CN118246642A

CN118246642A - Order scheduling system

Info

Publication number: CN118246642A
Application number: CN202211659391.9A
Authority: CN
Inventors: 沈倩; 赵根; 王健炜; 程尧; 吴敏; 黄昊
Original assignee: Beijing Sankuai Online Technology Co Ltd
Current assignee: Beijing Sankuai Online Technology Co Ltd
Filing date: 2022-12-22
Publication date: 2024-06-25

Abstract

The application discloses an order scheduling system, and belongs to the technical field of computers. The system at least comprises a dispatching module and an automatic driving vehicle, wherein the dispatching module is used for switching a relay distribution mode into a full-flow distribution mode or switching the full-flow distribution mode into the relay distribution mode under the condition that a mode switching condition is met based on order data, the relay distribution mode is a mode of relay distribution by the automatic driving vehicle and a distributor, and the full-flow distribution mode is a mode of whole-course distribution by the distributor. The system selects the proper distribution mode through the mode switching condition, reduces the time consumption of a distribution mode selection scheme and improves the efficiency of mode switching.

Description

Order scheduling system

Technical Field

The application relates to the technical field of computers, in particular to an order scheduling system.

Background

With the development of online shopping, takeaway and other businesses, the number of orders is increasing, and how to distribute orders to improve the order distribution efficiency is becoming more and more important. Currently, various delivery modes are proposed for order delivery, for example, a full-flow rider delivery mode, a man-vehicle relay delivery mode and the like; multiple delivery modes can be adopted in a certain area in sequence for delivery, the delivery efficiency of each delivery mode is compared, and the delivery mode corresponding to the highest delivery efficiency is selected as the delivery mode of the area, but the delivery mode selection scheme is long in time consumption and low in selection efficiency.

Disclosure of Invention

The embodiment of the application provides an order scheduling system, which reduces the time consumption of a distribution mode selection scheme and improves the mode switching efficiency. The technical scheme is as follows:

in one aspect, an order dispatch system is provided, the system including at least a dispatch module and an autonomous vehicle,

The scheduling module is configured to switch, based on order data, a relay delivery mode to a full-flow delivery mode or switch the full-flow delivery mode to the relay delivery mode when a mode switching condition is satisfied, where the relay delivery mode is a mode of relay delivery by the automated driving vehicle and a dispatcher, and the full-flow delivery mode is a mode of full-flow delivery by the dispatcher.

In one possible implementation, the scheduling module is configured to determine, based on the order data, a first delivery efficiency and a second delivery efficiency, where the first delivery efficiency represents an efficiency of delivering orders in the relay delivery mode, and the second delivery efficiency represents an efficiency of delivering orders in the full-flow delivery module;

The scheduling module is configured to switch the relay delivery mode to the full-flow delivery mode or switch the full-flow delivery mode to the relay delivery mode in response to the first delivery efficiency and the second delivery efficiency satisfying the mode switching condition.

In one possible implementation, the order data is historical order data of the full-process delivery mode in the first area, or the order data is historical order data of the relay delivery mode in the first area;

The scheduling module is used for determining influence characteristics corresponding to the first area based on the historical order data, wherein the influence characteristics are used for representing influence factors of order distribution time consumption;

The scheduling module is configured to predict a first delivery efficiency of the relay delivery mode or predict a second delivery efficiency of the full-flow delivery mode based on the impact feature.

In one possible implementation, the scheduling module is configured to predict time-consuming information of a dispatcher's dispatch stage in the relay dispatch mode based on the impact feature;

the scheduling module is used for acquiring time-consuming information of an order handing-over stage in the relay distribution mode;

The scheduling module is configured to predict a first delivery efficiency of the relay delivery mode based on time-consuming information of the delivery stage of the dispatcher and time-consuming information of the order handing-over stage.

In a possible implementation manner, the scheduling module is used for predicting a single-trip quantity of the single-trip collection corresponding to the relay distribution mode based on the influence characteristics and the distribution required duration, wherein the single-trip quantity of the single-trip collection is used for representing the quantity of orders distributed by the automatic driving vehicle in one trip;

The scheduling module is configured to predict time consumption information of the dispatcher delivery stage based on the single-pass set single quantity and a target influencing factor in the influencing feature, where the target influencing factor is a influencing factor that influences time consumption of a first delivery stage in the full-flow delivery mode, and the first delivery stage is a delivery stage in the full-flow delivery mode corresponding to the dispatcher delivery stage in the relay delivery mode.

In one possible implementation, the scheduling module is configured to determine a number of orders that are distributed by the dispatcher in a unit time period based on time-consuming information of the dispatcher in a distribution stage, time-consuming information of the order delivery stage, and the single-pass set amount;

the scheduling module is used for determining the order quantity as the first delivery efficiency of the relay delivery mode.

In one possible implementation, the influencing features include at least one of:

a single-entering interval, wherein the single-entering interval represents the difference of receiving time of two adjacent orders, and the single-entering interval is an influence factor for time consumption of a single-collecting stage;

The single picking and placing duration is Shan Jun, and the picking and placing duration is an influence factor of time consumption in the picking and placing stage;

A first length of trunk, the trunk indicating a coincident route of a plurality of orders to be dispatched together, the first length being a time consuming factor of influence of a trunk departure phase and a trunk return phase;

the time-consuming information of the branch trip stage corresponding to one order, wherein the branch represents the route of any order of the orders distributed together, which is not overlapped with other orders;

Time-consuming information of a spur backhaul phase, which represents a phase in which delivery capacity returns from any spur to the trunk;

Time consuming information for an order delivery phase corresponding to an order, the order delivery phase representing a phase of delivering the order to a user.

In one possible implementation, the impact characteristics, the delivery requirement duration, and the single pass set of single amounts satisfy the following relationship data:

N＝(SLA-T4-S/V)/(M+F+T5+T6)；

Wherein N represents the single-trip quantity, SLA represents the distribution requirement duration, T4 represents the time-consuming information of the order handing-over stage in the relay distribution mode, S represents the first length, V represents the running speed of the automatic driving vehicle in the relay distribution mode, M represents the order-in interval, F represents the Shan Jun picking and placing duration, T5 represents the time-consuming information of the branch going-off stage corresponding to one order, and T6 represents the time-consuming information of the order delivery stage corresponding to one order.

In a possible implementation manner, the scheduling module is configured to predict time-consuming information corresponding to the full-flow distribution mode based on the impact feature, where the time-consuming information is used to represent time consumed for completing one-time order distribution by adopting the full-flow distribution mode;

The scheduling module is configured to predict a second delivery efficiency of the full-flow delivery mode based on the time-consuming information.

In a possible implementation manner, the scheduling module is configured to determine a single-pass set single quantity corresponding to the full-flow distribution mode based on the impact feature and the distribution requirement duration, where the single-pass set single quantity is used to represent the number of orders distributed in one pass;

The scheduling module is used for predicting time consumption information corresponding to the full-flow distribution mode based on the single-pass set quantity and the influence characteristic.

In one possible implementation, the historical order data is historical order data of the full-flow delivery mode in the first region;

the scheduling module is used for determining first influence characteristics corresponding to each order based on a plurality of orders in the historical order data;

The scheduling module is used for determining the numerical range of the first influence characteristic based on the first influence characteristic corresponding to each order;

The scheduling module is used for determining the statistical value of the first influence characteristic corresponding to each order as a second influence characteristic, wherein the statistical value is the average value or the median value of the first influence characteristic corresponding to each order;

the scheduling module is used for predicting third distribution efficiency of the full-flow distribution mode based on the second influence characteristic;

The scheduling module is configured to update the second impact feature based on a difference value between the third distribution efficiency and the second distribution efficiency, so as to converge the difference value, where the updated second impact feature belongs to the numerical range;

And the scheduling module is used for determining the updated second influence characteristic as the influence characteristic corresponding to the first area.

In a possible implementation manner, the scheduling module is further configured to divide the order data into order sub-data corresponding to a plurality of time slices;

The scheduling module is configured to switch the relay delivery mode to the full-flow delivery mode or switch the full-flow delivery mode to the relay delivery mode under the corresponding time segment based on the order sub-data corresponding to each time segment and the mode switching condition.

