CN115545591A - Distribution path planning method, device, equipment and storage medium - Google Patents
Distribution path planning method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115545591A CN115545591A CN202110735434.6A CN202110735434A CN115545591A CN 115545591 A CN115545591 A CN 115545591A CN 202110735434 A CN202110735434 A CN 202110735434A CN 115545591 A CN115545591 A CN 115545591A
- Authority
- CN
- China
- Prior art keywords
- planning
- candidate
- orders
- order
- delivered
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 515
- 238000000605 extraction Methods 0.000 claims description 39
- 238000012545 processing Methods 0.000 claims description 33
- 230000015654 memory Effects 0.000 claims description 16
- 238000012163 sequencing technique Methods 0.000 claims description 15
- 230000004044 response Effects 0.000 claims description 13
- 230000002776 aggregation Effects 0.000 claims description 11
- 238000004220 aggregation Methods 0.000 claims description 11
- 230000006870 function Effects 0.000 description 22
- 238000004422 calculation algorithm Methods 0.000 description 17
- 230000008569 process Effects 0.000 description 15
- 230000002093 peripheral effect Effects 0.000 description 10
- 230000001133 acceleration Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 6
- 238000003066 decision tree Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 235000012054 meals Nutrition 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000011451 sequencing strategy Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 239000000919 ceramic Substances 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000004083 survival effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0835—Relationships between shipper or supplier and carriers
- G06Q10/08355—Routing methods
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Factory Administration (AREA)
Abstract
The application discloses a distribution path planning method, a distribution path planning device, a distribution path planning equipment and a storage medium, and belongs to the technical field of computers. The method comprises the following steps: obtaining order information of a plurality of orders to be delivered of delivery capacity, wherein the order information at least comprises a starting position, an ending position and predicted delivery time; predicting path quality information corresponding to the candidate planning methods according to the acquired multiple order information and planning strategies of the candidate planning methods, wherein the path quality information represents the quality of distribution paths planned for the multiple orders to be distributed by adopting the candidate planning methods, and the planning strategies of different candidate planning methods are different; selecting a target planning method from the multiple candidate planning methods according to the path quality information corresponding to the multiple candidate planning methods; and planning distribution paths for the plurality of orders to be distributed by adopting a target planning method. The target planning method is selected by predicting the quality of the distribution paths planned by different planning side rules, so that the quality of the planned distribution paths is ensured.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a storage medium for planning a distribution route.
Background
With the continuous development of computer technology, the instant delivery services such as take-out, car sharing, express delivery and the like are promoted. Generally, a distribution capacity is allocated with a plurality of orders, in order to improve the distribution efficiency of the distribution capacity, a distribution system plans a distribution path of the plurality of orders according to a starting position and an ending position of the plurality of orders, and the distribution capacity completes the orders in sequence according to the planned distribution path. Therefore, how to plan a delivery route with high quality for delivery capacity becomes a problem that needs to be solved at present.
Disclosure of Invention
The embodiment of the application provides a distribution path planning method, a distribution path planning device, equipment and a storage medium, and improves the quality of a planned distribution path, so that the distribution efficiency of distribution capacity distribution orders is improved. The technical scheme is as follows:
in one aspect, a delivery path planning method is provided, and the method includes:
obtaining order information of a plurality of orders to be delivered of delivery capacity, wherein the order information at least comprises a starting position, an ending position and predicted delivery time;
predicting path quality information corresponding to the candidate planning methods according to the acquired multiple order information and planning strategies of the candidate planning methods, wherein the path quality information represents the quality of distribution paths planned for the multiple orders to be distributed by adopting the candidate planning methods, and the planning strategies of different candidate planning methods are different;
selecting a target planning method from the candidate planning methods according to the path quality information corresponding to the candidate planning methods;
and planning distribution paths for the plurality of orders to be distributed by adopting the target planning method.
In one aspect, a delivery path planning apparatus is provided, the apparatus including:
the system comprises an acquisition module, a delivery module and a delivery module, wherein the acquisition module is used for acquiring order information of a plurality of to-be-delivered orders of delivery capacity, and the order information at least comprises a starting position, an ending position and predicted delivery time;
the prediction module is used for predicting path quality information corresponding to the candidate planning methods according to the acquired multiple order information and planning strategies of the candidate planning methods, wherein the path quality information represents the quality of distribution paths planned for the multiple orders to be distributed by adopting the candidate planning methods, and the planning strategies of different candidate planning methods are different;
a selecting module, configured to select a target planning method from the multiple candidate planning methods according to path quality information corresponding to the multiple candidate planning methods;
and the planning module is used for planning distribution paths for the plurality of orders to be distributed by adopting the target planning method.
In a possible implementation manner, the path quality information is a quality score, and the predicting module is configured to predict, according to the plurality of order information and the planning strategies of the plurality of candidate planning methods, a quality score corresponding to each candidate planning method; or,
the path quality information is an arrangement order of the candidate planning methods in the candidate planning methods, the prediction module is configured to predict an arrangement order of the candidate planning methods according to the order information and planning strategies of the candidate planning methods, and use the arrangement order of the candidate planning methods as the path quality information corresponding to the candidate planning methods, and the candidate planning methods are ordered according to a high-quality order of a delivery path planned for the orders to be delivered.
In a possible implementation manner, the selecting module is configured to select, according to a quality score corresponding to each candidate planning method, a candidate planning distribution method with a highest quality score from the multiple candidate planning methods as the target planning method; or,
the selecting module is configured to select, according to an arrangement order of the candidate planning methods, a candidate planning method corresponding to a target order from the candidate planning methods as the target planning method, where the target order is an arrangement order of a candidate planning method with highest path quality of a distribution path planned for the order to be distributed among the candidate planning methods.
In a possible implementation manner, the path quality information is the same or different, and the predicting module is configured to predict, according to the multiple order information and the planning strategies of the multiple candidate planning methods, whether the quality of the delivery paths planned by using the multiple candidate planning methods according to the multiple orders to be delivered is the same; and determining the prediction result as path quality information corresponding to the candidate planning methods.
In a possible implementation manner, the selecting module is configured to select, in response to that the path quality information indicates that the quality of the delivery paths planned for the multiple orders to be delivered by using the multiple candidate planning methods is the same, any one candidate planning method from the multiple candidate planning methods as the target planning method; or,
the selecting module is configured to determine each candidate planning method as the target planning method in response to that the quality of the distribution paths planned for the multiple orders to be distributed by using the multiple candidate planning methods is different in the path quality information.
In one possible implementation, the planning module includes:
the planning unit is used for planning distribution paths for the plurality of orders to be distributed by adopting each target planning method in response to the plurality of target planning methods to obtain a plurality of distribution paths;
and the selecting unit is used for determining the distribution path with the highest path quality in the plurality of distribution paths as the target distribution path.
In one possible implementation, the prediction module includes:
the characteristic extraction unit is used for extracting the characteristics of the plurality of order information based on the planning strategies of the plurality of candidate planning methods to obtain order characteristics related to the path quality;
and the predicting unit is used for processing the order features based on the planning strategies of the candidate planning methods and predicting the path quality information corresponding to the candidate planning methods.
In a possible implementation manner, the predicting unit is configured to obtain a prediction model of the multiple candidate planning methods, process the order features, and predict path quality information corresponding to the multiple candidate planning methods, where the prediction model is configured to predict, according to the order features of the multiple orders to be delivered, whether a planning strategy of each candidate planning method is suitable for the multiple orders to be delivered; or,
the prediction unit is configured to obtain a prediction model of each candidate planning method, process the order features respectively, and predict path quality information corresponding to each candidate planning method, where the prediction model is configured to predict, according to the order features of multiple orders to be delivered, whether a planning strategy of the candidate planning method is suitable for the multiple orders to be delivered.
In a possible implementation manner, the path quality information is the same or different, the order features include a plurality of order sub-features, and the prediction unit is configured to obtain a plurality of classification rules corresponding to the planning strategies of the candidate planning methods; processing the sub-characteristics of the orders according to the classification rules to obtain classification results, wherein the classification results are the same or different; and determining path quality information corresponding to the candidate planning methods according to the obtained classification result.
In a possible implementation manner, the feature extraction unit is configured to perform feature extraction on the plurality of order information based on a plurality of dimensions corresponding to the plurality of candidate planning methods to obtain the order feature, where the plurality of dimensions are dimensions to which the order information that affects path quality and is determined based on planning policies of the plurality of candidate planning methods belongs.
In one possible implementation, the planning strategy of the plurality of candidate planning methods includes at least: sequencing the plurality of orders to be delivered according to the order urgency degree, and planning the delivery paths of the plurality of orders to be delivered according to the sequence of the plurality of orders to be delivered; sequencing the plurality of orders to be delivered according to the predicted delivery time, and planning the delivery paths of the plurality of orders to be delivered according to the sequence of the plurality of orders to be delivered;
the feature extraction unit is configured to perform at least one of:
performing feature extraction on the plurality of order information based on order attribute dimensions to obtain order attribute features;
performing feature extraction on the plurality of order information based on order distance dimensions to obtain distance attribute features among a plurality of task positions in the plurality of orders to be delivered, wherein the plurality of task positions comprise initial positions and end positions of the orders to be delivered;
and processing the plurality of order information based on the task point aggregation dimension to obtain the aggregation attribute characteristics of the starting position and the ending position in the plurality of orders to be delivered.
In a possible implementation manner, the planning module is configured to determine an order to be delivered, which has completed a pickup task, in the plurality of orders to be delivered as a first type of order to be delivered; determining the orders to be delivered, which do not complete the goods taking task, in the plurality of orders to be delivered as a second type of orders to be delivered; planning a first delivery path for the first type of orders to be delivered by adopting the target planning method; continuing to plan a second distribution path for the second type of order to be distributed based on the first distribution path; and determining the second delivery path as the delivery path of the plurality of orders to be delivered.
In one aspect, a computer device is provided that includes one or more processors and one or more memories having at least one program code stored therein, the at least one program code being loaded by the one or more processors and executed to implement the operations performed by the delivery path planning method according to any of the possible implementations described above.
In one aspect, a computer-readable storage medium is provided, in which at least one program code is stored, and the at least one program code is loaded and executed by a processor to implement the operations performed by the delivery path planning method according to any one of the above possible implementation manners.
In one aspect, there is provided a computer program or computer program product comprising: computer program code which, when executed by a computer, causes the computer to carry out the operations performed by the delivery path planning method of any one of the possible implementations as described above.
The beneficial effects brought by the technical scheme provided by the embodiment of the application at least comprise:
according to the distribution path planning method, the distribution path planning device, the distribution path planning equipment and the storage medium, the path quality of a distribution path planned for the order to be distributed by different planning methods can be predicted according to the characteristics of the order to be distributed, so that the target planning method is selected according to the prediction result, the distribution path of the order to be distributed is planned according to the target planning method, the processing amount of distribution path planning is reduced compared with the case that the distribution path is planned for the order to be distributed by adopting each planning method, the path quality of the planned distribution path is ensured, and the distribution efficiency of distribution capacity for distributing the order according to the distribution path is ensured.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic illustration of an implementation environment provided by an embodiment of the present application;
fig. 2 is a flowchart of a delivery path planning method according to an embodiment of the present application;
fig. 3 is a flowchart of a method for planning a delivery route according to an embodiment of the present disclosure;
FIG. 4 is a flow chart of a process order feature provided by an embodiment of the present application;
fig. 5 is a schematic structural diagram of a distribution route planning apparatus according to an embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of another delivery path planning apparatus according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of a terminal provided in an embodiment of the present application;
fig. 8 is a schematic structural diagram of a server according to an embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
It will be understood that the terms "first," "second," and the like as used herein may be used herein to describe various concepts, which are not limited by these terms unless otherwise specified. These terms are only used to distinguish one concept from another. For example, a first candidate planning method may be referred to as a second candidate planning method, and similarly, the second candidate planning method may be referred to as the first candidate planning method, without departing from the scope of the present application.
As used herein, the term "at least one," "a plurality," "each," "any," at least one includes one, two, or more than two, a plurality includes two or more than two, and each refers to each of the corresponding plurality, and any refers to any one of the plurality, for example, the plurality of candidate planning methods includes 3 candidate planning methods, and each refers to each of the 3 candidate planning methods, and any refers to any one of the 3 candidate planning methods, which may be the first, the second, or the third.
The distribution path planning method provided by the embodiment of the application is applied to computer equipment, and in a possible implementation manner, the computer equipment is a server. The server can be a server, a server cluster composed of a plurality of servers, or a cloud computing service center. In one possible implementation, the computer device includes a terminal and a server.
Fig. 1 is a schematic diagram of an implementation environment provided in an embodiment of the present application, and as shown in fig. 1, the implementation environment includes a first terminal 101, a second terminal 102, and a server 103. The first terminal 101 is connected with the server 103 through a wireless or wired network; the second terminal 102 and the server 103 are connected through a wireless or wired network.
Optionally, the first terminal 101 is any type of terminal such as a desktop computer, a tablet computer, or a mobile phone, the second terminal 102 is any type of terminal such as a desktop computer, a tablet computer, or a mobile phone, and the server 103 is a server, or a server cluster composed of a plurality of servers, or a cloud computing service center.
The first terminal 101 has installed thereon a first application served by the server 103, by which the first terminal 101 can implement functions such as data transmission, message interaction, and the like. Optionally, the first application is an application in an operating system of the first terminal 101 or an application provided by a third party. For example, the first application is an e-commerce application having a function of shopping, but of course, the e-commerce application can also have other functions, such as a comment function, a mailing function, and the like.
The second terminal 102 has installed thereon a second application provided by the server 103, through which the second terminal 102 can implement functions such as data transmission, message interaction, and the like. Optionally, the second application is an application in an operating system of the second terminal 102, or an application provided by a third party. For example, the second application is an order taking application having an order taking function, but of course, the order taking application can also have other functions, such as a shopping function, a comment function, and the like.
The server 103 is configured to receive an order uploaded by the first terminal 101, allocate the order to a distribution capacity, plan a distribution path according to a plurality of orders to be distributed currently in the distribution capacity, and push the planned distribution path to the distribution capacity, so that the distribution capacity sequentially distributes the plurality of orders to be distributed according to the distribution path. Optionally, the server 103 is a scheduling server.
The distribution path planning method provided by the embodiment of the application can be applied to any distribution scene.
For example, to take-away scenarios.
In a peak dining period, a delivery capacity has a plurality of orders to be delivered, and the delivery capacity needs to sequentially deliver the plurality of orders to be delivered, and if the delivery path planning method provided by the embodiment of the application is adopted, a delivery path with good path quality can be provided for the delivery capacity, so that the delivery capacity can deliver the plurality of orders to be delivered as soon as possible, and the delivery efficiency of the orders is improved.
It should be noted that, in the embodiment of the present application, the delivery scenario is only exemplarily described in a take-away scenario, and is not limited to the delivery scenario.
Fig. 2 is a flowchart of a delivery path planning method according to an embodiment of the present application. The embodiment of the present application takes an execution subject as an example for an exemplary description, and the embodiment includes:
201. the server obtains order information of a plurality of orders to be delivered for delivery capacity, wherein the order information at least comprises a starting position, an ending position and a predicted delivery time.
The order to be delivered is an order for which delivery capacity has not been completed. For example, the order to be delivered is an order of an unfinished pick-up task and delivery task; as another example, the order to be dispensed is an order that has completed the pick up task but has not completed the delivery task.
The delivery capacity is a capacity for delivering an order, wherein the delivery capacity may be a rider, a take-out robot, an express robot, and the like, and is not limited in the embodiment of the present application. The multiple orders to be delivered for a delivery capacity are the multiple orders for which the delivery capacity has not yet completed delivery.
The order information of the order to be delivered at least comprises a starting position, an ending position and a predicted delivery time of the order to be delivered, so that the delivery capacity is indicated to pick up the goods at the starting position, and the picked-up goods are delivered to the ending position before the predicted delivery time. When planning the distribution path of a plurality of orders to be distributed, planning is required according to the order information of the plurality of orders to be distributed, so that the distribution capacity can smoothly complete the distribution task according to the requirements in the order information.
202. The server predicts path quality information corresponding to the candidate planning methods according to the acquired multiple order information and planning strategies of the candidate planning methods, wherein the path quality information represents the quality of distribution paths planned for the multiple orders to be distributed by the candidate planning methods, and planning strategies of different candidate planning methods are different.
In the embodiment of the present application, a plurality of planning methods are provided in the server, and any one of the planning methods may be adopted to plan the delivery paths of a plurality of orders to be delivered. The planning strategies adopted by different planning methods are different, and when the distribution paths are planned for a plurality of orders to be distributed, the planned distribution paths may be the same or different. If the planned delivery paths are different, the path quality of the planned delivery paths may also be different. Therefore, in order to plan a delivery path with higher quality, the embodiment of the present application determines which planning method is suitable for planning a delivery path for a plurality of orders to be delivered according to the order information of the plurality of orders to be delivered.
Whether a planning method is suitable for planning a distribution path for the order to be distributed is determined by whether the planning strategy of the planning method is matched with the characteristics of the order to be distributed, so in the embodiment of the application, a plurality of planning methods arranged in a server are used as candidate planning methods, and path quality information corresponding to the candidate planning methods is predicted according to the acquired order information and the planning strategies of the candidate planning methods.
203. And the server selects a target planning method from the multiple candidate planning methods according to the path quality information corresponding to the multiple candidate planning methods.
Since the path quality information corresponding to the candidate planning method indicates the quality of the distribution path planned by the candidate planning method for the multiple orders to be distributed, it can be determined whether the candidate planning method is suitable for planning the distribution path for the multiple orders to be distributed according to the path quality information corresponding to the multiple candidate planning methods, so that a planning method suitable for planning the distribution path for the multiple orders to be distributed can be selected. Or determining which candidate planning method is suitable for planning the distribution path for the multiple orders to be distributed according to the path quality information corresponding to the multiple candidate planning methods.
204. The server plans a distribution path for the plurality of orders to be distributed by adopting a target planning method.
According to the distribution path planning method provided by the embodiment of the application, the path quality of the distribution path planned for the order to be distributed by different planning methods can be predicted according to the characteristics of the order to be distributed, so that the target planning method is selected according to the prediction result, the distribution path of the order to be distributed is planned according to the target planning method, the processing amount of distribution path planning is reduced compared with the method of planning the distribution path for the order to be distributed by adopting each planning method, the path quality of the planned distribution path is ensured, and the distribution efficiency of the distribution capacity of the order to be distributed according to the distribution path is ensured.
Fig. 3 is a flowchart of a delivery path planning method according to an embodiment of the present application. The embodiment of the present application takes an execution subject as an example for an exemplary description, and the embodiment includes:
301. the server obtains order information of a plurality of orders to be delivered for delivering capacity, wherein the order information at least comprises a starting position, an ending position and a predicted delivery time.
In the embodiment of the present application, the order information is used to indicate a delivery requirement of the to-be-delivered order on delivery capacity. For example, the starting position in the order information is used for indicating the delivery capacity corresponding to the order to be delivered to go to the starting position for taking goods; the end position in the order information is used for indicating the delivery capacity corresponding to the order to be delivered to the end position for delivery; the estimated time of arrival of the order is used to indicate that the delivery capacity corresponding to the order to be delivered completes the delivery task of the order to be delivered before the estimated time of arrival.
It should be noted that, in the embodiment of the present application, order information is only exemplified by the order information including a start position, an end position, and a predicted delivery time, and the order information is exemplarily described without limitation, and optionally, the order information may further include other information, for example, taking a take-out scenario as an example, and the order information further includes a predicted meal delivery time; as another example, the order information also includes the current location of the delivery route; as another example, the order information also includes a generation time of the order.
It should be noted that, in this embodiment of the present application, the execution timing of the step 301 is not limited, and in a possible implementation manner, the execution timing of the step 301 is: new orders are assigned to the delivery capacity. Optionally, the server performs the step of obtaining order information of the plurality of orders to be delivered of the delivery capacity in response to assigning a new order to be delivered for the delivery capacity. That is, the server replans the delivery path for the delivery capacity each time a new order is assigned to the delivery capacity.
