CN109919532B - Logistics node determining method and device - Google Patents
Logistics node determining method and device Download PDFInfo
- Publication number
- CN109919532B CN109919532B CN201711330811.8A CN201711330811A CN109919532B CN 109919532 B CN109919532 B CN 109919532B CN 201711330811 A CN201711330811 A CN 201711330811A CN 109919532 B CN109919532 B CN 109919532B
- Authority
- CN
- China
- Prior art keywords
- node
- delivery
- logistics
- primary
- nodes
- 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.)
- Active
Links
Images
Abstract
The embodiment of the application provides a method and a device for determining a logistics node, which relate to the technical field of logistics and comprise the following steps: determining estimated logistics bill quantity from a plurality of primary nodes of a delivery site to secondary nodes of the delivery site; determining logistic cost parameters from the first-level nodes of the plurality of delivery places to the second-level nodes of the plurality of candidate delivery places; according to the estimated logistics bill quantity and logistics cost parameters, a node distribution model is utilized to determine a target delivery site secondary node and a delivery site primary node corresponding to the target delivery site secondary node, the purpose of adding the spliced direct-delivery line on the basis of the original direct-delivery line is achieved, the problems that the quantity of the existing direct-delivery line is small, the express delivery gathering time in the starting point of the existing direct-delivery line is long are solved, and the method has the advantages of improving logistics efficiency and reducing logistics cost.
Description
Technical Field
The present disclosure relates to the field of logistics technologies, and in particular, to a method and an apparatus for determining a logistics node.
Background
With the development of the express industry, the express business volume is also increased. However, in the case of rapid increase in the amount of couriers, the number of logistics transit centers is not significantly increased; meanwhile, the processing capacity of the transfer center cannot break through all the time due to the limitation of the field.
In general, a logistics merchant of electronic commerce cooperation counts average freight bill quantity of each website in a period of time in the past according to the dimension of a first-level node of the receiving site (the single quantity of the website sent to the first-level node of the receiving site), takes the average freight bill quantity as daily single quantity of the corresponding website, considers that the express package of the website can be intensively distributed if the daily single quantity of the website exceeds a preset threshold value, opens a direct transmission line of the website and the first-level node of the corresponding receiving site at the moment, and sends the express package of the website to the first-level node of the receiving site through a transfer station according to a conventional flow if the daily single quantity of the website does not exceed the preset threshold value.
However, the opening of the straight line in the logistics mode has higher freight traffic requirements on the net points, and because the self-gathering capacity of a single net point is limited by factors such as an area, the straight line of a certain net point is opened according to the logistics mode, and the number of packages of the net point needs to reach a larger preset threshold value, so that the opening time of the straight line is longer, and the number of net points meeting the freight traffic is smaller in a certain time, so that the logistics efficiency is lower.
Disclosure of Invention
The technical problem to be solved by the embodiment of the application is to provide a logistics node determining method, so as to solve the problems that the conventional logistics mode is used for opening a straight line, the freight traffic requirement on net points is high, the number of net points meeting the freight traffic is small, and the logistics efficiency is low.
Correspondingly, the embodiment of the application also provides a logistics node determining device which is used for guaranteeing the implementation and the application of the method.
In order to solve the above problems, an embodiment of the present application discloses a method for determining a logistics node, including:
determining estimated logistics bill quantity from a plurality of primary nodes of a delivery site to secondary nodes of the delivery site;
determining logistic cost parameters from the plurality of primary nodes of the delivery site to the plurality of secondary nodes of the candidate delivery site;
and determining a target delivery site secondary node and a delivery site primary node corresponding to the target delivery site secondary node by using a node distribution model according to the estimated logistics bill quantity and the logistics cost parameter.
The embodiment of the application discloses commodity circulation node determining device includes:
the first determining module is used for determining estimated logistics bill quantity from the first-level nodes of the delivery places to the second-level nodes of the receiving places;
A second determining module, configured to determine logistic cost parameters from the plurality of primary nodes of the delivery site to the plurality of secondary nodes of the candidate delivery site;
and the node distribution module is used for determining a target delivery site secondary node and a delivery site primary node corresponding to the target delivery site secondary node by utilizing a node distribution model according to the estimated logistics bill quantity and the logistics cost parameter.
Correspondingly, the embodiment of the application also discloses a device, which is characterized by comprising:
one or more processors; and
one or more machine readable media having instructions stored thereon, which when executed by the one or more processors, cause the apparatus to perform a method of determining a logistics node.
Accordingly, embodiments of the present application also disclose one or more machine-readable media having instructions stored thereon that, when executed by one or more processors, cause an apparatus to perform a method of determining a logistics node.
Embodiments of the present application include the following advantages:
according to the logistics node determining method and device, the estimated logistics bill quantity from the first-level nodes of the delivery site to the second-level nodes of the receiving site is determined; determining logistic cost parameters from the first-level nodes of the plurality of delivery places to the second-level nodes of the plurality of candidate delivery places; according to the estimated logistics bill quantity and logistics cost parameters, a node distribution model is utilized to determine a target delivery site secondary node and a delivery site primary node corresponding to the target delivery site secondary node, the purpose of increasing the splice delivery line on the basis of the original delivery line is achieved, the additional delivery line can be opened by rapidly gathering packages of a plurality of delivery nodes to one delivery site secondary node, the time required for gathering the packages to one delivery site secondary node is shorter, the problem of long logistics package gathering time in the starting point of the existing delivery line is solved, the number of the delivery lines is increased, logistics efficiency is improved, and the determination process of the estimated logistics bill quantity and logistics cost parameters are combined to participate in the determination process of the logistics nodes, so that the path of the package gathering is as short as possible, the determination of the logistics nodes can be optimized according to the logistics cost parameters, and the beneficial effects of reducing the logistics cost are achieved.
Drawings
FIG. 1 is a schematic process diagram of a method for determining a logistics node in an embodiment of the present application;
FIG. 2 is a flow chart of steps of a method for determining a logistics node in an embodiment of the present application;
FIG. 3 is a flowchart illustrating specific steps of a method for determining a logistics node in an embodiment of the present application;
FIG. 3A is a schematic diagram of an acceptance criteria function for simulated annealing in an embodiment of the application;
FIG. 4 is a flow chart of steps of a method for logistics transportation based on a method for determining logistics nodes in an embodiment of the present application;
FIG. 5 is a block diagram of a logistics node determining apparatus in an embodiment of the present application;
FIG. 6 is a specific block diagram of a determining device for a logistics node in an embodiment of the present application;
fig. 7 is a schematic diagram of a hardware structure of an apparatus in an embodiment of the present application.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will become more readily apparent, a more particular description of the invention briefly described above will be rendered by reference to specific embodiments that are illustrated in the appended drawings.
The common terms in the logistics node determining method provided by the application are as follows:
receiving site primary node: the express package is at last transfer center in commodity circulation transportation, and after the express package arrived the first grade node of receiving place, can be sent in the customer's hand by the express delivery person.
Receiving area secondary node: the system is divided into a plurality of goods collecting areas according to a routing rule, a place capable of supporting operation of a large number of packages is arranged in the goods collecting areas, and a first-level node of the goods receiving place is located in the center of the goods collecting areas as far as possible, and can be used as a second-level node of the goods receiving place.
Primary node of delivery site: the express package is at the first center of transporting in commodity circulation transportation for collect the express package of delivering from the storehouse.
Shipping site secondary node: and the network point is used for collecting a plurality of packages sent by the corresponding primary nodes of the delivery place, and opening a direct sending line from the secondary nodes of the delivery place to the secondary nodes of the receiving place when the quantity of the received packages meets the direct sending requirement.
At present, the whole sending flow of one express delivery is as follows: the delivery of the express delivery needs to be connected with the first-level node of the delivery place and the second-level node of the receiving place through the transfer center at present, so that the processing capacity of the transfer center is always unable to break through under the condition that the quantity of the express delivery is rapidly increased and limited by the place.
The concept of express delivery and direct delivery refers to that express delivery is directly sent to a receiving area secondary node from the receiving area secondary node, and a transfer center is not arranged in the middle of the direct delivery process, so that the sending efficiency can be greatly improved, and the transportation cost is reduced. In a specific implementation in an embodiment of the present application, the present application provides a concept of piece goods straight delivery, which can be decomposed into three parts: the first part is single-quantity estimation, the second part is rear-end goods gathering, and the third part is front-end goods gathering.
Firstly, the rear-end goods gathering is to combine the areas of the first-level nodes of the receiving places with similar receiving addresses in the express package destination on the premise of not influencing the aging, select one of the first-level nodes of the receiving places as a second-level node of the receiving places, and the second-level node of the receiving places has the meaning of being used as the end point of a direct-sending line and increases the single number of the direct-sending line.
And secondly, estimating the bill quantity by a server according to the historical bill quantity of the routes from the primary nodes of each delivery place to the secondary nodes of the receiving place.
And thirdly, front-end gathering is to select a node point aiming at a corresponding receiving-place secondary node from all the receiving-place secondary nodes as the receiving-place secondary node, and the corresponding receiving-place secondary node corresponding to the receiving-place secondary node is used as a terminal direct transmission line by matching the corresponding receiving-place secondary node for all the receiving-place secondary nodes so that the express received by the receiving-place primary nodes of all the receiving-places can be gathered at the corresponding receiving-place secondary node. Through front end gathering goods and rear end gathering goods, extra piece together goods and send out route directly has been increased on the basis of conventional line that sends out directly, has improved express delivery and has sent out efficiency directly, has saved the cost.
It should be noted that, in the embodiments of the present application, the receiving-place secondary node and the delivering-place secondary node need to have a place capable of supporting operations of a large number of packages and be located as far as possible in the center of the corresponding area.
Referring to fig. 1, a process schematic diagram based on a method for determining a logistics node in an embodiment of the present application is shown.
In a specific implementation of the logistics transportation method based on the secondary node of the delivery area, the logistics node determination method provided by the application needs to perform whole-network planning based on the split-shipment direct-delivery line once every set time interval, wherein the set time interval is several months, and the embodiment of the application does not limit the method. Referring to fig. 1, firstly, a single-volume estimation module extracts the historical logistics single volume from a first-level node of a delivery place to a first-level node of each receiving place in a preset time, and estimates estimated sub-logistics single volumes of a plurality of months in the future from the first-level node of each delivery place to the first-level node of each receiving place according to the historical logistics single volume.