In a possible implementation manner, the scheduling module is configured to switch the relay delivery mode to the full-flow delivery mode in response to the second delivery efficiency being greater than the first delivery efficiency and a difference between the second delivery efficiency and the first delivery efficiency being not less than a target threshold when the relay delivery mode is adopted by the system;

The scheduling module is configured to switch the full-flow delivery mode to the relay delivery mode in response to the first delivery efficiency being greater than the second delivery efficiency and a difference between the first delivery efficiency and the second delivery efficiency being not less than a target threshold when the system adopts the full-flow delivery mode.

In one aspect, there is provided an order dispatch method performed by an order dispatch system including at least a dispatch module and an autonomous vehicle, the method comprising:

the scheduling module switches a relay delivery mode to a full-flow delivery mode or switches the full-flow delivery mode to the relay delivery mode under the condition that a mode switching condition is met based on order data, wherein the relay delivery mode is a mode of relay delivery by the automatic driving vehicle and a dispatcher, and the full-flow delivery mode is a mode of full-flow delivery by the dispatcher.

In one possible implementation manner, the scheduling module switches a relay delivery mode to a full-flow delivery mode or switches the full-flow delivery mode to the relay delivery mode based on order data if a mode switching condition is met, and the method includes:

The scheduling module determines first delivery efficiency and second delivery efficiency based on the order data, wherein the first delivery efficiency represents the efficiency of delivering orders in the relay delivery mode, and the second delivery efficiency represents the efficiency of delivering orders in the full-flow delivery module;

The scheduling module switches the relay delivery mode to the full-flow delivery mode or switches the full-flow delivery mode to the relay delivery mode in response to the first delivery efficiency and the second delivery efficiency meeting the mode switching condition.

the determining, based on the order data, a first delivery efficiency and a second delivery efficiency includes:

the scheduling module determines an influence characteristic corresponding to the first area based on the historical order data, wherein the influence characteristic is used for representing an influence factor of order distribution time consumption;

the scheduling module predicts a first delivery efficiency of the relay delivery mode or predicts a second delivery efficiency of the full-flow delivery mode based on the impact characteristics.

In one possible implementation, the scheduling module predicts a first delivery efficiency of the relay delivery mode based on the impact characteristics, including:

the scheduling module predicts time-consuming information of a dispatcher delivery stage in the relay delivery mode based on the influence characteristics;

The scheduling module acquires time-consuming information of an order handing-over stage in the relay distribution mode;

The scheduling module predicts a first delivery efficiency of the relay delivery mode based on time consuming information of the delivery stage of the dispatcher and time consuming information of the order handing-over stage.

In one possible implementation, the scheduling module predicts time-consuming information for a dispatcher's dispatch stage in the relay dispatch mode based on the impact characteristics, including:

The scheduling module predicts single-trip bill collection quantity corresponding to the relay distribution mode based on the influence characteristics and the distribution required duration, wherein the single-trip bill collection quantity is used for representing the quantity of orders distributed by the automatic driving vehicle in one trip;

The scheduling module predicts time consumption information of the dispatcher delivery stage based on the single-pass set single quantity and a target influencing factor in the influencing feature, wherein the target influencing factor is a influencing factor influencing time consumption of a first delivery stage in the full-flow delivery mode, and the first delivery stage is a delivery stage corresponding to the dispatcher delivery stage in the relay delivery mode in the full-flow delivery mode.

In one possible implementation, the scheduling module predicts a first delivery efficiency of the relay delivery mode based on time-consuming information of the delivery stage of the delivery person and time-consuming information of the order handing-over stage, comprising:

The scheduling module determines the number of orders distributed by the distributor in a unit time period based on the time consumption information of the distribution stage of the distributor, the time consumption information of the order handing-over stage and the single-pass collection amount;

the scheduling module determines the order quantity as a first delivery efficiency of the relay delivery mode.

N＝(SLA-T4-S/V)/(M+F+T5+T6)；

In one possible implementation, the scheduling module predicts a second delivery efficiency of the full-flow delivery mode based on the impact feature, including:

the scheduling module predicts time consumption information corresponding to the full-flow distribution mode based on the influence characteristics, wherein the time consumption information is used for indicating time consumption for completing one-time order distribution by adopting the full-flow distribution mode;

the scheduling module predicts a second delivery efficiency of the full-flow delivery mode based on the time-consuming information.

In one possible implementation manner, the scheduling module predicts time-consuming information corresponding to the full-flow distribution mode based on the impact feature, including:

The scheduling module determines a single-pass collection quantity corresponding to the full-flow distribution mode based on the influence characteristics and the distribution required time length, wherein the single-pass collection quantity is used for representing the quantity of orders distributed in one pass;

And the scheduling module predicts time consumption information corresponding to the full-flow distribution mode based on the single-pass set quantity and the influence characteristic.

In one possible implementation, the historical order data is historical order data of the full-flow delivery mode in the first region; the scheduling module determines an impact feature corresponding to the first area based on the historical order data, including:

The scheduling module determines first influence characteristics corresponding to all orders based on a plurality of orders in the historical order data;

the scheduling module determines a numerical range of the first influence feature based on the first influence feature corresponding to each order;

The scheduling module determines the statistical value of the first influence characteristic corresponding to each order as a second influence characteristic, wherein the statistical value is the average value or the median value of the first influence characteristic corresponding to each order;

The scheduling module predicts third distribution efficiency of the full-flow distribution mode based on the second influence characteristic;

The scheduling module updates the second influence characteristic based on the difference value between the third distribution efficiency and the second distribution efficiency so as to enable the difference value to be converged, wherein the updated second influence characteristic belongs to the numerical range;

And the scheduling module determines the updated second influence characteristic as the influence characteristic corresponding to the first area.

the scheduling module divides the order data into order sub-data corresponding to a plurality of time slices;

The scheduling module switches the relay distribution mode to the full-flow distribution mode or switches the full-flow distribution mode to the relay distribution mode under the corresponding time slices based on the order sub-data corresponding to each time slice and the mode switching conditions.

In one possible implementation, the scheduling module, in response to the first delivery efficiency and the second delivery efficiency meeting the mode switching condition, switches the relay delivery mode to the full-flow delivery mode or switches the full-flow delivery mode to the relay delivery mode, includes:

the scheduling module responds to the situation that the second delivery efficiency is larger than the first delivery efficiency and the difference value between the second delivery efficiency and the first delivery efficiency is not smaller than a target threshold value when the system adopts the relay delivery mode, and then the relay delivery mode is switched to the full-flow delivery mode;

And under the condition that the system adopts the full-flow distribution mode, the scheduling module responds to the fact that the first distribution efficiency is larger than the second distribution efficiency, and the difference value between the first distribution efficiency and the second distribution efficiency is not smaller than a target threshold value, and then the full-flow distribution mode is switched to the relay distribution mode.

In one aspect, a computer readable storage medium having stored therein at least one program code loaded and executed by a processor to perform operations performed by an order dispatch method as any one of the possible implementations described above is provided.

In one aspect, there is provided a computer program or computer program product comprising: computer program code which, when executed by a computer, causes the computer to perform the operations performed by the order dispatch method as described above in any one of the possible implementations.

The order scheduling system provided by the embodiment of the application sets the mode switching condition, determines whether the order scheduling system meets the mode switching condition based on the order data, and switches the distribution mode of the order scheduling system when the order scheduling system meets the mode switching condition. The distribution efficiency of each distribution mode is compared without adopting a plurality of distribution modes in turn, so that the time consumption of a distribution mode selection scheme is reduced, and the efficiency of mode switching is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic illustration of an implementation environment provided by an embodiment of the present application;

FIG. 2 is a flow chart of an order scheduling method provided by an embodiment of the present application;

FIG. 3 is a flow chart of an order scheduling method provided by an embodiment of the present application;

FIG. 4 is a flow chart of a full-flow distribution mode according to an embodiment of the present application;

FIG. 5 is a delivery flow chart of a relay delivery mode according to an embodiment of the present application;

FIG. 6 is a flow chart of an order scheduling method provided by an embodiment of the present application;

FIG. 7 is a flow chart of an order scheduling method provided by an embodiment of the present application;

Fig. 8 is a schematic structural view of an autonomous vehicle according to an embodiment of the present application;

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

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings.

It is to be understood that the terms "first," "second," and the like, as used herein, may be used to describe various concepts, but are not limited by these terms unless otherwise specified. These terms are only used to distinguish one concept from another. For example, a first order may be referred to as a second order and a second order may be referred to as a first order without departing from the scope of the present application.

The terms "at least one", "a plurality", "each", "any" as used herein, at least one includes one, two or more, a plurality includes two or more, and each refers to each of a corresponding plurality, any one refers to any one of a plurality, for example, a plurality of orders includes 3 orders, and each refers to each of the 3 orders, any one refers to any one of the 3 orders, either the first, the second, or the third.

It should be noted that, the information (including but not limited to user equipment information, user personal information, etc.), data (including but not limited to data for analysis, stored data, presented data, etc.), and signals related to the present application are all authorized by the user or are fully authorized by the parties, and the collection, use, and processing of the related data is required to comply with the relevant laws and regulations and standards of the relevant countries and regions. For example, order data and the like referred to in the present application are acquired with sufficient authorization. And the information and the data are processed and then used in big data application scenes, and can not be identified to any natural person or generate specific association with the natural person.

The order scheduling system provided by the embodiment of the application can be applied to delivery scenes, such as take-away delivery scenes, express delivery scenes, warehouse delivery scenes and the like, and the embodiment of the application is not limited to the above. The system has two delivery modes, namely a relay delivery mode and a full-flow delivery mode, and can adopt any delivery mode to schedule orders and can also switch the delivery modes. For example, when the order dispatch system is in the full-flow delivery mode, if it is predicted that the relay delivery mode is adopted based on the order data, the order dispatch system may switch the full-flow delivery mode to the relay delivery mode.

The following two distribution scenarios are taken as examples for illustrating the embodiment of the present application.

For example, warehouse delivery scenarios:

Taking the storage as a vegetable storage (the vegetable storage can be regarded as a vegetable site), a user can place an order on the internet to purchase vegetables, and if the order scheduling system is in a full-flow distribution mode, the order scheduling system distributes the order to a distributor, and the distributor takes goods from the vegetable storage and distributes the goods to the user; if the order dispatch system is in relay delivery mode, the order dispatch system distributes the order to the automated driving vehicle and the dispatcher, the automated driving vehicle takes and delivers the order from the vegetable warehouse to the order delivery point (e.g., the user's cell gate), and the dispatcher takes and delivers the order from the order delivery point to the user.

As another example, express delivery scenario:

If the order scheduling system is in the full-flow delivery mode, delivering the express from the express station to the user by a delivery person; if the order dispatch system is in relay delivery mode, the automated driving vehicle delivers the courier from the courier station to the order delivery point (e.g., the user's cell gate, etc.), and the dispatcher delivers the courier from the order delivery point to the user.

An embodiment of the present application provides an order scheduling system, as shown in fig. 1, where the system at least includes a scheduling module 101 and an automatic driving vehicle 102, and the scheduling module 101 is configured to schedule an order, that is, allocate a delivery capacity to the order. The system has two modes, namely a relay delivery mode and a full-flow delivery mode, when the system is in the relay delivery mode, the dispatch module 101 distributes orders to the autonomous vehicle 102 and the dispatcher, and the delivery is completed by the autonomous vehicle 102 and the dispatcher in relay. For example, an order is dispatched by the autonomous vehicle 102 to an order delivery point, and an order is dispatched by a dispatcher from the order delivery point to a destination. When the system is in full-flow delivery mode, the dispatch module 101 distributes the order to the dispatcher, who delivers the order all the way through.

Wherein the scheduling module 101 may be a certain module in the device, for example, the scheduling module 101 is a module in the server; the scheduling module 101 may also be a stand-alone device, for example, the scheduling module 101 is a scheduling server, and embodiments of the present application are not limited to the scheduling module 101. In some embodiments, the scheduling module 101 is a scheduling server, where the scheduling server may be a server, a server cluster including several servers, or a cloud computing service center.

The autonomous vehicle 102 includes vehicles that travel on the ground (e.g., automobiles, trucks, buses, etc.), vehicles that travel in the air (e.g., drones, planes, helicopters, etc.), and vehicles that travel on or in the water (e.g., boats, submarines, etc.). The autonomous vehicle 102 may or may not accommodate one or more passengers. In addition, the autonomous vehicle 102 may be applied to unmanned distribution fields, such as, for example, express logistics fields, take-away meal fields, and the like.

In some embodiments, the system further includes a terminal 103, the terminal 103 is a terminal used by a dispatcher, the scheduling module 101 distributes orders to the dispatcher via the terminal 103, and the dispatcher receives orders, refuses orders, completes the dispatch, etc. via the terminal 103. The terminal 103 may be any type of terminal such as a mobile phone, a computer, a tablet computer, etc.

Fig. 2 is a flowchart of an order scheduling method according to an embodiment of the present application. The embodiment of the application is exemplified by taking an execution subject as an order scheduling system, wherein the system at least comprises a scheduling module and an automatic driving vehicle, and the embodiment comprises the following components:

201. The scheduling module switches the relay delivery mode to a full-flow delivery mode or switches the full-flow delivery mode to the relay delivery mode when the mode switching condition is satisfied based on the order data, wherein the relay delivery mode is a mode of relay delivery by an automatic driving vehicle and a delivery person, and the full-flow delivery mode is a mode of full-flow delivery by the delivery person.

The mode switching condition is a condition that the switching mode can bring benefits to the order scheduling system. For example, when the order dispatch system is in the full-flow delivery mode, the mode switching condition is that the delivery efficiency of the relay delivery mode is greater than the delivery efficiency of the full-flow delivery mode; for another example, when the order dispatch system is in the relay delivery mode, the mode switching condition is that the delivery efficiency of the whole-flow delivery mode is greater than the delivery efficiency of the relay delivery mode.

In the embodiment of the application, the order data is data of an order received by a system, such as order generation time, order distribution time, destination and the like. The embodiment of the application does not limit the order data. The scheduling module may determine which delivery mode to use based on the order data, and thus which delivery mode to use. In some embodiments, the order data is historical order data. The order dispatch system presumes which delivery mode is more suitable to be adopted in the next stage according to the historical order data, and switches to which delivery mode.

When the mode switching condition is met, the scheduling module switches the relay distribution mode to the full-flow distribution mode, or switches the full-flow distribution mode to the relay distribution mode, which means that: when the order dispatching system is in the relay distribution mode, if the mode switching condition is met, switching the relay distribution mode into a full-flow distribution mode; or when the order dispatching system is in the full-flow delivery mode, if the mode switching condition is met, the full-flow delivery mode is switched to the relay delivery mode.

According to the order scheduling method provided by the embodiment of the application, the mode switching condition is set, whether the order scheduling system meets the mode switching condition is determined based on the order data, and when the order scheduling system meets the mode switching condition, the distribution mode of the order scheduling system is switched. The distribution efficiency of each distribution mode is compared without adopting a plurality of distribution modes in turn, so that the time consumption of a distribution mode selection scheme is reduced, and the efficiency of mode switching is improved.

Fig. 3 is a flowchart of an order scheduling method according to an embodiment of the present application. The embodiment of the application is exemplified by taking an execution subject as an order dispatch system, wherein the order dispatch system at least comprises a dispatch module and an automatic driving vehicle, and the embodiment comprises the following steps:

301. The scheduling module determines a second delivery efficiency based on the historical order data for the full-flow delivery mode in the first region, the second delivery efficiency representing an efficiency of delivering orders using the full-flow delivery mode.

The first area may be any area, for example, the first area may be a certain city, a certain urban area in the city, or an area formed by a plurality of adjacent cells. In the embodiment of the application, the order scheduling system adopts a full-flow distribution mode in the first area, that is, the order scheduling system performs order scheduling by adopting the full-flow distribution mode aiming at the orders in the first area. The full-flow delivery mode is a mode in which a delivery person delivers the full-flow delivery.

In some embodiments, the order dispatch system employs the same delivery mode in different areas, i.e., the order dispatch system also employs a full flow delivery mode in areas other than the first area. In other embodiments, the order dispatch system may employ different delivery modes in different areas, i.e., the order dispatch system may employ a relay delivery mode in areas other than the first area, or may employ a full-flow delivery mode. For example, the order dispatch system may employ a full-flow dispatch mode in a first area, a relay dispatch mode in a second area, a full-flow dispatch mode in a third area, and so on. Wherein the second region and the third region are other regions than the first region.