In another possible implementation manner, the execution timing of step 301 is: and reaching the preset time length. Optionally, the server performs the step of acquiring the order information of the plurality of to-be-delivered orders of the delivery capacity once every first time period. The first time period is any time period, for example, 5 minutes, 10 minutes, and the like, and the first time period is not limited in this embodiment of the application.
302. And the server performs feature extraction on the plurality of order information based on the planning strategies of the plurality of candidate planning methods to obtain order features related to the path quality.
The server is provided with a plurality of planning methods, and any planning method can be adopted to plan the distribution paths of a plurality of orders to be distributed; each of the planning methods may also be employed to plan a delivery path for a plurality of orders to be delivered. If each planning method is adopted to plan the distribution paths of the multiple orders to be distributed, the distribution path planned by each planning method, specifically which distribution path is adopted, can be obtained, and the distribution path with the highest path quality can be selected from the multiple distribution paths by determining the path quality of the multiple distribution paths. The shorter the distribution distance of the distribution capacity for distributing the multiple orders to be distributed is, the higher the path quality is; the shorter the timeout period for the delivery capacity to deliver the plurality of orders to be delivered, the higher the path quality.
The server needs to plan the delivery path multiple times each day, for example, the delivery path is planned for different delivery capacities, or the delivery path is planned for different orders to be delivered with the same delivery capacity. Experiments show that the planning methods corresponding to the distribution paths with the highest path quality selected each time are not completely the same.
For example, 3 planning methods are adopted to plan the distribution paths for 10 distribution capacities respectively, and the distribution paths selected for the first and seventh distribution capacities are the distribution paths planned by the first planning method; the distribution path selected for the second to fifth and eighth distribution capacities is the distribution path planned by the second planning method; the delivery paths selected for the sixth, ninth, and tenth delivery capacities are the delivery paths planned by the third planning method.
Considering that multiple distribution paths need to be planned by adopting multiple planning methods every time the distribution paths are planned, the calculation amount of the server is large, and the time for determining the final distribution path is long. The optimal planning method is different and related to a plurality of orders to be delivered, also considering that the path is planned each time. The characteristics of the multiple orders to be delivered are different, and the suitable planning methods are also different.
For example, some orders of the orders to be delivered are orders with higher urgency if the planning strategy of the planning method is: sequencing according to the estimated delivery time of a plurality of orders to be delivered, sequentially inserting the positions corresponding to the plurality of orders to be delivered into a delivery path according to a greedy algorithm and the sequence of the plurality of orders to be delivered to obtain the delivery path planned for the plurality of orders to be delivered, so that the planning method is not suitable for planning the delivery path for the plurality of orders to be delivered; if the planning strategy of the planning method is as follows: and sequencing according to the urgency degrees of the orders to be delivered, sequentially inserting the positions corresponding to the orders to be delivered into the delivery paths according to the arrangement sequence of the orders to be delivered according to a greedy algorithm to obtain the delivery paths planned for the orders to be delivered, so that the planning method is suitable for planning the delivery paths for the orders to be delivered.
Therefore, the embodiment of the present application provides a method for selecting a planning method, which planning method is suitable for planning a delivery path for a plurality of orders to be delivered according to order information of the plurality of orders to be delivered of delivery capacity. That is, a plurality of planning methods set in the server are used as candidate planning methods, and the target planning method is selected by predicting the path quality information of each candidate planning method.
Since the characteristics of the plurality of orders to be delivered are different and the suitable planning method is also different, the planning strategy of the planning method suitable for planning the delivery path for the plurality of orders to be delivered corresponds to the characteristics of the plurality of orders to be delivered. Therefore, the method and the device can determine the characteristics of the order to be delivered based on the planning strategies of a plurality of candidate planning methods, and then determine which candidate planning method is suitable for planning the delivery path for the order to be delivered according to the characteristics of the order to be delivered.
The process of determining the characteristics of the order to be delivered based on the planning strategies of the candidate planning methods is step 302 described above. It should be noted that the planning strategies of the multiple candidate planning methods are different, and the order features matched with each planning strategy are order features with different dimensions. In one possible implementation manner, the performing, by the server, feature extraction on the plurality of order information based on a planning policy of a plurality of candidate planning methods to obtain an order feature associated with the path quality includes: and performing feature extraction on the plurality of order information based on a plurality of dimensions corresponding to the plurality of candidate planning methods to obtain the order features, wherein the plurality of dimensions are dimensions to which the order information which influences the path quality and is determined based on the planning strategies of the plurality of candidate planning methods belongs.
It should be noted that the dimension corresponding to each candidate planning method may be preset. Optionally, the server is provided with a corresponding relationship between the planning method and the dimensionality, and determines a plurality of dimensionalities corresponding to the plurality of candidate planning methods according to the corresponding relationship. Alternatively, the algorithm of the feature extraction may be preset, and optionally, the server is provided with a correspondence between the planning method and the feature extraction algorithm, and determines the feature extraction algorithms corresponding to the plurality of candidate planning methods according to the correspondence. It should be noted that each candidate planning method may correspond to one or more feature extraction algorithms, and each feature extraction algorithm is used for performing feature extraction on order information from one dimension.
In one possible implementation, the planning strategy of the plurality of candidate planning methods includes at least: sequencing the plurality of orders to be delivered according to the order urgency degree, and planning the delivery paths of the plurality of orders to be delivered according to the sequence of the plurality of orders to be delivered; sequencing the multiple orders to be delivered according to the predicted delivery time, and planning delivery paths of the multiple orders to be delivered according to the sequence of the multiple orders to be delivered; and sequencing the plurality of orders to be delivered according to the estimated arrival time and the estimated delivery cost, and planning delivery paths of the plurality of orders to be delivered according to the sequence of the plurality of orders to be delivered.
In the embodiment of the present application, it is considered that orders with an early estimated time of delivery are more urgent than orders with a late estimated time of delivery. If orders with late estimated delivery times are delivered first, a large timeout may result for orders with early estimated delivery times, thereby verifying delivery efficiency for orders. For example, the current time is 10 am 50 minutes, the projected delivery time for order 1 is 11 am 10 minutes, and the projected delivery time for order 2 is 11 am. The remaining delivery time period for order 1 is 20 minutes, while the remaining delivery time period for order 2 is only 10 minutes, and thus the urgency of order 2 is higher relative to order 1. Therefore, in the embodiment of the present application, the planning strategy of the candidate planning method may be to sort the multiple orders to be delivered according to the expected arrival time, and plan the delivery paths of the multiple orders to be delivered according to the sort order of the multiple orders to be delivered. For example, according to a greedy algorithm, the positions corresponding to the multiple orders to be delivered are sequentially inserted into the delivery path according to the arrangement order of the multiple orders to be delivered, so as to obtain a delivery path planned for the multiple orders to be delivered.
In addition, in the embodiment of the present application, it is also considered that in some cases, the estimated delivery time may not accurately reflect the urgency of the order, for example, the current time is 5 pm, the estimated delivery time of order 1 is 5 pm, and the delivery capacity is 1 km away from the end position of order 1; the estimated delivery time of the order 2 is 5 pm and 6 pm, and the distance between the delivery capacity and the end position of the order 2 is 2 km; it can be seen that the estimated delivery time for order 2 is later than order 1, but this does not mean that order 1 is more urgent than order 2. Conversely, since order 2 is delivered over a longer distance, it takes longer for the delivery capacity to reach the end of order 2, resulting in a higher probability of time-out, whereas order 1 is closer, resulting in a shorter probability of time-out than order 2. Therefore, the embodiment of the application also provides a planning method considering the estimated delivery time and the delivery distance of the order at the same time. Determining the urgency level of the order according to the estimated arrival time and the delivery distance of the order, optionally, the urgency parameters corresponding to the estimated arrival time of the order, the delivery distance of the order, and the urgency level of the order satisfy the following relationship:
wherein, delta i The urgency parameter is corresponding to the urgency degree of the ith order and is used for representing the urgency degree of the order; d i Is the distance, ETA, between the end location of the ith order and the current location of the delivery capacity i Is the projected delivery time of the ith order; and ct is the current time.
Therefore, in the embodiment of the present application, the planning strategy of the candidate planning method may be to sort the multiple orders to be delivered according to the urgency of the orders, and plan the delivery paths of the multiple orders to be delivered according to the ranking order of the multiple orders to be delivered. For example, according to a greedy algorithm, the positions corresponding to the multiple orders to be delivered are sequentially inserted into the delivery path according to the arrangement order of the multiple orders to be delivered, so as to obtain a delivery path planned for the multiple orders to be delivered.
In the following, only taking the two candidate planning methods, namely "order sorting according to the order urgency" and "order sorting according to the predicted delivery time", as examples of the multiple candidate planning methods, the method performs feature extraction on multiple order information based on multiple dimensions corresponding to the multiple candidate planning methods to obtain order features, and performs an exemplary explanation.
Optionally, feature extraction is performed on the plurality of order information based on a plurality of dimensions corresponding to a plurality of candidate planning methods to obtain order features, where the order features include at least one of the following:
(1) And performing feature extraction on the plurality of order information based on the order attribute dimension to obtain order attribute features.
Based on the order attribute dimension, performing feature extraction on a plurality of order information to obtain order attribute features, wherein the method comprises the following steps: and performing feature extraction on at least one of the initial position, the ending position, the order generation time and the estimated delivery time in each order information based on the order attribute dimension to obtain order attribute features.
Optionally, the order attribute feature comprises at least one of: the survival time of the order to be delivered; the remaining delivery duration of the order to be delivered; the distribution distance of the order to be distributed; and the urgency parameter is used for indicating the urgency degree of delivering the order to be delivered, is inversely proportional to the remaining delivery time length of the order to be delivered and is directly proportional to the remaining delivery distance of the order to be delivered.
The order attribute feature can indicate whether the candidate planning method is suitable for planning the delivery path for the multiple orders to be delivered to a certain extent, for example, the higher the urgency parameter of the orders to be delivered is, the more suitable the candidate planning method of "ordering the orders according to the urgency degree of the orders" is to be adopted; the lower the urgency parameters of the orders to be delivered, the more suitable it is to adopt the candidate planning method of "order ordering by projected arrival time".
