WO2021147353A1

WO2021147353A1 - Order dispatch

Info

Publication number: WO2021147353A1
Application number: PCT/CN2020/115991
Authority: WO
Inventors: 王圣尧; 包建东; 郑环宇
Original assignee: 北京三快在线科技有限公司
Priority date: 2020-01-21
Filing date: 2020-09-17
Publication date: 2021-07-29
Also published as: CN113222305B; CN113222305A

Abstract

Clustering is performed on each order to be dispatched according to order information of each order to be dispatched within a time unit, and a plurality of order groups are obtained; delivery transport forces corresponding to each order group are respectively determined; with respect to each order group, match degrees between each order to be dispatched within said order group and delivery transport forces corresponding to the order group are determined according to the order information of each order to be dispatched within the order group and delivery information of each delivery transport force corresponding to the order group; order dispatch is performed on each order to be dispatched according to the match degrees.

Description

Order scheduling

This disclosure claims the priority of the Chinese patent application filed on January 21, 2020, the application number is 202010071676.5, and the invention title is "Order scheduling method, device, storage medium and electronic equipment", the entire content of which is incorporated into this application by reference middle.

Technical field

The present disclosure relates to the field of Internet technology, and in particular, to an order scheduling method, device, storage medium, and electronic equipment.

Background technique

With the development of computer technology, businesses such as food delivery and carpooling have also emerged, and the scale of their corresponding orders has also been increasing. In order to continuously optimize costs, it is becoming more and more important to improve the efficiency of order distribution.

Summary of the invention

The purpose of the present disclosure is to provide an order scheduling method, device, storage medium, and electronic equipment, which can reduce the amount of data calculation and improve real-time performance.

In order to achieve the above objective, according to the first aspect of the present disclosure, there is provided an order scheduling method. The method includes: clustering each pending order according to the order information of each pending order within a time unit to obtain Multiple order groups; respectively determine the delivery capacity corresponding to each of the order groups; for each of the order groups, according to the order information of each of the pending orders in the order group and the respective delivery corresponding to the order group The distribution information of the capacity determines the matching degree between each of the pending orders in the order group and each of the distribution capacity corresponding to the order group; according to each of the matching degrees, each of the pending orders is determined Carry out order scheduling.

Optionally, the clustering of the to-be-dispatched orders according to the order information of the to-be-dispatched orders in a time unit, and after obtaining a plurality of order groups, the method further includes: Set a threshold order group, split the order group into multiple order groups, wherein the number of orders to be dispatched in each order group obtained by the split is less than the preset threshold.

Optionally, the clustering the to-be-dispatched orders according to the order information of the to-be-dispatched orders in a time unit to obtain multiple order groups includes: according to the quantity of each of the to-be-dispatched orders and the preset The threshold value determines the number of cluster centers; clusters the pending orders according to the number of cluster centers and the order information of each pending order to obtain the multiple order groups.

Optionally, the performing order scheduling on each of the pending orders according to each of the matching degrees includes: for each of the pending orders, determining the delivery capacity with the highest matching degree corresponding to the pending orders Is the target delivery capacity corresponding to the order to be dispatched; each order to be dispatched is delivered to the corresponding target delivery capacity.

Optionally, after determining, for each order to be dispatched, the delivery capacity corresponding to the order to be dispatched with the highest matching degree as the target delivery capacity corresponding to the order to be dispatched, the method further includes: For each target delivery capacity, if there are more than two pending orders corresponding to the target delivery capacity, the pending order with the highest matching degree corresponding to the target delivery capacity is determined as the target corresponding to the target delivery capacity Order; in the case that there is one order to be dispatched corresponding to the target delivery capacity, the order to be dispatched is determined as the target order corresponding to the target delivery capacity;

The distributing each of the pending orders to the corresponding target distribution capacity includes: allocating each of the target orders to the respective corresponding target distribution capacity.

Optionally, the method further includes: for each target delivery capacity, if there are two or more orders to be dispatched with the highest matching degree corresponding to the target delivery capacity, if each of the highest matching orders is If the task point information of the to-be-scheduled orders is the same, each of the to-be-scheduled orders is taken as the target order of the target delivery capacity; if the task point information of each of the to-be-scheduled orders with the highest matching degree is different, then each of the to-be-scheduled orders is different The dispatch order selects a to-be dispatched order as the target order of the target delivery capacity.

Optionally, the method further includes: taking orders other than the target order among the to-be-dispatched orders as the to-be-dispatched orders in the next time unit.

Optionally, the order information includes different types of task point information; the clustering of the orders to be dispatched according to the order information of the orders to be dispatched in a time unit includes: according to the order information of the orders to be dispatched in the time unit The task point information of the same type of the to-be-scheduled orders clusters the to-be-scheduled orders.

Optionally, the respectively determining the delivery capacity corresponding to each of the order groups includes: for each of the order groups, the distance between the current position and the starting position of each of the to-be-scheduled orders in the order group The delivery capacity less than the preset distance is determined as the delivery capacity corresponding to the order group.

Optionally, the determining, according to the order information of each order to be dispatched in the order group and the distribution information of the delivery capacity corresponding to the order group, determine that each of the orders to be dispatched in the order group and all the orders The matching degree between each of the distribution capacity corresponding to the order group includes: for each of the distribution capacity, according to the distribution information of the distribution capacity, respectively determine to pre-order each of the pending orders in the order group After being allocated to the distribution capacity, the target parameter corresponding to the distribution capacity, the size of the target parameter is used to distinguish the pros and cons of pre-allocating the pending orders to each of the distribution capacities; according to the distribution capacity and The target parameter corresponding to each of the to-be-dispatched orders determines the degree of matching between each of the to-be-dispatched orders and the delivery capacity.

According to a second aspect of the present disclosure, there is provided an order scheduling device, the device comprising: a clustering module, configured to perform order scheduling on each pending order according to the order information of each pending order within a time unit Clustering to obtain multiple order groups; the first determining module is configured to determine the delivery capacity corresponding to each of the order groups; the second determining module is configured to determine the delivery capacity corresponding to each of the order groups according to The order information of each order to be dispatched in the order group and the distribution information of each delivery capacity corresponding to the order group are determined to determine each of the orders to be dispatched in the order group and each corresponding to the order group The degree of matching between the distribution capacity; the scheduling module is configured to perform order scheduling on each of the orders to be dispatched according to each of the degrees of matching.

Optionally, the clustering module includes: a splitting sub-module configured to split the order group into multiple order groups for an order group in which the number of orders to be scheduled exceeds a preset threshold, wherein, The number of orders to be dispatched in each order group obtained by splitting is less than the preset threshold.

Optionally, the clustering module is configured to determine the number of cluster centers according to the number of each of the pending orders and the preset threshold; according to the number of the cluster centers, and each of the pending orders The order information of the dispatch order clusters the pending orders to obtain the multiple order groups.

Optionally, the scheduling module includes: a first determining sub-module configured to determine, for each of the pending orders, the delivery capacity with the highest matching degree corresponding to the pending orders as the first determining sub-module. Dispatch the target delivery capacity corresponding to the order; the allocation sub-module is configured to allocate each of the pending orders to the corresponding target delivery capacity.

Optionally, the scheduling module includes: a second determining sub-module configured to deliver capacity for each target, and when there are more than two orders to be dispatched corresponding to the target distribution capacity, the The pending order with the highest matching degree corresponding to the target delivery capacity is determined as the target order corresponding to the target delivery capacity; in the case that there is one pending order corresponding to the target delivery capacity, the pending order is determined as the The target order corresponding to the target delivery capacity; the allocation sub-module is configured to allocate each of the target orders to the corresponding target delivery capacity.

Optionally, the device is further configured to target delivery capacity for each target, and if there are two or more orders to be dispatched with the highest matching degree corresponding to the target delivery capacity, if the highest matching degree is If the task point information of each order to be dispatched is the same, then each order to be dispatched is regarded as the target order of the target delivery capacity; if the task point information of each order to be dispatched with the highest matching degree is different, then the order is different from each other. The to-be-dispatched order selects a to-be-dispatched order as the target order of the target delivery capacity.

Optionally, the device further includes: a third determining module configured to take orders other than the target order among the pending orders as the pending orders to be dispatched in the next time unit.

Optionally, the order information includes different types of task point information; the clustering module includes: a clustering sub-module configured to perform tasks of the same type according to each of the to-be-scheduled orders in the time unit Point information to cluster the pending orders.

Optionally, the first determining module is configured to: for each of the order groups, determine the delivery capacity whose current position is less than a preset distance from the starting position of each of the orders to be dispatched in the order group Is the delivery capacity corresponding to the order group.

Optionally, the second determining module includes: a third determining sub-module configured to determine, for each of the distribution capacity, according to the distribution information of the distribution capacity, to separately determine the distribution of each of the orders in the order group. The target parameter corresponding to the delivery capacity after the order to be dispatched is pre-allocated to the delivery capacity, and the size of the target parameter is used to distinguish the pros and cons of pre-allocating the order to be dispatched to each delivery capacity; according to the The target parameter corresponding to the delivery capacity and each of the orders to be dispatched determines the degree of matching between each of the orders to be dispatched and the delivery capacity.

According to a third aspect of the present disclosure, there is provided a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the steps of any of the methods described in the first aspect are implemented.

According to a fourth aspect of the present disclosure, there is provided an electronic device including: a memory on which a computer program is stored; and a processor configured to execute the computer program in the memory to implement the following steps: For the order information of each pending order within a time unit, cluster each pending order to obtain multiple order groups; respectively determine the delivery capacity corresponding to each of the order groups; for each of the order groups, according to The order information of each order to be dispatched in the order group and the distribution information of each delivery capacity corresponding to the order group determine each of the orders to be dispatched in the order group and each corresponding to the order group The degree of matching between the distribution capacity; according to each degree of matching, order scheduling is performed on each of the orders to be dispatched.

In the above technical solution, since each pending order is clustered in the present disclosure, when calculating the matching degree between the pending order and the delivery capacity, only the matching between the delivery capacity corresponding to its order group needs to be calculated Therefore, it can effectively reduce the amount of calculation required to calculate the matching degree, and during order scheduling, it can also perform partial scheduling for each order group. On the one hand, it effectively reduces the complexity of order scheduling, and on the other hand, it reduces the complexity of order scheduling. The amount of calculation during order scheduling improves the efficiency and accuracy of order scheduling. It has good real-time performance and fast speed. It can be applied to large-scale order scheduling tasks and meet the needs of instant delivery services. In addition, it can also be used within the time unit. The pending orders are processed in parallel to further improve the efficiency of order scheduling. Moreover, because the method provided by the present disclosure can greatly reduce the amount of data access and the calculation of the algorithm, and reduce the requirements for memory and computing resources when implementing the method, it can also effectively broaden the order scheduling method provided by the present disclosure. The scope of application.

Other features and advantages of the present disclosure will be described in detail in the following specific embodiments.

Description of the drawings

The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure, but do not constitute a limitation to the present disclosure. In the attached picture:

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

FIG. 2 is a flowchart of an exemplary embodiment of order scheduling for orders to be scheduled according to the matching degree;

Fig. 3 is a block diagram of an order scheduling device according to an embodiment of the present disclosure;

Fig. 4 is a block diagram showing an electronic device according to an exemplary embodiment;

Fig. 5 is a block diagram showing an electronic device according to an exemplary embodiment;

Fig. 6 is a schematic diagram showing an implementation environment according to an exemplary embodiment.

Detailed ways

The specific embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present disclosure, and are not used to limit the present disclosure.

In related technologies, take the takeaway scenario as an example, and order scheduling is usually carried out in a geographical dimension. For example, every minute all new orders are matched with dispatchers in the area in real time through a scheduling algorithm. However, considering the system stability requirements, the matching calculation process requirements usually need to be completed in a relatively short time. Since the matching of multiple orders and multiple distributors is a global optimization, there may be coupling between each matching relationship. Therefore, through the above method, the amount of calculation required for order scheduling is too large and time-consuming.

Fig. 1 shows a flowchart of an order scheduling method according to an embodiment of the present disclosure. As shown in Figure 1, the method may include:

In S11, cluster each pending order according to the order information of each pending order within a time unit to obtain multiple order groups.

Wherein, the order information includes starting position information and destination position information corresponding to the order to be dispatched. Optionally, the starting location information is the initial location corresponding to the order to be dispatched. Take a takeaway scenario as an example. The starting location information is the location of the merchant who made the items in the order, and the destination location information is the expected delivery of the order. s position. In the car reservation scenario, the starting location information is the user's pick-up location corresponding to the order, and the destination location information is the user's drop-off location corresponding to the order. Optionally, the starting location information and the destination location information respectively indicate one or more locations. For example, in a takeaway scenario, one order corresponds to multiple stores, that is, the user may purchase items from multiple stores in one order At this time, you need to go to each store to obtain the corresponding items, so as to deliver the prepared items to the destination location. In this case, there are multiple locations indicated by the starting location information, that is, corresponding to each store’s Location.

Among them, the duration of the time unit can be set according to actual usage scenarios. For example, for scenarios with higher real-time requirements, the duration is set to be shorter, and for scenarios with lower real-time requirements, the duration is set to be longer. In another example, different time lengths are set according to different time periods. Take a takeaway scenario as an example, the time length set during the evening peak period is shorter, and the time length set for other time periods is slightly longer. The above are only exemplary descriptions, and the present disclosure does not limit this.

In S12, the delivery capacity corresponding to each order group is determined respectively. Optionally, the delivery capacity includes one or more of delivery personnel, delivery robots, and unmanned vehicles. The distribution capacity corresponding to the determined order group is the distribution capacity used to distribute the pending orders in the order group.

Among them, the distribution capacity refers to the manpower or material resources that can carry out the distribution.

In S13, for each order group, according to the order information of each pending order in the order group and the distribution information of each delivery capacity corresponding to the order group, it is determined that each pending order in the order group corresponds to the order group The matching degree between the various distribution capacity of. For example, the distribution information of the distribution capacity is the current location of the distribution capacity, the information of the orders currently to be distributed by the distribution capacity, and so on. Among them, the matching degree between the order to be delivered and the delivery capacity is used to characterize the pros and cons of the order to be dispatched by the delivery capacity. Wherein, the greater the matching degree, the better the delivery capacity to deliver the pending order.

Optionally, the pros and cons of the delivery capacity of the pending order refers to the possibility that the delivery capacity will deliver the order in a timely manner, where the better the delivery capacity is to deliver the pending order, the delivery capacity will deliver the order in time The higher the probability, the worse the delivery capacity to deliver the pending order, and the lower the probability that the delivery capacity will complete the order in time.

Among them, after clustering each order to be dispatched, the orders to be dispatched in each order group and the corresponding delivery capacity of the order group can be separately dispatched, so that when calculating the matching degree between the order to be dispatched and the delivery capacity, It only needs to be calculated separately for each order group, and there is no need to match the current pending orders with the corresponding delivery capacity of other order groups, which can effectively reduce the amount of calculation required for order scheduling.

It should be noted that in the above step S13, each order group is processed in parallel, or each order group is processed in sequence, or each time the target quantity of order groups is processed in parallel, and then the remaining target quantity is processed in parallel. The order group is processed, and so on, the embodiment of the present disclosure does not limit the processing manner of each order group.

In S14, order scheduling is performed on each pending order according to each matching degree.