The historical order data for the full-flow delivery mode in the first region is: the order dispatch system receives order data for an order received when the full flow dispatch mode is employed in the first area. The historical order data may include order generation time, order delivery duration, order delivery track, etc., and the historical order data may include any data related to an order, and the embodiment of the application does not limit the historical order data.

In some embodiments, considering that the characteristics of the order may change over time, so that the distribution efficiency of the distribution mode changes, in order to accurately determine the second distribution efficiency, the historical order data in the embodiment of the present application is the historical order data in a target period, where the target period is any period, and the embodiment of the present application does not limit the target period. For example, the historical order data is historical order data of a month before in the first area.

The second delivery efficiency represents the efficiency of delivering orders using the full flow delivery mode. In some embodiments, the second delivery efficiency is the number of orders completed per unit time by one delivery person when the full-flow delivery mode is employed. Considering that the number of orders completed in the unit time of the dispatcher is also related to the order density, for example, during the peak period of the order, the number of orders completed in the unit time of the dispatcher is greater, and during the low peak period of the order, the number of orders completed in the unit time of the dispatcher is less. Therefore, in determining the second delivery efficiency, the historical order data may be divided into order sub-data corresponding to a plurality of time slices, and the second delivery efficiency corresponding to each time slice may be determined based on the order sub-data corresponding to each time slice.

The time segment may correspond to any time length, and the embodiment of the application does not limit the time segment. And, the duration corresponding to each time segment in the plurality of time segments may be the same or different, which is not limited in the embodiment of the present application.

For example, the number of the cells to be processed, dividing the historical order data into 0 to 0 half, 0 to 1 half, 1 half to 2 half, 2 to 3 half, 3 half to 4 half, 4 to 5 half, 5 half to 6 half, 6 to 7 half, 7 to 8 half, 8 to 9 half, 9 to 10 half, 10 to 11 half, 11 to 12 half, 12 to 12 half from 12 to 13, from 13 to 14, from 14 to 15, from 15 to 16, from 16 to 17, from 17 to 18, from 18 to 19, from 19 to 20, from 20 to 21, from 21 to 22, from 22 to 23, from 23 to 23 and from 23 to 0, respectively, and determining the second distribution efficiency corresponding to each time segment.

Considering that the change of the order quantity in the order peak period is relatively large and the change of the order quantity in the order low peak period is relatively small, the time slices with smaller duration can be used for dividing the order peak period, and the time slices with larger duration can be used for dividing the order low peak period. For another example, the historical order data is divided into order sub-data corresponding to 21 to 7 points, 7 to 11 points, 11 to 11 points half, 11 to 12 points half, 12 to 13 points half, 13 to 17 points half, 17 to 18 points half, 18 to 19 points half, 19 to 20 points half, 20 to 20 points half and 20 to 21 points respectively, and the second distribution efficiency corresponding to each time segment is determined.

302. The scheduling module determines an influence characteristic corresponding to the first area based on the historical order data, wherein the influence characteristic is used for representing an influence factor of order distribution time consumption.

In the embodiment of the application, the distribution mode adopted by the order scheduling system in the first area is a full-flow distribution mode, so that the distribution efficiency of the full-flow distribution mode can be directly determined based on the historical order data, and the order scheduling system does not adopt the relay distribution mode in the first area, so that the distribution efficiency of the relay distribution mode is estimated based on the historical order data of the full-flow distribution mode in the first area.

First, as shown in fig. 4, the delivery process of the full-flow delivery mode may include a pick-and-place duration T1, a pick-and-place duration T2, a trunk outbound distance T3, a trunk outbound distance T5, a delivery duration T6, a trunk return distance T7, and a trunk return distance T8. The order dispatching system is used for dispatching orders to the dispatcher, wherein the dispatcher waits for the order dispatching system to dispatch orders for the dispatcher at a first place, and the first place is a goods taking place corresponding to the orders in the first area. The dispatcher begins dispensing from the first location after the collected orders reach the target quantity or the collected orders reach the time limit. The order collection time period T1 is the time period for which the dispatcher waits at the first place. The picking and placing time T2 is the time for picking and placing the articles corresponding to the collected orders. The trunk departure distance T3 is the time when the dispatcher starts from the first place to reach the gate of the user cell, the trunk departure distance T5 is the time when the dispatcher starts from the gate of the user cell to reach the gate of the user home, the delivery time T6 is the time when the dispatcher delivers the order to the user, the trunk return distance T7 is the time when the dispatcher returns from the gate of the user home to the gate of the user cell, and the trunk return distance T8 is the time when the dispatcher returns from the gate of the user cell to the first place.

The delivery process of the relay delivery mode may be as shown in fig. 5, and the delivery process includes a pick-and-place duration T1, a pick-and-place duration T2, a trunk departure duration T3, a handover duration T4, and a trunk return T8 of the autonomous vehicle. The dispatch process also includes a dispatcher's hand-over time period T4, a leg out time period T5, a delivery time period T6, and a leg return time period T7. Wherein the autonomous vehicle waits at a first location for an order dispatch system to allocate an order for the autonomous vehicle. The autonomous vehicle starts delivery from the first location after the collected orders reach the target quantity or after the collected orders reach the time limit. The album duration T1 is a duration in which the automated guided vehicle waits at the first place. The picking and placing time T2 is the time for picking and placing the articles corresponding to the collected orders. The trunk departure distance T3 is the length of time that the autonomous vehicle starts from the first location to reach the subscriber cell gate, which is the order delivery point. The delivery time period T4 is a time period during which the automated driving vehicle delivers an order to the dispatcher. The trunk backhauler T8 is the length of time that the autonomous vehicle is returning from the user cell gate to the first location. The branch trip T5 is the time for the dispatcher to reach the user's home gate from the user's home gate, the delivery time T6 is the time for delivering the order to the user, and the branch return T7 is the time for the dispatcher to return to the user's home gate from the user's home gate.

As can be seen from the distribution flows shown in fig. 4 and 5, most of the distribution stages in the whole-flow distribution mode and the relay distribution mode are the same, so that the time-consuming information of the relay distribution mode can be estimated based on the time-consuming influencing factor (i.e., the influencing feature of the first area) of the distribution in the whole-flow distribution mode, thereby predicting the distribution efficiency of the relay distribution mode.

In some embodiments, the scheduling module determines the impact characteristics based on the historical order data, including: the scheduling module determines first influence characteristics corresponding to all orders based on a plurality of orders in the historical order data; and determining the statistical value of the first influence features corresponding to the orders as the influence features of the first area, wherein the statistical value is the average value or the median value of the first influence features corresponding to the orders.

Considering that the average value or the median value of the first influence features corresponding to each order may not be sufficiently accurate to be determined as the influence features of the first area, the embodiment of the application further provides a method for checking and correcting the influence features of the first area. In some embodiments, the scheduling module determines the impact characteristics based on the historical order data, including: the scheduling module determines first influence characteristics corresponding to each order based on a plurality of historical orders in the historical order data; determining a numerical range of the first influence feature based on the first influence feature corresponding to each order; the scheduling module determines the statistical value of the first influence characteristic corresponding to each order as a second influence characteristic, wherein the statistical value is the average value or the median value of the first influence characteristic corresponding to each order; predicting a third delivery efficiency of the full-flow delivery mode based on the second impact feature; updating the second influence characteristic based on the difference between the third distribution efficiency and the second distribution efficiency to enable the difference to be converged, wherein the updated second influence characteristic belongs to the numerical range; and the scheduling module determines the updated second influence characteristic as the influence characteristic corresponding to the first area.

According to the embodiment of the application, the value range of the influence characteristic is determined through the first influence characteristic corresponding to each order; firstly, predicting the distribution efficiency of the whole-flow distribution mode by adopting the average value or the median value of the first influence features corresponding to each order, and if the predicted distribution efficiency of the whole-flow distribution mode is the same as or similar to the real distribution efficiency of the whole-flow distribution mode, indicating that the average value or the median value of the first influence features corresponding to each order can more accurately represent the influence factors of the whole first area, directly determining the average value or the median value as the influence features corresponding to the first area. If the predicted distribution efficiency of the full-flow distribution mode is larger than the actual distribution efficiency of the full-flow distribution mode, the predicted distribution efficiency of the full-flow distribution mode needs to be re-valued within the range of the influence characteristics, so that the predicted distribution efficiency of the full-flow distribution mode is the same as or similar to the actual distribution efficiency of the full-flow distribution mode, and the re-valued influence characteristics can accurately represent the influence factors of the whole first area.

In some embodiments, the influencing feature comprises at least one of:

(1) And a entering interval, wherein the entering interval represents the difference of receiving time of two adjacent orders, and the entering interval is an influence factor for time consumption of the single-stage collection.

In some embodiments, the scheduling module determines the order entry interval based on the historical order data, including: an order entry interval is determined based on the times of receipt of the plurality of orders in the historical order data.

Optionally, the scheduling module determines the order entry interval based on the time of receipt of the plurality of orders, including: the scheduling module determines the receiving time interval of each two adjacent orders based on the receiving time of the orders, and determines the statistical value of the obtained receiving time intervals as the entering time interval.

Optionally, the scheduling module determines the order entry interval based on the time of receipt of the plurality of orders, including: the scheduling module determines a time length of a collection of a plurality of orders and the number of orders for the plurality of orders distributed by a distributor at a time, and determines a time interval based on the time length of the collection and the number of orders.

(2) And taking the goods placing duration of the single, wherein the goods placing time of the single is an influence factor of time consumption of the goods placing stage.

In some embodiments, the scheduling module determines a length of time to pick and place each and a number of orders to pick and place based on the historical order data; and determining the time length for taking and placing the goods by the single based on the time length for taking and placing the goods each time and the order quantity of taking and placing the goods.

(3) A first length of trunk indicating a coincident route of a plurality of orders to be dispatched together, the first length being a time consuming contributor to trunk departure and trunk return phases.

In the full-flow delivery mode, the delivery person completes the trunk departure phase and the trunk return phase, and in the relay delivery mode, the automatic driving vehicle completes the trunk departure phase and the trunk return phase. The speed of the autonomous vehicle is known, so it is the length of the trunk that affects the time consumed by the trunk departure phase and the time consumed by the trunk return phase.

(4) The branch line of time-consuming information of the branch line going-out stage corresponding to one order represents a route of any order of a plurality of orders distributed together, which does not coincide with other orders.

If a plurality of orders need to be distributed in one cell when a distributor distributes, time-consuming information of the branch going-out stage of the distributor is time-consuming information from a gate of the cell to the completion of distributing the plurality of orders. The time-consuming information of the branch departure phase corresponding to one order is determined based on the time-consuming information of the branch departure phase of the dispatcher and the order quantity of a plurality of orders in the cell.

In the full-flow delivery mode and the relay delivery mode, the branch delivery stage is completed by a delivery person, and the two stages are not different. Therefore, the time-consuming information of the branch trip stage in the whole-flow distribution mode can be directly used as the time-consuming information of the branch trip stage in the relay distribution mode.

(5) Time-consuming information of the spur backhaul phase, which represents the phase of the distribution capacity from any spur back to the trunk.

In the full-process delivery mode and the relay delivery mode, the branch line return stage is completed by a delivery person, and the two modes are not different. Therefore, the time-consuming information of the branch line backhaul stage in the full-flow delivery mode can be directly used as the time-consuming information of the branch line backhaul stage in the relay delivery mode.

(6) Time consuming information for an order delivery phase corresponding to an order, the order delivery phase representing a phase of delivering the order to a user.

In the full-flow delivery mode and the relay delivery mode, the order delivery phase is completed by a delivery person, and the two modes are not different, so that the time-consuming information of the order delivery phase in the full-flow delivery mode can be directly used as the time-consuming information of the order delivery phase in the relay delivery mode.

303. The scheduling module predicts a first delivery efficiency based on the impact characteristic, the first delivery efficiency representing an efficiency of delivering orders in a relay delivery mode.

Since the influence feature is used to represent an influence factor that is time-consuming for order delivery, delivery efficiency of the relay delivery mode can be predicted based on the influence feature.

In the relay distribution mode, since the automated guided vehicle and the distributor can simultaneously perform order distribution, the distribution efficiency of the distributor can be used as the distribution efficiency of the relay distribution mode when determining the distribution efficiency of the relay distribution mode. In some embodiments, the scheduling module predicts the first delivery efficiency based on the impact feature, comprising: the scheduling module predicts time consumption information of a delivery stage of a delivery person in the relay delivery mode based on the influence characteristics; the scheduling module acquires time-consuming information of an order handover stage in a relay distribution mode; the scheduling module predicts a first delivery efficiency of the relay delivery mode based on the time-consuming information of the delivery stage of the dispatcher and the time-consuming information of the order handing-over stage. The dispatcher dispatching stage comprises a branch trip stage, an order delivery stage and a branch return stage.

It should be noted that the full-flow distribution mode does not include an order delivery stage, and therefore, time-consuming information of the order delivery stage can be obtained from historical order data of other areas. In some embodiments, the second region employs a relay distribution mode. The scheduling module obtains time consumption information of an order handing-over stage in the relay distribution mode, and the time consumption information comprises the following steps: the scheduling module determines time-consuming information of an order handing-over stage in the relay distribution mode based on historical order data of the relay distribution mode in the second area.

Another point to be noted is that, in either the relay distribution mode or the full-flow distribution mode, the distribution capacity collects a plurality of orders at the first location, and distributes the plurality of orders one time. Thus, in predicting the first delivery efficiency, there is also a need to predict a single pass of the aggregate amount for order data representing one pass delivery of the autonomous vehicle. In some embodiments, the scheduling module predicts time-consuming information for the dispatcher's dispatch stage in the relay dispatch mode based on the impact feature, comprising: the scheduling module predicts single-pass collection quantity corresponding to the relay distribution mode based on the influence characteristics and the distribution required time length; based on the single volume of the single set and a target influencing factor in influencing characteristics, time-consuming information of a delivery stage of the delivery person is predicted, wherein the target influencing factor is a influencing factor influencing time consumption of a first delivery stage in a full-flow delivery mode, and the first delivery stage is a delivery stage corresponding to the delivery stage of the delivery person in a relay delivery mode in the full-flow delivery mode.

For example, the first delivery phase is a branch departure phase, an order delivery phase, and a branch return phase of the delivery person in the full-flow delivery mode.

In some embodiments, different areas have different dispensing requirement durations, and the dispensing requirement durations may be obtained from a corresponding relationship between the areas and the dispensing requirement durations.

Optionally, the impact characteristics, the delivery requirement duration, and the single pass set volume satisfy the following relationship data:

N＝(SLA-T4-S/V)/(M+F+T5+T6)；

Wherein N represents a single-pass quantity of collection, SLA represents a delivery request duration, T4 represents time-consuming information of an order delivery stage in a relay delivery mode, S represents a first length, V represents a running speed of an automatic driving vehicle in the relay delivery mode, M represents a single-in interval, F represents a time-consuming information of a branch delivery stage corresponding to an order, T5 represents time-consuming information of an order delivery stage corresponding to an order, and N represents a time-consuming information of a branch delivery stage corresponding to an order.

In some embodiments, the delivery efficiency of the relay delivery mode is represented by the number of orders that one delivery person completes per unit time. Optionally, the scheduling module predicts the first delivery efficiency of the relay delivery mode based on the time-consuming information of the delivery stage of the delivery person and the time-consuming information of the order handing-over stage, including: the scheduling module determines the number of orders distributed by the distributor in a unit time period based on time consumption information of the distribution stage of the distributor, time consumption information of the order handing-over stage and single-pass quantity; the scheduling module determines the order quantity as a first delivery efficiency of a relay delivery mode.

For example, the first delivery efficiency=60×n/(t4+t7+ (t5+t6) ×n). Wherein N is a single-pass collection amount, T4 is time-consuming information of an order handover stage, T5 is time-consuming information of a branch trip stage, T6 is time-consuming information of an order delivery stage and T7 is time-consuming information of a branch return stage.

In step 301, the second distribution efficiency corresponding to the different time slices may be determined, and in step 302 and step 303, the influence characteristics and the first distribution efficiency corresponding to the different time slices may be determined.

304. The scheduling module switches the full-flow delivery mode to the relay delivery mode in response to the first delivery efficiency and the second delivery efficiency meeting the mode switching condition.

In some embodiments, the scheduling module switches the full-process delivery mode to the relay delivery mode in response to the first delivery efficiency and the second delivery efficiency satisfying a mode switch condition, comprising: when the system adopts the relay distribution mode, responding to the fact that the second distribution efficiency is larger than the first distribution efficiency, switching the relay distribution mode into a full-flow distribution mode; and under the condition that the system adopts the full-flow distribution mode, switching the full-flow distribution mode into the relay distribution mode in response to the fact that the first distribution efficiency is larger than the second distribution efficiency and the difference value between the first distribution efficiency and the second distribution efficiency is not smaller than the target threshold value.

In view of the increase in cost associated with performing the mode switching, it is also necessary to consider the difference between the first distribution efficiency and the second distribution efficiency in order to perform the mode switching more reasonably. In some embodiments, the scheduling module switches the full-process delivery mode to the relay delivery mode in response to the first delivery efficiency and the second delivery efficiency satisfying a mode switch condition, comprising: under the condition that the system adopts a relay distribution mode, responding to the fact that the second distribution efficiency is larger than the first distribution efficiency, and the difference value between the second distribution efficiency and the first distribution efficiency is not smaller than a target threshold value, switching the relay distribution mode into a full-flow distribution mode; and under the condition that the system adopts the full-flow distribution mode, switching the full-flow distribution mode into the relay distribution mode in response to the fact that the first distribution efficiency is larger than the second distribution efficiency and the difference value between the first distribution efficiency and the second distribution efficiency is not smaller than the target threshold value.

In some embodiments, the second delivery efficiency determined in step 301 is a first delivery efficiency corresponding to each time segment, and the first delivery efficiency determined in step 303 is also a second delivery efficiency corresponding to each time segment, where a delivery mode suitable for each time segment may be determined based on the first delivery efficiency and the second delivery efficiency corresponding to the time segment, and a full-flow delivery mode or a relay delivery mode may be determined based on the distribution of time segments corresponding to the same delivery mode.

For example, since the time slices corresponding to the full-flow delivery mode are relatively continuous and the time slices corresponding to the relay delivery mode are relatively discrete, the full-flow delivery mode is directly adopted in consideration of the increased cost of replacing the delivery mode. For another example, the time segments corresponding to the full-process delivery mode and the relay delivery mode are relatively continuous (for example, the delivery mode suitable for the morning and the noon is the relay delivery mode, and the delivery mode suitable for the afternoon and the evening is the full-process delivery mode), then the full-process delivery mode and the relay delivery mode can be switched based on the time segments corresponding to the same delivery mode (for example, the morning and the noon are switched to the relay delivery mode, and the afternoon and the evening are switched to the full-process delivery mode).

Fig. 6 is a flowchart of an order scheduling method according to an embodiment of the present application. The embodiment of the application is exemplified by taking an execution subject as an order dispatch system, wherein the order dispatch system at least comprises a dispatch module and an automatic driving vehicle, and the embodiment comprises the following steps:

601. the scheduling module determines a first delivery efficiency based on historical order data for the relay delivery mode in the first region, the first delivery efficiency representing an efficiency of delivering orders in the relay delivery mode.

The step 601 is the same as the step 301, and will not be described in detail here.

602. The scheduling module determines an influence characteristic corresponding to the first area based on the historical order data, wherein the influence characteristic is used for representing an influence factor of order distribution time consumption.

The step 602 is the same as the step 302, and will not be described in detail herein.

It should be noted that, in the embodiment of the present application, the influencing feature corresponding to the first area is determined based on the historical order data of the relay distribution mode, and the relay distribution mode includes an order delivery stage, so that the influencing feature corresponding to the first area may include time-consuming information of an order delivery stage corresponding to an order, where the order delivery stage indicates a stage of delivering an order between the automated driving vehicle and the dispatcher.

603. The scheduling module predicts a second delivery efficiency based on the impact characteristic, the second delivery efficiency representing an efficiency of delivering orders in a full-flow delivery mode.

As can be seen from fig. 4 and 5, the relay distribution mode is more than the full-flow distribution mode, and the rest of the order delivery stages are the same as the full-flow distribution mode. Accordingly, time-consuming information corresponding to each stage in the full-flow distribution mode can be predicted based on the influence features. In some embodiments, the scheduling module predicts a second delivery efficiency based on the impact feature, the second delivery efficiency representing an efficiency of delivering orders in a full-flow delivery mode, comprising: the scheduling module predicts time consumption information corresponding to the full-flow distribution mode based on the influence characteristics, wherein the time consumption information is used for indicating time consumption for completing one-time order distribution by adopting the full-flow distribution mode; the scheduling module predicts a second delivery efficiency of the full-flow delivery mode based on the time-consuming information.

Similarly, in either the relay delivery mode or the full-flow delivery mode, the delivery capacity collects a plurality of orders at the first location and delivers the plurality of orders in one pass. Thus, in predicting the second delivery efficiency, there is also a need to predict a single pass of the aggregate amount for the order data representing the delivery of one pass by the delivery person. In some embodiments, the scheduling module predicts time-consuming information corresponding to the full-flow delivery mode based on the impact feature, including: the scheduling module determines single-pass single-collection quantity corresponding to the whole-flow distribution mode based on the influence characteristics and the distribution required time length, wherein the single-pass single-collection quantity is used for representing the quantity of orders distributed in one pass; based on the single-pass set quantity and the influence characteristics, time-consuming information corresponding to the full-flow distribution mode is predicted.

For example, the second delivery efficiency=60×n/(t1+t2+t3+t7+t8+ (t5+t6) ×n).

604. The scheduling module switches the relay delivery mode to a full-flow delivery mode in response to the first delivery efficiency and the second delivery efficiency meeting a mode switching condition.

Step 604 is similar to step 304 described above and will not be described in detail herein.

The order scheduling method provided by the embodiment of the application can be as shown in fig. 7, and the two delivery modes, namely, the full-flow delivery mode and the relay delivery mode, are modeled first to obtain the delivery flow of the full-flow delivery mode and the delivery flow of the relay delivery mode shown in fig. 4 and 5. Historical operating data (including historical order data) for a first area is collected, and an impact characteristic for the first area is determined based on the historical operating data for the first area. According to the historical operation data, calculating the real distribution efficiency OPSH (one distribution capacity for one hour to finish single quantity) of a distribution mode adopted by the first area and a supply and demand model of the first area (the supply and demand model is the relation data for determining single-pass single quantity); calculating a simulated delivery efficiency OPSH (a delivery capacity of one hour to complete a single quantity) of a delivery mode adopted by the first area based on the supply and demand model, and iteratively optimizing the supply and demand model based on a difference value between the actual delivery efficiency and the simulated delivery efficiency; and calculating the distribution efficiency of the two distribution modes by adopting the two supply and demand models, and selecting the optimal distribution mode in the first area based on the distribution efficiency of the two distribution modes to realize dynamic configuration.

The embodiment of the application also provides an order dispatching system which at least comprises a dispatching module and an automatic driving vehicle,

The scheduling module is configured to switch, based on order data, a relay delivery mode to a full-flow delivery mode or to switch the full-flow delivery mode to the relay delivery mode when a mode switching condition is satisfied, wherein the relay delivery mode is a mode of relay delivery by the automated driving vehicle and a dispatcher, and the full-flow delivery mode is a mode of full-flow delivery by the dispatcher.

In one possible implementation, the scheduling module is configured to determine, based on the order data, a first delivery efficiency and a second delivery efficiency, where the first delivery efficiency is indicative of an efficiency of delivering orders using the relay delivery mode, and the second delivery efficiency is indicative of an efficiency of delivering orders using the full-flow delivery module;

The scheduling module is used for determining an influence characteristic corresponding to the first area based on the historical order data, wherein the influence characteristic is used for representing an influence factor of order distribution time consumption;

The scheduling module is used for predicting the first delivery efficiency of the relay delivery mode or predicting the second delivery efficiency of the full-flow delivery mode based on the influence characteristic.

the scheduling module is used for acquiring time-consuming information of an order handover stage in the relay distribution mode;

the scheduling module is used for predicting the first delivery efficiency of the relay delivery mode based on the time consumption information of the delivery stage of the delivery person and the time consumption information of the order handing-over stage.

In one possible implementation, the scheduling module is configured to predict a single-trip pick-up quantity corresponding to the relay delivery mode based on the impact feature and the delivery requirement duration, where the single-trip pick-up quantity is used to represent a number of orders delivered by the autonomous vehicle in one trip;

The scheduling module is configured to predict time consumption information of the dispatcher's delivery stage based on the single-pass set of single-pass values and a target influencing factor in the influencing feature, where the target influencing factor is a influencing factor that influences time consumption of a first delivery stage in the full-flow delivery mode, and the first delivery stage is a delivery stage in the full-flow delivery mode corresponding to the dispatcher's delivery stage in the relay delivery mode.

In one possible implementation, the scheduling module is configured to determine a number of orders that are distributed by the dispatcher in a unit time period based on the time-consuming information of the dispatcher in the distribution stage, the time-consuming information of the order delivery stage, and the single-pass set amount;

In one possible implementation, the influencing feature comprises at least one of:

a entering interval, wherein the entering interval represents the difference between receiving time of two adjacent orders, and the entering interval is an influence factor for time consumption of a single-stage;

the single-picking and placing duration is the time-consuming influence factor of picking and placing phases;

a first length of trunk indicating a coincident route of a plurality of orders to be dispatched together, the first length being a time consuming factor of influence for a trunk departure phase and a trunk return phase;

In one possible implementation, the impact feature, the delivery requirement duration, and the single pass set of orders satisfy the following relationship data:

N＝(SLA-T4-S/V)/(M+F+T5+T6)；

Wherein N represents the single-trip quantity, SLA represents the distribution request duration, T4 represents the time-consuming information of the order delivery stage in the relay distribution mode, S represents the first length, V represents the running speed of the autonomous vehicle in the relay distribution mode, M represents the order-in interval, F represents the order-out duration, T5 represents the time-consuming information of the branch delivery stage corresponding to an order, and T6 represents the time-consuming information of the order delivery stage corresponding to an order.

In a possible implementation manner, the scheduling module is configured to predict time-consuming information corresponding to the full-flow distribution mode based on the impact feature, where the time-consuming information is used to represent time consumed for completing one-time order distribution by using the full-flow distribution mode;

the scheduling module is used for predicting the second distribution efficiency of the whole-flow distribution mode based on the time consumption information.

In one possible implementation manner, the scheduling module is configured to determine a single-pass collection amount corresponding to the full-flow distribution mode based on the impact feature and the distribution requirement duration, where the single-pass collection amount is used to represent the number of orders distributed in one pass;

The scheduling module is used for predicting time consumption information corresponding to the full-flow distribution mode based on the single-pass collection quantity and the influence characteristic.

In one possible implementation, the historical order data is historical order data for the full-flow distribution mode in the first region;

the scheduling module is used for determining the statistical value of the first influence features corresponding to each order as the second influence features, wherein the statistical value is the average value or the median value of the first influence features corresponding to each order;

the scheduling module is used for predicting third distribution efficiency of the whole-flow distribution mode based on the second influence characteristic;

The scheduling module is configured to update the second impact feature based on a difference between the third distribution efficiency and the second distribution efficiency, so as to make the difference converge, where the updated second impact feature belongs to the numerical range;

The scheduling module is configured to determine the updated second impact feature as an impact feature corresponding to the first area.

the scheduling module is configured to switch the relay distribution mode to the full-flow distribution mode or switch the full-flow distribution mode to the relay distribution mode under the corresponding time segment based on the order sub-data corresponding to each time segment and the mode switching condition.

Fig. 8 is a block diagram of an autonomous vehicle 800 according to an embodiment of the present application. The autonomous vehicle 800 includes: a processor 801 and a memory 802.

Processor 801 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and the like. The processor 801 may be implemented in at least one hardware form of DSP (DIGITAL SIGNAL Processing), FPGA (Field-Programmable gate array), PLA (Programmable Logic Array ). The processor 801 may also include a main processor, which is a processor for processing data in an awake state, also referred to as a CPU (Central Processing Unit ), and a coprocessor; a coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 801 may integrate a GPU (Graphics Processing Unit, image processor) for rendering and drawing of content required to be displayed by the display screen. In some embodiments, the processor 801 may also include an AI (ARTIFICIAL INTELLIGENCE ) processor for processing computing operations related to machine learning.

Memory 802 may include one or more computer-readable storage media, which may be non-transitory. Memory 802 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in memory 802 is used to store at least one program code for execution by processor 801 to implement the order scheduling method provided by the method embodiments of the present application.

In some embodiments, autonomous vehicle 800 may optionally further include: a peripheral interface 803, and at least one peripheral. The processor 801, the memory 802, and the peripheral interface 803 may be connected by a bus or signal line. Individual peripheral devices may be connected to the peripheral device interface 803 by buses, signal lines, or a circuit board. Specifically, the peripheral device includes: at least one of radio frequency circuitry 804, a display 805, a camera 806, audio circuitry 807, a positioning component 808, and a power supply 809.

Peripheral interface 803 may be used to connect at least one Input/Output (I/O) related peripheral to processor 801 and memory 802. In some embodiments, processor 801, memory 802, and peripheral interface 803 are integrated on the same chip or circuit board; in some other embodiments, either or both of the processor 801, the memory 802, and the peripheral interface 803 may be implemented on separate chips or circuit boards, which is not limited in this embodiment.

The Radio Frequency circuit 804 is configured to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 804 communicates with a communication network and other communication devices via electromagnetic signals. The radio frequency circuit 804 converts an electrical signal into an electromagnetic signal for transmission, or converts a received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 804 includes: antenna systems, RF transceivers, one or more amplifiers, tuners, oscillators, digital signal processors, codec chipsets, subscriber identity module cards, and so forth. The radio frequency circuit 804 may communicate with other autonomous vehicles via at least one wireless communication protocol. The wireless communication protocol includes, but is not limited to: metropolitan area networks, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and/or WiFi (WIRELESS FIDELITY ) networks. In some embodiments, the radio frequency circuit 804 may further include NFC (NEAR FIELD Communication) related circuits, which is not limited by the present application.

The display 805 is used to display a UI (User Interface). The UI may include graphics, text, icons, video, and any combination thereof. When the display 805 is a touch display, the display 805 also has the ability to collect touch signals at or above the surface of the display 805. The touch signal may be input as a control signal to the processor 801 for processing. At this time, the display 805 may also be used to provide virtual buttons and/or virtual keyboards, also referred to as soft buttons and/or soft keyboards. In some embodiments, the display 805 may be one, providing a front panel of the autonomous vehicle 800; in other embodiments, the display 805 may be at least two, each disposed on a different surface of the autonomous vehicle 800 or in a folded configuration; in still other embodiments, the display 805 may be a flexible display disposed on a curved surface or a folded surface of the autonomous vehicle 800. Even more, the display 805 may be arranged in an irregular pattern other than rectangular, i.e., a shaped screen. The display 805 may be made of LCD (Liquid CRYSTAL DISPLAY), OLED (Organic Light-Emitting Diode), or other materials.

The camera assembly 806 is used to capture images or video. Optionally, the camera assembly 806 includes a front camera and a rear camera. The front camera is arranged on the front panel of the automatic driving vehicle, and the rear camera is arranged on the back of the automatic driving vehicle. In some embodiments, the at least two rear cameras are any one of a main camera, a depth camera, a wide-angle camera and a tele camera, so as to realize that the main camera and the depth camera are fused to realize a background blurring function, and the main camera and the wide-angle camera are fused to realize a panoramic shooting and Virtual Reality (VR) shooting function or other fusion shooting functions. In some embodiments, the camera assembly 806 may also include a flash. The flash lamp can be a single-color temperature flash lamp or a double-color temperature flash lamp. The dual-color temperature flash lamp refers to a combination of a warm light flash lamp and a cold light flash lamp, and can be used for light compensation under different color temperatures.

Audio circuitry 807 may include a microphone and a speaker. The microphone is used for collecting sound waves of users and the environment, converting the sound waves into electric signals, inputting the electric signals to the processor 801 for processing, or inputting the electric signals to the radio frequency circuit 804 for voice communication. For purposes of stereo acquisition or noise reduction, a plurality of microphones may be provided at different portions of the autonomous vehicle 800, respectively. The microphone may also be an array microphone or an omni-directional pickup microphone. The speaker is used to convert electrical signals from the processor 801 or the radio frequency circuit 804 into sound waves. The speaker may be a conventional thin film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, not only the electric signal can be converted into a sound wave audible to humans, but also the electric signal can be converted into a sound wave inaudible to humans for ranging and other purposes. In some embodiments, audio circuit 807 may also include a headphone jack.

The locating component 808 is utilized to locate the current geographic location of the autonomous vehicle 800 for navigation or LBS (Location Based Service, location-based services). The positioning component 808 may be a positioning component based on the United states GPS (Global Positioning System ), the Beidou system of China, the Granati system of Russia, or the Galileo system of the European Union.

The power supply 809 is used to power the various components in the autonomous vehicle 800. The power supply 809 may be an alternating current, direct current, disposable battery, or rechargeable battery. When the power supply 809 includes a rechargeable battery, the rechargeable battery may support wired or wireless charging. The rechargeable battery may also be used to support fast charge technology.

In some embodiments, autonomous vehicle 800 also includes one or more sensors 810. The one or more sensors 810 include, but are not limited to: acceleration sensor 811, gyroscope sensor 812, pressure sensor 813, fingerprint sensor 814, optical sensor 815, and proximity sensor 816.

The acceleration sensor 811 may detect the magnitudes of accelerations on three coordinate axes of the coordinate system established with the autonomous vehicle 800. For example, the acceleration sensor 811 may be used to detect components of gravitational acceleration in three coordinate axes. The processor 801 may control the display screen 805 to display a user interface in a landscape view or a portrait view based on the gravitational acceleration signal acquired by the acceleration sensor 811. Acceleration sensor 811 may also be used for the acquisition of motion data of a game or user.

The gyro sensor 812 may detect the body direction and the rotation angle of the autonomous vehicle 800, and the gyro sensor 812 may collect the 3D motion of the user on the autonomous vehicle 800 in cooperation with the acceleration sensor 811. The processor 801 may implement the following functions based on the data collected by the gyro sensor 812: motion sensing (e.g., changing UI according to a tilting operation by a user), image stabilization at shooting, game control, and inertial navigation.

The pressure sensor 813 may be disposed at a side frame of the autonomous vehicle 800 and/or at an underside of the display screen 805. When the pressure sensor 813 is provided at a side frame of the autonomous vehicle 800, a grip signal of the autonomous vehicle 800 by a user may be detected, and the processor 801 performs left-right hand recognition or quick operation according to the grip signal collected by the pressure sensor 813. When the pressure sensor 813 is disposed at the lower layer of the display screen 805, the processor 801 controls the operability control on the UI interface according to the pressure operation of the user on the display screen 805. The operability controls include at least one of a button control, a scroll bar control, an icon control, and a menu control.

The fingerprint sensor 814 is used to collect a fingerprint of a user, and the processor 801 identifies the identity of the user based on the fingerprint collected by the fingerprint sensor 814, or the fingerprint sensor 814 identifies the identity of the user based on the collected fingerprint. Upon recognizing that the user's identity is a trusted identity, the processor 801 authorizes the user to perform relevant sensitive operations including unlocking the screen, viewing encrypted information, downloading software, paying for and changing settings, etc. The fingerprint sensor 814 may be provided on the front, back, or side of the autonomous vehicle 800. When a physical key or vendor Logo is provided on the autonomous vehicle 800, the fingerprint sensor 814 may be integrated with the physical key or vendor Logo.

The optical sensor 815 is used to collect the ambient light intensity. In one embodiment, the processor 801 may control the display brightness of the display screen 805 based on the intensity of ambient light collected by the optical sensor 815. Specifically, when the intensity of the ambient light is high, the display brightness of the display screen 805 is turned up; when the ambient light intensity is low, the display brightness of the display screen 805 is turned down. In another embodiment, the processor 801 may also dynamically adjust the shooting parameters of the camera module 806 based on the ambient light intensity collected by the optical sensor 815.

A proximity sensor 816, also referred to as a distance sensor, is provided on the front panel of the autonomous vehicle 800. The proximity sensor 816 is used to collect the distance between the user and the front of the autonomous vehicle 800. In one embodiment, when the proximity sensor 816 detects that the distance between the user and the front of the autonomous vehicle 800 gradually decreases, the processor 801 controls the display 805 to switch from the bright screen state to the off screen state; when the proximity sensor 816 detects that the distance between the user and the front face of the autonomous vehicle 800 gradually increases, the processor 801 controls the display screen 805 to switch from the off-screen state to the on-screen state.

Those skilled in the art will appreciate that the configuration shown in fig. 8 is not limiting and that the autonomous vehicle 800 may include more or fewer components than shown, or may combine certain components, or may employ a different arrangement of components.

Fig. 9 is a schematic structural diagram of a server according to an embodiment of the present application, where the server 900 may have a relatively large difference due to different configurations or performances, and may include one or more processors (Central Processing Units, CPUs) 901 and one or more memories 902, where at least one program code is stored in the memories 902, and the at least one program code is loaded and executed by the processors 901 to implement the methods provided in the foregoing method embodiments. Of course, the server may also have a wired or wireless network interface, a keyboard, an input/output interface, and other components for implementing the functions of the device, which are not described herein.

The server 900 is configured to perform the steps performed by the server in the method embodiments described above.

In an exemplary embodiment, a computer readable storage medium, e.g. a memory comprising program code, executable by a processor in a computer device to perform the order scheduling method of the above-described embodiments, is also provided. For example, the computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

In an exemplary embodiment, a computer program or a computer program product is also provided, which comprises computer program code which, when executed by a computer, causes the computer to implement the order scheduling method in the above-described embodiments.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, where the program may be stored in a computer readable storage medium, and the above storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The foregoing description of the preferred embodiments of the present application is not intended to limit the application, but rather, the application is to be construed as limited to the appended claims.

Claims

1. An order dispatch system, characterized in that the system comprises at least a dispatch module and an automatic driving vehicle,

2. The system of claim 1, wherein the system further comprises a controller configured to control the controller,

The scheduling module is used for determining first delivery efficiency and second delivery efficiency based on the order data, wherein the first delivery efficiency represents the efficiency of delivering orders in the relay delivery mode, and the second delivery efficiency represents the efficiency of delivering orders in the full-flow delivery module;

3. The system of claim 2, wherein the order data is historical order data for the full-process delivery mode in the first area or the order data is historical order data for the relay delivery mode in the first area;

4. The system of claim 3, wherein the system further comprises a controller configured to control the controller,

The scheduling module is used for predicting time-consuming information of a dispatcher delivery stage in the relay delivery mode based on the influence characteristics;

5. The system of claim 4, wherein the system further comprises a controller configured to control the controller,

The scheduling module is used for predicting single-trip quantity of the relay delivery mode based on the influence characteristics and the delivery required time length, wherein the single-trip quantity of the relay delivery mode is used for representing the quantity of orders delivered by the automatic driving vehicle in one trip;

6. The system of claim 5, wherein the system further comprises a controller configured to control the controller,

The scheduling module is used for determining the number of the orders distributed by the distributor in a unit time period based on the time consumption information of the distribution stage of the distributor, the time consumption information of the order handing-over stage and the single-pass collection amount;

7. A system according to claim 3, wherein the influencing features comprise at least one of:

8. The system of claim 7, wherein the impact characteristics, the delivery demand duration, and the single pass set of single amounts satisfy the following relationship data:

N＝(SLA-T4-S/V)/(M+F+T5+T6)；

9. The system of claim 3, wherein the system further comprises a controller configured to control the controller,

The scheduling module is used for predicting time consumption information corresponding to the full-flow distribution mode based on the influence characteristics, wherein the time consumption information is used for indicating time consumption for completing one-time order distribution by adopting the full-flow distribution mode;

10. The system of claim 9, wherein the system further comprises a controller configured to control the controller,

The scheduling module is used for determining single-pass collection quantity corresponding to the full-flow distribution mode based on the influence characteristics and the distribution required time length, wherein the single-pass collection quantity is used for representing the quantity of orders distributed in one pass;

11. The system of claim 3, wherein the historical order data is historical order data for the full-flow distribution mode in the first area;

12. The system of claim 1, wherein the system further comprises a controller configured to control the controller,

The scheduling module is further used for dividing the order data into order sub-data corresponding to a plurality of time slices;

13. The system of claim 2, wherein the system further comprises a controller configured to control the controller,

The scheduling module is configured to switch the relay delivery mode to the full-flow delivery mode in response to the second delivery efficiency being greater than the first delivery efficiency and a difference between the second delivery efficiency and the first delivery efficiency being not less than a target threshold when the relay delivery mode is adopted by the system;