In addition, each receiving area primary node may be divided into a plurality of receiving area according to a first preset rule, a receiving area primary node which can support the operation of a large number of packages in the receiving area and is located at the center of the corresponding area as far as possible is used as a candidate receiving area secondary node, for example, in the example of fig. 1, three primary receiving nodes including a receiving area primary node 1a, a receiving area primary node 1b and a receiving area primary node 1c are provided, at this time, a receiving area primary node 1c which can support the operation of a large number of packages and is located at the center of the corresponding area as far as possible is selected as a candidate receiving area secondary node 1, and the candidate receiving area secondary node is used for sending the received express packages to other receiving area primary nodes in the corresponding area. Specifically, as shown in fig. 1, the first-level node 1a of the receiving area, the first-level node 1b of the receiving area, and the second-level node 1 of the receiving candidate area are located in the same collecting area.
The estimated bill quantity from the first-level node of the delivery place to the second-level node of the receiving place is counted, for example, the estimated bill quantity of the second-level node 1 of the candidate receiving place is the sum of the estimated sub bill quantity of the first-level node 1a of the delivery place, the first-level node 1b of the delivery place and the estimated sub bill quantity of the second-level node 1 of the delivery place sent to the goods collecting area where the second-level node 1 of the receiving place is located, wherein the estimated sub bill quantity of the second-level node 1 of the delivery place sent to the corresponding goods collecting area when being used as one first-level node of the delivery place is referred to as the estimated sub bill quantity of the second-level node 1 of the delivery place.
Further, for each of the shipping areas, a candidate shipping area secondary node may be selected from the shipping area primary nodes according to a second preset rule, in the figure, three primary shipping nodes including a shipping area primary node 1a, a shipping area primary node 1b, and a shipping area primary node 1c are provided, at this time, a shipping area primary node 1c which is capable of supporting the operation of a large number of packages and is located as far as possible in the center of the corresponding area is selected as the candidate shipping area secondary node 1, and the candidate shipping area secondary node 1 is for the shipping area corresponding to the candidate shipping area secondary node 1, and may receive the parcels of the shipping area primary node 1a and the shipping area primary node 1 b.
Finally, selecting a candidate delivery site secondary node as a target delivery site secondary node based on a node allocation model through a node allocation module, determining a delivery site primary node corresponding to the target delivery site secondary node, namely a delivery site primary node 1a, determining the candidate delivery site secondary node 1 as the target delivery site secondary node 1 after receiving allocation information of the candidate delivery site secondary node 1 sent by a server by the delivery site primary node 1b, gathering the express delivery received to the corresponding collection area to the allocated target delivery site secondary node 1, sending the received express delivery package to the target delivery site secondary node 1 by the target delivery site secondary node 1 according to a delivery address to the corresponding delivery site primary node 1a, sending the received express delivery package to the delivery site primary node 1b, and finally sending the received express delivery package to a customer through a conventional flow.
Referring to fig. 2, a step flow chart of a method for determining a logistics node of the present application is shown, which may specifically include the following steps:
In the embodiment of the application, the database of the logistics system stores historical logistics list data from all the primary nodes of the delivery place to the primary nodes of each receiving place within a preset time, and the single-quantity estimation can estimate daily logistics list quantity of the primary nodes of the delivery place in a future period through one or more of the historical logistics list data.
In the embodiment of the application, the estimated logistics single quantity of the two-level node of the receiving area is counted, and the estimated logistics single quantity can be used as input in solving a subsequent node distribution model, so that the function of the node distribution model is perfected.
For the receiving area secondary nodes at the rear end, for each receiving area secondary node, the estimated logistics list amount from the receiving area primary node to the receiving area secondary node is counted, and whether the estimated logistics list amount meets the requirement of the direct-sending list amount can be judged. The method can execute the subsequent steps for the receiving area secondary node of which the estimated logistics single quantity meets the direct-delivery single quantity requirement, and does not execute the subsequent steps for the receiving area secondary node of which the estimated logistics single quantity does not meet the direct-delivery single quantity requirement, so that the calculated quantity is saved, and the system overhead is saved.
For example: the second-level nodes of the receiving site aiming at the first-level nodes of the receiving site are single quantities of cities such as Beijing, harbin, tianjin, huand Haote, and the like, and can be combined into the single quantity to the Beijing to be used as input in the solving of a follow-up node distribution model.
Specifically, the estimated sub-logistics list amount from the first-level node of the estimated delivery site to the first-level nodes of each receiving site can be calculated by counting the average value of the historical logistics list amounts in a preset time; through a time sequence model; the estimated sub-logistics single quantity obtained by the three methods covers almost all factors influencing the change of the logistics single quantity, so that the estimated sub-logistics single quantity obtained by the three methods can be weighted and averaged to obtain the most accurate estimated sub-logistics single quantity, and the estimated sub-logistics single quantity needs to be estimated for each receiving area secondary node.
In this embodiment of the present application, the logistic cost parameter from the first-level node of the plurality of shipping places to the second-level node of the plurality of candidate shipping places refers to a distance between each first-level node of the shipping places to each second-level node of the shipping places in the corresponding goods collecting area, and the logistic cost parameter data is stored in a database of the logistic system and can be extracted and invoked through a relevant interface. The logistic cost parameter may include a distance, a logistic cost, and the like, which are not limited in the embodiment of the present application. For example, the logistic cost parameter may be that the distance from the primary node a of the delivery site to the secondary node a of the candidate delivery site is 5.3 km, and the distance from the primary node B of the delivery site to the secondary node B of the candidate delivery site is 1.7 km.
And 203, determining a target delivery site secondary node and a delivery site primary node corresponding to the target delivery site secondary node by using a node allocation model according to the estimated logistics sheet quantity and the logistics cost parameter.
In the embodiment of the application, through a preset node distribution model, the estimated logistics list quantity from each shipping place primary node to the corresponding receiving place secondary node and the distance between each shipping place primary node and each shipping place secondary node in the corresponding goods collecting area are distributed to at least one preferred shipping place secondary node for each shipping place primary node by taking the sum of the minimum distances from each shipping place primary node to the corresponding shipping place secondary node as a target under the condition of meeting the direct invoice quantity range through a genetic algorithm, and the selection strategy of a genetic algorithm to a parent matrix can be optimized through an analog annealing algorithm, so that the genetic algorithm can be helped to jump out of a local optimal solution.
For example, a batch of express delivery is sent from Hangzhou, shaoxing, ningbo, wuxi, xishan, xianyang, baozhen to Beijing, tianjin, harbin, shijia. However, for Hangzhou-Beijing, shaoxing-Tianjin, ningbo-Harbin, wuxi-Shijizhuang, hangzhou and Xishan histories are larger than a first histories threshold, which indicates that Hangzhou and Xishan meet the site scale requirements, the Hangzhou, shaoxing, ningbo and Wuxi belonging to the same area can be selected as the secondary node of the delivery site, and Xishan, xianyang and Baozhen belonging to the same area can be selected as the secondary node of the delivery site. The division of Shaoxing, ningbo, wuxi to Hangzhou, xianyang, baoji to Xishan minimizes the logistics cost. Then Shaoxing, ningbo, tin-free to Beijing, tianjin, harbin, shijia logistic package to Hangzhou, chiyang, bao chicken to Beijing, tianjin, harbin, shijia logistic package to Xiean. Simultaneously, beijing can be selected from Beijing, tianjin, harbin and Shijia belonging to the same area as a second-level node of a receiving place, shaoxing, ningbo and Wuxi are carried out after collection of goods to Hangzhou, a direct transmission line of Hangzhou-Beijing, sian-Beijing is opened, and after express delivery reaches the Beijing, the Beijing is sent to Tianjin, harbin and Shijia according to the receiving place of the express delivery. Therefore, on the basis of the original Hangzhou-Beijing direct-sending line, a Ningbo-Beijing direct-sending line is added, and the logistics efficiency is improved.
In summary, according to the method for determining a logistics node provided by the embodiment of the application, the estimated logistics list amount from the first-level nodes of the delivery site to the second-level nodes of the receiving site is determined; determining logistic cost parameters from the first-level nodes of the plurality of delivery places to the second-level nodes of the plurality of candidate delivery places; according to the estimated logistics bill quantity and logistics cost parameters, a node distribution model is utilized to determine a target delivery site secondary node and a delivery site primary node corresponding to the target delivery site secondary node, the purpose of increasing the splice delivery line on the basis of the original delivery line is achieved, the additional delivery line can be opened by rapidly gathering packages of a plurality of delivery nodes to one delivery site secondary node, the time required for gathering the packages to one delivery site secondary node is shorter, the problem of long logistics package gathering time in the starting point of the existing delivery line is solved, the number of the delivery lines is increased, the logistics efficiency can be improved, and the route of the package gathering is as short as possible due to the fact that the estimated logistics bill quantity and logistics cost parameters are combined to participate in the determination process of the logistics nodes, so that the determination of the logistics node can be optimized according to the logistics cost parameters, and the logistics cost is reduced.
Referring to fig. 3, a flowchart illustrating specific steps of a method for determining a logistics node in the present application may specifically include the following steps:
In this embodiment of the present application, the first preset rule may be a routing rule, where the routing rule refers to that the router selects an optimal path according to information in the routing table, and forwards data. The routing rule can be applied to the logistics field, namely, according to the characteristic data of the receiving area primary nodes stored in the logistics server, the receiving area primary nodes with convenient traffic or close adjacent distances are divided into corresponding collecting areas, so that the condition that the receiving area primary nodes in the collecting areas are convenient in traffic and close adjacent distances is met, the characteristic data of the receiving area primary nodes comprise the size of the receiving area primary nodes, the distance from other receiving area primary nodes is close to far, the traffic convenience degree of the located positions is high, and the like, for example, a national collecting area can be divided into a north China area, a south China area, a northwest area and the like according to the routing rule, and each total area can be further subdivided into a plurality of small areas so as to further optimize the function of rear-end collecting.
Further, after the goods collecting area is divided, according to a routing rule, a first receiving area node which is used as a second receiving area node and can support operation of a large number of packages in the goods collecting area, is located at the center of the corresponding area as far as possible, has a historical goods receiving bill quantity larger than a second historical single quantity threshold value, and after the second receiving area node receives the express delivery, the second receiving area node sends the express delivery to the corresponding first receiving area node according to the goods receiving area. The efficiency of express delivery transportation has been improved. Among the first-order nodes of the receiving land, the first-order node of the receiving land closest to the center of the area may be selected as the second-order node of the receiving land, the second-order node of the receiving land having the historic receipt amount larger than the second threshold.
For example, the delivery of the first-class nodes of the receiving places such as Beijing, harbin, tianjin, huand Hao can be uniformly and firstly sent to the Beijing, and then the delivery of the first-class nodes of the final receiving places from the Beijing is carried out, wherein the Beijing is the second-class node of the candidate receiving places in the region of Harbin, tianjin, huand Hao.
Optionally, step 301 may further include sub-step 3011 and sub-step 3012.
Substep 3011, dividing each receiving location primary node into a plurality of collection areas according to a routing rule.
In this embodiment of the present application, the routing rule refers to that the router selects an optimal path according to information in the routing table, and forwards the data. The routing rule can be applied to the logistics field, namely, according to the characteristic data of the first-level nodes of the receiving places stored in the logistics server, the first-level nodes of the receiving places with convenient transportation or close adjacent distances are divided into corresponding goods collecting areas, so that the condition that the first-level nodes of the receiving places in the goods collecting areas are convenient to transport and close adjacent distances is met, the characteristic data of the first-level nodes of the receiving places comprise the size of the first-level nodes of the receiving places, the distance from the first-level nodes of the other receiving places is close to the first-level nodes of the receiving places, the transportation convenience degree of the positions is high, for example, the nationwide goods collecting area can be divided into a North China area, a south China area, a northwest area and other total areas according to the routing rule, and each total area can be further subdivided into a plurality of small areas so as to further optimize the functions of rear-end goods collection.
In the substep 3012, a receiving location primary node with a history flow order greater than a first preset threshold is selected from the receiving location primary nodes in each collection area as a candidate receiving location secondary node for the collection area.
Further, after the goods collecting area is divided, according to a routing rule, a first-level node of a receiving area, which can support operation of a large number of packages, in the goods collecting area and is located at the center of the corresponding area as far as possible is selected as a second-level node of the candidate receiving area, and after the target second-level node of the receiving area receives the express delivery, the second-level node of the receiving area sends the express delivery to the corresponding first-level node of the receiving area according to the receiving area. The efficiency of express delivery transportation has been improved.
For example, the first-level nodes of the receiving place can be the express delivery of centers such as Beijing, harbin, tianjin, huand Hatch, and the like, and the first-level nodes are uniformly sent to the Beijing, and then the first-level nodes are sent to the final destination center from the Beijing, and the Beijing is the second-level nodes of the receiving place of the areas belonging to Harbin, tianjin, huand Hatch.
This step may refer to step 201, and will not be described herein.
Optionally, step 302 may further comprise sub-step 3021, sub-step 3022 and sub-step 3023.
In a substep 3021, a historical logistics sheet amount from the primary node of the delivery site to the primary nodes of the receiving sites is obtained.
In the embodiment of the application, the database of the logistics system stores the historical logistics list quantity data from all the primary nodes of the delivery sites to the primary nodes of the receiving sites within the preset time, and the historical logistics list quantity data can be obtained by calling the corresponding interfaces.
Sub-step 3022, estimating estimated sub-logistics sheet amounts from the primary node of the delivery site to the primary nodes of the receiving sites according to the historical logistics sheet amounts.
In the step, the bill quantity estimation is to estimate daily bill quantity of the first-level node of the delivery place in a future period through the historical bill quantity data, and the estimated bill quantity data can be used for screening out the direct line from the first-level node of the delivery place meeting the direct bill quantity to the second-level node of the receiving place, and selecting the second-level node of the delivery place for the first-level node of the delivery place which does not meet the direct bill quantity, so that the sum of the estimated sub bill quantity of the first-level nodes of each delivery place corresponding to the second-level node of the delivery place can meet the requirement of the direct bill quantity.
Optionally, step 3022 may further include sub-step 30221, sub-step 30222, and sub-step 30223.
Sub-step 30221, inputting, into a regression model, a historical logistics list amount from the primary node of the delivery site to the primary nodes of each receiving site within a preset time and a factor parameter corresponding to the historical logistics list amount, and obtaining an estimated sub-logistics list amount from the primary node of the delivery site to the primary node of each receiving site, where the factor parameter includes: and training the regression model through the historical logistics list quantity from the primary node of the delivery place to the primary node of each receiving place within preset time and factor parameters corresponding to the historical logistics list quantity.
In practical application, the historical logistics single volume data of the express delivery network point is affected by a plurality of factors, for example: in different seasons, customers can purchase different products under the influence of seasons, for example, the throughput of air conditioning express delivery of some nodes in summer is more than that of other months, the historical single-volume data of the throughput express delivery nodes of cotton quilt express delivery of other nodes in winter is more than that of other months, or the express delivery nodes can generate a large quantity of orders under the influence of double 11 shopping nodes and black friday shopping nodes in 11 months. Therefore, the historical logistics sheet data of the express network points are greatly influenced by factors such as goods information, month, trend and the like.
In the embodiment of the application, a regression model can be preset, the regression model is obtained by training the historical logistics list amount from the primary node of the delivery site to the primary node of each receiving site within a preset time and factors corresponding to the historical logistics list amount based on a regression analysis algorithm, and the regression analysis is a calculation method and theory for researching the specific dependency relationship of one variable(s) on another variable(s). The method comprises the steps of starting from a group of sample data, determining mathematical relations among variables, carrying out various statistical tests on the credibility of the relations, and finding out which variables are significant in influence and not significant in influence from a plurality of variables affecting a specific variable. The value of one or more variables is predicted or controlled based on the calculated relationship, and the degree of accuracy of such prediction or control is given. It should be noted that, the regression model used in the present application may use linear regression, vector regression, lifting regression tree, etc., which is not limited in this application.
Therefore, the regression model is built by training the historical logistics list amount and the influence factors from the primary nodes of each delivery place to the primary nodes of each receiving place within the preset time to obtain a mathematical relation between the historical logistics list amount and the influence factors, wherein the influence factors in the mathematical relation are given a preset weight, such as the weight of goods information > the weight of trend > the weight of month. According to the mathematical relation, the estimated sub-logistics list quantity from the primary node of the delivery site to the primary nodes of each receiving site is estimated, and the more accurate estimated sub-logistics list quantity can be estimated by using the influence factors, so that the seasonal, trend and other factors are considered in the whole secondary node selection method of the delivery site, and the accuracy of secondary node selection of the delivery site is improved.
And a substep 30222, inputting the historical logistics list quantity from the primary node of the delivery place to the primary node of each receiving place within a preset time into a time sequence model, and obtaining the estimated sub-logistics list quantity from the primary node of the delivery place to the primary node of each receiving place, wherein the time sequence model is obtained through the historical logistics list quantity from the primary node of the delivery place to the primary node of each receiving place within the preset time and the date training corresponding to the historical logistics list quantity.
In production and scientific research, observation measurements are made on a variable or a set of variables x (t), and the discrete numbers obtained, which are arranged in time order at a series of instants t1, t2, …, tn (t being the independent variable) and used to interpret the mathematical expressions of the variables and the interrelationships, constitute a set of sequences, which we call the time series.
In the embodiment of the application, the method based on the time sequence can provide more accurate single-volume estimation by mining the trend and periodicity of the single-volume change of the historical logistics through a time sequence model, and the types of the time sequence model include, but are not limited to, an arma model, an arch model and the like.
Firstly, calculating daily single quantity (n 1, n2, …, n 30) of the line for nearly 30 days; and inputting the 30-day single quantity into a time sequence model, and outputting the model to obtain the estimated sub-logistics single quantity of the line.
For example, to predict the daily amount of the first node of the delivery site in the remaining Hangzhou area of Hangzhou, the first node of the receiving site in the Beijing transportation center, the daily amount of the route for about 30 days is calculated first, for example, (9013,8563, …, 8921), the daily amount of the route is input into the time series model, and after training, the estimated sub-amount of the logistics is output as 8792.
Sub-step 30223, taking the average value of the historic logistics list quantity from the primary node of the delivery place to the primary node of each receiving place in the preset time as the estimated sub-logistics list quantity from the primary node of the delivery place to the primary node of each receiving place.
And sub-step 30224, inputting the historical logistics list quantity of the primary node of the delivery site to the primary nodes of the receiving sites within a preset time and factor parameters corresponding to the historical logistics list quantity into a regression model, and obtaining the first estimated sub-logistics list quantity of the primary node of the delivery site to the primary nodes of the receiving sites. And inputting the historical logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place within a preset time into a time sequence model, and obtaining the second estimated sub-logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place. And taking the average value of the historical logistics list quantity from the primary node of the delivery place to the primary node of each receiving place in the preset time as the third estimated sub logistics list quantity from the primary node of the delivery place to the primary node of each receiving place. And carrying out weighted average on the first estimated sub-logistics single quantity, the second estimated sub-logistics single quantity and the third estimated sub-logistics single quantity by preset weights to obtain the estimated sub-logistics single quantity from the primary node of the delivery site to the primary nodes of the receiving sites.
In this step, in the foregoing substep 30221, substep 30222, and substep 30223, the first estimated sub-flow amount, the second estimated sub-flow amount, and the third estimated sub-flow amount are calculated respectively, and among these three results, the first estimated sub-flow amount is relatively more accurate, so that a weighted average may be performed on these three results, and a higher weight may be given to the first estimated sub-flow amount, and the obtained weighted average result is the estimated sub-flow amount covering most of the influencing factors and the time sequence factors, which further improves the accuracy of the estimated sub-flow amount, and further improves the accuracy of the second node selection of the shipping site.
For example, if the first estimated sub-stream count is a, the second estimated sub-stream count is B, and the third estimated sub-stream count is C, the final estimated sub-stream count=a×0.5+b×0.25+c×0.25.
Sub-step 3023, counting the estimated logistics list from each primary node of the delivery site to each secondary node of the candidate delivery site according to the primary nodes of the delivery site corresponding to each secondary node of the candidate delivery site.
In this embodiment of the present application, for the receiving area secondary node selected in step 301, the estimated logistics single quantity of the receiving area secondary node is counted, which can be used as the input when the subsequent node allocation model is solved, so as to perfect the function of the node allocation model. The number of the estimated logistics list amounts needs to meet the requirement of the direct-delivery list amounts, specifically, when the collection area is divided, the collection area is divided with the aim that the sum of the estimated sub logistics list amounts of the first-level nodes of the delivery area corresponding to the first-level nodes of the receiving area in the collection area is required to reach the direct-delivery list amounts.
And step 303, selecting candidate secondary nodes of the delivery site from the primary nodes of the delivery sites according to a second preset rule.
In the method, for the network points in the primary node of the delivery place, the estimated sub logistics list quantity does not meet the direct delivery list quantity requirement, the secondary node of the delivery place can be distributed for the network points to collect the goods, the secondary node of the delivery place mainly bears the function of the goods collection point, and the primary node of the delivery place delivers the received express delivery to the distributed secondary node of the delivery place and then takes charge of collecting the goods for direct delivery. The secondary node of the delivery site needs to possess several characteristics: 1. there are sites that can support the operation of a large number of packages. 2. The position is as central as possible.
Optionally, step 303 may further comprise sub-step 3031 and sub-step 3032.
Sub-step 3031, aggregating the primary node of the delivery place into a plurality of dot clusters according to a clustering algorithm according to the longitude and latitude of the position of the primary node of the delivery place.
The selection strategy of the candidate delivery site secondary node is as follows:
firstly, clustering all primary nodes of a delivery place according to longitude and latitude to obtain a plurality of dot clusters. Here, a Density-based clustering method, such as DBSCAN (clustering algorithm, english: density-Based Spatial Clustering of Applications with Noise), is adopted, and DBSCAN is a representative Density-based clustering algorithm. Unlike the partitioning and hierarchical clustering method, which defines clusters as the largest set of densely connected points, it is possible to partition a region having a sufficiently high density into clusters and find clusters of arbitrary shape in a noisy spatial database.
And substep 3032, determining the primary node of the delivery site closest to the center of the dot cluster as the secondary node of the candidate delivery site, wherein the estimated sub-logistics list amount in the dot cluster is larger than a second preset threshold value.
And combining the selection strategies in the substep 3031, further screening out large dots according to the estimated sub-logistics list quantity of the primary node of the delivery site, and setting the large dots close to the cluster center as the secondary node of the delivery site.
In this step, according to the estimated result of the substep 3022, the nodes in the primary node of the shipping place, in which the estimated sub-logistics sheet amount is greater than the preset threshold, are screened as large nodes, and the large nodes need to have a site capable of supporting the operation of a large number of packages, and finally the large nodes close to the cluster center in the large nodes meeting the conditions are set as the secondary node of the shipping place, which has the advantages of meeting the transportation of a large number of cargoes and being convenient to traffic with the surrounding primary nodes of the shipping place.
The selection of the two-stage nodes of the delivery area improves the front end goods gathering capacity of express delivery straight delivery logistics, increases the goods splicing straight delivery line on the basis of the conventional straight delivery line, reduces the cost of straight delivery logistics transportation and improves logistics efficiency.
For a specific description of this step, reference may be made to step 202 above, and will not be repeated here.
And 305, determining a target delivery site secondary node and a delivery site primary node corresponding to the target delivery site secondary node by using a node distribution model according to the estimated logistics sheet quantity and the logistics cost parameter.
For a specific description of this step, reference may be made to step 203 above, and details are not repeated here.
Optionally, the node allocation model is configured to determine a target destination secondary node and a destination primary node corresponding to the target destination secondary node, with a minimum sum of logistic cost parameters from each destination primary node to a corresponding destination secondary node under a condition that a direct bill amount range is satisfied.
In the embodiment of the application, through a preset node allocation model, the estimated logistics amount from each shipping place primary node to the corresponding receiving place secondary node and the distance between each shipping place primary node and each shipping place secondary node of the corresponding receiving place secondary node are distributed to at least one preferred shipping place secondary node for each shipping place primary node by taking the sum of the minimum distances from each shipping place primary node to the corresponding shipping place secondary node as a target under the condition of meeting the direct invoice amount range through a genetic algorithm, and the shipping place primary node can select any one from a plurality of preferred shipping place secondary nodes or can further screen the plurality of preferred shipping place secondary nodes through an analog annealing algorithm, so that the optimal shipping place secondary node is selected.
Optionally, step 305 may further include sub-step 3051, sub-step 3052.
And step 3051, inputting the estimated logistics single quantity and logistics cost parameters into a genetic model, and determining at least one group of target delivery site secondary nodes and the corresponding relation between the target delivery site secondary nodes and the delivery site primary nodes.
In the embodiment of the application, the node allocation model includes: genetic model.
In the embodiment of the application, the specific steps for selecting the secondary node of the target shipping place based on the genetic model are as follows:
step A1: an initial solution is constructed.
In this step, the primary node of the delivery site and the secondary node of the delivery site are initially encoded for one secondary node of the delivery site, and after encoding. The primary node of the delivery site becomes a vector, and the number in the vector represents the secondary node of the collection and delivery site corresponding to the primary node of the delivery site. It is generally necessary to generate two initial codes as parents and parents in a genetic algorithm, and calculate the fitness of the parents and parents, which is the sum of the distances between the secondary nodes of each shipment place and the corresponding primary nodes of each shipment place.
For example: and calculating the estimated logistics list quantity from the primary node of the delivery place to the secondary node of the receiving place, and making an estimated logistics list table, and calculating the distance between the primary node of the delivery place and the secondary node of the delivery place, so as to make a primary node of the delivery place and a secondary node distance table of the delivery place.
Estimated logistics list table
Primary node and secondary node distance meter for delivery site
There are provided a primary node set { A1, A2, …, an } of the delivery site, and a secondary node set { J1, J2, …, jm }.
Taking n=10, m=3 as an example (i.e., ten primary nodes at the origin and 3 secondary nodes at the origin)
As an example, an initial solution may be constructed as [2,1,3,1,2,2,3,1,1,2], the first subscript number 2 of which indicates that the primary node A1 of the origin is assigned to the secondary node J2 of the origin, the second subscript number 1 indicates that the primary node A2 of the origin is assigned to the secondary node J1 of the origin, the third subscript number 3 indicates that the primary node A3 of the origin is assigned to the secondary node J3 of the origin, and so on.
Thus, two solutions Sol1 and Sol2 can be constructed as parent parents:
Sol1＝[2,1,3,1,2,2,3,1,1,2]；
sol2＝[1,2,3,1,1,2,2,2,1,2]。
the two solutions represent the corresponding relations between two primary nodes of the delivery place and secondary nodes of the delivery place, and calculate the fitness K1 and K2 of Sol1 and Sol2, namely calculate the sum of the distances between the secondary nodes of the delivery place and the corresponding primary nodes of the delivery place according to the distance table of the primary nodes of the delivery place and the secondary nodes of the delivery place, and the sum of the distances between the secondary nodes of the delivery place and the corresponding primary nodes of the delivery place, which correspond to the corresponding relations of Sol1 and Sol 2.
Further, a range condition satisfying the sum of the estimated single amounts of the straight-run logistics, such as 9000-12000, may be set.
Step A2: a new solution is generated.
In this step, the parent and the parent are crossed (cross) and mutated (mutation), the crossed strategy generally uses a truncated interchange method, the mutated strategy generally uses a fixed mutation probability or a decay probability, the crossed and mutated parent can evolve more solutions, and more preferable solutions can be evolved, and a solution which satisfies the sum of the distances between the secondary nodes of each shipment place and the corresponding primary nodes of each shipment place under the condition of straight bill quantity is generated through the crossed and mutated, namely the more preferable solution.
For example, the crossover is specifically pair sol1= [2,1,3,1,2,2,3,1,1,2]; sol2 = [1,2,3,1,1,2,2,2,1,2] is crossed, the 6 th subscript and the 7 th subscript in Sol1 and Sol2 are selected as a cutting point, the first six subscripts of Sol1 and the last four subscripts of Sol2 are combined into a new child [2,1,3,1,2,2,2,2,1,2], and the first six subscripts of Sol2 and the last four subscripts of Sol1 are combined into another new child [1,2,3,1,1,2,3,1,1,2].
The mutation is to mutate a certain subscript number in Sol1 and Sol2 with random probability, and in this example, the subscript number after mutation cannot be greater than m (m=3), i.e. cannot exceed the number of secondary nodes of the shipping place.
Such as: sol1 = [2,1,3,1,2,2,3,1,1,2]
The new filial generation obtained by mutation is [1,1,3,1,2,2,3,1,1,2]
Step A3: fine-tuning the feasible solution.
In this step, regarding the obtained child, the sum of the total estimated amount of the object flow of each secondary node of the delivery site for the secondary node of the receiving site and the distance between each secondary node of the delivery site and each corresponding primary node of the delivery site is calculated in the relation between the primary node of the delivery site and the secondary node of the delivery site corresponding to the child, the sum of the distances which do not satisfy the condition of the direct amount of the object flow is multiplied by a preset penalty coefficient (such as penalty coefficient=1.2), the fitness of the child is reduced (under the constraint of targeting the sum of the minimum distances, the sum of the distances is multiplied by a value which is greater than one, the probability of the distance being the preferred solution is lower), so that when the cross mutation is performed again, the child which does not satisfy the constraint is not selected as the parent because the child fitness is small.
And finally, repeating the steps A2 and A3, iterating for preset times, selecting the child with the highest fitness in the current sequence as a parent body and a parent body, and repeating the cross mutation process until the sequence length is met.
Because different initial parents may eventually get different best solutions, multiple rounds of calculation are also performed for parent generation. In a new calculation, after the initial parent is generated, the above procedure is repeated to obtain the optimal solution finally generated by the initial parent. For example, if 100 solutions need to be generated, 100 rounds of iteration are required.
And comparing the final solutions generated by all parents, and selecting the solution with the maximum fitness as the final output. And converting the final output solution back to the delivery relation between the primary node of the delivery place and the secondary node of the target delivery place, namely, distributing a secondary node of the target delivery place to the primary node of the delivery place, and if the primary node of the delivery place is not distributed with the secondary node of the target delivery place, delivering the final output solution to the distribution center.
Sub-step 3052, the node allocation model further includes: and when a plurality of groups of target delivery site secondary nodes and the corresponding relation between the target delivery site secondary nodes and the delivery site primary nodes occur, determining an optimal group of target delivery site secondary nodes and the corresponding relation between the target delivery site secondary nodes and the delivery site primary nodes by using the annealing model.
In the embodiment of the application, based on a genetic algorithm model, a simulated annealing algorithm is applied to the substep 3051, the steps A2 and A3 are repeated in the genetic algorithm, the preset times are iterated, and the offspring with the highest fitness in the current sequence is selected as the father and mother.
The simulated annealing algorithm provides an acceptance criterion function
In the function, T0 is a preset initial threshold, x is a ratio of the current iteration number to the maximum iteration number, α is a half-life period, and a function curve of the initial threshold is shown in fig. 3A, wherein the larger the iteration number is, the smaller the probability that the child is received as a parent, the smaller the iteration number is, the larger the probability that the child is received as a parent, and by accepting a criterion function, a solution generated by each iteration can be jumped out more opportunely, so that selection of the parent is further optimized, and the finally generated optimal solution is obtained after multiple rounds of iteration. It should be noted that, the primary node of the shipping place may select any one from a plurality of preferred secondary nodes of the shipping place, or may optimize the selection strategy of the genetic algorithm on the parent through the simulated annealing algorithm, so as to help the genetic algorithm jump out of the local optimal solution. The present application is not limited in this regard.
Referring to fig. 4, a step flow chart of a logistics transportation method based on a logistics node determining method of the present application is shown, which specifically may include the following steps:
and step 401, selecting candidate receiving place secondary nodes from the receiving place primary nodes according to a first preset rule.
Reference may be made to step 301 at this step and will not be described in detail here.
In the step, the historical logistics list data from the first-level nodes of the delivery places to the first-level nodes of the receiving places in the preset time are stored in a database of a logistics system, the server can estimate the estimated sub logistics list from the first-level nodes of the delivery places to the first-level nodes of the receiving places by extracting the historical logistics list data, and then the estimated logistics list from the first-level nodes of the delivery places to the second-level nodes of the receiving places is counted according to the second-level nodes of the receiving places to which the first-level nodes of the receiving places belong.
Reference may be made to step 303 at this step and will not be described in detail here.
Reference may be made to step 304 at this step and will not be described in detail here.
And step 405, determining a target secondary node of the delivery place and a primary node of the delivery place corresponding to the target secondary node of the delivery place by using a node distribution model according to the estimated logistics sheet quantity and the logistics cost parameter.
Reference may be made to step 305 at this step and will not be described in detail here.
And step 406, when the primary node of the delivery place receives the logistics package sent to the primary node of the receiving place corresponding to the secondary node of the target receiving place, determining that the logistics route of the logistics package is from the primary node of the delivery place to the corresponding secondary node of the target delivery place, from the secondary node of the target delivery place to the secondary node of the target receiving place, and from the secondary node of the target receiving place to the primary node of the receiving place.
In the step, the current delivery progress of the express delivery can be determined by scanning the identification code when the express delivery reaches any one of the middle points in the delivery flow, and the delivery progress information can be uploaded to the server after the identification code is scanned.
Specifically, a first-level node of a delivery place obtains distribution information of a second-level node of the delivery place fed back by the server according to the collection request by sending the collection request to the server, distributes a second-level node of a target delivery place for the first-level node of the delivery place, when a member is sent to the first-level node of the delivery place by a delivery package, the first-level node of the delivery place sends distribution progress information of the delivery to the server through scanning the delivery progress information of the delivery according to the distributed second-level node information of the target delivery place, and the server feeds the distribution progress information of the delivery to a customer through a terminal so that the customer can know where the delivery is to be for the second-level node of the target delivery place to collect the delivery.
After the target delivery site secondary node receives the express delivery sent to the goods collecting area, the identification code of the express delivery is scanned and uploaded to the server, the delivery object of the express delivery can be determined to be the corresponding target delivery site secondary node, after the target delivery site secondary node corresponding to the target delivery site secondary node is determined, the express delivery is distributed to the target delivery site secondary node, and then the received express delivery is sent to the corresponding delivery site primary node according to the delivery site by the target delivery site secondary node, and finally the received express delivery is sent to a customer through a conventional process.
And step 407, when the primary node of the delivery site receives the logistic package sent to the primary nodes of the delivery site corresponding to the secondary nodes of other delivery sites, sending the logistic package according to a conventional mode.
In this step, when the delivery site primary node receives the logistic package sent to the receiving site primary node corresponding to the other receiving site secondary node, it may be determined that the straight spring is not reached, and at this time, the logistic package may be sent in a conventional manner, that is, by the delivery site primary node sending the logistic package through the delivery site transfer center.
In summary, according to the method for determining the logistics node provided by the embodiment of the present application, each receiving area primary node is divided into a plurality of receiving areas according to a routing rule, one receiving area secondary node serving as the receiving area is selected from each receiving area primary node in each receiving area, and for each receiving area secondary node, a plurality of receiving area secondary nodes for each receiving area secondary node are selected from each receiving area primary node according to a density clustering rule; and then, estimating estimated sub-logistics quantity from the first-level node of the delivery place to the first-level node of each receiving place, and distributing one of the second-level nodes of the plurality of delivery places in the goods collecting area for each first-level node of the delivery place according to the estimated logistics quantity from the first-level node of each delivery place to the second-level node of the receiving place and the distance between the first-level node of each delivery place and the second-level node of each receiving place, so that the aim of adding a spliced direct-delivery line on the basis of the original direct-delivery line is fulfilled, the additional direct-delivery line can be opened by rapidly gathering packages of the plurality of delivery nodes to the second-level node of one delivery place, the time required for gathering the packages to the second-level node of one delivery place is shorter, the problem that the gathering time of the logistics packages in the starting point of the existing direct-delivery line is long is solved, the number of the direct-delivery lines is increased, the logistics efficiency is improved, and the route of the package polymers is ensured to be as short as possible according to the estimated logistics quantity and the logistics cost parameters are combined to the determination process of the estimated logistics cost parameters.
Referring to fig. 5, a block diagram of a logistics node determining apparatus of the present application is shown, which may specifically include the following modules:
a first determining module 501 is configured to determine a predicted bill quantity from a plurality of primary nodes of a delivery site to a plurality of secondary nodes of the delivery site.
A second determining module 502 is configured to determine logistic cost parameters from the plurality of primary nodes of the origin to the plurality of secondary nodes of the candidate origin.
And the node allocation module 503 is configured to determine, according to the estimated logistics sheet amount and the logistics cost parameter, a target secondary node of the shipping place and a primary node of the shipping place corresponding to the target secondary node by using a node allocation model.
Referring to fig. 6, a specific structure diagram of a logistics node determining apparatus of the present application is shown, which may specifically include the following modules:
the first selection module 601 is configured to select a candidate receiving-site secondary node from the receiving-site primary nodes according to a first preset rule.
Optionally, the first selection module 601 may further include:
the goods collecting area dividing sub-module is used for dividing the first-level nodes of each goods receiving place into a plurality of goods collecting areas according to a routing rule;
the first selecting sub-module is used for selecting one receiving area primary node with the historical logistics list quantity larger than a first preset threshold value from the receiving area primary nodes in each collecting area as a candidate receiving area secondary node for the collecting area.
A first determining module 602 is configured to determine a predicted bill quantity from a plurality of primary nodes of a delivery site to a plurality of secondary nodes of the delivery site.
Optionally, the first determining module 602 may further include:
and the first acquisition sub-module is used for acquiring the historical logistics list quantity from the primary node of the delivery place to the primary nodes of the receiving places.
And the first estimating sub-module is used for estimating the estimated sub-logistics list quantity from the first-level node of the delivery site to the first-level nodes of the receiving sites according to the historical logistics list quantity.
Optionally, the first estimating sub-module may further include:
the regression model unit is used for inputting the historical logistics list quantity of the primary node of the delivery site to the primary node of each receiving site within the preset time and factor parameters corresponding to the historical logistics list quantity into the regression model, and obtaining the estimated sub logistics list quantity of the primary node of the delivery site to the primary node of each receiving site, wherein the factor parameters comprise: and training the regression model through the historical logistics list quantity from the primary node of the delivery place to the primary node of each receiving place within preset time and factor parameters corresponding to the historical logistics list quantity.
The time sequence model unit is used for inputting the historical logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place within the preset time into the time sequence model, obtaining the estimated sub logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place, and obtaining the time sequence model through the historical logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place within the preset time and the date training corresponding to the historical logistics list quantity.
And the average value estimating unit is used for taking the average value of the historical logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place in the preset time as the estimated sub logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place.
The first estimating unit is used for inputting the historical logistics list quantity of the first-stage node of the delivery place to the first-stage nodes of the receiving places in the preset time and factor parameters corresponding to the historical logistics list quantity into the regression model, and obtaining the first estimated sub-logistics list quantity of the first-stage node of the delivery place to the first-stage node of the receiving places.
The second estimating unit is used for inputting the historical logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place within the preset time into the time sequence model, and obtaining the second estimated sub-logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place.
And the third estimating unit is used for taking the average value of the historical logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place in the preset time as the third estimated sub logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place.
The weighted average unit is used for weighted average of the first estimated sub-logistics single quantity, the second estimated sub-logistics single quantity and the third estimated sub-logistics single quantity according to preset weights, and the estimated sub-logistics single quantity from the primary node of the delivery site to the primary nodes of the receiving sites is obtained.
And the statistics sub-module is used for counting the estimated logistics list quantity from each primary node of the delivery site to each secondary node of the candidate delivery site according to the primary node of the delivery site corresponding to each secondary node of the candidate delivery site.
The second selecting module 603 is configured to select a candidate secondary node of the shipping place from the primary nodes of the respective shipping places according to a second preset rule.
Optionally, the second selecting module 603 may further include:
and the node cluster aggregation sub-module is used for aggregating the primary node of the delivery place into a plurality of node clusters according to a clustering algorithm according to the longitude and latitude of the position of the primary node of the delivery place.
And the second selecting sub-module is used for determining the primary node of the delivery site closest to the center of the dot cluster as the secondary node of the candidate delivery site, wherein the estimated sub-logistics list quantity in the dot cluster is larger than a second preset threshold value.
A second determining module 604 is configured to determine logistic cost parameters from the plurality of primary nodes of the origin to the plurality of secondary nodes of the candidate origin.
The node allocation module 605 is configured to determine, according to the estimated logistics sheet amount and the logistics cost parameter, a target secondary node of the shipping place and a primary node of the shipping place corresponding to the target secondary node of the shipping place by using a node allocation model.
Optionally, the node allocation module 605 may further include:
and the genetic model submodule is used for inputting the estimated logistics quantity and logistics cost parameters into a genetic model and determining at least one group of target delivery site secondary nodes and the corresponding relation between the target delivery site secondary nodes and the delivery site primary nodes.
And when a plurality of groups of target delivery site secondary nodes and the corresponding relation between the target delivery site secondary nodes and the delivery site primary nodes occur, determining an optimal group of target delivery site secondary nodes and the corresponding relation between the target delivery site secondary nodes and the delivery site primary nodes by utilizing the annealing model.
The first path determining module 606 is configured to determine, when the first node of the delivery site receives a logistics package sent to a first node of the receiving site corresponding to the second node of the target receiving site, that a logistics route of the logistics package is from the first node of the delivery site to the second node of the corresponding target delivery site, from the second node of the target delivery site to the second node of the target receiving site, and from the second node of the target receiving site to the first node of the receiving site.
And the second path determining module 607 is configured to send the logistic package according to a conventional manner when the first-level node of the receiving place receives the logistic package sent to the first-level nodes of the receiving place corresponding to the second-level nodes of the other receiving places.
In summary, according to the logistics node determining device provided by the embodiment of the present application, each receiving area primary node is divided into a plurality of receiving areas according to a routing rule, one receiving area secondary node serving as the receiving area is selected from the receiving area primary nodes in each receiving area, and for each receiving area secondary node, a plurality of receiving area secondary nodes for the receiving area secondary nodes are selected from the receiving area primary nodes according to a density clustering rule; and then, estimating estimated sub-logistics quantity from the first-level node of the delivery place to the first-level node of each receiving place, and distributing one of the second-level nodes of the plurality of delivery places in the goods collecting area for each first-level node of the delivery place according to the estimated logistics quantity from the first-level node of each delivery place to the second-level node of the receiving place and the distance between the first-level node of each delivery place and the second-level node of each delivery place, so that the aim of adding a spliced direct-delivery line on the basis of the original direct-delivery line is fulfilled, the additional direct-delivery line can be opened by rapidly gathering packages of the plurality of delivery nodes to the second-level node of one delivery place, the time required for gathering the packages to the second-level node of one delivery place is shorter, the problem that the gathering time of the logistics packages in the starting point of the existing direct-delivery line is long is solved, the quantity of the direct-delivery line is increased, the logistics efficiency can be improved, and the route of the package polymer is ensured to be as short as possible according to the estimated logistics quantity and the logistics cost parameters are combined to the determination process of the estimated logistics cost parameters.
For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.
Fig. 7 is a schematic structural diagram of a server according to an embodiment of the present application. Referring to fig. 7, a server 700 may be used to implement the post address recommendation method provided in the above embodiments. The server 700 may vary considerably in configuration or performance and may include one or more central processing units (central processing units, CPU) 722 (e.g., one or more processors) and memory 732, one or more storage media 730 (e.g., one or more mass storage devices) storing applications 742 or data 744. Wherein memory 732 and storage medium 730 may be transitory or persistent. The program stored in the storage medium 730 may include one or more modules (not shown), each of which may include a series of instruction operations on a server. Still further, the central processor 722 may be configured to communicate with the storage medium 730 and execute a series of instruction operations on the server 700 in the storage medium 730.
The server 700 may also include one or more power supplies 726, one or more wired or wireless network interfaces 750, one or more input/output interfaces 758, one or more keyboards 756, and/or one or more operating systems 741, such as Windows ServerTM, mac OS XTM, unixTM, linuxTM, freeBSDTM, and the like. The central processor 722 may execute, among other things, the following instructions on the server 700:
determining estimated logistics bill quantity from a plurality of primary nodes of a delivery site to secondary nodes of the delivery site;
determining logistic cost parameters from the plurality of primary nodes of the delivery site to the plurality of secondary nodes of the candidate delivery site;
and determining a target delivery site secondary node and a delivery site primary node corresponding to the target delivery site secondary node by using a node distribution model according to the estimated logistics bill quantity and the logistics cost parameter.
Optionally, a candidate receiving site secondary node is selected from the receiving site primary nodes according to a first preset rule.
Optionally, dividing each receiving area primary node into a plurality of collecting areas according to a routing rule;
and selecting one receiving area primary node with the historical logistics quantity larger than a first preset threshold value from the receiving area primary nodes in each collecting area as a candidate receiving area secondary node for the collecting area.
Optionally, a candidate primary node is selected from the primary nodes of each shipment according to a second preset rule.
Optionally, according to the longitude and latitude of the position of the primary node of the delivery site, the primary node of the delivery site is aggregated into a plurality of dot clusters according to a clustering algorithm;
and determining the primary node of the delivery site closest to the center of the dot cluster as the secondary node of the candidate delivery site, wherein the estimated sub-logistics list quantity in the dot cluster is larger than a second preset threshold value.
Optionally, acquiring the historical logistics list amount from the primary node of the delivery site to the primary nodes of the receiving sites;
estimating estimated sub-logistics list quantity from the first-level node of the delivery site to each first-level node of the receiving site according to the historical logistics list quantity;
and counting the estimated logistics list from each primary node of the delivery site to each secondary node of the candidate delivery site according to the primary node of the delivery site corresponding to each secondary node of the candidate delivery site.
Optionally, the node allocation model is configured to determine a target destination secondary node and a destination primary node corresponding to the target destination secondary node, with a minimum sum of logistic cost parameters from each destination primary node to a corresponding destination secondary node under a condition that a direct bill amount range is satisfied.
Optionally, the node allocation model includes: a genetic model; the step of determining the target delivery site secondary node and the delivery site primary node corresponding to the target delivery site secondary node by using a node distribution model according to the estimated logistics bill quantity and the logistics cost parameter comprises the following steps:
inputting the estimated logistics quantity and logistics cost parameters into a genetic model, and determining at least one group of target delivery site secondary nodes and the corresponding relation between the target delivery site secondary nodes and the delivery site primary nodes.
Optionally, the node allocation model further includes: annealing the model; the step of inputting the estimated logistics quantity and logistics cost parameters into a genetic model to determine at least one group of target delivery site secondary nodes and the corresponding relation between the target delivery site secondary nodes and the delivery site primary nodes comprises the following steps:
when a plurality of groups of target delivery site secondary nodes and the corresponding relation between the target delivery site secondary nodes and the delivery site primary nodes occur, determining an optimal group of target delivery site secondary nodes and the corresponding relation between the target delivery site secondary nodes and the delivery site primary nodes by utilizing the annealing model.
Optionally, factor parameters corresponding to the historical logistics list amount and the historical logistics list amount from the primary node of the delivery site to the primary node of each receiving site in a preset time are input into a regression model, and the estimated sub logistics list amount from the primary node of the delivery site to the primary node of each receiving site is obtained, wherein the factor parameters comprise: and training the regression model through the historical logistics list quantity from the primary node of the delivery place to the primary node of each receiving place within preset time and factor parameters corresponding to the historical logistics list quantity.
Optionally, the historical logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place in the preset time is input into a time sequence model, the estimated sub logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place is obtained, and the time sequence model is obtained through the historical logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place in the preset time and the date training corresponding to the historical logistics list quantity.
Optionally, taking the average value of the historical logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place in a preset time as the estimated sub logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place.
Optionally, inputting the historical logistics list quantity of the first-level node of the delivery site to each first-level node of the receiving site within a preset time and factor parameters corresponding to the historical logistics list quantity into a regression model to obtain a first estimated sub-logistics list quantity from the first-level node of the delivery site to each first-level node of the receiving site;
inputting the historical logistics list quantity from the first-level node of the delivery site to the first-level node of each receiving site in a preset time into a time sequence model, and obtaining a second estimated sub-logistics list quantity from the first-level node of the delivery site to the first-level node of each receiving site;
taking the average value of the historical logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place in the preset time as the third estimated sub-logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place;
and carrying out weighted average on the first estimated sub-logistics single quantity, the second estimated sub-logistics single quantity and the third estimated sub-logistics single quantity by preset weights to obtain the estimated sub-logistics single quantity from the primary node of the delivery site to the primary nodes of the receiving sites.
Optionally, when the primary node of the delivery site receives the logistic package sent to the primary node of the receiving site corresponding to the secondary node of the target receiving site, determining that the logistic line of the logistic package is from the primary node of the delivery site to the corresponding secondary node of the target delivery site, from the secondary node of the target delivery site to the secondary node of the target receiving site, and from the secondary node of the target receiving site to the primary node of the receiving site;
And when the primary node of the delivery site receives the logistic package sent to the primary nodes of the delivery site corresponding to the secondary nodes of other delivery sites, sending the logistic package in a conventional mode.
Embodiments of the present application provide an apparatus, one or more machine-readable media having instructions stored thereon, which when executed by the one or more processors, cause the apparatus to perform a method of determining a logistics node.
Embodiments of the present application also provide one or more machine-readable media having instructions stored thereon that, when executed by one or more processors, perform a method of determining a logistics node.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.
It will be apparent to those skilled in the art that embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, the present embodiments may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present embodiments have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the present application.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.
The above description is made in detail on a method and an apparatus for determining a logistics node provided by the present application, and specific examples are applied to illustrate the principles and embodiments of the present application, where the above description of the examples is only used to help understand the method and core ideas of the present application; meanwhile, as those skilled in the art will have modifications in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.
Claims (28)
1. A method for determining a logistics node is characterized by comprising the following steps of
Determining estimated logistics bill quantity from a plurality of primary nodes of a delivery site to secondary nodes of the delivery site;
determining logistic cost parameters from the plurality of primary nodes of the delivery site to the plurality of secondary nodes of the candidate delivery site;
determining a target delivery site secondary node and a delivery site primary node corresponding to the target delivery site secondary node by using a node distribution model according to the estimated logistics bill quantity and logistics cost parameters;
when the first-level node of the delivery place receives the logistics package sent to the first-level node of the receiving place corresponding to the second-level node of the target receiving place, determining that a logistics line of the logistics package is from the first-level node of the delivery place to the second-level node of the corresponding target delivery place, from the second-level node of the target delivery place to the second-level node of the target receiving place, and from the second-level node of the target receiving place to the first-level node of the receiving place;
When the first-level node of the delivery site receives the logistic package sent to the first-level nodes of the delivery site corresponding to the second-level nodes of other delivery sites, the logistic package is sent in a conventional mode;
wherein, the first-level node of the receiving area is: the express package is transported to the last transfer center in the logistics transportation process;
the second-level node of the receiving area is as follows: dividing the system into a plurality of goods collecting areas according to a routing rule, wherein the system is provided with a receiving area primary node which can support the operation of a large number of packages and is positioned in the center of the goods collecting area as much as possible;
the primary node of the delivery site is as follows: the express package is used for collecting the express package which is taken out of the warehouse in the first transfer center in the logistics transportation process;
the secondary node of the delivery site is as follows: and the network point is used for collecting a plurality of packages sent by the corresponding primary nodes of the delivery place, and opening a direct sending line from the secondary nodes of the delivery place to the secondary nodes of the receiving place when the quantity of the received packages meets the direct sending requirement.
2. The method as recited in claim 1, further comprising:
and selecting a candidate receiving place secondary node from the receiving place primary nodes according to a first preset rule.
3. The method of claim 2, wherein the step of selecting candidate receiving site secondary nodes from the receiving site primary nodes according to a first preset rule comprises:
Dividing the first-level node of each receiving area into a plurality of goods collecting areas according to a routing rule;
and selecting one receiving area primary node with the historical logistics quantity larger than a first preset threshold value from the receiving area primary nodes in each collecting area as a candidate receiving area secondary node for the collecting area.
4. The method as recited in claim 1, further comprising:
and selecting candidate secondary nodes of the delivery places from the primary nodes of the delivery places according to a second preset rule.
5. The method of claim 4, wherein the step of selecting candidate primary nodes from among the respective primary nodes according to a second preset rule comprises:
according to the longitude and latitude of the position of the primary node of the delivery site, the primary node of the delivery site is aggregated into a plurality of dot clusters according to a clustering algorithm;
and determining the primary node of the delivery site closest to the center of the dot cluster as the secondary node of the candidate delivery site, wherein the estimated sub-logistics list quantity in the dot cluster is larger than a second preset threshold value.
6. The method of claim 1, wherein the step of determining the estimated logistics sheet from the plurality of primary nodes of the origin to the secondary nodes of the destination comprises:
Acquiring historical logistics list quantity from the primary node of the delivery site to the primary nodes of the receiving sites;
estimating estimated sub-logistics list quantity from the first-level node of the delivery site to each first-level node of the receiving site according to the historical logistics list quantity;
and counting the estimated logistics list from each primary node of the delivery site to each secondary node of the candidate delivery site according to the primary node of the delivery site corresponding to each secondary node of the candidate delivery site.
7. The method of claim 1, wherein the node allocation model is configured to determine a target destination secondary node and a destination primary node corresponding to the target destination secondary node, with a minimum sum of logistic cost parameters from each destination primary node to a corresponding destination secondary node, under a condition that a direct invoice amount range is satisfied.
8. The method of claim 7, wherein the node allocation model comprises: a genetic model; the step of determining the target delivery site secondary node and the delivery site primary node corresponding to the target delivery site secondary node by using a node distribution model according to the estimated logistics bill quantity and the logistics cost parameter comprises the following steps:
inputting the estimated logistics quantity and logistics cost parameters into a genetic model, and determining at least one group of target delivery site secondary nodes and the corresponding relation between the target delivery site secondary nodes and the delivery site primary nodes.
9. The method of claim 8, wherein the node allocation model further comprises: annealing the model; the step of inputting the estimated logistics quantity and logistics cost parameters into a genetic model to determine at least one group of target delivery site secondary nodes and the corresponding relation between the target delivery site secondary nodes and the delivery site primary nodes comprises the following steps:
when a plurality of groups of target delivery site secondary nodes and the corresponding relation between the target delivery site secondary nodes and the delivery site primary nodes occur, determining an optimal group of target delivery site secondary nodes and the corresponding relation between the target delivery site secondary nodes and the delivery site primary nodes by utilizing the annealing model.
10. The method of claim 6, wherein the step of predicting the estimated sub-sheet amount from the primary node of the origin to the primary node of each receiving destination based on the historical sheet amounts comprises:
inputting factor parameters corresponding to the historical logistics list quantity and the historical logistics list quantity of the primary node of the delivery site to the primary node of each receiving site in a preset time into a regression model, and obtaining the estimated sub logistics list quantity from the primary node of the delivery site to the primary node of each receiving site, wherein the factor parameters comprise: and training the regression model through the historical logistics list quantity from the primary node of the delivery place to the primary node of each receiving place within preset time and factor parameters corresponding to the historical logistics list quantity.
11. The method of claim 6, wherein the step of predicting the estimated sub-sheet amount from the primary node of the origin to the primary node of each receiving destination based on the historical sheet amounts comprises:
and inputting the historical logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place within the preset time into a time sequence model, obtaining the estimated sub logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place, and obtaining the time sequence model through training the historical logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place within the preset time and the date corresponding to the historical logistics list quantity.
12. The method of claim 6, wherein the step of predicting the estimated sub-sheet amount from the primary node of the origin to the primary node of each receiving destination based on the historical sheet amounts comprises:
and taking the average value of the historical logistics list quantity from the primary node of the delivery place to the primary node of each receiving place in the preset time as the estimated sub logistics list quantity from the primary node of the delivery place to the primary node of each receiving place.
13. The method of claim 6, wherein the step of predicting the estimated sub-sheet amount from the primary node of the origin to the primary node of each receiving destination based on the historical sheet amounts comprises:
Inputting the historical logistics list quantity of the first-level node of the delivery site to the first-level nodes of the receiving site within a preset time and factor parameters corresponding to the historical logistics list quantity into a regression model to obtain a first estimated sub-logistics list quantity from the first-level node of the delivery site to the first-level node of the receiving site;
inputting the historical logistics list quantity from the first-level node of the delivery site to the first-level node of each receiving site in a preset time into a time sequence model, and obtaining a second estimated sub-logistics list quantity from the first-level node of the delivery site to the first-level node of each receiving site;
taking the average value of the historical logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place in the preset time as the third estimated sub-logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place;
and carrying out weighted average on the first estimated sub-logistics single quantity, the second estimated sub-logistics single quantity and the third estimated sub-logistics single quantity by preset weights to obtain the estimated sub-logistics single quantity from the primary node of the delivery site to the primary nodes of the receiving sites.
14. A logistics node determining apparatus, comprising:
the first determining module is used for determining estimated logistics bill quantity from the first-level nodes of the delivery places to the second-level nodes of the receiving places;
A second determining module, configured to determine logistic cost parameters from the plurality of primary nodes of the delivery site to the plurality of secondary nodes of the candidate delivery site;
the node distribution module is used for determining a target delivery site secondary node and a delivery site primary node corresponding to the target delivery site secondary node by utilizing a node distribution model according to the estimated logistics sheet quantity and the logistics cost parameter;
the first path determining module is used for determining that a logistics route of the logistics package is from the first delivery site level node to the corresponding second delivery site level node when the first delivery site level node receives the logistics package sent to the first delivery site level node corresponding to the second delivery site level node, then from the second delivery site level node to the second delivery site level node, and then from the second delivery site level node to the first delivery site level node;
the second path determining module is used for sending the logistics package according to a conventional mode when the first-level node of the delivery site receives the logistics package sent to the first-level nodes of the delivery site corresponding to the second-level nodes of other delivery sites;
wherein, the first-level node of the receiving area is: the express package is transported to the last transfer center in the logistics transportation process;
The second-level node of the receiving area is as follows: dividing the system into a plurality of goods collecting areas according to a routing rule, wherein the system is provided with a site capable of supporting operation of a large number of packages, and the position of the system is as far as possible at a first-level node of a receiving site in the center of the goods collecting area;
the primary node of the delivery site is as follows: the express package is used for collecting the express package which is taken out of the warehouse in the first transfer center in the logistics transportation process;
the secondary node of the delivery site is as follows: and the network point is used for collecting a plurality of packages sent by the corresponding primary nodes of the delivery place, and opening a direct sending line from the secondary nodes of the delivery place to the secondary nodes of the receiving place when the quantity of the received packages meets the direct sending requirement.
15. The apparatus as recited in claim 14, further comprising:
and the first selection module is used for selecting candidate receiving place secondary nodes from the receiving place primary nodes according to a first preset rule.
16. The apparatus of claim 15, wherein the first selection module comprises:
the goods collecting area dividing sub-module is used for dividing the first-level nodes of each goods receiving place into a plurality of goods collecting areas according to a routing rule;
the first selecting sub-module is used for selecting one receiving area primary node with the historical logistics list quantity larger than a first preset threshold value from the receiving area primary nodes in each collecting area as a candidate receiving area secondary node for the collecting area.
17. The apparatus as recited in claim 14, further comprising:
and the second selection module is used for selecting candidate primary nodes of the delivery places from the primary nodes of the delivery places according to a second preset rule.
18. The apparatus of claim 17, wherein the second selection module comprises:
the node cluster aggregation sub-module is used for aggregating the primary node of the delivery place into a plurality of node clusters according to a clustering algorithm according to the longitude and latitude of the position of the primary node of the delivery place;
and the second selecting sub-module is used for determining the primary node of the delivery site closest to the center of the dot cluster as the secondary node of the candidate delivery site, wherein the estimated sub-logistics list quantity in the dot cluster is larger than a second preset threshold value.
19. The apparatus of claim 14, wherein the first determining module comprises:
the first acquisition sub-module is used for acquiring the historical logistics bill quantity from the primary node of the delivery site to the primary nodes of the receiving sites;
the first estimating sub-module is used for estimating the estimated sub-logistics list quantity from the first-level node of the delivery site to the first-level nodes of each receiving site according to the historical logistics list quantity;
and the statistics sub-module is used for counting the estimated logistics list quantity from each primary node of the delivery site to each secondary node of the candidate delivery site according to the primary node of the delivery site corresponding to each secondary node of the candidate delivery site.
20. The apparatus of claim 14, wherein the node allocation model is configured to determine a target destination secondary node and a destination primary node corresponding to the target destination secondary node, with a minimum sum of logistic cost parameters for each destination primary node to a corresponding destination secondary node, under conditions that satisfy a range of direct orders.
21. The apparatus of claim 20, wherein the node allocation model comprises: a genetic model, the node assignment module comprising:
and the genetic model submodule is used for inputting the estimated logistics quantity and logistics cost parameters into a genetic model and determining at least one group of target delivery site secondary nodes and the corresponding relation between the target delivery site secondary nodes and the delivery site primary nodes.
22. The apparatus of claim 21, wherein the node allocation model further comprises: an annealing model, the distribution module comprising:
and when a plurality of groups of target delivery site secondary nodes and the corresponding relation between the target delivery site secondary nodes and the delivery site primary nodes occur, determining an optimal group of target delivery site secondary nodes and the corresponding relation between the target delivery site secondary nodes and the delivery site primary nodes by utilizing the annealing model.
23. The apparatus of claim 19, wherein the first pre-evaluation sub-module comprises:
the regression model unit is used for inputting the historical logistics list quantity of the primary node of the delivery site to the primary node of each receiving site within the preset time and factor parameters corresponding to the historical logistics list quantity into the regression model, and obtaining the estimated sub logistics list quantity of the primary node of the delivery site to the primary node of each receiving site, wherein the factor parameters comprise: and training the regression model through the historical logistics list quantity from the primary node of the delivery place to the primary node of each receiving place within preset time and factor parameters corresponding to the historical logistics list quantity.
24. The apparatus of claim 19, wherein the first pre-evaluation sub-module comprises:
the time sequence model unit is used for inputting the historical logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place within the preset time into the time sequence model, obtaining the estimated sub logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place, and obtaining the time sequence model through the historical logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place within the preset time and the date training corresponding to the historical logistics list quantity.
25. The apparatus of claim 19, wherein the first pre-evaluation sub-module comprises:
and the average value estimating unit is used for taking the average value of the historical logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place in the preset time as the estimated sub logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place.
26. The apparatus of claim 19, wherein the first pre-evaluation sub-module comprises:
the first estimating unit is used for inputting the historical logistics list quantity of the first-level node of the delivery place to the first-level nodes of the receiving places in a preset time and factor parameters corresponding to the historical logistics list quantity into a regression model to obtain a first estimated sub-logistics list quantity of the first-level node of the delivery place to the first-level node of the receiving places;
the second estimating unit is used for inputting the historical logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place within a preset time into a time sequence model, and obtaining a second estimated sub-logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place;
the third estimating unit is used for taking the average value of the historical logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place in the preset time as the third estimated sub logistics list quantity from the first-level node of the delivery place to the first-level node of each receiving place;
The weighted average unit is used for weighted average of the first estimated sub-logistics single quantity, the second estimated sub-logistics single quantity and the third estimated sub-logistics single quantity according to preset weights, and the estimated sub-logistics single quantity from the primary node of the delivery site to the primary nodes of the receiving sites is obtained.
27. An apparatus, comprising:
one or more processors; and
one or more machine readable media having instructions stored thereon, which when executed by the one or more processors, cause the processors to perform the method of any of claims 1-13.
28. One or more machine readable media having instructions stored thereon, which when executed by one or more processors, cause the processors to perform the method of any of claims 1-13.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711330811.8A CN109919532B (en) | 2017-12-13 | 2017-12-13 | Logistics node determining method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711330811.8A CN109919532B (en) | 2017-12-13 | 2017-12-13 | Logistics node determining method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109919532A CN109919532A (en) | 2019-06-21 |
| CN109919532B true CN109919532B (en) | 2023-06-27 |
Family
ID=66958966
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711330811.8A Active CN109919532B (en) | 2017-12-13 | 2017-12-13 | Logistics node determining method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109919532B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110348612B (en) * | 2019-06-24 | 2022-12-27 | 深圳市恒路物流股份有限公司 | Distribution center cargo quantity prediction method and device |
| CN110516842B (en) * | 2019-07-18 | 2022-04-12 | 北京首钢自动化信息技术有限公司 | Two-stage coordination and optimized stowage method for large steel coil logistics |
| CN111882117A (en) * | 2020-07-07 | 2020-11-03 | 上海中通吉网络技术有限公司 | Express trunk route line flow prediction method, device and equipment |
| CN112474403B (en) * | 2020-12-03 | 2022-10-18 | 中邮信息科技(北京)有限公司 | Autonomous package management method, device, medium and electronic equipment |
| CN116384853B (en) * | 2023-03-01 | 2024-02-09 | 湖北普罗格科技股份有限公司 | Digital twin intelligent logistics management method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007153618A (en) * | 2005-11-09 | 2007-06-21 | Yamato Transport Co Ltd | Transportation information processing method |
| CN103984735A (en) * | 2014-05-21 | 2014-08-13 | 北京京东尚科信息技术有限公司 | Method and device for generating recommended delivery place name |
| CN105989456A (en) * | 2015-02-11 | 2016-10-05 | 成都诺铱科技有限公司 | Logistics multistage shunting distribution process |
| CN106096881A (en) * | 2016-06-08 | 2016-11-09 | 沈阳工业大学 | Storage consolidating the load mode vehicle path adverse selection method of operating |
| WO2017036331A1 (en) * | 2015-09-02 | 2017-03-09 | 阿里巴巴集团控股有限公司 | Logistics service information processing method and device |
| CN107194656A (en) * | 2017-07-04 | 2017-09-22 | 北京惠赢天下网络技术有限公司 | A kind of method and device for planning of the Distribution path based on standard container order |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160232637A1 (en) * | 2013-09-20 | 2016-08-11 | Nec Corporation | Shipment-Volume Prediction Device, Shipment-Volume Prediction Method, Recording Medium, and Shipment-Volume Prediction System |
-
2017
- 2017-12-13 CN CN201711330811.8A patent/CN109919532B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007153618A (en) * | 2005-11-09 | 2007-06-21 | Yamato Transport Co Ltd | Transportation information processing method |
| CN103984735A (en) * | 2014-05-21 | 2014-08-13 | 北京京东尚科信息技术有限公司 | Method and device for generating recommended delivery place name |
| CN105989456A (en) * | 2015-02-11 | 2016-10-05 | 成都诺铱科技有限公司 | Logistics multistage shunting distribution process |
| WO2017036331A1 (en) * | 2015-09-02 | 2017-03-09 | 阿里巴巴集团控股有限公司 | Logistics service information processing method and device |
| CN106096881A (en) * | 2016-06-08 | 2016-11-09 | 沈阳工业大学 | Storage consolidating the load mode vehicle path adverse selection method of operating |
| CN107194656A (en) * | 2017-07-04 | 2017-09-22 | 北京惠赢天下网络技术有限公司 | A kind of method and device for planning of the Distribution path based on standard container order |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109919532A (en) | 2019-06-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109919532B (en) | Logistics node determining method and device | |
| Zhalechian et al. | A self-adaptive evolutionary algorithm for a fuzzy multi-objective hub location problem: An integration of responsiveness and social responsibility | |
| Wang et al. | A genetic-algorithm-based approach to the two-echelon capacitated vehicle routing problem with stochastic demands in logistics service | |
| CN106527381B (en) | A kind of fast evaluation method towards parallel batch processing machine dynamic dispatching | |
| CN109819047B (en) | Mobile edge computing resource allocation method based on incentive mechanism | |
| CN104598994A (en) | Related logistics transportation optimized dispatching method with time-varying time window | |
| CN111368999B (en) | Logistics scheduling system | |
| CN107909228B (en) | Dynamic vehicle goods receiving and dispatching path planning method and device based on modular factor calculation | |
| CN111199375B (en) | Intelligent logistics transportation system | |
| CN113487081B (en) | Path optimization method based on logistics tracking | |
| CN111027911B (en) | Automatic logistics storage transportation scheduling system | |
| CN108256969A (en) | A kind of public bicycles lease point dispatcher-controlled territory division methods | |
| CN113259144A (en) | Storage network planning method and device | |
| CN108564391A (en) | A kind of shared electric vehicle needing forecasting method and system considering subjective and objective information | |
| CN113128744A (en) | Distribution planning method and device | |
| CN114897217A (en) | Fresh food electricity merchant front-end bin site selection-path planning method | |
| CN115759917A (en) | Logistics path planning method based on improved mixed ant colony algorithm | |
| CN110992123B (en) | Order distribution method and device | |
| CN110889738B (en) | Order distribution method and device | |
| Rabbani et al. | Solving uncapacitated multiple allocation p-hub center problem by Dijkstra’s algorithm-based genetic algorithm and simulated annealing | |
| CN115689412A (en) | Multi-period freight pricing and logistics network planning method | |
| CN111626492A (en) | Fuzzy multi-target opportunity constraint planning method for electric vehicle charging network | |
| Zhang et al. | Quantified edge server placement with quantum encoding in internet of vehicles | |
| XueJing et al. | Application of Genetic Algorithm in Logistics Path Optimization | |
| CN116029637A (en) | Cross-border electronic commerce logistics channel intelligent recommendation method and device, equipment and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |