the service scheduling parameter value related to the target vehicle may be extracted from the service scheduling parameter values stored in advance. Next, a specific process of obtaining the parameter value based on the analysis of the related information of the plurality of reference vehicles will be described.

As shown in fig. 5, the service scheduling parameter value may be determined according to the following steps:

s501, determining a distance value from each charging station where the reference vehicle is located to each candidate parking station, vehicle supply service information and charging demand service information of each candidate parking station, and an actual service scheduling score from the charging station where the reference vehicle is located to each candidate parking station;

s502, taking the distance value from each charging station where the reference vehicle is located to each candidate parking lot station, the vehicle supply service information and the charging demand service information of each candidate parking lot station as independent variables of a service scheduling relation function to be constructed, taking the service scheduling score from the charging station where the reference vehicle is located to each candidate parking lot station as a dependent variable of the service scheduling relation function to be constructed, and constructing the service scheduling relation function;

s503, carrying out iterative operation on the constructed service scheduling relation function based on the initial value of the service scheduling parameter until the difference value between the service scheduling score obtained by the iterative operation and the actual service scheduling score is smaller than a preset difference value, and stopping the iterative operation to obtain the service scheduling parameter.

Here, the distance value from each charging station where the reference vehicle is located to each candidate parking station, the vehicle supply service information of each candidate parking station, and the charging demand service information may be used as arguments of a service scheduling relationship function to be constructed, and the service scheduling score from the charging station where the reference vehicle is located to each candidate parking station may be used as a dependent variable of the service scheduling relationship function to be constructed, so as to construct the service scheduling relationship function, that is, the present application embodiment obtains in advance corresponding data of a plurality of sets of arguments and dependent variables related to the reference vehicle, where the actual service scheduling score may be determined based on a condition that the reference vehicle stops at the parking station at the historical time, for example, the service scheduling score corresponding to the parking station where the reference vehicle actually stops may be 10 minutes. Therefore, iterative operation can be performed on the constructed service scheduling relation function based on the corresponding data of the multiple groups of independent variables and dependent variables until the difference value between the service scheduling score obtained by the iterative operation and the actual service scheduling score is smaller than the preset difference value, and the iteration is stopped to obtain the service scheduling parameter.

It should be noted that, in the process of determining the service scheduling parameter based on the established service scheduling relationship function or in the process of determining the service scheduling score based on the service scheduling parameter, each data amount may be pulled to the same reference level, that is, the distance value, the vehicle supply service information, and the charging demand service information may be normalized first.

It is considered that the three factors of the above-described distance value, vehicle supply service information, and charge demand service information have different influences on the determination of the service scheduling score for different time periods. In the embodiment of the application, when it is determined that the current scheduling time information of the target vehicle falls within a first time interval range, the determined distance value, the service scheduling parameter value preset for the distance value, the vehicle supply service information of the candidate parking lot station, the service scheduling parameter value preset for the vehicle supply service information, the charging demand service information of the candidate parking lot station and the service scheduling parameter value preset for the charging demand service information can be subjected to weighted summation operation, so that a service scheduling score from a charging station where the target vehicle is located to each candidate parking lot station is obtained; when it is determined that the current scheduling time information of the target vehicle falls within the second time interval range, the vehicle supply service information of the candidate parking lot station and the service scheduling parameter value preset for the vehicle supply service information, the determined distance value, the charging demand service information of the candidate parking lot station and the service scheduling parameter value preset for the product of the distance value and the charging demand service information can be subjected to weighted summation operation, and a service scheduling score from the charging station where the target vehicle is located to each candidate parking lot station is obtained.

The first time interval range may refer to a time interval range in which the vehicle demand is relatively large in the daytime, and the second time interval range may refer to a time interval range in which the vehicle demand is relatively small in the nighttime, so that the first time interval range may refer to a continuous time interval range, such as 7:00 am to 9:30 pm, and the second time interval range may also refer to a continuous time interval range, such as 9:30 am to 7:00 pm. In this embodiment, the first time interval range may be composed of a plurality of sub-time interval ranges, such as the sub-time interval range corresponding to the peak time of the vehicle, which is 7:30 am to 10:00 am and 5:30 pm to 9:00 pm, and similarly, the second time interval range may also be composed of a plurality of sub-time interval ranges, such as the sub-time interval range corresponding to the peak time of the vehicle, which is 10:30 am to 2 pm: 30 and 9:30 PM to 7:00 AM. Regardless of the manner of dividing the time interval range, the embodiment of the present application may perform a weighted summation operation based on the service scheduling parameter value corresponding to the time interval range to determine the service scheduling score.

It should be noted that, because the corresponding weighting modes are different for the time interval ranges in which the current scheduling time of the target vehicle falls, different service scheduling relationship functions may be constructed for different time interval ranges, that is, when the service scheduling relationship function is constructed in the embodiment of the present application, the service scheduling relationship function may be established in consideration of the historical scheduling time of the reference vehicle, so as to adapt to the determination of the service scheduling scores in different time periods.

In order to further understand the method for determining the service scheduling score based on the weighting manner, a scheduling scheme of a batch of electric vehicles is taken as an example, and is described with reference to a specific formula. That is, for any electric vehicle in a batch of electric vehicles, the score of each candidate parking lot according to the vehicle may be scheduled, and the parking lot with the highest comprehensive score may be selected as the target parking lot, that is, the target parking lot recommended for the batch of vehicles such that the optimization function corresponding to the following equation is maximized.

Wherein the content of the first and second substances,

wherein S is_wdScore for indicating that the w-th vehicle is recommended to the d-th candidate parking lot (i.e., the service scheduling score, R, described above)_wdFor indicating whether the w-th vehicle is recommended to the d-th candidate parking lot, T_dThe method is used for representing the maximum vehicle returning amount of the D-th candidate parking lot, W represents the W-th vehicle (one vehicle can correspond to one charging work order), the dereferencing range of the W-th vehicle is {1,2, …, W }, the total number of W vehicles is W, D represents the D-th candidate parking lot, the dereferencing range of the D-th candidate parking lot is {1,2, …, D }, and the total number of D candidate parking lots is D.

For optimizing functions

For calculating the service scheduling score matrix (determined by the service scheduling scores of the vehicles in a vehicle lot), since the manner of determining the service scheduling score of each vehicle is similar, the following description will be made in connection with the manner of calculating one service scheduling score. Here, considering that the manner of determining the service scheduling score is different for different time periods, taking the day time period as the first time interval range and the night time period as the second time interval range as an example, the determination may be made based on the following formula.

Wherein S is_DAYFor representing service scheduling scores, S, corresponding to the daytime time period_NIGHTIs used for expressing the service scheduling score corresponding to the night time period, wherein, w_DEM、w_ETA、w_LNKTo calculate S_DAYThree service scheduling parameter values, w, employed_DEM、w_ETA&LNKTo calculate S_NIGHTTwo service scheduling parameter values, S, are used_DEM、S_ETAAnd S_LNKThe sub-item score corresponding to the vehicle supply service information, the sub-item score corresponding to the distance value, and the sub-item score corresponding to the charging demand service information may be normalized by a Sigmoid normalization function, and may be determined by the following equation.

Wherein x is_DEMFor indicating vehicle-supplied service information, x_ETAFor indicating a distance value, x, of a charging station to a candidate parking station_LNKThe K, B is used for representing the charging demand service information, and the equation (3) is substituted into the equation (2) to determine the service scheduling score in the daytime period and the service scheduling score in the nighttime period, which means that different weighting methods are selected for different time periods in the embodiment of the present application, so that the vehicle scheduling can be performed more reasonably.

EXAMPLE III

The third embodiment of the present application provides a method for determining a service scheduling score based on a model training mode, where after a service scheduling model is obtained through pre-training, the method may determine the service scheduling score from a charging station where a target vehicle is located to each candidate parking lot station by inputting first attribute information of the charging station where the target vehicle is located, and second attribute information and supply and demand service information of each candidate parking lot station into the pre-trained service scheduling model.

The first attribute information of the charging station may include one or more of charging station identification information, charging station position information, an idle number of fast charging heads and an idle number of slow charging heads, the second attribute information of the candidate parking lot station includes one or more of lot station identification information, lot station position information, an occupied number of parking lots in parking lots set in the candidate parking lot station, and an idle number of vehicles, and the supply and demand service information may include vehicle supply service information and charging demand service information.

Considering that the training process of the service scheduling model is a key step of the service scheduling score determination method, the model training process is described next with reference to fig. 6.

S601, constructing a service scheduling model to be trained based on the model initial parameters;

s602, aiming at each vehicle sample, inputting the acquired first attribute information of the charging station where the vehicle sample is located, the second attribute information of each candidate parking lot station and supply and demand service information into the service scheduling model to be trained, and determining a service scheduling score from the vehicle sample to each candidate parking lot station, which is output by the model, based on model initial parameters;

s603, comparing the scheduling result output by the model and corresponding to the service scheduling score from the vehicle sample to each candidate parking lot with the scheduling result marking information of the vehicle sample, if the comparison result is inconsistent, adjusting the initial parameters of the model until the comparison result is consistent, and training to obtain the model parameters of the service scheduling model.

Here, the service scheduling model to be trained may be first constructed based on model initial parameters, then the acquired first attribute information of the charging station where the vehicle sample is located, and the second attribute information and the supply and demand service information of each parking lot candidate are input to the service scheduling model to be trained, the service scheduling score from the vehicle sample to each parking lot candidate output by the model is determined based on the model initial parameters, and when it is determined that the scheduling result corresponding to the service scheduling score from the vehicle sample to each parking lot candidate output by the model is not consistent with the scheduling result labeling information of the vehicle sample, the model initial parameters need to be adjusted until the comparison result is consistent, the model parameters of the service scheduling model may be trained.

In the embodiment of the application, a process of training the service scheduling model, that is, a process of training parameters of the relevant model, after the parameters of the relevant model are determined, the first attribute information, the second attribute information and the supply and demand service information corresponding to the target vehicle are input into the trained service scheduling model, so that the service scheduling scores from the target vehicle to each candidate parking lot station can be determined. Here, the service scheduling model may be a multi-classification model or a plurality of bi-classification models, and if the matching relationship between the vehicle sample and the corresponding actually scheduled parking lot is 1, the score is determined to be the highest, and the other matching relationship may be 0.

Considering that a vehicle dispatcher is used as a key person for vehicle dispatching, in order to improve the accuracy of model training, in the actual process of model training, relevant information (such as identity information, common position information and the like) of the vehicle dispatcher can be used as input data of the model training to perform the model training.

In addition, in practical application, the scheduling result verification information fed back by the vehicle dispatcher can be acquired, and the scheduling annotation result can be updated when the scheduling result verification information is determined to be inconsistent with the scheduling result annotation information, so that the accuracy of the service scheduling model is further improved by adjusting the model parameters.

Based on the above embodiments, the embodiments of the present application further provide a vehicle scheduling apparatus, and the implementation of the following various apparatuses may refer to the implementation of the method, and repeated details are not repeated.

Example four

As shown in fig. 7, a vehicle dispatching device provided in the fourth embodiment of the present application includes:

the information acquisition module 701 is used for acquiring first attribute information of a charging station where a target vehicle is located, and second attribute information and supply and demand service information of each candidate parking lot station;

a score determining module 702, configured to determine a service scheduling score from the charging station where the target vehicle is located to each candidate parking lot according to the first attribute information of the charging station where the target vehicle is located, and the second attribute information and the supply and demand service information of each candidate parking lot;

a station determining module 703, configured to determine a candidate parking station with the highest service scheduling score as a target parking station;

a vehicle dispatching module 704, configured to issue an instruction for dispatching the target vehicle to the target parking lot.

In one embodiment, the first attribute information of the charging station includes charging station location information, and the second attribute information of the parking candidate includes station location information; the supply and demand service information comprises vehicle supply service information and charging demand service information; the score determination module 702 is configured to determine a service dispatch score from the charging station at which the target vehicle is located to each candidate parking station according to the following steps:

In some embodiments, the score determination module 702 is configured to determine a service dispatch score from the charging station at which the target vehicle is located to each candidate parking lot station according to the following steps:

In some embodiments, the score determination module 702 is configured to determine the service scheduling parameter value as follows:

In some embodiments, the second attribute information of the candidate parking lot further includes a current number of free vehicles in a parking space set by the candidate parking lot; the vehicle supply service information includes a vehicle supply number; the information acquisition module 701 is configured to determine vehicle provision service information according to the following steps:

In some embodiments, the charging demand service information includes a charging demand amount; the information obtaining module 701 is configured to determine the charging demand service information according to the following steps:

In another embodiment, the score determination module 702 is configured to determine a service dispatch score from the charging station at which the target vehicle is located to each candidate parking lot station as follows:

In some embodiments, the score determination module 702 is configured to train the service scheduling model as follows:

In yet another embodiment, the apparatus further comprises:

the label updating module 705 is used for acquiring the scheduling result verification information fed back by the vehicle dispatcher;

EXAMPLE five

As shown in fig. 8, a schematic structural diagram of an electronic device provided in the fifth embodiment of the present application includes: the vehicle control device comprises a processor 801, a storage medium 802 and a bus 803, wherein the storage medium 802 stores machine-readable instructions executable by the processor 801 (such as execution instructions corresponding to an information acquisition module 701, a score determination module 702, a station determination module 703 and a vehicle scheduling module 704 in the vehicle control device in fig. 7, and the like), when an electronic device runs, the processor 801 communicates with the storage medium 802 through the bus 803, and the machine-readable instructions, when executed by the processor 801, perform the following processes:

and dispatching the target vehicle to the target parking station.

In one embodiment, the first attribute information of the charging station includes charging station location information, and the second attribute information of the parking candidate includes station location information; the supply and demand service information comprises vehicle supply service information and charging demand service information; in the processing executed by the processor 801, the determining a service scheduling score from the charging station where the target vehicle is located to each parking lot candidate according to the first attribute information of the charging station where the target vehicle is located, and the second attribute information and the supply and demand service information of each parking lot candidate includes:

In some embodiments, the above-mentioned processing executed by the processor 801, wherein the determining a service scheduling score from the charging station where the target vehicle is located to each parking lot candidate based on the determined distance value, the vehicle supply service information and the charging demand service information of the parking lot candidate, and the preset respective service scheduling parameter values, includes:

In some embodiments, in the processing performed by the processor 801, the service scheduling parameter value may be determined according to the following steps:

In some embodiments, the second attribute information of the candidate parking lot further includes a current number of free vehicles in a parking space set by the candidate parking lot; the vehicle supply service information includes a vehicle supply number; in the processing executed by the processor 801 described above, the vehicle-supply-service information is determined as follows:

In some embodiments, the charging demand service information includes a charging demand amount; in the processing executed by the processor 801 described above, the charging demand service information is determined as follows:

In another embodiment, in the processing executed by the processor 801, the determining a service scheduling score from the charging station where the target vehicle is located to each parking lot candidate according to the first attribute information of the charging station where the target vehicle is located, and the second attribute information and the supply and demand service information of each parking lot candidate includes:

In some embodiments, the processor 801 may perform the process described above, wherein the service scheduling model may be trained according to the following steps:

In another embodiment, the processing performed by the processor 801 further includes:

Embodiments of the present application also provide a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by the processor 801 to perform the steps of the vehicle scheduling method.

Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, and the like, and when a computer program on the storage medium is run, the vehicle scheduling method can be executed, so that the problem that the vehicle resource utilization rate is low or the vehicle use requirement cannot be met due to lack of a reasonable vehicle scheduling scheme in the related art is solved, and the effects of reasonably scheduling the vehicle resources and improving the vehicle resource utilization rate on the premise of meeting the vehicle use requirement are achieved.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to corresponding processes in the method embodiments, and are not described in detail in this application. In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and there may be other divisions in actual implementation, and for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or modules through some communication interfaces, and may be in an electrical, mechanical or other form.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules 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 can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into 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 such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A vehicle scheduling method, characterized in that the method comprises:

2. The vehicle scheduling method of claim 1, wherein the first attribute information of the charging station includes charging station location information, and the second attribute information of the parking candidate includes station location information; the supply and demand service information comprises vehicle supply service information and charging demand service information; the determining a service scheduling score from the charging station where the target vehicle is located to each candidate parking lot station according to the first attribute information of the charging station where the target vehicle is located, and the second attribute information and the supply and demand service information of each candidate parking lot station includes:

3. The vehicle scheduling method of claim 2, wherein the determining a service scheduling score from the charging station where the target vehicle is located to each of the candidate parking lots based on the determined distance value, the vehicle supply service information and the charging demand service information of the candidate parking lots, and preset respective service scheduling parameter values comprises:

4. The vehicle scheduling method of claim 2 wherein the service scheduling parameter value is determined according to the steps of:

5. The vehicle scheduling method according to claim 2, wherein the second attribute information of the candidate parking lot further includes a current number of free vehicles in a parking space set by the candidate parking lot; the vehicle supply service information includes a vehicle supply number; determining vehicle service provision information as follows:

6. The vehicle scheduling method according to claim 2, wherein the charge demand service information includes a charge demand amount; determining charging demand service information according to the following steps:

7. The vehicle scheduling method of claim 1, wherein determining the service scheduling score from the charging station where the target vehicle is located to each parking lot candidate according to the first attribute information of the charging station where the target vehicle is located, and the second attribute information and the supply and demand service information of each parking lot candidate comprises:

8. The vehicle scheduling method of claim 7 wherein the service scheduling model is trained according to the following steps:

9. The vehicle scheduling method of claim 8, further comprising:

10. The vehicle scheduling method according to any one of claims 7 to 9, wherein the first attribute information of the charging station includes one or more of charging station identification information, charging station location information, an idle number of fast charging heads and an idle number of slow charging heads provided in the charging station; the second attribute information of the candidate parking lot station comprises one or more of lot identification information, lot position information, the number of occupied parking spaces in the parking spaces set by the candidate parking lot station and the number of free vehicles; the supply and demand service information of the candidate parking lot includes one or more of vehicle supply service information and charging demand service information.

11. A vehicle dispatching device, comprising:

12. 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 via the bus when the electronic device is operating, the processor executing the machine-readable instructions to perform the steps of the vehicle scheduling method according to any one of claims 1 to 10.

13. A computer-readable storage medium, having stored thereon a computer program for performing, when being executed by a processor, the steps of the vehicle scheduling method according to any one of claims 1 to 10.