Among them, it can be seen from the above that the matching degree corresponding to each order to be dispatched only includes the matching degree between it and the delivery capacity corresponding to the order group to which the order to be dispatched belongs. Therefore, when order scheduling is performed, it can be targeted for each order group. Dispatch separately.

Since each pending order is clustered in the present disclosure, when calculating the matching degree between the pending order and the delivery capacity, only the matching degree between the delivery capacity corresponding to its order group needs to be calculated, which can effectively reduce The amount of calculation required to calculate the matching degree, and when performing order scheduling, it can also perform partial scheduling for each order group. On the one hand, it effectively reduces the complexity of order scheduling, on the other hand, it also reduces the calculation during order scheduling. In order to improve the efficiency and accuracy of order scheduling, the real-time performance is good, the speed is fast, and it can be applied to large-scale order scheduling tasks, and can meet the needs of instant delivery services. In addition, it can also be used for pending orders in the time unit. Parallel processing can further improve the efficiency of order scheduling. Moreover, because the method provided by the present disclosure can greatly reduce the amount of data access and the calculation of the algorithm, and reduce the requirements for memory and computing resources when implementing the method, it can also effectively broaden the order scheduling method provided by the present disclosure. The scope of application.

In order to enable those skilled in the art to better understand the technical solutions provided by the embodiments of the present disclosure, the above steps are further described below.

Optionally, the order information includes different types of task point information. For example, it includes the task point information of the starting type, such as the locations of multiple merchants in the same order in the example described above, and optionally, it also includes the task point information of the destination type, such as the order corresponding to the example described above The user’s drop-off location, etc. For example, take a takeaway order as an example, each order information includes the initial type of task point information, such as the location of the merchant making the takeaway corresponding to the takeaway order (ie the pickup location); it also includes the purpose type of task point information, The user who ordered the takeout expects the delivery location (that is, the delivery location) of the takeout.

The exemplary embodiment of clustering the to-be-dispatched orders according to the order information of the to-be-dispatched orders in a time unit is as follows, including:

Clustering the to-be-scheduled orders according to the task point information of the same type of the to-be-scheduled orders in the time unit.

Take the takeaway scenario as an example. In one embodiment, clustering is performed according to the starting position of each order to be scheduled. Therefore, the starting positions of the orders to be scheduled in the same cluster obtained are similar, so as to be able to group as much as possible. The pending orders corresponding to the merchants in the business district are clustered. In another embodiment, clustering can be performed according to the destination positions of the orders to be scheduled, so that the destination positions of the orders to be scheduled in the same cluster obtained are similar, so that users belonging to similar cells or communities can be assigned to the corresponding to-be-scheduled orders Orders are clustered.

Therefore, through the above technical solution, the to-be-scheduled orders are clustered according to the task point information of the same type of each to-be-scheduled order in a time unit, so that the to-be-scheduled orders with similar starting positions or similar destination positions can be clustered To the same order group. Therefore, by clustering orders to be dispatched, orders to be dispatched that are close to each other can be grouped into the same order group, while orders to be dispatched in different order groups are far apart, so there is no need to consider different order groups when scheduling orders. The influence between the orders to be dispatched realizes the independent order dispatching of each order group, and can effectively reduce the amount of data calculation in the order dispatching process.

Optionally, in another embodiment, after the clustering operation, for an order group in which the number of orders to be scheduled exceeds a preset threshold, the order group is split into multiple order groups, where the splitting The number of orders to be dispatched in each order group obtained is less than the preset threshold. Optionally, the preset threshold is set according to actual usage scenarios, which is not limited in the present disclosure.

For example, after the clustering operation, N clusters will be obtained. After that, determine the number of pending orders in each cluster. If the number of pending orders in one of the clusters (denoted as cluster C) exceeds the preset threshold, cluster C is split at this time. Optionally, the distance threshold is further adjusted to perform re-clustering according to the order information of the pending orders in cluster C. For example, during the initial clustering, cluster any two orders to be scheduled whose starting position is less than M1, and when splitting cluster C, set the starting position of cluster C to any two orders whose starting position is less than M2. Clustering of orders to be dispatched, where M2 is less than M1.

For example, the K-Means (K-means clustering) algorithm is used for re-clustering during splitting, where K is any integer greater than or equal to 1, for example, the value of K is based on the number of orders to be scheduled in cluster C and the The preset threshold is determined. For example, if the number of orders to be scheduled in cluster C is Q, and the preset threshold is P, then the value of K is greater than the ratio of Q to P, so as to avoid sub-clusters after splitting as much as possible The number of pending orders is greater than the preset threshold.

That is to say, for an order group whose number of orders to be dispatched exceeds a preset threshold, the number of cluster centers (K) is determined according to the number of orders to be dispatched in the order group and the number of the preset threshold. According to the K clusters The center re-clusters the order group to obtain K clusters, that is, re-divides the order group into K order groups.

Optionally, the above-mentioned K-Means algorithm can not only be applied to the process of re-dividing order groups, but also can be applied to the process of dividing each pending order within a time unit into multiple order groups. In an embodiment, clustering the scheduled orders according to the order information of each pending order in a time unit to obtain multiple order groups includes: determining the number of cluster centers according to the number of each pending order and a preset threshold ;According to the number of cluster centers and the order information of each pending order, the scheduled orders are clustered to obtain multiple order groups.

In another embodiment, if there is a sub-cluster whose number of orders to be scheduled exceeds a preset threshold in the sub-cluster after splitting, the sub-cluster is further split until the sub-cluster obtained by splitting cluster C The data of the orders to be dispatched is less than the preset threshold, that is, the number of orders to be dispatched in each order group obtained by splitting is less than the preset threshold. Among them, the method of splitting the sub-clusters is similar to the above, and will not be repeated here.

Through the above technical solution, it can be ensured that each order group contains a small number of pending orders, thereby further reducing the computing resources consumed in subsequent calculations of the matching degree between pending orders and delivery capacity. And to a certain extent, it can also ensure that the number of orders to be allocated in each order group is relatively uniform, ensuring high concurrency in order scheduling while also ensuring the consistency of processing efficiency, thereby ensuring the accuracy of order scheduling.

Optionally, in S12, an exemplary embodiment of separately determining the delivery capacity corresponding to each order group is as follows, this step may include:

For each of the order groups, the delivery capacity whose current position is less than the preset distance from the starting position of each pending order in the order group is determined as the delivery capacity corresponding to the order group.

For example, when allocating delivery capacity for orders to be dispatched, in order to reduce the ineffective movement of delivery capacity, that is, to avoid excessively long travel between the movement of the delivery capacity from its current position to the starting position of the order to be dispatched, in this embodiment , When determining the delivery capacity corresponding to the order group, the delivery capacity that is closer to the initial position of the order to be dispatched will be preferentially selected.

As an example, for each order group, the starting position of each order to be dispatched in the order group is determined. Optionally, the starting position is determined according to the order information of the order to be dispatched. If there are multiple positions indicated by the starting position information corresponding to the order to be dispatched, the first position on the path corresponding to the order to be dispatched among the positions indicated by the starting position information is used as the starting position. If the position indicated by the starting position information corresponding to the to-be-dispatched order is one, the position is directly used as the starting position.

For example, if there are multiple locations indicated by the starting location information corresponding to the order to be dispatched, the multiple locations indicated by the starting location information are connected according to the shortest path rule to obtain the driving route, and the first The first position or the last position is used as the starting position.

In an embodiment, for each order to be dispatched, the distance between the order to be dispatched and each delivery capacity is determined according to the initial position of the order to be dispatched and the current position of each delivery capacity, and the distance is less than the preset distance The distribution capacity of is used as the distribution capacity to be allocated. Optionally, calculating the distance between two location points is to determine two locations in the map, obtain at least one driving path between the two locations, determine the shortest driving path in the at least one driving path, and set the shortest The length of the driving path is determined as the distance between two location points.

In another embodiment, for each order to be dispatched, a position range within a preset distance range centered on the order to be dispatched is determined, and the delivery capacity whose current position belongs to the position range is determined as the delivery capacity to be allocated. Wherein, determining a position range centered on the order to be dispatched within a preset distance range refers to determining a position range centered on the order to be dispatched and the distance from the center does not exceed the preset distance. Optionally, determining the position range according to the position and distance of the center point is to determine a circular area with the order to be dispatched as the center and the preset distance range as the radius. Subsequently, the delivery capacity whose current location belongs to the circular area is determined as the delivery capacity to be allocated.

Therefore, the distribution capacity to be allocated determined according to each pending order in the order group is taken as the distribution capacity corresponding to the order group.

Through the above technical solution, when determining the distribution capacity corresponding to the order group, the distribution capacity whose current position is less than the preset distance from the starting position of each pending order in the order group is determined as the distribution capacity corresponding to the order group Distribution capacity, on the one hand, can ensure that the distribution capacity reaches the initial position of the pending order in a timely manner, thereby improving the efficiency of order distribution. On the other hand, it can avoid excessive invalid movement of the distribution capacity, thereby saving the resources consumed by the distribution capacity to reach the initial position of the pending order, and improving the rationality and comprehensiveness of the order scheduling method.

Optionally, in S13, according to the order information of each pending order in the order group and the distribution information of each delivery capacity corresponding to the order group, it is determined that each pending order in the order group corresponds to the order group. An exemplary embodiment of the degree of matching between various distribution capacities is as follows, and this step includes:

For each of the distribution capacity, according to the distribution information of the distribution capacity, respectively determine the target parameter corresponding to the distribution capacity after each pending order in the order group is pre-allocated to the distribution capacity, and the size of the target parameter Used to distinguish the pros and cons of pre-allocating the pending order to each distribution capacity;

The degree of matching between each order to be dispatched and the delivery capacity is determined according to the target parameter corresponding to the delivery capacity and each order to be dispatched.

For example, the target parameter is determined by the increase in the distribution itinerary corresponding to the distribution capacity after the order to be dispatched is pre-allocated to the distribution capacity. For example, the increase in the distribution itinerary is used to determine the degree of matching between the order to be dispatched and the distribution capacity. . For example, after allocating order X to the distribution capacity, its distribution itinerary increases by a large amount, which means that after the distribution capacity is increased to deliver the order X, it needs to increase more itineraries to complete the distribution. For example, the distribution capacity needs to be bypassed. The order X is delivered by route, that is, the matching degree between the pending order and the delivery capacity is low. After allocating order X to the distribution capacity, the increase in the distribution itinerary is small, which means that after the distribution capacity is increased to distribute the order X, it only needs to add a small amount of itinerary to complete the distribution, if the distribution capacity can be delivered along the way The order X, that is, the order to be dispatched has a higher degree of matching with the delivery capacity.

For example, the following describes an exemplary embodiment of the increase in the distribution journey corresponding to the distribution capacity after each pending order in the order group is pre-allocated to the distribution capacity according to the distribution information of the distribution capacity. .

If the distribution order X is added to the distribution capacity, the order distribution path is planned according to the assigned order of the distribution capacity and the order X, so as to distribute each order assigned and distributed. In one embodiment, when determining the order delivery route, the search is performed according to the order information (for example, the starting location information and the destination location information) of each order allocated by the delivery capacity, that is, according to the order information of each order , Traverse all the order connection sequence and obtain the total path in each alternative scheme, and use the shortest path as the order delivery path. The difference between the order delivery path and the order delivery path before the unallocated order X is determined as the delivery itinerary increase, that is, the order delivery path change after the order X is pre-allocated for the delivery capacity.

In another embodiment, after the order X is pre-allocated for the delivery capacity, for the delivery capacity, according to the greedy algorithm and the set constraints, with the goal of maximizing the order delivery efficiency, insert into the delivery path of the order For the task point information of each order, the trial planning path corresponding to the distribution capacity is obtained, wherein the constraint condition is related to the set of each task point. Then, according to the planned arrival time corresponding to each task point information and the estimated arrival time corresponding to each task point information determined based on the trial planning route, the trial planning route is adjusted to obtain the order delivery route corresponding to the delivery capacity. Similarly, after the order delivery path is determined, the difference between the order delivery path and the order delivery path before the unallocated order X is determined as the delivery itinerary increase.

Optionally, after determining the delivery itinerary growth amount, take the reciprocal of the delivery itinerary growth amount and perform normalization processing, so as to obtain the degree of matching between the pending order and the delivery capacity, where the delivery itinerary The smaller the increase, the corresponding target parameter indicates that the pre-allocation of the pending order to the distribution capacity is the better, that is, the greater the matching degree between the pending order and the distribution capacity. Among them, the above method of determining the matching degree is only an exemplary description, and is only used to indicate the negative correlation between the growth of the delivery itinerary and the matching degree, that is, the greater the growth of the delivery itinerary, the greater the relationship between the corresponding pending order and the delivery capacity The smaller the matching degree of is not used to limit the present disclosure.

As another example, the target parameter is determined by the timeout period corresponding to the order to be delivered for the delivery capacity after the order to be dispatched is pre-allocated to the delivery capacity. As in the above example, after it is determined that the order X is allocated to the order delivery route corresponding to the delivery capacity, the delivery time corresponding to each order in the order delivery route is determined. After that, the sum of the time periods in which the delivery time of each order is later than the planned arrival time of the corresponding order is determined as the timeout time corresponding to the pending order of the delivery capacity. Wherein, the shorter the timeout period, the corresponding target parameter indicates that the pre-allocation of the pending order to the distribution capacity is the better, that is, the greater the degree of matching between the pending order and the distribution capacity. Optionally, the method for determining the matching degree according to the timeout period is the same as the above-mentioned method for determining the matching degree. For example, taking the inverse of the timeout period and performing normalization to obtain the matching degree, the relationship between the timeout period and the matching degree is negatively correlated , That is, the longer the timeout period, the smaller the matching degree between the corresponding pending order and the delivery capacity.

As another example, after the target parameter is pre-allocated to the delivery capacity through the order to be dispatched, the delivery itinerary increase corresponding to the delivery capacity and the order to be dispatched to the delivery capacity after the order to be dispatched is pre-allocated to the delivery capacity. The corresponding timeout period is determined. For example, the weights corresponding to the timeout time and the delivery itinerary increase are set in advance, so that when the time-out time and the delivery itinerary increase are determined, the weighted sum is determined according to the respective weights as the target parameter, and the matching degree is determined according to the target parameter. Optionally, the matching degree is also determined by taking the reciprocal of the weighted sum and performing normalization. In this embodiment, the smaller the target parameter, the better the pre-allocation of the pending order to the distribution capacity, that is, the greater the degree of matching between the pending order and the distribution capacity.

It should be noted that the method of determining the matching degree according to the target parameters in the above examples is only exemplary, and it is only used to indicate that the determined target parameter and the matching degree are negatively correlated, that is, the larger the target parameter, the corresponding The smaller the matching degree between the order to be dispatched and the delivery capacity is, it is not used to limit the present disclosure.

In the above technical solution, the target parameters corresponding to the distribution capacity after each pending order in the order group is pre-allocated to the distribution capacity are determined according to the distribution information of the distribution capacity for each of the distribution capacity. ; Determine the degree of matching between each order to be dispatched and the delivery capacity according to the target parameter corresponding to the delivery capacity and each order to be dispatched. Therefore, in the above technical solution, it is possible to pre-allocate orders for the distribution capacity, and determine the matching degree between the pending order and the distribution capacity according to the parameter change of the distribution capacity after the order is allocated, so that the parameter change can be used to determine the matching degree between the order to be dispatched and the distribution capacity. The delivery capacity of the delivery of the order is quantitatively expressed, which provides accurate data support for subsequent order scheduling based on the matching degree, and can ensure the rationality of order scheduling and meet the use requirements of order scheduling services.

Optionally, in S14, according to the matching degree, an exemplary embodiment of order scheduling for the order to be scheduled is as follows, as shown in FIG. 2, this step may include:

In S21, for each order to be dispatched, the delivery capacity with the highest matching degree corresponding to the order to be dispatched is determined as the target delivery capacity corresponding to the order to be dispatched.

Among them, the method of determining the matching degree has been described in detail above, and will not be repeated here. In this step, the delivery capacity with the highest matching degree corresponding to the pending order is determined as the target delivery capacity corresponding to the pending order, that is, the optimal delivery capacity of the scheduled order is first used to deliver the pending order Order.

For each target delivery capacity, if there are more than two orders to be dispatched corresponding to the target delivery capacity, execute S22, and if there is one order to be dispatched corresponding to the target delivery capacity, execute S23;

In S22, the pending order with the highest matching degree corresponding to the target delivery capacity is determined as the target order corresponding to the target delivery capacity;

In S23, the pending order is determined as the target order corresponding to the target delivery capacity.

For example, for an order group, the corresponding delivery capacity is A1, A2, A3, and the pending orders are C1, C2, C3, C4, C5. In S21, the target delivery capacity corresponding to C1 is determined to be A2, The determined target distribution capacity corresponding to C2 is A1, the determined target distribution capacity corresponding to C3 is A1, the determined target distribution capacity corresponding to C4 is A1, and the determined target distribution capacity corresponding to C5 is A3.

Therefore, for the target delivery capacity A1, the corresponding pending orders are C2, C3, C4. In this case, one of the multiple pending orders is selected as the target delivery capacity A1 in this scheduling process. The target order is the order for A1 to deliver. For example, the order to be dispatched with the highest matching degree corresponding to the target delivery capacity is determined as the target order corresponding to the target delivery capacity. If the matching degree between C3 and A1 is higher than the matching degree between C2 and A1, and the matching degree between C3 and A1 is higher than the matching degree between C4 and A1, then C3 is taken as the target order of A1. At this time, C2 and C3 did not perform scheduling allocation in this order scheduling.

For the target delivery capacity A2, the corresponding pending order is C1. At this time, C1 is directly used as the target order of A2. Similarly, take C5 as the target order for A3.

The method of determining the target order in other order groups adopts the same method as described above, and will not be repeated here. As a result, each order group can be determined separately, and high concurrency in the calculation of the order delivery method can also be ensured, and the efficiency of order scheduling can be effectively improved.

Optionally, if the matching degrees of the multiple pending orders corresponding to the target delivery capacity are the same and all have the highest value, it is determined whether the task point information of the multiple pending orders is the same, if the tasks of the multiple pending orders If the point information is the same, then the multiple pending orders will be regarded as the target order of the target delivery capacity; if the multiple pending orders have different task point information, then a pending order will be randomly selected from the multiple pending orders as the target Target order for delivery capacity.

For example, for the target distribution capacity A1, the corresponding pending orders are C2, C3, and C4, where the matching degree between C2 and A1 and the matching degree between C3 and A1 are higher than the matching degree between C4 and A1, and the matching degree between C2 and A1 is higher than that between C4 and A1. The matching degree of A1 is the same as the matching degree of C3 and A1, then C2 and C3 are taken as the target orders of A1. Optionally, C2 and C3 may be orders generated by two users in the same office building to purchase items at the same merchant. In this way, the starting positions and destination positions of C2 and C3 are the same, and the corresponding matching degrees are also the same.

In S24, each target order is assigned to its corresponding target delivery capacity.

As in the above example, each target order in the to-be-dispatched order is determined, so that each target order can be assigned to its corresponding target delivery capacity. For example, assign target order C3 to target delivery capacity A1, target order C1 to target delivery capacity A2, and target order C5 to target delivery capacity A3 to complete this order scheduling.

For example, assigning each target order to its corresponding target delivery capacity is to add the order information of the target order to the delivery information of the target delivery capacity, that is, the target order is regarded as the order to be delivered for the target delivery capacity.

In the above technical solution, by determining the distribution capacity that best matches the order to be dispatched, when the distribution capacity overlaps, the distribution capacity is assigned the most suitable order to be dispatched, so as to ensure that in this scheduling, the For the dispatched order, the distribution capacity assigned to it is the most suitable, and for the distribution capacity of each assigned order, the assigned order is also the most suitable, so as to ensure the accuracy of the order scheduling, which is the follow-up The fast delivery of orders provides the basis, and can simplify the complexity of global order scheduling and improve the efficiency of order scheduling.

As in the above example, in one order scheduling, when multiple orders to be scheduled correspond to the same target delivery capacity, only one of the target delivery capacity can be selected as the target order for delivery. Therefore, the orders to be dispatched may not be able to be dispatched all through one order dispatch. For example, the pending orders C2 and C3 in the above example, that is, no scheduling allocation is performed in this order scheduling. Therefore, the present disclosure also provides the following embodiments to ensure that each pending order can be scheduled, thereby ensuring user experience.

Among them, the target order is the order scheduled during the order scheduling process of this time unit. Therefore, for the orders that are not scheduled during the order scheduling process of this time unit (that is, orders other than the target order among the pending orders) ), the partial order is regarded as the to-be-dispatched order to be scheduled in the next time unit, so that the partial order can be scheduled in the subsequent scheduling process.

It should be noted that, in addition to the above-mentioned orders, the pending orders to be scheduled in the next time unit also include the newly created orders to be scheduled during the scheduling process of the current time unit, such as those in the current time unit. During the order scheduling process, a new order created by the user.

For example, when performing order scheduling in the next time unit, that is, according to the pending orders to be scheduled in the next time unit, the steps S11-S14 are re-executed, thereby realizing real-time scheduling of pending orders and improving scheduling efficiency. The implementation of the steps S11-S14 has been described in detail above, and will not be repeated here.

Therefore, through the above technical solution, orders that are not scheduled during the scheduling process of the current time unit are scheduled, so as to ensure that all pending orders can be scheduled, improve the accuracy and efficiency of order scheduling, and meet the use of immediate order scheduling services. Needs to improve user experience.

The present disclosure also provides an order scheduling device. As shown in FIG. 3, the device 300 includes: a clustering module 301 configured to perform an order for each pending order within a time unit. Orders are dispatched for clustering to obtain multiple order groups; the first determining module 302 is configured to determine the delivery capacity corresponding to each of the order groups; the second determining module 303 is configured to target each order group. According to the order group, according to the order information of each order to be dispatched in the order group and the distribution information of each delivery capacity corresponding to the order group, determine each order to be dispatched in the order group and each delivery capacity corresponding to the order group The degree of matching between each; the scheduling module 304 is configured to perform order scheduling on each of the pending orders according to each of the degrees of matching.

Optionally, the clustering module includes: a splitting sub-module configured to split the order group into multiple order groups for an order group in which the number of orders to be scheduled exceeds a preset threshold, wherein the splitting The number of orders to be dispatched in each of the divided order groups is less than the preset threshold.

Optionally, the scheduling module includes: a first determining sub-module configured to determine, for each of the pending orders, the delivery capacity with the highest matching degree corresponding to the pending orders as the first determining sub-module that corresponds to the pending orders Corresponding target delivery capacity; an allocation sub-module configured to allocate each of the pending orders to the corresponding target delivery capacity.

Optionally, the scheduling module includes: a second determining sub-module configured to deliver capacity for each target. In the case that there are more than two orders to be dispatched corresponding to the target distribution capacity, it will be delivered to the target. The order to be dispatched with the highest matching degree corresponding to the capacity is determined as the target order corresponding to the target delivery capacity; if there is one order to be dispatched corresponding to the target delivery capacity, the order to be dispatched is determined as the target order corresponding to the target delivery capacity Target orders; an allocation sub-module configured to allocate each of the target orders to their corresponding target delivery capacity.

Optionally, the order information includes different types of task point information; the clustering module includes:

The clustering sub-module is configured to cluster the to-be-scheduled orders according to the task point information of the same type of the to-be-scheduled orders in the time unit.

Optionally, the first determining module is configured to: for each of the order groups, determine the delivery capacity whose current position is less than a preset distance from the starting position of each order to be dispatched in the order group as the The delivery capacity corresponding to the order group.

Optionally, the second determining module includes: a third determining sub-module configured to determine, for each of the distribution capacity, according to the distribution information of the distribution capacity, each pending order in the order group After being pre-allocated to the distribution capacity, the target parameter corresponding to the distribution capacity, the size of the target parameter is used to distinguish the pros and cons of pre-allocating the pending order to each distribution capacity; the fourth determining sub-module is configured to It is used to determine the matching degree between each order to be dispatched and the distribution capacity according to the target parameter corresponding to the distribution capacity and each order to be dispatched.

Regarding the device in the foregoing embodiment, the manner in which each module performs operation has been described in the embodiment of the method, and will not be elaborated here.

Fig. 4 is a block diagram showing an electronic device 400 according to an exemplary embodiment. As shown in FIG. 4, the electronic device 400 includes a processor 401 and a memory 402. Optionally, the electronic device 400 further includes one or more of a multimedia component 403, an input/output (I/O) interface 404, and a communication component 405.

The processor 401 is used to control the overall operation of the electronic device 400 to complete all or part of the steps in the above-mentioned order scheduling method. The memory 402 is used to store various types of data to support the operation of the electronic device 400. The data includes, for example, instructions for any application or method to operate on the electronic device 400, and application-related data, such as Contact data, messages sent and received, pictures, audio, video, etc. Optionally, the memory 402 is implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, SRAM for short), electrically erasable and programmable memory devices. Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM) , Read-Only Memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 403 may include a screen and an audio component. The screen is, for example, a touch screen, and the audio component is used to output and/or input audio signals. For example, the audio component includes a microphone, which is used to receive external audio signals. Optionally, the received audio signal is further stored in the memory 402 or sent through the communication component 405. The audio component also includes at least one speaker for outputting audio signals. The I/O interface 404 provides an interface between the processor 401 and other interface modules. The above-mentioned other interface modules may be a keyboard, a mouse, a button, and the like. Optionally, these buttons are virtual buttons or physical buttons. The communication component 405 is used for wired or wireless communication between the electronic device 400 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or one or more of them The combination is not limited here. Therefore, the corresponding communication component 405 includes: a Wi-Fi module, a Bluetooth module, an NFC module, and so on.

In an exemplary embodiment, the electronic device 400 is controlled by one or more application specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), digital signal processor (Digital Signal Processor, DSP for short), and digital signal processing equipment (Digital Signal Processing Device). Processing Device, referred to as DSPD), programmable logic device (Programmable Logic Device, referred to as PLD), field programmable gate array (Field Programmable Gate Array, referred to as FPGA), controller, microcontroller, microprocessor or other electronic components , Used to execute the above order scheduling method.

In another exemplary embodiment, there is also provided a computer-readable storage medium including program instructions that, when executed by a processor, implement the steps of the above-mentioned order scheduling method. For example, the computer-readable storage medium is the aforementioned memory 402 including program instructions, and the aforementioned program instructions can be executed by the processor 401 of the electronic device 400 to complete the aforementioned order scheduling method.

Fig. 5 is a block diagram showing an electronic device 500 according to an exemplary embodiment. For example, the electronic device 500 is provided as a server. 5, the electronic device 500 includes a processor 522, the number of which may be one or more, and a memory 532 for storing a computer program executable by the processor 522. Optionally, the computer program stored in the memory 532 includes one or more modules each corresponding to a set of instructions. In addition, the processor 522 is configured to execute the computer program to execute the aforementioned order scheduling method.

Optionally, the electronic device 500 further includes a power supply component 526 and a communication component 550, the power supply component 526 is configured to perform power management of the electronic device 500, and the communication component 550 is configured to implement the communication of the electronic device 500, for example, wired or Wireless communication. Optionally, the electronic device 500 further includes an input/output (I/O) interface 558. Optionally, the operation of the electronic device 500 is based on an operating system stored in the memory 532, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, and so on.

In another exemplary embodiment, there is also provided a computer-readable storage medium including program instructions that, when executed by a processor, implement the steps of the above-mentioned order scheduling method. For example, the computer-readable storage medium may be the aforementioned memory 532 including program instructions, and the aforementioned program instructions may be executed by the processor 522 of the electronic device 500 to complete the aforementioned order scheduling method.

In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the following steps are implemented: According to the order information of each pending order in a time unit, Each pending order is clustered to obtain multiple order groups; the distribution capacity corresponding to each order group is determined respectively; for each order group, according to the order information of each pending order in the order group and the distribution capacity corresponding to the order group To determine the matching degree between each pending order in the order group and each distribution capacity corresponding to the order group; according to each matching degree, order scheduling is performed on each pending order.

In an exemplary embodiment, when the program is executed by the processor, the following steps are further implemented: for an order group in which the number of orders to be dispatched exceeds a preset threshold, the order group is split into multiple order groups, where the split The number of orders to be dispatched in each order group is less than the preset threshold.

In an exemplary embodiment, when the program is executed by the processor, the following steps are implemented: determine the number of cluster centers according to the number of orders to be dispatched and a preset threshold; according to the number of cluster centers, and the orders of each order to be dispatched The information is clustered on the orders to be dispatched, and multiple order groups are obtained.

In an exemplary embodiment, when the program is executed by the processor, the following steps are implemented: for each order to be dispatched, the delivery capacity with the highest matching degree corresponding to the order to be dispatched is determined as the target delivery capacity corresponding to the order to be dispatched; Assign each pending order to the corresponding target delivery capacity.

In an exemplary embodiment, when the program is executed by the processor, the following steps are also implemented: for each target delivery capacity, if there are more than two orders to be dispatched corresponding to the target delivery capacity, the order corresponding to the target delivery capacity will be The pending order with the highest matching degree is determined as the target order corresponding to the target delivery capacity; when there is one pending order corresponding to the target delivery capacity, the pending order is determined as the target order corresponding to the target delivery capacity; Dispatching orders to the corresponding target distribution capacity includes: assigning each target order to its corresponding target distribution capacity.

In an exemplary embodiment, when the program is executed by the processor, the following steps are further implemented: taking orders other than the target order among the pending orders as the pending orders to be dispatched in the next time unit.

In an exemplary embodiment, the order information includes different types of task point information; when the program is executed by the processor, the following steps are implemented: according to the same type of task point information of each pending order in a time unit, the pending orders are gathered kind.

In an exemplary embodiment, when the program is executed by the processor, the following steps are implemented: For each order group, determine the delivery capacity whose current position and the starting position of each pending order in the order group are less than the preset distance The distribution capacity corresponding to the order group.

In an exemplary embodiment, when the program is executed by the processor, the following steps are implemented: for each distribution capacity, according to the distribution information of the distribution capacity, it is determined to pre-allocate each pending order in the order group to the distribution capacity, and the distribution The target parameter corresponding to the capacity. The size of the target parameter is used to distinguish the pros and cons of pre-allocating the pending orders to each distribution capacity; according to the distribution capacity and the target parameters corresponding to each pending order, determine the difference between each pending order and the distribution capacity suitability.

In an exemplary embodiment, an electronic device is provided. The electronic device includes: a memory on which a computer program is stored; and a processor configured to execute the computer program in the memory to implement the following steps: The order information of each pending order in a time unit is clustered to obtain multiple order groups; the delivery capacity corresponding to each order group is determined respectively; for each order group, according to each pending order in the order group The order information of the dispatch order and the distribution information of each distribution capacity corresponding to the order group, determine the matching degree between each pending order in the order group and each distribution capacity corresponding to the order group; according to each matching degree, each pending order is determined Carry out order scheduling.

In an exemplary embodiment, the processor is further configured to execute a computer program in the memory to implement the following steps: for an order group in which the number of orders to be dispatched exceeds a preset threshold, the order group is split into Multiple order groups, where the number of orders to be dispatched in each of the split order groups is less than a preset threshold.

In an exemplary embodiment, the processor is configured to execute a computer program in the memory to implement the following steps: determine the number of cluster centers according to the number of orders to be dispatched and a preset threshold; The quantity and the order information of each pending order are clustered to obtain multiple order groups.

In an exemplary embodiment, the processor is further configured to execute a computer program in the memory to implement the following steps: for each pending order, the delivery capacity with the highest matching degree corresponding to the pending order is determined as The target delivery capacity corresponding to the order to be dispatched; each order to be dispatched is assigned to the corresponding target delivery capacity.

In an exemplary embodiment, the processor is further configured to execute a computer program in the memory to implement the following steps: for each target distribution capacity, in the case where there are more than two orders to be dispatched corresponding to the target distribution capacity Next, the order to be dispatched with the highest matching degree corresponding to the target delivery capacity is determined as the target order corresponding to the target delivery capacity; when there is one order to be dispatched corresponding to the target delivery capacity, the order to be dispatched is determined as the target delivery The target order corresponding to the capacity; the processor is configured to execute a computer program in the memory to implement the following steps: each target order is assigned to the corresponding target distribution capacity.

In an exemplary embodiment, the processor is further configured to execute a computer program in the memory to implement the following steps: take orders other than the target order among the orders to be scheduled as the orders to be scheduled in the next time unit Pending orders.

In an exemplary embodiment, the order information includes different types of task point information; the processor is configured to execute a computer program in the memory to implement the following steps: according to the same type of orders for each pending order in a time unit Task point information, clustering orders to be scheduled.

In an exemplary embodiment, the processor is configured to execute a computer program in the memory to implement the following steps: For each order group, compare the current position with the starting position of each pending order in the order group. The delivery capacity whose distance is less than the preset distance is determined as the delivery capacity corresponding to the order group.

In an exemplary embodiment, the processor is configured to execute a computer program in the memory to implement the following steps: for each distribution capacity, according to the distribution information of the distribution capacity, respectively determine the order group to be dispatched After the order is pre-allocated to the distribution capacity, the target parameter corresponding to the distribution capacity. The size of the target parameter is used to distinguish the pros and cons of pre-allocating the pending orders to each distribution capacity; each is determined according to the distribution capacity and the target parameters corresponding to each pending order The degree of matching between pending orders and delivery capacity.

In another exemplary embodiment, a computer program product is further provided, the computer program product includes a computer program that can be executed by a programmable device, and the computer program has a function for executing the foregoing when executed by the programmable device. The code part of the order scheduling method.

In an exemplary embodiment, a computer program product is provided. The computer program product includes a computer program that can be executed by a programmable device. When the computer program is executed by an electronic device, the following steps are implemented: Order information of orders to be dispatched, cluster each order to be dispatched to obtain multiple order groups; respectively determine the delivery capacity corresponding to each order group; for each order group, according to the order information of each order to be dispatched in the order group The distribution information of each distribution capacity corresponding to the order group determines the matching degree between each pending order in the order group and each distribution capacity corresponding to the order group; order scheduling is performed on each pending order according to each matching degree.

In an exemplary embodiment, when the computer level is executed by the electronic device, the following steps are further implemented: for an order group in which the number of orders to be dispatched exceeds a preset threshold, the order group is split into multiple order groups, where The number of orders to be dispatched in each of the divided order groups is less than the preset threshold.

In an exemplary embodiment, when the computer level is executed by an electronic device, the following steps are implemented: determine the number of cluster centers according to the number of orders to be dispatched and a preset threshold; according to the number of cluster centers, and the number of orders to be dispatched The order information clusters the orders to be scheduled to obtain multiple order groups.

In an exemplary embodiment, when the computer level is executed by an electronic device, the following steps are implemented: for each pending order, the delivery capacity with the highest matching degree corresponding to the pending order is determined as the target delivery capacity corresponding to the pending order ; Assign each pending order to the corresponding target distribution capacity.

In an exemplary embodiment, when the computer level is executed by the electronic device, the following steps are also implemented: For each target delivery capacity, if there are more than two orders to be dispatched corresponding to the target delivery capacity, it will correspond to the target delivery capacity. The pending order with the highest matching degree is determined as the target order corresponding to the target delivery capacity; in the case of one pending order corresponding to the target delivery capacity, the pending order is determined as the target order corresponding to the target delivery capacity; The allocation of pending orders to the corresponding target delivery capacity includes: allocating each target order to its corresponding target delivery capacity.

In an exemplary embodiment, when the computer level is executed by the electronic device, the following step is further implemented: taking orders other than the target order among the orders to be dispatched as orders to be dispatched in the next time unit.

In an exemplary embodiment, the order information includes different types of task point information; when the computer level is executed by the electronic device, the following steps are implemented: according to the same type of task point information of each pending order in a time unit, the pending order is processed Clustering.

In an exemplary embodiment, when the computer level is executed by the electronic device, the following steps are implemented: For each order group, the distance between the current position and the starting position of each pending order in the order group is smaller than the delivery capacity of the preset distance Determine the delivery capacity corresponding to the order group.

In an exemplary embodiment, when the computer level is executed by the electronic device, the following steps are implemented: for each distribution capacity, according to the distribution information of the distribution capacity, respectively determine to pre-allocate each pending order in the order group to the distribution capacity, The target parameter corresponding to the distribution capacity, the size of the target parameter is used to distinguish the pros and cons of pre-allocating the pending orders to each distribution capacity; according to the distribution capacity and the target parameters corresponding to each pending order, determine the difference between each pending order and the distribution capacity The degree of match.

Fig. 6 is a schematic diagram showing an implementation environment according to an exemplary embodiment. As shown in Fig. 6, the implementation environment includes a plurality of first terminals 601, a plurality of second terminals 602, and a server 603. The terminal 601 is directly or indirectly connected to the server 603 in a wired or wireless manner, and the multiple second terminals 602 are directly or indirectly connected to the server 603 in a wired or wireless manner, respectively.

Optionally, multiple first terminals 601 are installed with a first target application client, multiple second terminals 602 are installed with a second target application client, and the server 603 is for the first target application client and the second target application client. The server that provides services at the end. Among them, the first target application client is a client with a purchasing service function, for example, the first target application client is a shopping client, an instant messaging client, and so on. The second target application client is a client with a task distribution function, for example, a delivery client.

Optionally, multiple first terminals 601 upload multiple user orders to the server 602, and the server 602 performs order scheduling on the multiple orders, and distributes the delivery tasks of the multiple orders to multiple second terminals 602. The user using the second terminal 602 delivers the multiple orders.

The optional embodiments of the present disclosure are described in detail above with reference to the accompanying drawings. However, the present disclosure is not limited to the above-mentioned embodiments. Within the scope of the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure. These simple modifications All belong to the protection scope of the present disclosure.

In addition, it should be noted that the various technical features described in the foregoing embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, various possible combinations are not described separately in the present disclosure.

In addition, various different embodiments of the present disclosure can also be combined arbitrarily, as long as they do not violate the idea of the present disclosure, they should also be regarded as the content disclosed in the present disclosure.

Claims

An order scheduling method, the method includes:

Clustering each of the pending orders according to the order information of each pending order within a time unit to obtain multiple order groups;

Respectively determine the delivery capacity corresponding to each of the order groups;

For each of the order groups, determine each of the pending orders in the order group according to the order information of each of the pending orders in the order group and the distribution information of each delivery capacity corresponding to the order group The degree of matching between the respective delivery capacities corresponding to the order group;

According to each of the matching degrees, order scheduling is performed on each of the pending orders.
The method according to claim 1, wherein the clustering the to-be-dispatched orders according to the order information of the to-be-dispatched orders in a time unit, and after obtaining a plurality of order groups, the method further comprises:

For an order group in which the number of orders to be dispatched exceeds a preset threshold, the order group is split into multiple order groups, where the number of orders to be dispatched in each of the split order groups is less than the preset Threshold.
The method according to claim 1, wherein the clustering the to-be-dispatched orders according to the order information of each to-be-dispatched order in a time unit to obtain multiple order groups includes:

Determine the number of cluster centers according to the number of orders to be dispatched and the preset threshold;

Cluster the pending orders according to the number of cluster centers and the order information of each pending order to obtain multiple order groups, so that the number of pending orders in each of the order groups is smaller than all the pending orders. The preset threshold.
The method according to claim 1, wherein the performing order scheduling on each of the pending orders according to each of the matching degrees includes:

For each order to be dispatched, determining the delivery capacity with the highest matching degree corresponding to the order to be dispatched as the target delivery capacity corresponding to the order to be dispatched;

Allocating each of the pending orders to the corresponding target delivery capacity.
The method according to claim 4, after determining, for each of the pending orders, the delivery capacity with the highest matching degree corresponding to the pending orders as the target delivery capacity corresponding to the pending orders, The method also includes:

For each target delivery capacity, if there are more than two pending orders corresponding to the target delivery capacity, the pending order with the highest matching degree corresponding to the target delivery capacity is determined as the target corresponding to the target delivery capacity Order; in the case that there is one order to be dispatched corresponding to the target delivery capacity, the order to be dispatched is determined as the target order corresponding to the target delivery capacity;

The allocating each of the pending orders to the corresponding target distribution capacity includes:

Allocating each of the target orders to their corresponding target distribution capacity.
The method according to claim 5, further comprising:

Taking orders other than the target order among the to-be-dispatched orders as the to-be-dispatched orders in the next time unit.
The method according to claim 1, wherein the order information includes different types of task point information;

The clustering of each pending order according to the order information of each pending order within a time unit includes:

Clustering the to-be-scheduled orders according to the task point information of the same type of each of the to-be-scheduled orders in the time unit.
The method according to claim 1, wherein the respectively determining the delivery capacity corresponding to each of the order groups comprises:

For each of the order groups, a delivery capacity whose current position is less than a preset distance from the starting position of each of the to-be-dispatched orders in the order group is determined as the delivery capacity corresponding to the order group.
The method according to claim 1, wherein the order information of each of the pending orders in the order group and the distribution information of the delivery capacity corresponding to the order group are used to determine each of the order groups. The matching degree between the order to be dispatched and each of the distribution capacity corresponding to the order group includes:

For each of the distribution capacity, according to the distribution information of the distribution capacity, respectively determine the target parameters corresponding to the distribution capacity after each of the pending orders in the order group is pre-allocated to the distribution capacity, so The size of the target parameter is used to distinguish the pros and cons of pre-allocating the to-be-dispatched orders to each delivery capacity;

The degree of matching between each order to be dispatched and the delivery capacity is determined according to the target parameter corresponding to the delivery capacity and each of the orders to be dispatched.
An order scheduling device, the device comprising:

The clustering module is configured to cluster the to-be-dispatched orders according to the order information of the to-be-dispatched orders in a time unit to obtain multiple order groups;

The first determining module is configured to separately determine the delivery capacity corresponding to each of the order groups;

The second determining module is configured to determine, for each of the order groups, according to the order information of each of the pending orders in the order group and the distribution information of each delivery capacity corresponding to the order group The degree of matching between each of the pending orders in the order group and each of the distribution capacity corresponding to the order group;

The scheduling module is configured to perform order scheduling on each of the pending orders according to each of the matching degrees.
A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, realizes the steps of the method described in any one of claims 1-9.
An electronic device including:

A memory on which a computer program is stored;

The processor is configured to execute the computer program in the memory to implement the following steps:

Clustering each of the pending orders according to the order information of each pending order within a time unit to obtain multiple order groups;

Respectively determine the delivery capacity corresponding to each of the order groups;

For each of the order groups, determine each of the pending orders in the order group according to the order information of each of the pending orders in the order group and the distribution information of each delivery capacity corresponding to the order group The degree of matching between the respective delivery capacities corresponding to the order group;

According to each of the matching degrees, order scheduling is performed on each of the pending orders.
The electronic device according to claim 12, the processor is further configured to execute the computer program in the memory to implement the following steps:

For an order group in which the number of orders to be dispatched exceeds a preset threshold, the order group is split into multiple order groups, where the number of orders to be scheduled in each of the split order groups is less than the preset Threshold.
The electronic device according to claim 12, the processor is configured to execute the computer program in the memory to implement the following steps:

Determine the number of cluster centers according to the number of each of the pending orders and the preset threshold;

Clustering the pending orders according to the number of the cluster centers and the order information of each of the pending orders to obtain the multiple order groups.
The electronic device according to claim 12, the processor is further configured to execute the computer program in the memory to implement the following steps:

For each order to be dispatched, determining the delivery capacity with the highest matching degree corresponding to the order to be dispatched as the target delivery capacity corresponding to the order to be dispatched;

Allocating each of the pending orders to the corresponding target delivery capacity.
The electronic device according to claim 15, wherein the processor is further configured to execute the computer program in the memory to implement the following steps:

For each target delivery capacity, if there are more than two pending orders corresponding to the target delivery capacity, the pending order with the highest matching degree corresponding to the target delivery capacity is determined as the target corresponding to the target delivery capacity Order; in the case that there is one order to be dispatched corresponding to the target delivery capacity, the order to be dispatched is determined as the target order corresponding to the target delivery capacity;

The processor is configured to execute the computer program in the memory to implement the following step: allocating each of the target orders to their corresponding target distribution capacity.
The electronic device according to claim 16, wherein the processor is further configured to execute the computer program in the memory to implement the following steps:

Take orders other than the target order among the pending orders as pending orders to be scheduled in the next time unit.
The electronic device according to claim 12, wherein the order information includes different types of task point information;

The processor is configured to execute the computer program in the memory to implement the following steps:

Clustering the to-be-scheduled orders according to the task point information of the same type of each of the to-be-scheduled orders in the time unit.
The electronic device according to claim 12, the processor is configured to execute the computer program in the memory to implement the following steps:

For each of the order groups, a delivery capacity whose current position is less than a preset distance from the starting position of each of the to-be-dispatched orders in the order group is determined as the delivery capacity corresponding to the order group.
The electronic device according to claim 12, the processor is configured to execute the computer program in the memory to implement the following steps:

For each of the distribution capacity, according to the distribution information of the distribution capacity, respectively determine the target parameters corresponding to the distribution capacity after each of the pending orders in the order group is pre-allocated to the distribution capacity, so The size of the target parameter is used to distinguish the pros and cons of pre-allocating the to-be-dispatched orders to each delivery capacity;

The degree of matching between each order to be dispatched and the delivery capacity is determined according to the target parameter corresponding to the delivery capacity and each of the orders to be dispatched.