For example, feature extraction is performed on the initial position and the end position in the order information to obtain the distribution distance of the order to be distributed; and performing feature extraction on the order generation time and the current time to obtain the survival time of the order to be distributed and the like.
(2) And performing feature extraction on the plurality of order information based on the order distance dimension to obtain distance attribute features among a plurality of task positions in the plurality of orders to be delivered, wherein the plurality of task positions comprise the initial positions and the end positions of the orders to be delivered.
The method for extracting the characteristics of the multiple order information based on the order distance dimension to obtain the distance attribute characteristics among multiple task positions in the multiple orders to be delivered, wherein the multiple task positions comprise the initial positions and the end positions of the orders to be delivered, and the method comprises the following steps of: and processing at least one of the starting position, the ending position, the current position of the delivery capacity and the delivery state in each order information based on the order distance dimension to obtain a distance attribute characteristic, wherein the delivery state represents whether the delivery capacity finishes the picking task of the order to be delivered.
Optionally, the distance attribute feature comprises at least one of: the quantity of the orders to be delivered without completing the goods taking task and the proportion of the orders to be delivered without completing the goods taking task in the plurality of orders to be delivered are calculated; the distance between each position to be reached in the plurality of orders to be distributed and a position central point is the central point of each position to be reached in the orders to be distributed; the distance between each initial position in the to-be-distributed orders with uncompleted picking tasks and an initial central point, wherein the initial central point is the central point of each initial position in the to-be-distributed orders with uncompleted picking tasks; the distance between each termination position in the plurality of orders to be delivered and a termination center point, wherein the termination center point is the center point of each termination position in the plurality of orders to be delivered; a distance between each of the plurality of orders to be delivered and a current location of the delivery capacity.
For example, if the number of orders to be delivered for which pick-up tasks are not completed is less than 2, then it is more appropriate to use the candidate planning method of "order ordering by projected delivery time". If the number of orders to be delivered for which pick up tasks are not completed is greater than or equal to 2, then it is not very different whether the candidate planning method of "order ordering by order urgency" or "order ordering by projected delivery time" is employed.
(3) And performing feature extraction on the plurality of order information based on the task point aggregation dimension to obtain the aggregation attribute features of the initial position and the end position in the plurality of orders to be delivered.
The method comprises the following steps of performing feature extraction on a plurality of order information based on task point aggregation dimensions to obtain aggregation attribute features of initial positions and end positions in a plurality of orders to be delivered, wherein the method comprises the following steps: and performing feature extraction on the initial position and the end position in each order information based on the distance dimension of the task points to obtain an aggregation attribute feature.
Optionally, the aggregated attribute feature comprises at least one of: the number of cluster centers; an attribute of a position in each cluster; the number of starting positions in each cluster; the number of termination locations in each cluster; the remaining delivery duration of orders to be delivered in each cluster.
For example, if the number of cluster centers is less than 3, then it is not very different whether the candidate planning method of "order by order urgency" or "order by projected time of delivery" is used. If the number of cluster centers is greater than or equal to 3, then it is more appropriate to use the candidate planning method of "sort orders by order urgency".
303. And the server processes the order features based on the planning strategies of the candidate planning methods and predicts the path quality information corresponding to the candidate planning methods.
After the server obtains the order features, the server further processes the order features based on a planning strategy of a candidate planning method to determine whether the candidate planning method is suitable for the multiple orders to be delivered, and the path quality information corresponding to the multiple candidate planning methods obtained by processing the orders can indicate whether the candidate planning method is suitable for the multiple orders to be delivered.
It should be noted that the path quality information corresponding to the multiple candidate planning methods may be a quality score corresponding to each candidate planning method, and the higher the quality score is, the higher the path quality of the distribution path planned for the multiple orders to be distributed by the candidate planning method is; the path quality information corresponding to the multiple candidate planning methods may also be an arrangement order of the multiple candidate planning methods, that is, the path quality information is an arrangement number of the candidate planning methods in the multiple candidate planning methods, and the multiple candidate delivery paths are ordered according to a quality height of a delivery path planned for the multiple orders to be delivered; or the path quality information corresponding to the candidate planning methods is the same or different, and if the path quality information corresponding to the candidate planning methods is the same, it indicates that the path quality of the distribution paths planned for the multiple orders to be distributed by using the candidate planning methods is consistent; if the path quality information corresponding to the candidate planning methods is different, it indicates that the path quality of the delivery paths planned for the multiple orders to be delivered by using the candidate planning methods is inconsistent. The embodiment of the application does not limit the path quality information corresponding to a plurality of candidate planning methods.
In a possible implementation manner, the predicting the path quality information corresponding to the multiple candidate planning methods according to the obtained multiple order information and the planning strategies of the multiple candidate planning methods includes: and predicting the quality score corresponding to each candidate planning method according to the plurality of order information and the planning strategies of the plurality of candidate planning methods.
In another possible implementation manner, the predicting the path quality information corresponding to the multiple candidate planning methods according to the obtained multiple order information and the planning strategies of the multiple candidate planning methods, where the path quality information is an arrangement order of the candidate planning methods in the multiple candidate planning methods, includes: and predicting the arrangement sequence of the candidate planning methods according to the order information and the planning strategies of the candidate planning methods, and taking the arrangement sequence of the candidate planning methods as the path quality information corresponding to the candidate planning methods. The candidate delivery paths are ordered according to the quality height of the delivery paths planned for the orders to be delivered.
In another possible implementation manner, the determining, according to the obtained multiple order information and the planning strategies of the multiple candidate planning methods, the path quality information corresponding to the multiple candidate planning methods includes: predicting whether the quality of distribution paths planned for the multiple orders to be distributed by adopting the multiple candidate planning methods is the same or not according to the multiple order information and planning strategies of the multiple candidate planning methods; and determining the prediction result as the path quality information corresponding to the candidate planning methods.
It should be noted that the step 303 may be implemented by a prediction model, or may be implemented by classifying according to a classification rule, and the embodiment of the present application does not limit an implementation manner of the step 303.
In one possible implementation, step 303 described above is implemented by a predictive model. Optionally, the step of processing, by the server, the order feature based on a planning strategy of a plurality of candidate planning methods, and predicting path quality information of each candidate planning method includes: acquiring a prediction model of the candidate planning methods, processing order features and predicting path quality information corresponding to the candidate planning methods, wherein the prediction model is used for predicting whether a planning strategy of each candidate planning method is suitable for the candidate orders to be delivered according to the order features of the orders to be delivered; or, the obtaining of the prediction model of each candidate planning method respectively processes the order features and predicts the path quality information corresponding to each candidate planning method, and the prediction model is used for predicting whether the planning strategy of the candidate planning method is suitable for the multiple orders to be delivered according to the order features of the multiple orders to be delivered.
The obtained prediction models of the multiple candidate planning methods are obtained through training of multiple groups of sample data, each group of sample data comprises order information of multiple sample orders to be delivered, and sample path quality information of a delivery path planned for the multiple sample orders to be delivered by adopting each candidate planning method is adopted. The obtained prediction model of each candidate planning method is also obtained through training of multiple groups of sample data, each group of sample data comprises order information of a plurality of sample orders to be distributed, and the candidate planning method is adopted to plan sample path quality information of a distribution path of the sample orders to be distributed.
It should be noted that the output of the prediction models of the multiple candidate planning methods may be the quality score of each candidate planning method, may also be the ranking order of the multiple candidate planning methods, and may also be the same or different. And the output of the prediction model of each candidate planning method may be the quality score of the candidate planning method.
Optionally, the higher the quality score of the candidate planning method is, the higher the path quality of the distribution path planned for the multiple to-be-distributed orders by using the candidate planning method is; optionally, the higher the ranking of the candidate planning method is, the higher the path quality of the distribution path planned for the multiple orders to be delivered by using the candidate planning method is, or the lower the path quality of the distribution path planned for the multiple orders to be delivered by using the candidate planning method is.
In another possible implementation, the order features include a plurality of order sub-features, for example, the order sub-features are: the number of cluster centers, the attributes of the locations in each cluster, the number of starting locations in each cluster, the number of ending locations in each cluster, the remaining delivery duration of orders to be delivered in each cluster, etc. The step 303 is implemented by classifying according to a classification rule.
Optionally, the step of processing the order features by the server based on the planning strategies of the multiple candidate planning methods, and predicting the path quality information of each candidate planning method includes: obtaining a plurality of classification plans corresponding to planning strategies of a plurality of candidate planning methods, and processing a plurality of order sub-characteristics according to a plurality of classification rules to obtain classification results, wherein the classification results are the same or different; and determining the path quality information of each candidate planning method according to the obtained classification result.
It should be noted that, according to the plurality of classification rules, a plurality of order sub-features are processed, and the obtained classification result may be one or a plurality of. For example, as shown in fig. 4, the sub-features of the orders are processed according to a plurality of classification rules, and the obtained classification result is one, and the classification result may be determined as the path quality information corresponding to a plurality of candidate planning methods. Or, the obtained classification results are multiple, and path quality information corresponding to multiple candidate planning methods can be determined according to the obtained multiple classification results. For example, the classification result with the largest number of the same classification results in the multiple classification results is determined as the path quality information corresponding to the multiple candidate planning methods. For another example, the weights corresponding to different classification rules are different, and the weight corresponding to the classification rule may be used as the weight of the classification result determined according to the classification rule, and the weighting processing result is determined as the path quality information corresponding to the candidate planning methods by performing weighting processing on a plurality of classification results.
It should be noted that, the classification rules corresponding to the planning policies of the candidate planning methods are preset, for example, a decision tree is preset in the server, where the decision tree includes a plurality of nodes, and each node corresponds to one classification rule. Optionally, the obtaining of the classification rule corresponding to the planning strategy of the multiple candidate planning methods includes: a decision tree corresponding to the planning strategy of the plurality of candidate planning methods is obtained.
For example, the decision tree is shown in fig. 4, and determines whether the number of food taking points of the plurality of orders to be delivered is greater than 2, and if not, the classification result is the same; if the distribution time is more than 2, whether the remaining distribution time is less than 20 minutes or not is determined, if the distribution time is less than 20 minutes, the classification result is different, if the distribution time is not less than 20 minutes, whether the cluster center number is less than 3 or not is determined, if the cluster center number is less than 3, the classification result is different, and if the cluster center number is not less than 3, the classification result is the same.
Optionally, a plurality of classification plans corresponding to the planning strategies of the plurality of candidate planning methods are obtained, and the step of processing the plurality of order sub-features according to the plurality of classification rules to obtain a plurality of classification results may be performed by a classifier, where the classifier is a decision tree-based classification model, for example, the classifier is an XGBoost classifier. The XGboost takes the input order characteristics as the basis of leaf node branches, and the final classification result is output through multi-layer division.
In addition, in the embodiment of the present application, in order to ensure the accuracy of the classifier, max _ depth (maximum depth of the decision tree) of the classifier may be controlled in a range of 3 to 10, so as to prevent overfitting; set min _ child _ weight (the minimum weighted sum of all observations) to 1 to reduce overfitting; the learning rate is controlled to be in the range of 0.01 to 0.2 to reduce the weight value of each step, making the model more robust, and the like.
It should be noted that, in the embodiment of the present application, the step 302 and the step 303 are only taken as examples, and the prediction process is exemplarily described. In yet another embodiment, the prediction process includes: and predicting path quality information corresponding to the candidate planning methods according to the acquired order information and planning strategies of the candidate planning methods. Optionally, the order information may be processed according to a preset processing method to obtain order characteristics of a plurality of orders to be delivered, and the order characteristics are processed to predict path quality information corresponding to a plurality of candidate planning methods. The embodiment of the present application does not limit the process of "predicting the path quality information corresponding to the plurality of candidate planning methods according to the obtained plurality of order information and the planning strategies of the plurality of candidate planning methods".
304. And the server selects a target planning method from the multiple candidate planning methods according to the path quality information corresponding to the multiple candidate planning methods.
As can be seen from the description in step 303, the path quality information may be a quality score, an order of arrangement, the same or different, and the like, and the process of "selecting a target planning method from a plurality of candidate planning methods according to the path quality information corresponding to the plurality of candidate planning methods" is exemplarily illustrated in the embodiment of the present application in different forms of the path quality information.
In a possible implementation manner, the path quality information is a quality score, and the server selects a target planning method from a plurality of candidate planning methods according to the path quality information corresponding to the plurality of candidate planning methods, including: and selecting the candidate planning distribution method with the highest quality score from the plurality of candidate planning methods as a target planning method according to the quality score of each candidate planning method.
In another possible implementation manner, the path quality information is a ranking order, and the server selects the target planning method from the multiple candidate planning methods according to the path quality information corresponding to the multiple candidate planning methods, including: according to the arrangement sequence of the candidate planning methods, selecting the candidate planning method corresponding to the target sequence from the candidate planning methods as the target planning method, wherein the target sequence is the arrangement sequence of the candidate planning method with the highest path quality of the distribution path planned for the orders to be distributed in the candidate planning methods. For example, the plurality of candidate planning methods are arranged in order from high to low in the quality of the delivery path planned for the plurality of orders to be delivered, and the target order is the first order; for another example, the candidate planning methods are arranged in order from low to high quality of the distribution paths planned for the orders to be distributed, and the target order is the last order.
It should be noted that, in the two possible implementation manners, the quality of the distribution paths planned for the multiple orders to be distributed by using the multiple candidate planning methods is different, and therefore, an optimal candidate planning method can be selected, and in another possible implementation manner, it is not possible to distinguish which distribution planning method is higher in quality of the distribution paths planned for the multiple orders to be distributed by using the distribution planning method. In response to the path quality information indicating that the quality of the delivery paths planned for the plurality of orders to be delivered by the plurality of candidate planning methods is the same, selecting any one candidate planning method from the plurality of candidate planning methods as a target planning method; or, in response to the path quality information indicating that the quality of the delivery paths planned for the plurality of orders to be delivered by the plurality of candidate planning methods is different, determining each candidate planning method as a target planning method.
Optionally, the path quality information may be a quality score, where the path quality information indicates that the quality of the distribution paths planned for the multiple orders to be distributed by using the multiple candidate planning methods is the same, and indicates that the quality scores corresponding to the candidate planning methods are the same; alternatively, the path quality information may be the same.
305. The server plans a distribution path for the plurality of orders to be distributed by adopting a target planning method.
The planning strategy adopted by the candidate planning method is as follows: and sequencing the orders to be distributed according to an order sequencing strategy, and sequentially inserting the positions corresponding to the orders to be distributed into a distribution path according to a greedy algorithm and the sequence of the orders to be distributed to obtain the distribution path planned for the orders to be distributed. And the order ranking strategies adopted by different candidate planning methods are different.
The server adopts a target planning method to plan a distribution path for a plurality of orders to be distributed, and the method comprises the following steps: and the server sorts the multiple orders to be delivered according to a target order sorting strategy indicated by the target planning method, and sequentially inserts the positions corresponding to the multiple orders to be delivered into the delivery path according to a greedy algorithm and the arrangement sequence of the multiple orders to be delivered to obtain the delivery path planned for the multiple orders to be delivered.
The following embodiments of the application illustrate a greedy algorithm: optionally, the server sequentially inserts the positions corresponding to the multiple orders to be delivered into the delivery path according to an arrangement order of the multiple orders to be delivered according to a greedy algorithm, so as to obtain a delivery path planned for the multiple orders to be delivered, including: for a kth order to be delivered of the plurality of orders to be delivered, performing the steps of: determining a plurality of optional arrival sequences corresponding to target positions in the kth order to be delivered according to the arrival sequence of the plurality of target positions in the currently determined kth-1 th delivery route, wherein the optional arrival sequence is an arrival sequence before or after any one of the plurality of target positions, and the target positions are positions which are required to be reached by delivery capacity and are not reached yet in the corresponding order to be delivered; updating the (k-1) th distribution path according to each selectable distribution sequence of the target position in the (k) th order to be distributed to obtain a plurality of alternative distribution paths; and determining a candidate distribution path with the highest quality in the multiple candidate distribution paths as a kth distribution path ", and then determining the obtained last distribution path as a distribution path planned for the multiple orders to be distributed, wherein k is any integer greater than or equal to 2.
It should be noted that, when determining multiple optional arrival orders corresponding to the target location in the kth order to be delivered, if the target location in the kth order to be delivered only includes a delivery location (a termination location in the order information), the optional arrival order of the target location may be an arrival order before or after any target location in the kth-1 delivery route. If the destination locations in the kth order to be delivered include a pick location and a delivery location (a starting location and an ending location in the order information), the alternative arrival order of the pick locations may be an arrival order before or after any of the destination locations in the k-1 delivery route, and the alternative arrival order of the delivery locations needs to be after the arrival order of the pick locations.
In a possible implementation manner, there may be a plurality of target planning methods, and the server plans the delivery path for a plurality of orders to be delivered by using the target planning method, including: and in response to the plurality of target planning methods, planning a distribution path for the plurality of orders to be distributed by adopting each target planning method to obtain a plurality of distribution paths, and determining the distribution path with the highest path quality in the plurality of distribution paths as the target distribution path.
The distribution of multiple orders to be distributed requires that the distribution power is overtime as little as possible, so the expected overtime duration corresponding to the distribution route with higher route quality should be as small as possible, and the distribution distance of the distribution route should be as short as possible. Optionally, an embodiment of the present application provides a method for determining a path quality of a delivery path according to a predicted timeout duration and a predicted delivery distance, where the predicted timeout duration, the predicted delivery distance, and the path quality of the delivery path satisfy the following relationship:
wherein, A is a path quality parameter of the distribution path, which is used for representing the path quality of the distribution path; min is a minimum function, max is a maximum function, t i Predicted delivery time, T, for delivering the ith order to be delivered as indicated by the delivery path i Estimated time of arrival for ith order to be delivered, d i Is the delivery distance for the ith order to be delivered. max (t) i -T i 0) represents when t i -T i When greater than 0, max (t) i -T i 0) value of t i -T i A value of (d); when t is i -T i Max (t) at 0 or less i -T i ) The value of (d) is 0.
It should be noted that, in a possible implementation manner, the multiple to-be-delivered orders include to-be-delivered orders for which the pickup task has been completed and to-be-delivered orders for which the pickup task has not been completed, and taking a take-out scene as an example, after a rider takes a meal, if the meal is not delivered for a long time, the quality of the meal may be reduced, and therefore, the delivery task needs to be preferentially executed for the to-be-delivered orders for which the pickup task has been completed in the embodiment of the present application. Optionally, planning a delivery path for a plurality of orders to be delivered by using a target planning method includes: determining the order to be delivered, which has completed the goods taking task, in the plurality of orders to be delivered as a first type of order to be delivered; determining the orders to be delivered with uncompleted picking tasks in the plurality of orders to be delivered as second-class orders to be delivered; planning a first distribution path for a first type of orders to be distributed by adopting a target planning method, and continuing to plan a second distribution path for a second type of orders to be distributed on the basis of the first distribution path; and determining the second delivery path as a delivery path of a plurality of orders to be delivered.
Planning a first distribution path for a first type of orders to be distributed by adopting a target planning method, and continuously planning a second distribution path for a second type of orders to be distributed on the basis of the first distribution path; determining the second delivery path as a delivery path of a plurality of orders to be delivered, including: sequencing the first types of orders to be delivered according to a target order sequencing strategy indicated by a target planning method, and sequentially inserting the position corresponding to each first type of order to be delivered into a delivery path according to a greedy algorithm and the sequence of the first types of orders to be delivered to obtain a first delivery path planned for the first types of orders to be delivered; and sequencing the second types of orders to be distributed according to a target order sequencing strategy indicated by a target planning method, sequentially inserting the position corresponding to each second type of order to be distributed into the first distribution path according to a greedy algorithm and the sequence of the second types of orders to be distributed to obtain a second distribution path, and determining the second distribution path as the distribution path of the plurality of orders to be distributed.
306. The server recommends the delivery path to the delivery capacity.
After obtaining the delivery path, the server may recommend the delivery capacity to the delivery capacity, so as to instruct the delivery capacity to complete the delivery tasks of the plurality of orders to be delivered according to the delivery path in sequence. The server recommending the delivery path to the delivery capacity may send the delivery path to the client registered by the delivery capacity.
According to the distribution path planning method provided by the embodiment of the application, the path quality of the distribution path planned for the order to be distributed by different planning methods can be predicted according to the characteristics of the order to be distributed, so that the target planning method is selected according to the prediction result, the distribution path of the order to be distributed is planned according to the target planning method, the processing amount of distribution path planning is reduced compared with the method of planning the distribution path for the order to be distributed by adopting each planning method, the path quality of the planned distribution path is ensured, and the distribution efficiency of the distribution capacity of the distribution order according to the distribution path is ensured.
In addition, the order to be delivered is further divided into the first type of order and the second type of order, and when the delivery path is planned, the order which has completed the goods taking task is considered preferentially, so that the order which has completed the goods taking task can be completed as soon as possible, and the quality reduction of the articles corresponding to the order due to the long delivery time is avoided.
In addition, the embodiment of the application also predicts the path quality information corresponding to the candidate planning methods through the prediction model, and ensures the accuracy of the obtained path quality information, so that a better candidate planning method can be selected to plan the distribution path for the multiple orders to be distributed.
It should be noted that, in the embodiment of the present application, the first planning method (RETA) is to sort the multiple orders to be delivered according to the expected arrival time of the orders, and sequentially insert the positions corresponding to the multiple orders to be delivered into the delivery path according to the order sequence of the multiple orders to be delivered according to a greedy algorithm, so as to obtain the delivery path planned for the multiple orders to be delivered. And a second planning method (RU) is used for sequencing the orders to be distributed according to the urgency degree of the orders, and sequentially inserting the positions corresponding to the orders to be distributed into the distribution path according to the arrangement sequence of the orders to be distributed according to a greedy algorithm to obtain the distribution path planned for the orders to be distributed.
Since the planned delivery paths of the RETA and the RU for the same multiple orders to be delivered may be different, in order to evaluate the effects of the two planning methods, in the embodiment of the present application, two areas are selected for experiments, and the path quality of the delivery paths planned by the two planning methods is counted. The statistical results are shown in table 1.
TABLE 1
As can be seen from Table 1, the average distance between RETA and the optimal result is smaller, however, the RU can plan better delivery routes than RETA on more examples in terms of the number of optimal routes. This indicates that both RETA and RU planning methods are effective and that neither planning method can outperform the other in all scenarios, each with the best use of the birth lead. Therefore, in the embodiment of the present application, in order to ensure the path quality of the distribution path planned for the multiple orders to be distributed, a target planning method may be selected according to characteristics (usage scenarios) of the multiple orders to be distributed, so as to plan the distribution path for the multiple orders to be distributed.
Fig. 5 is a schematic structural diagram of a delivery route planning apparatus according to an embodiment of the present application, and referring to fig. 5, the apparatus includes:
an obtaining module 501, configured to obtain order information of a plurality of to-be-delivered orders of delivery capacity, where the order information at least includes a starting location, an ending location, and a predicted delivery time;
the predicting module 502 is configured to predict, according to the obtained multiple order information and planning strategies of multiple candidate planning methods, path quality information corresponding to the multiple candidate planning methods, where the path quality information indicates quality of a delivery path planned for the multiple orders to be delivered by using the candidate planning methods, and planning strategies of different candidate planning methods are different;
a selecting module 503, configured to select a target planning method from the multiple candidate planning methods according to the path quality information corresponding to the multiple candidate planning methods;
a planning module 504, configured to plan a distribution path for the multiple orders to be distributed by using the target planning method.
As shown in fig. 6, in a possible implementation manner, the path quality information is a quality score, and the predicting module 502 is configured to predict a quality score corresponding to each candidate planning method according to the plurality of order information and the planning strategies of the plurality of candidate planning methods; or,
the path quality information is an arrangement order of the candidate planning methods in the candidate planning methods, and the predicting module 502 is configured to predict an arrangement order of the candidate planning methods according to the order information and planning strategies of the candidate planning methods, and use the arrangement order of the candidate planning methods as the path quality information corresponding to the candidate planning methods, where the candidate planning methods are ordered according to a high-quality order of a delivery path planned for the orders to be delivered.
In a possible implementation manner, the selecting module 503 is configured to select, according to the quality score corresponding to each candidate planning method, a candidate planning distribution method with the highest quality score from the multiple candidate planning methods as the target planning method; or,
the selecting module 503 is configured to select, according to the arrangement order of the candidate planning methods, a candidate planning method corresponding to a target order from the candidate planning methods as the target planning method, where the target order is the arrangement order of the candidate planning method with the highest path quality of the distribution path planned for the multiple orders to be distributed in the candidate planning methods.
In a possible implementation manner, the path quality information is the same or different, and the predicting module 502 is configured to predict, according to the multiple order information and the planning strategies of the multiple candidate planning methods, whether the quality of the delivery paths planned by using the multiple candidate planning methods according to the multiple orders to be delivered is the same; and determining the prediction result as path quality information corresponding to the candidate planning methods.
In a possible implementation manner, the selecting module 503 is configured to select, in response to that the path quality information indicates that the quality of the delivery paths planned for the multiple orders to be delivered by using the multiple candidate planning methods is the same, any candidate planning method from the multiple candidate planning methods as the target planning method; or,
the selecting module 503 is configured to determine each candidate planning method as the target planning method in response to that the quality of the distribution paths planned for the multiple orders to be distributed by using the multiple candidate planning methods is different in the path quality information.
In one possible implementation, the planning module 504 includes:
a planning unit 5041, configured to plan, in response to that the number of the target planning methods is multiple, a distribution path for the multiple orders to be distributed by using each target planning method, so as to obtain multiple distribution paths;
a selecting unit 5042 is configured to determine a distribution path with the highest path quality among the plurality of distribution paths as a target distribution path.
In one possible implementation, the prediction module 502 includes:
a feature extraction unit 5021, configured to perform feature extraction on the multiple pieces of order information based on the planning strategies of the multiple candidate planning methods to obtain order features associated with path quality;
a predicting unit 5022, configured to process the order features based on the planning strategies of the multiple candidate planning methods, and predict path quality information corresponding to the multiple candidate planning methods.
In a possible implementation manner, the predicting unit 5022 is configured to obtain prediction models of the multiple candidate planning methods, process the order features, and predict path quality information corresponding to the multiple candidate planning methods, where the prediction models are configured to predict whether a planning strategy of each candidate planning method is suitable for the multiple orders to be delivered according to the order features of the multiple orders to be delivered; or,
the predicting unit 5022 is configured to obtain a prediction model of each candidate planning method, process the order features respectively, and predict path quality information corresponding to each candidate planning method, where the prediction model is configured to predict whether a planning strategy of the candidate planning method is suitable for the multiple orders to be delivered according to the order features of the multiple orders to be delivered.
In a possible implementation manner, the path quality information is the same or different, the order features include a plurality of order sub-features, and the predicting unit 5022 is configured to obtain a plurality of classification rules corresponding to planning strategies of the plurality of candidate planning methods; processing the plurality of order sub-features according to the plurality of classification rules to obtain classification results, wherein the classification results are the same or different; and determining path quality information corresponding to the candidate planning methods according to the obtained classification result.
In a possible implementation manner, the feature extraction unit 5021 is configured to perform feature extraction on the plurality of order information based on a plurality of dimensions corresponding to the plurality of candidate planning methods to obtain the order features, where the plurality of dimensions are dimensions to which the order information that affects the path quality and is determined based on the planning strategies of the plurality of candidate planning methods belongs.
In one possible implementation, the planning strategy of the plurality of candidate planning methods includes at least: sequencing the plurality of orders to be delivered according to the order urgency degree, and planning the delivery paths of the plurality of orders to be delivered according to the sequence of the plurality of orders to be delivered; sequencing the plurality of orders to be delivered according to the predicted delivery time, and planning the delivery paths of the plurality of orders to be delivered according to the sequence of the plurality of orders to be delivered;
the feature extraction unit 5021 is configured to perform at least one of:
performing feature extraction on the plurality of order information based on order attribute dimensions to obtain order attribute features;
performing feature extraction on the plurality of order information based on order distance dimensions to obtain distance attribute features among a plurality of task positions in the plurality of orders to be distributed, wherein the plurality of task positions comprise initial positions and end positions of the orders to be distributed;
and processing the plurality of order information based on the task point aggregation dimension to obtain the aggregation attribute characteristics of the initial positions and the end positions in the plurality of orders to be distributed.
In a possible implementation manner, the planning module 504 is configured to determine an order to be delivered, which has completed the picking task, in the plurality of orders to be delivered as a first type of order to be delivered; determining the orders to be delivered with uncompleted picking tasks in the plurality of orders to be delivered as second-class orders to be delivered; planning a first delivery path for the first type of orders to be delivered by adopting the target planning method; continuing to plan a second distribution path for the second type of orders to be distributed based on the first distribution path; and determining the second delivery path as the delivery path of the plurality of orders to be delivered.
It should be noted that: in the distribution path planning apparatus provided in the above embodiment, when planning a distribution path, only the division of the function modules is exemplified, and in practical applications, the function distribution may be completed by different function modules according to needs, that is, the internal structure of the computer device is divided into different function modules to complete all or part of the functions described above. In addition, the apparatus for planning a delivery path and the method for planning a delivery path provided in the foregoing embodiments belong to the same concept, and specific implementation processes thereof are described in detail in the method embodiments, and are not described herein again.
In an exemplary embodiment, a computer device is provided, which comprises one or more processors and one or more memories, in which at least one program code is stored, which is loaded and executed by the one or more processors to implement the delivery path planning method as in the above embodiments.
Optionally, the computer device is provided as a terminal. Fig. 7 shows a block diagram of a terminal 700 according to an exemplary embodiment of the present application. The terminal 700 may be: a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III, motion video Experts compression standard Audio Layer 3), an MP4 player (Moving Picture Experts Group Audio Layer IV, motion video Experts compression standard Audio Layer 4), a notebook computer, or a desktop computer. Terminal 700 may also be referred to by other names such as user equipment, portable terminal, laptop terminal, desktop terminal, and so on.
The terminal 700 includes: a processor 701 and a memory 702.
In some embodiments, the terminal 700 may further optionally include: a peripheral interface 703 and at least one peripheral. The processor 701, the memory 702, and the peripheral interface 703 may be connected by buses or signal lines. Various peripheral devices may be connected to peripheral interface 703 via a bus, signal line, or circuit board. Specifically, the peripheral device includes: at least one of radio frequency circuitry 704, display 705, camera 706, audio circuitry 707, positioning components 708, and power source 709.
The peripheral interface 703 may be used to connect at least one peripheral device related to I/O (Input/Output) to the processor 701 and the memory 702. In some embodiments, processor 701, memory 702, and peripheral interface 703 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 701, the memory 702, and the peripheral interface 703 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.
The Radio Frequency circuit 704 is used for receiving and transmitting RF (Radio Frequency) signals, also called electromagnetic signals. The radio frequency circuitry 704 communicates with a communication network and other communication devices via electromagnetic signals. The rf circuit 704 converts an electrical signal into an electromagnetic signal to transmit, or converts a received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 704 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a subscriber identity module card, and so forth. The radio frequency circuitry 704 may communicate with other terminals via at least one wireless communication protocol. The wireless communication protocols include, but are not limited to: metropolitan area networks, various generation mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and/or WiFi (Wireless Fidelity) networks. In some embodiments, the radio frequency circuit 704 may also include NFC (Near Field Communication) related circuits, which are not limited in this application.
The display screen 705 is used to display a UI (User Interface). The UI may include graphics, text, icons, video, and any combination thereof. When the display screen 705 is a touch display screen, the display screen 705 also has the ability to capture touch signals on or over the surface of the display screen 705. The touch signal may be input to the processor 701 as a control signal for processing. At this point, the display 705 may also be used to provide virtual buttons and/or a virtual keyboard, also referred to as soft buttons and/or a soft keyboard. In some embodiments, the display 705 may be one, providing the front panel of the terminal 700; in other embodiments, the display 705 can be at least two, respectively disposed on different surfaces of the terminal 700 or in a folded design; in still other embodiments, the display 705 may be a flexible display disposed on a curved surface or on a folded surface of the terminal 700. Even more, the display 705 may be arranged in a non-rectangular irregular pattern, i.e. a shaped screen. The Display 705 may be made of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), or other materials.
The camera assembly 706 is used to capture images or video. Optionally, the camera assembly 706 includes a front camera and a rear camera. The front camera is arranged on the front panel of the terminal, and the rear camera is arranged on the back of the terminal. In some embodiments, the number of the rear cameras is at least two, and each rear camera is any one of a main camera, a depth-of-field camera, a wide-angle camera and a telephoto camera, so that the main camera and the depth-of-field camera are fused to realize a background blurring function, and the main camera and the wide-angle camera are fused to realize panoramic shooting and VR (Virtual Reality) shooting functions or other fusion shooting functions. In some embodiments, camera assembly 706 may also include a flash. The flash lamp can be a monochrome temperature flash lamp or a bicolor temperature flash lamp. The double-color-temperature flash lamp is a combination of a warm-light flash lamp and a cold-light flash lamp, and can be used for light compensation at different color temperatures.
The audio circuitry 707 may include a microphone and a speaker. The microphone is used for collecting sound waves of a user and the environment, converting the sound waves into electric signals, and inputting the electric signals to the processor 701 for processing or inputting the electric signals to the radio frequency circuit 704 to realize voice communication. For the purpose of stereo sound collection or noise reduction, a plurality of microphones may be provided at different portions of the terminal 700. The microphone may also be an array microphone or an omni-directional acquisition microphone. The speaker is used to convert electrical signals from the processor 701 or the radio frequency circuit 704 into sound waves. The loudspeaker can be a traditional film loudspeaker and can also be a piezoelectric ceramic loudspeaker. When the speaker is a piezoelectric ceramic speaker, the speaker can be used for purposes such as converting an electric signal into a sound wave audible to a human being, or converting an electric signal into a sound wave inaudible to a human being to measure a distance. In some embodiments, the audio circuitry 707 may also include a headphone jack.
The positioning component 708 is used to locate the current geographic Location of the terminal 700 for navigation or LBS (Location Based Service). The Positioning component 708 can be a Positioning component based on the GPS (Global Positioning System) in the united states, the beidou System in china, the graves System in russia, or the galileo System in the european union.
In some embodiments, terminal 700 also includes one or more sensors 710. The one or more sensors 170 include, but are not limited to: acceleration sensor 711, gyro sensor 712, pressure sensor 713, fingerprint sensor 714, optical sensor 715, and proximity sensor 716.
The acceleration sensor 711 can detect the magnitude of acceleration in three coordinate axes of a coordinate system established with the terminal 700. For example, the acceleration sensor 711 may be used to detect components of the gravitational acceleration in three coordinate axes. The processor 701 may control the display screen 705 to display the user interface in a landscape view or a portrait view according to the gravitational acceleration signal collected by the acceleration sensor 711. The acceleration sensor 711 may also be used for acquisition of motion data of a game or a user.
The gyro sensor 712 may detect a body direction and a rotation angle of the terminal 700, and the gyro sensor 712 may acquire a 3D motion of the user on the terminal 700 in cooperation with the acceleration sensor 711. The processor 701 may implement the following functions according to the data collected by the gyro sensor 712: motion sensing (such as changing the UI according to a user's tilting operation), image stabilization at the time of photographing, game control, and inertial navigation.
Pressure sensors 713 may be disposed on a side frame of terminal 700 and/or underneath display screen 705. When the pressure sensor 713 is disposed on a side frame of the terminal 700, a user's grip signal on the terminal 700 may be detected, and the processor 701 performs right-left hand recognition or shortcut operation according to the grip signal collected by the pressure sensor 713. When the pressure sensor 713 is disposed at a lower layer of the display screen 705, the processor 701 controls the operability control on the UI interface according to the pressure operation of the user on the display screen 705. The operability control comprises at least one of a button control, a scroll bar control, an icon control and a menu control.
The fingerprint sensor 714 is used for collecting a fingerprint of the user, and the processor 701 identifies the identity of the user according to the fingerprint collected by the fingerprint sensor 714, or the fingerprint sensor 714 identifies the identity of the user according to the collected fingerprint. When the user identity is identified as a trusted identity, the processor 701 authorizes the user to perform relevant sensitive operations, including unlocking a screen, viewing encrypted information, downloading software, paying, changing settings, and the like. The fingerprint sensor 714 may be disposed on the front, back, or side of the terminal 700. When a physical button or a vendor Logo is provided on the terminal 700, the fingerprint sensor 714 may be integrated with the physical button or the vendor Logo.
The optical sensor 715 is used to collect the ambient light intensity. In one embodiment, processor 701 may control the display brightness of display screen 705 based on the ambient light intensity collected by optical sensor 715. Specifically, when the ambient light intensity is high, the display brightness of the display screen 705 is increased; when the ambient light intensity is low, the display brightness of the display screen 705 is adjusted down. In another embodiment, processor 701 may also dynamically adjust the shooting parameters of camera assembly 706 based on the ambient light intensity collected by optical sensor 715.
A proximity sensor 716, also referred to as a distance sensor, is disposed on a front panel of the terminal 700. The proximity sensor 716 is used to collect the distance between the user and the front surface of the terminal 700. In one embodiment, when the proximity sensor 716 detects that the distance between the user and the front surface of the terminal 700 gradually decreases, the processor 701 controls the display 705 to switch from the bright screen state to the dark screen state; when the proximity sensor 716 detects that the distance between the user and the front surface of the terminal 700 is gradually increased, the processor 701 controls the display 705 to switch from the breath-screen state to the bright-screen state.
Those skilled in the art will appreciate that the configuration shown in fig. 7 is not limiting of terminal 700 and may include more or fewer components than shown, or some components may be combined, or a different arrangement of components may be used.
Optionally, the computer device is provided as a server. Fig. 8 is a schematic structural diagram of a server according to an embodiment of the present application, where the server 800 may generate a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 801 and one or more memories 802, where the memory 802 stores at least one program code, and the at least one program code is loaded and executed by the processors 801 to implement the methods provided by the method embodiments. Of course, the server may also have components such as a wired or wireless network interface, a keyboard, and an input/output interface, so as to perform input/output, and the server may also include other components for implementing the functions of the device, which are not described herein again.
The server 800 is configured to perform the steps performed by the server in the above method embodiments.
In an exemplary embodiment, a computer readable storage medium, such as a memory including program code, executable by a processor in a computer device to perform the targeted dispatch capacity allocation method of the above embodiments is also provided. For example, the computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
In an exemplary embodiment, a computer program or a computer program product is also provided, which comprises computer program code, which, when executed by a computer, causes the computer to implement the delivery path planning method in the above-described embodiments.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only exemplary of the present application and should not be taken as limiting, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (15)
1. A delivery path planning method, characterized in that the method comprises:
acquiring order information of a plurality of orders to be delivered of delivery capacity, wherein the order information at least comprises a starting position, an ending position and predicted delivery time;
predicting path quality information corresponding to the candidate planning methods according to the acquired multiple order information and planning strategies of the candidate planning methods, wherein the path quality information represents the quality of distribution paths planned for the multiple orders to be distributed by adopting the candidate planning methods, and the planning strategies of different candidate planning methods are different;
selecting a target planning method from the candidate planning methods according to the path quality information corresponding to the candidate planning methods;
and planning distribution paths for the orders to be distributed by adopting the target planning method.
2. The method according to claim 1, wherein predicting path quality information corresponding to a plurality of candidate planning methods according to the obtained plurality of order information and planning strategies of the plurality of candidate planning methods comprises:
the path quality information is a quality score, and the quality score corresponding to each candidate planning method is predicted according to the plurality of order information and planning strategies of the plurality of candidate planning methods; or,
the path quality information is an arrangement order of the candidate planning methods in the candidate planning methods, an arrangement order of the candidate planning methods is predicted according to the order information and planning strategies of the candidate planning methods, the arrangement order of the candidate planning methods is used as the path quality information corresponding to the candidate planning methods, and the candidate planning methods are ordered according to the quality of distribution paths planned for the orders to be distributed.
3. The method according to claim 2, wherein the selecting a target planning method from the plurality of candidate planning methods according to the path quality information corresponding to the plurality of candidate planning methods comprises:
selecting a candidate planning distribution method with the highest quality score from the plurality of candidate planning methods as the target planning method according to the quality score corresponding to each candidate planning method; or,
according to the arrangement sequence of the candidate planning methods, selecting a candidate planning method corresponding to a target sequence from the candidate planning methods as the target planning method, wherein the target sequence is the arrangement sequence of the candidate planning method with the highest path quality of a distribution path planned for the orders to be distributed in the candidate planning methods.
4. The method according to claim 1, wherein the path quality information is the same or different, and predicting the path quality information corresponding to a plurality of candidate planning methods according to the obtained plurality of order information and planning strategies of the plurality of candidate planning methods comprises:
predicting whether the quality of distribution paths planned for the multiple orders to be distributed by adopting the multiple candidate planning methods is the same or not according to the multiple order information and planning strategies of the multiple candidate planning methods;
and determining the prediction result as path quality information corresponding to the candidate planning methods.
5. The method according to claim 1, wherein selecting a target planning method from the plurality of candidate planning methods according to the path quality information corresponding to the plurality of candidate planning methods comprises:
in response to the path quality information indicating that the quality of the delivery paths planned for the plurality of orders to be delivered by the plurality of candidate planning methods is the same, selecting any one candidate planning method from the plurality of candidate planning methods as the target planning method; or,
and determining each candidate planning method as the target planning method in response to the fact that the quality of the distribution paths planned for the plurality of orders to be distributed by the plurality of candidate planning methods is different from the quality of the distribution paths planned for the plurality of orders to be distributed by the plurality of candidate planning methods.
6. The method of claim 1, wherein planning a delivery path for the plurality of orders to be delivered using the goal planning method comprises:
in response to the fact that the number of the target planning methods is multiple, adopting each target planning method to plan distribution paths for the orders to be distributed to obtain multiple distribution paths;
and determining the distribution path with the highest path quality in the plurality of distribution paths as a target distribution path.
7. The method according to claim 1, wherein predicting path quality information corresponding to a plurality of candidate planning methods according to the obtained plurality of order information and planning strategies of the plurality of candidate planning methods comprises:
based on the planning strategies of the candidate planning methods, performing feature extraction on the order information to obtain order features related to path quality;
and processing the order features based on the planning strategies of the candidate planning methods, and predicting the path quality information corresponding to the candidate planning methods.
8. The method according to claim 7, wherein the processing the order characteristics based on the planning strategies of the candidate planning methods to predict the path quality information corresponding to the candidate planning methods comprises:
obtaining a prediction model of the candidate planning methods, processing the order features, and predicting path quality information corresponding to the candidate planning methods, wherein the prediction model is used for predicting whether a planning strategy of each candidate planning method is suitable for the candidate orders to be delivered according to the order features of the candidate orders to be delivered; or,
and acquiring a prediction model of each candidate planning method, respectively processing the order characteristics, and predicting path quality information corresponding to each candidate planning method, wherein the prediction model is used for predicting whether a planning strategy of the candidate planning method is suitable for a plurality of orders to be delivered according to the order characteristics of the plurality of orders to be delivered.
9. The method according to claim 7, wherein the path quality information is the same or different, the order feature comprises a plurality of order sub-features, and the predicting the path quality information corresponding to the plurality of candidate planning methods by processing the order feature based on the planning strategies of the plurality of candidate planning methods comprises:
obtaining a plurality of classification rules corresponding to the planning strategies of the plurality of candidate planning methods;
processing the sub-characteristics of the orders according to the classification rules to obtain classification results, wherein the classification results are the same or different;
and determining path quality information corresponding to the candidate planning methods according to the obtained classification result.
10. The method according to claim 7, wherein the performing feature extraction on the plurality of order information based on the planning strategies of the plurality of candidate planning methods to obtain order features associated with path quality comprises:
and performing feature extraction on the plurality of order information based on a plurality of dimensions corresponding to the plurality of candidate planning methods to obtain the order features, wherein the plurality of dimensions are dimensions to which the order information which influences the path quality and is determined based on the planning strategies of the plurality of candidate planning methods belongs.
11. The method of claim 10, wherein the planning strategy for the plurality of candidate planning methods comprises at least: sequencing the plurality of orders to be delivered according to the order urgency degree, and planning the delivery paths of the plurality of orders to be delivered according to the sequence of the plurality of orders to be delivered; sequencing the plurality of orders to be delivered according to the predicted delivery time, and planning the delivery paths of the plurality of orders to be delivered according to the sequence of the plurality of orders to be delivered;
the step of performing feature extraction on the plurality of order information based on a plurality of dimensions corresponding to the plurality of candidate planning methods to obtain the order features comprises at least one of the following steps:
performing feature extraction on the plurality of order information based on order attribute dimensions to obtain order attribute features;
performing feature extraction on the plurality of order information based on order distance dimensions to obtain distance attribute features among a plurality of task positions in the plurality of orders to be delivered, wherein the plurality of task positions comprise initial positions and end positions of the orders to be delivered;
and processing the plurality of order information based on the task point aggregation dimension to obtain the aggregation attribute characteristics of the initial positions and the end positions in the plurality of orders to be distributed.
12. The method of claim 1, wherein planning a delivery path for the plurality of orders to be delivered using the goal planning method comprises:
determining the order to be delivered, which has completed the goods taking task, in the plurality of orders to be delivered as a first type of order to be delivered;
determining the orders to be delivered with uncompleted picking tasks in the plurality of orders to be delivered as second-class orders to be delivered;
planning a first delivery path for the first type of orders to be delivered by adopting the target planning method;
continuing to plan a second distribution path for the second type of orders to be distributed based on the first distribution path;
and determining the second delivery path as the delivery path of the plurality of orders to be delivered.
13. A delivery path planning apparatus, comprising:
the system comprises an acquisition module, a delivery module and a delivery module, wherein the acquisition module is used for acquiring order information of a plurality of to-be-delivered orders of delivery capacity, and the order information at least comprises a starting position, an ending position and predicted delivery time;
the prediction module is used for predicting path quality information corresponding to the candidate planning methods according to the acquired multiple order information and planning strategies of the candidate planning methods, wherein the path quality information represents the quality of distribution paths planned for the multiple orders to be distributed by adopting the candidate planning methods, and the planning strategies of different candidate planning methods are different;
a selecting module, configured to select a target planning method from the multiple candidate planning methods according to path quality information corresponding to the multiple candidate planning methods;
and the planning module is used for planning distribution paths for the plurality of orders to be distributed by adopting the target planning method.
14. A computer device comprising one or more processors and one or more memories having at least one program code stored therein, the at least one program code loaded into and executed by the one or more processors to perform operations performed by a delivery path planning method according to any one of claims 1 to 12.
15. A computer-readable storage medium having stored therein at least one program code, which is loaded and executed by a processor to perform operations performed by a delivery path planning method according to any one of claims 1 to 12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110735434.6A CN115545591A (en) | 2021-06-30 | 2021-06-30 | Distribution path planning method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110735434.6A CN115545591A (en) | 2021-06-30 | 2021-06-30 | Distribution path planning method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115545591A true CN115545591A (en) | 2022-12-30 |
Family
ID=84716859
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110735434.6A Pending CN115545591A (en) | 2021-06-30 | 2021-06-30 | Distribution path planning method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115545591A (en) |
-
2021
- 2021-06-30 CN CN202110735434.6A patent/CN115545591A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108304265B (en) | Memory management method, device and storage medium | |
| CN111080207A (en) | Order processing method, device, equipment and storage medium | |
| CN111144822A (en) | Warehouse-out time length determining method and device, computer equipment and storage medium | |
| CN110569220B (en) | Game resource file display method and device, terminal and storage medium | |
| CN111126925A (en) | Method and device for determining replenishment quantity of front bin, computer equipment and storage medium | |
| CN111612398A (en) | Warehouse goods distribution method and device, computer equipment and storage medium | |
| CN111563201A (en) | Content pushing method, device, server and storage medium | |
| CN115293841A (en) | Order scheduling method, device, equipment and storage medium | |
| CN113949678B (en) | Flow control method, flow control device, electronic equipment and computer readable storage medium | |
| CN111695981A (en) | Resource transfer method, device and storage medium | |
| CN110197055B (en) | Method, device, equipment and storage medium for managing information | |
| CN115545591A (en) | Distribution path planning method, device, equipment and storage medium | |
| CN112287193A (en) | Data clustering method and device, computer equipment and storage medium | |
| CN110928913A (en) | User display method, device, computer equipment and computer readable storage medium | |
| CN114862205B (en) | Resource allocation method, device, equipment and computer readable storage medium | |
| CN113469590B (en) | Delivery time interval distribution method, device, equipment and storage medium | |
| CN115311851B (en) | Road condition information determining method and device, electronic equipment and storage medium | |
| CN114971103A (en) | Distribution capacity selection method, distribution capacity selection device, distribution capacity selection equipment and storage medium | |
| CN116757565A (en) | Adjusting method, adjusting device, adjusting equipment and storage medium | |
| CN111798075A (en) | Transport capacity object scheduling method, device, server and storage medium | |
| CN112330220A (en) | Order scheduling method, device, server and storage medium | |
| CN115375053A (en) | Order distribution method, device, equipment and computer readable storage medium | |
| CN115293839A (en) | Order distribution method, device, equipment and computer readable storage medium | |
| CN116567805A (en) | Method, apparatus, device and computer readable storage medium for state recognition | |
| CN116432912A (en) | Distribution method and device of waybill collection, electronic equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |