CN111882117A - Express trunk route line flow prediction method, device and equipment - Google Patents
Express trunk route line flow prediction method, device and equipment Download PDFInfo
- Publication number
- CN111882117A CN111882117A CN202010646582.6A CN202010646582A CN111882117A CN 111882117 A CN111882117 A CN 111882117A CN 202010646582 A CN202010646582 A CN 202010646582A CN 111882117 A CN111882117 A CN 111882117A
- Authority
- CN
- China
- Prior art keywords
- parcel
- package
- information
- routing line
- acquiring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000003066 decision tree Methods 0.000 claims description 17
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 14
- 238000012549 training Methods 0.000 description 6
- 230000002354 daily effect Effects 0.000 description 4
- 230000003203 everyday effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a method, a device and a system for predicting route line flow of an express trunk line, belonging to the technical field of express delivery.A route line and parcel pair information of a target starting and ending point line in a target time period is obtained; acquiring the transport capacity information of each routing line based on the target time period; and predicting the parcel volume of each route line according to the parcel pair information, the transport capacity information of each route line and a preset prediction model. The invention can help to accumulate the experience of experts, reduce the dependence on the experience of experts and help the scheduling personnel with insufficient experience to learn the scheduling experience; the method can predict the package flow of the transfer and provide the package flow for dispatching personnel to carry out capacity allocation.
Description
Technical Field
The invention belongs to the technical field of express delivery, and particularly relates to a method, a device and equipment for predicting route line flow of an express trunk line.
Background
With the rapid development of the express industry, the competition in the industry is intensified day by day, the cost is reduced, the efficiency and the customer satisfaction degree are improved, and the method is a key factor for improving the competitiveness of a company.
The express transportation network comprises branch transportation and trunk transportation, wherein the trunk refers to a vehicle line from a transportation center to the transportation center, and the branch refers to a network point from the network point to the transportation center. With the increase of express delivery traffic, the existing trunk routing network is generally developed by gradually designing and optimizing experts with practical network planning experience. In actual operation, the number of packages between each operation point has fluctuation, and the dispatching of vehicles is relatively fixed, so that the routing of the packages depends on a dispatching expert to comprehensively and dynamically adjust and decide according to specific package carrying requirements and the transportation capacity resources of a company.
However, the experience of the scheduling expert is fuzzy and difficult to quantify, so that the experience is difficult to transfer, and the learning cost of a new scheduling person is high. Secondly, each transfer center is difficult to predict the parcel volume sent by other centers to the transfer center, and further the planning and scheduling of vehicle resources are difficult. Therefore, how to solve the routing problem of the express becomes a problem to be solved urgently in the prior art.
Disclosure of Invention
In order to at least solve the problems in the prior art, the invention provides an express trunk routing line flow prediction method, device and equipment.
The technical scheme provided by the invention is as follows:
on one hand, the method for predicting the flow of the route line of the express trunk line comprises the following steps:
acquiring routing line and package pair information of a target starting and ending line in a target time period;
acquiring the transport capacity information of each routing line based on the target time period;
and predicting the parcel volume of each routing line according to the parcel pair information, the transport capacity information of each routing line and a preset prediction model.
Optionally, the obtaining the transportation capacity information of each routing line includes: acquiring the transport capacity information of each package to the corresponding routing line;
predicting the parcel volume of each routing line according to the parcel pair information, the transport capacity information of each routing line and a preset prediction model, wherein the predicting comprises the following steps: and predicting the parcel volume of each parcel pair according to the parcel pair information, the transport capacity information of the routing line corresponding to each parcel pair and a preset prediction model.
Optionally, the method for constructing the preset model includes:
acquiring a routing line of the target starting and ending point line within a preset historical time period;
acquiring each routing line based on the routing information of the historical time period;
acquiring the package timeliness and cost of each routing line in the historical time period, and determining a target routing line;
based on the historical time period, acquiring package pair information and transport capacity of the target routing line, wherein the transport capacity comprises: the number of vehicles and the volume of vehicles, the parcel pair information for the target routing route including: the package number is recorded as a first package number;
acquiring the package quantity of other package pairs sharing the vehicle with the package of the target reason route in the historical time period, and recording the package quantity as a second package quantity;
and acquiring the preset prediction model according to the first parcel quantity, the second parcel quantity and the volume of the vehicle based on a mechanical algorithm.
Optionally, the machine learning algorithm includes:
decision trees, random forests or neural networks.
Optionally, the method further includes:
judging whether the parcel number is within a reference number threshold range, wherein the set standard of the reference number threshold is the load capacity of the target vehicle;
and if the number of the parcels is lower than the minimum value of the reference number threshold, placing the parcels similar to the terminal operation center into a target vehicle, wherein the number of the target vehicle is at least one.
Optionally, the method further includes: acquiring the weight information and the volume information of the parcel pair;
the method for setting the reference number threshold comprises the following steps:
acquiring a reference weight threshold according to the parcel weight information and the load weight information of the target vehicle; and the combination of (a) and (b),
acquiring a reference volume threshold according to the parcel volume information and the load volume information of the target vehicle;
determining the reference quantity threshold according to the reference weight threshold and the reference volume threshold.
In another aspect, an express trunk routing line traffic prediction apparatus includes: an acquisition module and a prediction module;
the acquisition module is used for acquiring the routing line and the package pair information of the target starting and ending line in the target time period; acquiring the transport capacity information of each routing line based on the target time period;
and the prediction module is used for predicting the parcel volume of each routing line according to the parcel pair information, the transport capacity information of each routing line and a preset prediction model.
Optionally, the obtaining module is configured to obtain the transportation capacity information of each package for the corresponding routing line; and the prediction module is used for predicting the parcel volume of each parcel pair according to the parcel pair information, the transport capacity information of the routing line corresponding to each parcel pair and a preset prediction model.
Optionally, the prediction module includes: the model building module is used for acquiring a routing line of the target starting and ending point line in a preset historical time period; acquiring each routing line based on the routing information of the historical time period; acquiring the package timeliness and cost of each routing line in the historical time period, and determining a target routing line; based on the historical time period, acquiring package pair information and transport capacity of the target routing line, wherein the transport capacity comprises: the number of vehicles and the volume of vehicles, the parcel pair information for the target routing route including: the package number is recorded as a first package number; acquiring the package quantity of other package pairs sharing the vehicle with the package of the target reason route in the historical time period, and recording the package quantity as a second package quantity; and acquiring the preset prediction model according to the first parcel quantity, the second parcel quantity and the volume of the vehicle based on a mechanical algorithm.
In another aspect, an express trunk routing line traffic prediction apparatus includes: a processor, and a memory coupled to the processor;
the memory is used for storing a computer program, and the computer program is at least used for executing the express trunk routing line flow prediction method;
the processor is used for calling and executing the computer program in the memory.
The invention has the beneficial effects that:
according to the method, the device and the equipment for predicting the flow of the route line of the express trunk line, provided by the embodiment of the invention, the route line and the parcel pair information of the target starting and ending point line in the target time period are obtained; acquiring the transport capacity information of each routing line based on the target time period; and predicting the parcel volume of each route line according to the parcel pair information, the transport capacity information of each route line and a preset prediction model. The invention can help to accumulate the experience of experts, reduce the dependence on the experience of experts and help the scheduling personnel with insufficient experience to learn the scheduling experience; the method can predict the package flow of the transfer and provide the package flow for dispatching personnel to carry out capacity allocation.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for predicting route line flow of an express trunk line according to an embodiment of the present invention;
fig. 2 is a schematic diagram of historical capacity in each direction of a departure of a taizhou according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating the number of parcels in each direction of a Taizhou departure according to an exemplary embodiment of the present invention;
FIG. 4 is a diagram illustrating the number of packages on different routes for a package in accordance with an embodiment of the present invention;
FIG. 5 is a data diagram of a package distribution decision tree for Taizhou-Jinan according to an embodiment of the present invention;
FIG. 6 is a schematic diagram illustrating comparison between predicted values and actual values according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an express trunk route line flow prediction device according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of an express trunk routing line traffic prediction device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the examples given herein without any inventive step, are within the scope of the present invention.
In order to at least solve the technical problem provided by the present invention, an embodiment of the present invention provides a method for predicting a route flow of an express trunk line.
The express transportation network comprises branch transportation and trunk transportation, wherein the trunk refers to a vehicle line from a transportation center to the transportation center, and the branch refers to a network point from the network point to the transportation center. Routing scheduling of express enterprises can guarantee timeliness of express delivery and consider cost, and is one of core capabilities of the express enterprises. The invention considers the problem of route line flow prediction of trunk transport.
The relay station network optimization has a plurality of related researches in the academic field, which prove that the network optimization can really achieve the purpose of reducing the cost, and the researches obtain better results on test data and can reduce the transportation cost. However, these methods are all optimized for the whole routing network, which may cause great changes to the established and operated network, especially the current routing planning has a considerable part of manually involved components, so that it is difficult for the enterprise to organize the implementation.
Fig. 1 is a schematic flow chart of a method for predicting route traffic of an express trunk according to an embodiment of the present invention, and referring to fig. 1, the method according to the embodiment of the present invention may include the following steps:
s11, acquiring the routing line and package pair information of the target starting and ending line in the target time period;
s12, acquiring the transport capacity information of each routing line based on the target time period;
and S13, predicting the parcel volume of each route line according to the parcel pair information, the transport capacity information of each route line and a preset prediction model.
Generally, a package is collected by a network point and then passes through at least two distribution centers, one is an initial transit center near the collection network point, and the other is a destination transit center near the end delivery network point. In this embodiment, the first distribution center through which the packages pass is referred to as o (origin), and the last distribution center is referred to as d (destination), and packages that are the same at the start point and the end point of the distribution center are considered to be the same, and are merged into a package flow of this OD pair. The package pair in this embodiment refers to packages having the same start point and end point of the distribution center, i.e., OD pairs.
If the goods quantity of the initial transit center and the destination transit center of the package does not meet the condition of the whole vehicle, the package with the similar destination direction is considered to be merged and loaded on the same vehicle. In reality, depending on daily traffic fluctuations, dispatchers may choose different routing methods for parcels of the same OD pair. For example, for a package from Guangzhou to Yiwu, the package can be directly sent from Guangzhou to Yiwu when the package volume is large, and the package can be transferred from Hangzhou and Jiaxing when the volume is not large enough.
In the invention, the cargo quantity comprises the parcel delivery quantity of each OD pair and the transfer parcel quantity between transfer centers. Capacity refers to vehicle information, including the number of different vehicle types, the weight and volume of cargo that can be loaded. The time efficiency of express delivery is the time length perceived by a user between the express delivery and the receiving, and is generally divided into the time of day, the time of day of the next day, the sending of morning, noon and evening in one day, and the like.
In a specific prediction process, for example, the parcel volume of each route from taizhou to kanan is predicted, the target time period to be predicted is a certain day of a month, and the target starting and ending point is from taizhou to kanan. Routing lines from taizhou to denna in the target time period can be acquired, and the routing lines include 4 types: the first is Taizhou direct Jinan, and the remaining three are transferred from Linyi, Hangzhou or Weifang respectively. And acquiring the transport capacity information of each line, and inputting the transport capacity information and the parcel pair information of each line into a preset prediction model so as to acquire the parcel volume of each routing line.
Optionally, the obtaining the transportation capacity information of each routing line includes: acquiring the transport capacity information of each package to the corresponding routing line; predicting the parcel volume of each route line according to the parcel pair information, the transport capacity information of each route line and a preset prediction model, and the method comprises the following steps: and predicting the parcel volume of each parcel pair according to the parcel pair information, the transport capacity information of the routing line corresponding to each parcel pair and a preset prediction model.
For example, the parcel volume from taizhou to jianan orthotics, the parcel volume from taizhou to linyi, the parcel volume from taizhou to hangfang and the parcel volume from taizhou to Weifang may be obtained, so that the worker may know the parcel volume reaching each operation center of jianan, linyi, Hangzhou or Weifang in the time period.
Optionally, the method for constructing the preset model includes: acquiring a routing line of a target starting point and a target ending point within a preset historical time period; acquiring each routing line based on the routing information of the historical time period; acquiring the package timeliness and cost of each routing line in a historical time period, and determining a target routing line; based on historical time periods, acquiring parcel pair information and transport capacity of the target routing line, wherein the transport capacity comprises: the number of vehicles and the volume of the vehicles, the parcel pair information of the target routing line includes: the package number is recorded as a first package number; acquiring the number of packages of other package pairs sharing the vehicle with the package of the target route in the historical time period, and recording as a second package number; and acquiring a preset prediction model according to the first wrapping quantity, the second wrapping quantity and the volume of the vehicle based on a mechanical algorithm.
Optionally, the machine learning algorithm includes: decision trees, random forests or neural networks.
In the embodiment of the invention, the rules of manual scheduling are learned from historical data and the manual scheduling is simulated, and in order to make the learning result interpretable, a decision tree model is used and is taken as an example for explanation. For example, in order to be able to accurately describe the problem and the pre-set prediction model used, the associated symbols are defined as follows.
N represents a set of distribution centers, i belongs to N;
k belongs to K and is a parcel flow with a starting center of i and a destination center of j;
bkis the number of packages k, bk∈B
A is the set of arcs connecting two distribution centers, (i, j) E.A
The available vehicles are C belonging to C, the corresponding capacity is V belonging to V, and the corresponding cost is P belonging to P
The parcel flow k may have m different routes, i.e.
，
Is the collection of distribution centers through which the parcel flow k passes,
＝(i，...，j)∈R，e∈E。
the set of arcs of operation of the vehicle cq is (i,.., j) ═ lq，lq∈L
Arc lleSet of vehicles operating on (i, e)
The input of the decision tree algorithm is the number b of packages of all OD pairs in history in a period of timekK belongs to K, and the transport capacity resource information comprises vehicles cqE.g. C, and vehicle route lqE.g. L. The algorithm outputs a routing scheduling rule of OD pairs, namely, the parcel flow k is in a route under different input bk data conditions
Number of packages distributed
In this embodiment, for the route allocation of a certain OD pair for a parcel flow, the workflow is as follows:
this OD over time in history versus the number of parcels per day bk(for simplicity of notation, no subscript is added to indicate time, but the number of packages varies from day to day, and other notations in this section below are similar), and routing
Number of packages
Data in history, which is fast in wrapping aging and low in cost, in a period of time can be selected as input of the algorithm.
Finding a route
First arc l ofoa(i, e) the set of vehicles operating on
Then counting the historical driving routes of the vehicles and finding an arc lieDaily capacity, i.e. daily in arc lieSum of volume of vehicle travelling on
For vehicle C found in the first stepieThe historical daily parcel number b of the other OD pairs sharing the vehicle with the parcel of this OD pair is counted in the historical datak', K' is K ', i.e. the route of the parcel flow K' comprises the arc lQeAnd from vehicle CieAnd (5) completing transportation.
And training a decision tree regression model. The used characteristics are the data obtained by calculation in the step one and the step two: this OD pair and other OD pairs with which the vehicle is shared have package number information bkAnd bk', and the daily volume and v of the associated vehiclele. The variable to be predicted is the route
Number of packages distributed
In this embodiment, a cart (classification and Regression trees) Regression tree may be used to train the decision tree model, and a binary recursive partitioning technique is adopted to divide the current sample set into two sub-sample sets, so that each generated non-leaf node has two branches. The feature values of the non-leaf nodes are true and false, the left branch is true, and the right branch is false. The generated binary decision tree can be converted into a plurality of sets of decision rules of 'if-then-else'. The text is processed by continuous variable in the input space b of training data setk，bk' (K '. epsilon.K ') and vleRecursively partitioning the region of each feature into two sub-regions and determining an output value on each sub-region
Starting from the root node, for each feature a cut point S is found, by selecting the feature and S that can yield the minimum degree of non-purity among all the features*The impure degree of the two child nodes is minimized. Prediction value of each leaf node
Is the average of the training set element outputs contained in the leaf node, and the impure degree uses the square error measurement of the true value and the predicted value.
In the new data, according to the obtained corresponding characteristic values, namely the related parcel number and the vehicle volume, the trained decision tree is used for carrying out traffic prediction on the route of a certain OD pair.
For example, the description is still given by taking taizhou to kannan as an example.
In the historical data, there may be four routing ways for packages from taizhou to jiannan, depending on the package and capacity resources in each direction of the current day, the first being taizhou orthodox jiannan, and the remaining three being transfers from linyi, hangzhou or weifang, respectively. Fig. 2 is a schematic diagram of historical capacity in each direction of a departure in a state according to an embodiment of the present invention, and referring to fig. 2, the historical capacity in each direction of a departure in a state is shown as follows, and includes: the sum of the capacity of the taizhou-kanan vehicles every day in the past year; the sum of the capacity of taizhou-linyi vehicles every day in the past year; the sum of the transport capacities of taizhou-hangzhou vehicles every day in the past year; the sum of the capacity of Taizhou-Weifang vehicles every day over the past year.
Fig. 3 is a schematic diagram of the parcel quantity in each direction of the taizhou departure according to an embodiment of the present invention, and referring to fig. 3, the parcel quantity in each direction of the taizhou departure includes: in the past year of historical data, the relative OD versus the number of parcels per day of the past year was obtained in the historical data. The number of packages of different OD pairs on the taizhou-denan vehicle was counted and found to carry only the taizhou-denan packages. Similarly, a Taizhou-linyi vehicle is loaded with a Taizhou-Jining, Taizhou-linyi, Taizhou-Jinan, Taizhou-Weifang parcel; the Taizhou-Hangzhou vehicle is loaded with packages of Taizhou-Hangzhou, Taizhou-Chongqing and Taizhou-Jinan; the vehicle of the taizhou-Weifang is loaded with packages of the taizhou-Weifang, the taizhou-Laiyang, the taizhou-Qingdao and the taizhou-Jinan.
The decision tree randomly extracts 70% of data in the input features as training data, namely the capacity data and the package quantity data, and learns package flow distribution rules of Taizhou-Jinan. The output data of the training data of the algorithm is the distribution number of the parcels on the four routes per day in the past year, and the corresponding 70% is also extracted as the training sample, referring to fig. 4, fig. 4 is a diagram illustrating the parcel number of the parcels on different routes according to the embodiment of the present invention.
Fig. 5 is a data diagram of a package distribution decision tree for taizhou-denan according to an embodiment of the present invention, please refer to fig. 5, wherein the package distribution rule learned by the decision tree is shown in fig. 5. For example, when the Taizhou-Jinan vehicle capacity does not exceed 30 (i.e., no Taizhou-Jinan orthokinetic vehicle), the Taizhou-Weifang parcel data does not exceed 6450, and the Taizhou-Weifang vehicle capacity does not exceed 125, the Taizhou-Linyi would be allocated 1724 parcels, the Taizhou-Hangzhou would be allocated 1162 parcels, the Taizhou-Jinan orthokinetic would have no parcel, and the Taizhou-Weifang would be allocated 2869 parcels. And predicting by using the learned decision tree rule in the rest 30% of test samples, so that the prediction accuracy of the trained decision tree model on unknown data can be obtained.
Fig. 6 is a schematic diagram illustrating comparison between predicted values and actual values according to an embodiment of the present invention, please refer to fig. 6, where a decision tree can better simulate a routing scheduling result of an expert. The four numbers in each leaf node (the lowest node of the decision tree) represent the parcel quantities of the four routes (taizhou- [ linyi, hangzhou, denna, Weifang ]).
Optionally, when determining the capacity of the package, the method may further include: judging whether the parcel number is within a reference number threshold range, wherein the set standard of the reference number threshold is the load capacity of the target vehicle; and if the number of the parcels is lower than the minimum value of the reference number threshold, the parcels similar to the terminal operation center are placed into the target vehicle, and the number of the target vehicles is at least one.
Optionally, the method further includes: acquiring the weight information and the volume information of the parcel pair; the setting method of the reference quantity threshold value comprises the following steps: acquiring a reference weight threshold according to the parcel weight information and the load weight information of the target vehicle; acquiring a reference volume threshold according to the parcel volume information and the load volume information of the target vehicle; and determining a reference quantity threshold according to the reference weight threshold and the reference volume threshold.
For example, both the weight and volume of the package are considered such that both the weight and volume are within preset ranges.
According to the method for predicting the flow of the route line of the express trunk line, provided by the embodiment of the invention, the route line and the parcel pair information of a target starting and ending point line in a target time period are obtained; acquiring the transport capacity information of each routing line based on the target time period; and predicting the parcel volume of each route line according to the parcel pair information, the transport capacity information of each route line and a preset prediction model. The invention can help to accumulate the experience of experts, reduce the dependence on the experience of experts and help the scheduling personnel with insufficient experience to learn the scheduling experience; the method can predict the package flow of the transfer and provide the package flow for dispatching personnel to carry out capacity allocation.
Based on a general inventive concept, the embodiment of the invention also provides an express trunk routing line flow prediction device.
Fig. 7 is a schematic structural diagram of an express trunk routing line traffic prediction apparatus according to an embodiment of the present invention, and referring to fig. 7, the express trunk routing line traffic prediction apparatus according to the embodiment of the present invention may include: an acquisition module 71 and a prediction module 72;
the acquisition module is used for acquiring the routing line and the package pair information of the target starting and ending point line in the target time period; acquiring the transport capacity information of each routing line based on the target time period;
and the prediction module is used for predicting the parcel volume of each route line according to the parcel pair information, the transport capacity information of each route line and a preset prediction model.
Optionally, the obtaining module is configured to obtain the transportation capacity information of each package for the corresponding routing line; and the prediction module is used for predicting the parcel volume of each parcel pair according to the parcel pair information, the transport capacity information of the routing line corresponding to each parcel pair and a preset prediction model.
Optionally, the prediction module includes: the model building module is used for obtaining a routing line of a target starting and ending point line in a preset historical time period; acquiring each routing line based on the routing information of the historical time period; acquiring the package timeliness and cost of each routing line in a historical time period, and determining a target routing line; based on historical time periods, acquiring parcel pair information and transport capacity of the target routing line, wherein the transport capacity comprises: the number of vehicles and the volume of the vehicles, the parcel pair information of the target routing line includes: the package number is recorded as a first package number; acquiring the number of packages of other package pairs sharing the vehicle with the package of the target reason route in the historical time period, and recording as a second package number; and acquiring a preset prediction model according to the first wrapping quantity, the second wrapping quantity and the volume of the vehicle based on a mechanical algorithm.
According to the express trunk route line flow prediction device provided by the embodiment of the invention, route line and parcel pair information of a target starting and ending point line in a target time period are obtained; acquiring the transport capacity information of each routing line based on the target time period; and predicting the parcel volume of each route line according to the parcel pair information, the transport capacity information of each route line and a preset prediction model. The invention can help to accumulate the experience of experts, reduce the dependence on the experience of experts and help the scheduling personnel with insufficient experience to learn the scheduling experience; the method can predict the package flow of the transfer and provide the package flow for dispatching personnel to carry out capacity allocation.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Based on a general inventive concept, the embodiment of the invention also provides an express trunk routing line flow prediction device.
Fig. 8 is a schematic structural diagram of an express trunk routing line traffic prediction device according to an embodiment of the present invention, and referring to fig. 8, the express trunk routing line traffic prediction device according to the embodiment of the present invention includes: a processor 81, and a memory 82 coupled to the processor.
The memory 82 is configured to store a computer program, where the computer program is at least used in the method for predicting the flow of the express trunk routing line described in any of the above embodiments;
the processor 81 is used to invoke and execute computer programs in the memory.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
It is understood that the same or similar parts in the above embodiments may be mutually referred to, and the same or similar parts in other embodiments may be referred to for the content which is not described in detail in some embodiments.
It should be noted that the terms "first," "second," and the like in the description of the present invention are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Further, in the description of the present invention, the meaning of "a plurality" means at least two unless otherwise specified.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. An express trunk routing line flow prediction method is characterized by comprising the following steps:
acquiring routing line and package pair information of a target starting and ending line in a target time period;
acquiring the transport capacity information of each routing line based on the target time period;
and predicting the parcel volume of each routing line according to the parcel pair information, the transport capacity information of each routing line and a preset prediction model.
2. The method of claim 1, wherein said obtaining capacity information for each of said routing lines comprises: acquiring the transport capacity information of each package to the corresponding routing line;
predicting the parcel volume of each routing line according to the parcel pair information, the transport capacity information of each routing line and a preset prediction model, wherein the predicting comprises the following steps: and predicting the parcel volume of each parcel pair according to the parcel pair information, the transport capacity information of the routing line corresponding to each parcel pair and a preset prediction model.
3. The method according to claim 1, wherein the method for constructing the preset model comprises:
acquiring a routing line of the target starting and ending point line within a preset historical time period;
acquiring each routing line based on the routing information of the historical time period;
acquiring the package timeliness and cost of each routing line in the historical time period, and determining a target routing line;
based on the historical time period, acquiring package pair information and transport capacity of the target routing line, wherein the transport capacity comprises: the number of vehicles and the volume of vehicles, the parcel pair information for the target routing route including: the package number is recorded as a first package number;
acquiring the package quantity of other package pairs sharing the vehicle with the package of the target reason route in the historical time period, and recording the package quantity as a second package quantity;
and acquiring the preset prediction model according to the first parcel quantity, the second parcel quantity and the volume of the vehicle based on a mechanical algorithm.
4. The method of claim 3, wherein the machine learning algorithm comprises:
decision trees, random forests or neural networks.
5. The method of claim 3, further comprising:
judging whether the parcel number is within a reference number threshold range, wherein the set standard of the reference number threshold is the load capacity of the target vehicle;
and if the number of the parcels is lower than the minimum value of the reference number threshold, placing the parcels similar to the terminal operation center into a target vehicle, wherein the number of the target vehicle is at least one.
6. The method of claim 5, further comprising: acquiring the weight information and the volume information of the parcel pair;
the method for setting the reference number threshold comprises the following steps:
acquiring a reference weight threshold according to the parcel weight information and the load weight information of the target vehicle; and the combination of (a) and (b),
acquiring a reference volume threshold according to the parcel volume information and the load volume information of the target vehicle;
determining the reference quantity threshold according to the reference weight threshold and the reference volume threshold.
7. An express trunk routing line flow prediction device, comprising: an acquisition module and a prediction module;
the acquisition module is used for acquiring the routing line and the package pair information of the target starting and ending line in the target time period; acquiring the transport capacity information of each routing line based on the target time period;
and the prediction module is used for predicting the parcel volume of each routing line according to the parcel pair information, the transport capacity information of each routing line and a preset prediction model.
8. The apparatus of claim 7, wherein the obtaining module is configured to obtain capacity information of each package for a corresponding routing line; and the prediction module is used for predicting the parcel volume of each parcel pair according to the parcel pair information, the transport capacity information of the routing line corresponding to each parcel pair and a preset prediction model.
9. The apparatus of claim 7, wherein the prediction module comprises: the model building module is used for acquiring a routing line of the target starting and ending point line in a preset historical time period; acquiring each routing line based on the routing information of the historical time period; acquiring the package timeliness and cost of each routing line in the historical time period, and determining a target routing line; based on the historical time period, acquiring package pair information and transport capacity of the target routing line, wherein the transport capacity comprises: the number of vehicles and the volume of vehicles, the parcel pair information for the target routing route including: the package number is recorded as a first package number; acquiring the package quantity of other package pairs sharing the vehicle with the package of the target reason route in the historical time period, and recording the package quantity as a second package quantity; and acquiring the preset prediction model according to the first parcel quantity, the second parcel quantity and the volume of the vehicle based on a mechanical algorithm.
10. An express trunk routing line traffic prediction device, comprising: a processor, and a memory coupled to the processor;
the memory is used for storing a computer program at least for executing the express trunk routing line traffic prediction method of any one of claims 1 to 6;
the processor is used for calling and executing the computer program in the memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010646582.6A CN111882117A (en) | 2020-07-07 | 2020-07-07 | Express trunk route line flow prediction method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010646582.6A CN111882117A (en) | 2020-07-07 | 2020-07-07 | Express trunk route line flow prediction method, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111882117A true CN111882117A (en) | 2020-11-03 |
Family
ID=73150384
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010646582.6A Pending CN111882117A (en) | 2020-07-07 | 2020-07-07 | Express trunk route line flow prediction method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111882117A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112474403A (en) * | 2020-12-03 | 2021-03-12 | 中邮信息科技(北京)有限公司 | Autonomous package management method, device, medium and electronic equipment |
| CN116911470A (en) * | 2023-09-12 | 2023-10-20 | 深圳市宏大供应链服务有限公司 | Data analysis method, system and storage medium based on deep learning |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109784820A (en) * | 2019-03-28 | 2019-05-21 | 上海中通吉网络技术有限公司 | A kind of express delivery routing intelligence solution, device, terminal device and storage medium |
| CN109829667A (en) * | 2017-11-23 | 2019-05-31 | 菜鸟智能物流控股有限公司 | Method and device for predicting parcel volume of logistics node |
| CN109919532A (en) * | 2017-12-13 | 2019-06-21 | 菜鸟智能物流控股有限公司 | Logistics node determination method and device |
| WO2019120159A1 (en) * | 2017-12-20 | 2019-06-27 | 菜鸟智能物流控股有限公司 | Method for determining logistics route and related device |
| CN110046749A (en) * | 2019-03-22 | 2019-07-23 | 杭州师范大学 | It is a kind of based on real-time road electric business package with city o2o wrap up Common Distribution system |
-
2020
- 2020-07-07 CN CN202010646582.6A patent/CN111882117A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109829667A (en) * | 2017-11-23 | 2019-05-31 | 菜鸟智能物流控股有限公司 | Method and device for predicting parcel volume of logistics node |
| CN109919532A (en) * | 2017-12-13 | 2019-06-21 | 菜鸟智能物流控股有限公司 | Logistics node determination method and device |
| WO2019120159A1 (en) * | 2017-12-20 | 2019-06-27 | 菜鸟智能物流控股有限公司 | Method for determining logistics route and related device |
| CN109948958A (en) * | 2017-12-20 | 2019-06-28 | 菜鸟智能物流控股有限公司 | Logistics routing determination method and related equipment |
| CN110046749A (en) * | 2019-03-22 | 2019-07-23 | 杭州师范大学 | It is a kind of based on real-time road electric business package with city o2o wrap up Common Distribution system |
| CN109784820A (en) * | 2019-03-28 | 2019-05-21 | 上海中通吉网络技术有限公司 | A kind of express delivery routing intelligence solution, device, terminal device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 李朝敏: "《物流配送运作与实训》", 31 January 2012, 《中国物资出版社》, pages: 10 - 11 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112474403A (en) * | 2020-12-03 | 2021-03-12 | 中邮信息科技(北京)有限公司 | Autonomous package management method, device, medium and electronic equipment |
| CN116911470A (en) * | 2023-09-12 | 2023-10-20 | 深圳市宏大供应链服务有限公司 | Data analysis method, system and storage medium based on deep learning |
| CN116911470B (en) * | 2023-09-12 | 2024-01-02 | 深圳市宏大供应链服务有限公司 | Data analysis method, system and storage medium based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110555640B (en) | Route planning method and device | |
| Cattaruzza et al. | The multi-trip vehicle routing problem with time windows and release dates | |
| Figliozzi | The time dependent vehicle routing problem with time windows: Benchmark problems, an efficient solution algorithm, and solution characteristics | |
| WO2018196525A1 (en) | Goods handling method and device | |
| CN111950803A (en) | Logistics object delivery time prediction method and device, electronic equipment and storage medium | |
| CN110276466B (en) | Method and device for determining packet cluster establishment in distribution network | |
| Grzybowska et al. | Decision support system for real-time urban freight management | |
| CN111882117A (en) | Express trunk route line flow prediction method, device and equipment | |
| CN113128744A (en) | Distribution planning method and device | |
| Berghida et al. | EBBO: an enhanced biogeography-based optimization algorithm for a vehicle routing problem with heterogeneous fleet, mixed backhauls, and time windows | |
| JP7487765B2 (en) | CONTAINER LOADING PLANNING DEVICE, METHOD, AND PROGRAM | |
| CN111667085A (en) | Method, device, medium and electronic equipment for determining logistics routing network | |
| CN113988485B (en) | Site arrival amount prediction method and device, electronic equipment and computer readable medium | |
| Zhou et al. | A scalable vehicle assignment and routing strategy for real-time on-demand ridesharing considering endogenous congestion | |
| Jiang et al. | A scheme for determining vehicle routes based on Arc-based service network design | |
| CN113592282A (en) | Article distribution method and device | |
| Serra et al. | Last-mile scheduling under uncertainty | |
| CN111947676A (en) | Express delivery path planning method and device, electronic equipment and storage medium | |
| Chen et al. | Data mining-based dispatching system for solving the local pickup and delivery problem | |
| Hao et al. | Introduction to the dynamic pickup and delivery problem benchmark--ICAPS 2021 competition | |
| Heggen et al. | A multi-objective approach for intermodal train load planning | |
| CN110163543B (en) | Delivery decision method and device and computer readable storage medium | |
| Cherif-Khettaf et al. | New notation and classification scheme for vehicle routing problems | |
| CN113408836B (en) | Logistics route evaluation method and device, storage medium and electronic equipment | |
| Skålnes et al. | The multistage stochastic vehicle routing problem with dynamic occasional drivers |
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 |