CN111461624B

CN111461624B - Logistics line planning method, device, equipment and storage medium

Info

Publication number: CN111461624B
Application number: CN202010310871.9A
Authority: CN
Inventors: 刘梦超; 陈超
Original assignee: Dongpu Software Co Ltd
Current assignee: Dongpu Software Co Ltd
Priority date: 2020-04-20
Filing date: 2020-04-20
Publication date: 2023-07-11
Anticipated expiration: 2040-04-20
Also published as: CN111461624A

Abstract

The invention relates to the technical field of logistics distribution, and discloses a logistics route planning method, a logistics route planning device, logistics route planning equipment and a logistics route planning storage medium, which are used for realizing maximum loading distribution of vehicles, improving matching degree of people and vehicles and efficiency of collecting and distributing the vehicles, and reducing logistics distribution cost of single operators. The logistics route planning method comprises the following steps: training logistics historical processing information classified by a salesman through an ant colony algorithm to obtain a path optimization model, extracting corresponding express order information, express delivery addresses and distributable vehicle information from express information to be processed by the salesman in a path planning process, taking the information as constraint conditions of a planned path, calculating matching parameters between the salesman and the vehicle information by using the path optimization model, and planning an optimal path based on the matching parameters.

Description

Logistics line planning method, device, equipment and storage medium

Technical Field

The present invention relates to the field of logistics distribution technologies, and in particular, to a method, an apparatus, a device, and a storage medium for planning a logistics route.

Background

With the continuous development of market economy and logistics technology, logistics distribution is also rapidly developed, especially the popularization of internet shopping at present, the express delivery is increased year by year, and the increase of workload necessarily affects the overall distribution efficiency of the business staff on the express.

In the prior art, when a service person realizes the processing of collecting and sending the parts, the line planning is seriously dependent on personal experience, most of the line planning is processed based on the situation of an order received before the service person starts, in actual operation, new processing orders are often generated by the service person in the process of attendance or sending the parts, and in the case of the situation, the new processing orders are not processed, that is, the situation of not combining with the order of the net points, the dynamic sensing of collecting or sending the parts is adopted to improve the processing efficiency, even some service persons often have the problem of underload or overlarge redundancy when the service person goes out, and the existing mode can solve the problem of matching the personnel, the vehicles and the goods, but the cost control of the personnel, the goods and the cost is difficult to realize, so that the processing efficiency is low, and even the phenomenon of customer complaints is generated.

Disclosure of Invention

The invention mainly aims to solve the technical problem that the logistics processing efficiency is low due to the fact that the existing logistics route planning mode is inaccurate in achieving height matching between people, vehicles and goods.

The first aspect of the present invention provides a logistics route planning method, which includes:

acquiring express mail information to be processed by a current salesman, and position information of a distribution center where the current salesman is located and vehicle information of a currently available vehicle of the distribution center;

Analyzing all express mail information which is responsible for the salesmen to obtain corresponding express mail order information and a dispatching address set, and numbering each dispatching address in the dispatching address set;

taking the vehicle information, the order information and the delivery address set as constraint conditions of logistics route planning, and calculating matching parameters between the salesmen and available vehicles by using a path optimization model, wherein the path optimization model is a model obtained by training logistics historical processing information through an ant colony algorithm;

and planning an optimal logistics line corresponding to the salesman according to the matching parameters.

Optionally, in a first implementation manner of the first aspect of the present invention, the calculating, using the vehicle information, the order information, and the group address set as constraint conditions of logistics route planning and using a path optimization model, a matching parameter between the salesman and the available vehicle includes:

counting the total distribution amount of the order information to be processed by the salesman;

selecting at least one vehicle from the available vehicles according to the total delivery amount, wherein the loading requirement comprises that the maximum load of the vehicle is greater than or equal to the total delivery amount;

Taking the distribution center as an origin, and respectively traversing the at least one vehicle through all the dispatch addresses in the dispatch address set based on the path optimization model to obtain a plurality of logistics lines;

calculating unit distribution cost of each logistics line in the plurality of logistics lines, and calculating matching parameters between the salesmen and corresponding vehicles based on the unit distribution cost.

Optionally, in a second implementation manner of the first aspect of the present invention, using the distribution center as an origin, traversing, by the path optimization model, the at least one vehicle through all the dispatch addresses in the dispatch address set, and obtaining a plurality of logistics routes includes:

setting an origin of each of the at least one vehicle as location information of the distribution center;

randomly selecting one vehicle from the at least one vehicle as a first vehicle;

selecting a dispatch address from the dispatch address set as a first dispatch address based on the first vehicle;

traversing path information between the distribution center and the first dispatch address through the path optimization model, and storing the first dispatch address into a preset tabu list;

After the traversal of the dispatch addresses is completed, selecting the next dispatch address from the dispatch address set to traverse and store the tabu list;

after traversing all the dispatch addresses in the dispatch address set, clearing the tabu list, and planning an optimal logistics route between the salesman and the first vehicle based on all path information obtained by traversing;

and selecting a second vehicle from the rest vehicles to traverse the dispatch address set, and outputting a corresponding optimal logistics line.

Optionally, in a third implementation manner of the first aspect of the present invention, the selecting, based on the first vehicle, one dispatch address from the dispatch address set as the first dispatch address includes:

calculating the probability of the first vehicle passing through each dispatch address according to a preset probability conversion rule;

and selecting one dispatch address with the highest probability as the first dispatch address.

Optionally, in a fourth implementation manner of the first aspect of the present invention, after the planning, according to the matching parameter, an optimal logistics route corresponding to the salesman further includes:

new order information of the network points passing through the optimal commodity circulation line is obtained at fixed time, wherein the new order information is a member-collecting order or a member-sending order;

Judging whether the new order information belongs to an order on the optimal commodity circulation line;

if yes, the new order information is embedded into the optimal logistics line according to the path optimization model.

Optionally, in a fifth implementation manner of the first aspect of the present invention, after the acquiring new order information of a website passing through the optimal object line at the timing, before the determining whether the new order information belongs to an order on the optimal object line, the method further includes:

acquiring current positioning information of the salesman;

judging whether the positioning information is consistent with the position information of the distribution center;

if yes, executing the step of judging whether the new order information belongs to the order on the optimal commodity circulation line;

if the addresses are inconsistent, an unprocessed dispatch address is selected from the dispatch address set to form a second dispatch address set;

and taking the positioning information as an origin of the vehicle, and planning a logistics line for the second dispatch address set by utilizing the path optimization model.

Optionally, in a sixth implementation manner of the first aspect of the present invention, the method for logistics route planning includes training to obtain the path optimization model by:

Acquiring n pieces of logistics history processing information of the salesman, and analyzing the n pieces of logistics history processing information to obtain n sending addresses and vehicle information of m vehicles;

according to the data analysis principle of the ant colony algorithm, analyzing records of m vehicles passing through each dispatching address;

and constructing the path optimization model according to the records obtained by analysis.

A second aspect of the present invention provides a logistics route planning apparatus, comprising:

the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring express information to be processed by a current salesman, position information of a distribution center where the current salesman is located and vehicle information of a currently available vehicle of the distribution center;

the analysis module is used for analyzing all express mail information which is responsible for the salesmen to obtain corresponding express mail order information and a dispatching address set, and numbering each dispatching address in the dispatching address set;

the model analysis module is used for taking the vehicle information, the order information and the delivery address set as constraint conditions of logistics route planning, and calculating matching parameters between the salesmen and the available vehicles by utilizing a path optimization model, wherein the path optimization model is a model obtained by training logistics history processing information through an ant colony algorithm;

And the line generation module is used for planning an optimal logistics line corresponding to the salesman according to the matching parameters.

Optionally, in a first implementation manner of the second aspect of the present invention, the model analysis module includes:

the statistics unit is used for counting the total distribution amount of the order information to be processed by the salesmen;

a selecting unit, configured to select at least one vehicle that meets a loading requirement from the available vehicles according to the total delivery amount, where the loading requirement includes that a maximum load of the vehicles is greater than or equal to the total delivery amount;

the analysis unit is used for respectively traversing the at least one vehicle through all the dispatch addresses in the dispatch address set based on the path optimization model by taking the distribution center as an origin to obtain a plurality of logistics lines;

the calculating unit is used for calculating the unit distribution cost of each logistics line in the plurality of logistics lines and calculating the matching parameters between the salesmen and the corresponding vehicles based on the unit distribution cost.

Optionally, in a second implementation manner of the second aspect of the present invention, the analysis unit is specifically configured to:

Optionally, in a third implementation manner of the second aspect of the present invention, the analysis unit is specifically configured to:

Optionally, in a fourth implementation manner of the second aspect of the present invention, the logistics route planning apparatus further includes:

the optimization module is used for: new order information of the network points passing through the optimal commodity circulation line is obtained at fixed time, wherein the new order information is a member-collecting order or a member-sending order; judging whether the new order information belongs to an order on the optimal commodity circulation line; if yes, the new order information is embedded into the optimal logistics line according to the path optimization model.

Optionally, in a fifth implementation manner of the second aspect of the present invention, the optimization module is further configured to: acquiring current positioning information of the salesman; judging whether the positioning information is consistent with the position information of the distribution center; if yes, executing the step of judging whether the new order information belongs to the order on the optimal commodity circulation line; if the addresses are inconsistent, an unprocessed dispatch address is selected from the dispatch address set to form a second dispatch address set; and taking the positioning information as an origin of the vehicle, and planning a logistics line for the second dispatch address set by utilizing the path optimization model.

Optionally, in a fifth implementation manner of the second aspect of the present invention, the logistics route planning apparatus further includes:

The model training module is used for: acquiring n pieces of logistics history processing information of the salesman, and analyzing the n pieces of logistics history processing information to obtain n sending addresses and vehicle information of m vehicles; according to the data analysis principle of the ant colony algorithm, analyzing records of m vehicles passing through each dispatching address; and constructing the path optimization model according to the records obtained by analysis.

A third aspect of the present invention provides a logistics route planning apparatus, comprising: a memory and at least one processor, the memory having instructions stored therein, the memory and the at least one processor being interconnected by a line; the at least one processor invokes the instructions in the memory to cause the logistics planning apparatus to perform the logistics planning method described above.

A fourth aspect of the present invention provides a computer readable storage medium having a computer program stored therein which, when run on a processor on a computer, causes the computer to perform the above-described method of logistics route planning.

According to the technical scheme provided by the invention, the logistics history processing information classified by the operators is trained through the ant colony algorithm to obtain the path optimization model, in the path planning process, corresponding express order information, express delivery addresses and distributable vehicle information are extracted from express information to be processed by the operators, the information is used as constraint conditions of a planned path, the path optimization model is utilized to calculate matching parameters between the operators and the vehicle information, and the optimal path is planned based on the matching parameters, so that the learning of path planning experience based on a learning mode of a machine algorithm is realized, the input of manual operation can be reduced, the maximum loading of vehicles can be realized through the relation between the express information and the express to be processed by the operators, the matching degree of people and vehicles is improved, meanwhile, the efficiency of dispatching the express delivery is improved, and the logistics distribution cost of a single operator is reduced.

Drawings

FIG. 1 is a schematic diagram of a first embodiment of a method for planning a logistics route according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart of training a path optimization model according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of a second embodiment of a method for planning a logistics route according to the present invention;

FIG. 4 is a flow chart of a vehicle traversing a dispatch address set according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of a third embodiment of a method for planning a logistics route according to the present invention;

FIG. 6 is a diagram illustrating a fourth embodiment of a method for planning a logistics route according to an embodiment of the present invention;

FIG. 7 is a schematic diagram of a first embodiment of a logistics route planning apparatus according to an embodiment of the present invention;

FIG. 8 is a schematic diagram of a second embodiment of a logistics route planning apparatus according to an embodiment of the present invention;

fig. 9 is a schematic structural diagram of an embodiment of the logistics route planning apparatus of the present invention.

Detailed Description

The embodiment of the invention provides a logistics line planning method, a device, equipment and a storage medium, wherein the method carries out path planning on the processing business of each salesman through a path optimization model constructed by an ant colony algorithm, in particular, the method adopts a scientific and reasonable method to determine the distribution route by acquiring express mail information to be processed in a period of time and vehicle information of available vehicles in a distribution center, calculates matching parameters between personnel and vehicles by utilizing the path optimization model based on the express mail information and the vehicle information, and plans out an optimal logistics line based on the matching parameters.

Not only can the logistics planning efficiency be improved, but also the logistics economic benefit and the logistics scientificalness can be realized, and the urban traffic pressure can be relieved, the energy can be saved, the pollution can be reduced, the inherent unification of the efficiency, the resources, the environment and the value concept can be realized, and the progress of the logistics industry and the sustainable development of the social economy can be promoted.

Furthermore, the construction of the transfer center in the logistics line can be realized through the planning mode, so that the high-efficiency utilization rate of the transfer center is ensured.

The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.

For ease of understanding, a specific flow of an embodiment of the present invention is described below, referring to fig. 1, and fig. 1 is a flow chart of a method for planning a logistics route according to the present invention. The order of the steps in the flowchart may be changed and some steps may be omitted according to various needs. The method is mainly applied to a logistics distribution system, particularly part of functions of a business person in the system, such as a mobile phone of the business person, the mobile phone is provided with APP software for taking and sending, the APP is the functional software with the functions of logistics line planning and express mail tracking, the system distributes corresponding business persons according to the sending addresses of the express mail, the APP software plans the sending path of the express mail after receiving order information of the express mail, in the embodiment, the order information received by the APP can be an order of sending the express mail or an order of collecting the express mail, and the specific implementation flow is as follows:

101. acquiring express mail information to be processed by a current salesman, and position information of a distribution center where the current salesman is located and vehicle information of a currently available vehicle of the distribution center;

in this embodiment, the to-be-processed express mail information may be delivery information or package information; in the process of collecting the express mail information, the express mail information is obtained by classifying according to the salesmen, specifically, the information of the salesmen needing to be subjected to logistics route planning or optimization, such as employee numbers corresponding to the salesmen, can be uniquely identified, then the order information processed by the salesmen is called out from an order database through an APP according to the information of the salesmen, wherein the order information can be unprocessed orders in the range before and after the current time period or all unprocessed orders related to the salesmen in the database.

Further, by locating the location information of the distribution center where the salesman is located through the GPS, in practical application, the distribution center can be understood as the start point and the end point of the distribution activity, which includes the warehouse, the port, etc. with the functions of distributing goods, stock, picking, etc., and the attributes of the distribution center, which need to be considered in the VRP problem, include the geographic location, the number of available distribution vehicles, etc. Generally, they are divided into a single distribution center and a plurality of distribution centers. If a distribution center is selected, the express information of the service personnel can be sent from one place, and the express information does not need to be fetched across different distribution centers.

The distribution center searches the vehicle information of the vehicles which can be called to send or pick up the vehicle at the current moment, and the corresponding search can be performed according to the operator when searching the vehicle information, for example, a logistics company can be provided with a plurality of distribution vehicles, when searching, the team where the logistics company is located is determined according to the information of the operator, and then the vehicle information of the vehicles which are not sent out currently in the team is determined.

In this embodiment, when there are a plurality of determined distribution centers, vehicles of the plurality of distribution centers need to be considered in searching for available vehicles, and it is needless to say that it is also possible to specify that the distribution vehicles must be acquired from each distribution center, and the route planning process to be considered is to replace the vehicles for dispatch.

In the present embodiment, when acquiring the vehicle information, specifically, the maximum load, specification, speed, maximum travel distance, and the like of each vehicle that can be invoked are acquired.

102. Analyzing all express mail information which is responsible for the salesmen to obtain corresponding express mail order information and a dispatching address set, and numbering each dispatching address in the dispatching address set;

in the step, when the express mail information is analyzed, the express mail information is specifically analyzed through a text and picture recognition technology, the editable information in the express mail information is extracted through the text recognition technology, such as an address item, a remark item and the like, when the express mail information belongs to a picture, the picture recognition technology is used for recognizing the image and the text part in the express mail information, and the extracted express mail order information comprises the delivery requirement of the order and the delivery goods quantity of the express mail information; after all express information of the salesmen is extracted, the extracted express addresses are formed into an express address set, addresses in the express address set are randomly numbered to obtain an address sequence, and finally the address sequence is used as an allowable access address list of each available vehicle.

103. Taking the vehicle information, the order information and the delivery address set as constraint conditions of logistics route planning, and calculating matching parameters between the salesmen and available vehicles by using a path optimization model;

in this embodiment, the path optimization model is a model obtained by training logistics history processing information through an ant colony algorithm, and when a logistics route is planned, vehicle information, order information and a delivery address set of available vehicles are used as initial conditions for planning the logistics route, that is, the planned route must be transported by the selected available vehicles, the addresses passed by the route are specified addresses in the delivery address set, and when a express mail is delivered based on the logistics route, the requirements in the order information can be basically met.

When the path optimization model is utilized to calculate the matching parameters, specifically, different vehicles are sequentially selected from available vehicles to traverse all the addresses in the dispatch address set according to the ant algorithm principle in the path optimization model to obtain a plurality of lines, then the time for respectively transporting the express mail to the dispatch address through the plurality of lines, parameters such as path distance, cost and the like are calculated, whether the parameters meet the requirements in order information and the transportation requirements of the system on the salesmen are judged, and one optimal logistics line of the vehicle is selected from the plurality of lines based on the judgment result.

For example, the number of available vehicles is 5, the dispatch address is 3, and vehicles which can meet the transportation requirement and can also meet the dispatch requirement are selected from 5 vehicles by using the path optimization model, and the specific implementation process can be as follows:

firstly, numbering 5 vehicles and 3 dispatch addresses, namely { A1, A2, A3, A4, A5} and { D1, D2, D3};

then, randomly selecting one of { A1, A2, A3, A4 and A5} as a transport vehicle, traversing { D1, D2 and D3} to obtain a plurality of lines, and then selecting an optimal logistics line as the transport vehicle from the plurality of lines until the calculation of the logistics lines of 5 vehicles is completed;

for example, firstly, A1 pair { D1, D2, D3} is selected to perform traversal processing to obtain a plurality of routes of d1→d2→d3, d1→d3→d3, D3→d1→d2, and an optimal route is selected from the routes, wherein the optimal route can be understood as a delivery route meeting the requirement of an A1 vehicle, the requirement is low in cost, the loading capacity of the goods and the vehicles is large, and the path length is moderate, so that the matching parameters of the A1 vehicle and the current delivery capacity of the operators are obtained. After the traversal of the A1 vehicle is completed, the processing of A2, A3, A4, A5 is continued in the same manner as A1. The final output matching parameters include the matching parameters of 5 vehicles relative to the salesman.

104. And planning an optimal logistics line corresponding to the salesman according to the matching parameters.

In this embodiment, when the matching parameters include matching parameters of a plurality of vehicles and the salesman, the step further includes selecting an optimal one from the matching parameters, and planning and outputting a logistics route based on the optimal matching parameter.

In this embodiment, the step may further output logistics lines for all matching parameters of the plurality of vehicles and the salesman, and then further select a best output from the plurality of output logistics lines, where the specific selection may be according to constraint conditions of a mathematical model, for example, constraint conditions of the mathematical model are line time length, distance, cost and transportation amount, and the specific comparison may be considered according to priorities in the constraint conditions, for example: and evaluating the logistics lines according to the sequence of time window > cargo capacity > distance > cost, and directly outputting the corresponding lines as optimal lines after the evaluation is passed.

In this embodiment, the output logistics line includes two sections of going and returning, and the general express processing is placed in the going for processing, but in practical application, the express processing can be uniformly distributed according to practical requirements, so that the step further includes determining the type of the express information before outputting the optimal line, the type includes an article collecting and an article sending, if the article collecting is performed, the line of the returning section is preferentially selected to collect the article, and the outgoing is performed according to the current road condition; if the route is the route, the route of the output route is selected to be the route in a centralized way, and the return route is output according to the current road condition.

Through the implementation, the express delivery route of the salesman is planned based on the route optimization model trained by the ant colony algorithm, and the route planning optimization is realized by the algorithm model, so that the calculated express or dispatch route can meet the matching degree between the salesman and the vehicle to the greatest extent due to the characteristics of self-organization, parallel calculation and positive feedback search, the delivery route is determined by adopting a scientific and reasonable method, the satisfaction degree of the customer to the logistics delivery service can be enhanced, the delivery cost of a logistics enterprise is reduced, and the delivery efficiency is improved.

In this embodiment, the path optimization model is obtained by training through an ant colony algorithm, and the training process is specifically shown in fig. 2.

201. Collecting distribution order information which is already distributed from a physical distribution system, and classifying the distribution order information;

in this step, the delivery order information includes two orders, namely, a pick-up order and a dispatch order, the two orders are categorized according to the operators, and meanwhile, the pick-up order and the dispatch order of each operator are distinguished.

202. Initializing the classified order information to obtain a traversal address and vehicle information;

In this embodiment, the initialization refers to resolving order information, extracting information of a dispatch address and information of a transport vehicle, and counting the number of times each transport vehicle passes through each address.

203. Traversing all dispatch addresses through an ant colony algorithm to obtain information left by the dispatch addresses of the vehicle;

204. and outputting an optimal path and an optimal path length according to the left information, and training based on the output path to obtain a path optimization model.

In this embodiment, the ant colony algorithm is an algorithm obtained by simulating a motion law of foraging of real ants in nature. When ants find food, the ants can always find a shortest path from the food source to the ant cavity and can adapt to environmental changes, such as when obstacles suddenly appear on the foraging path of the ant colony, the ants can quickly avoid and find other paths from the food source to the ant cavity again. It is found that this is because, during the course of the movement of the ant, a secretion-pheromone (pheomone) can be released on the path it passes through, and other ants can perceive the presence and intensity of this substance during the movement and select the path with a large amount of pheromone as their own movement direction. Since the amount of information on the shorter path remains relatively large in the same time, ants selecting shorter paths are also increasing, which is a positive feedback phenomenon.

For the training process, the following analysis is performed from the ant perspective, and the specific principle is as follows:

step 1, initializing parameters, and setting related parameters: the number of addresses N, the total number of ants m, and the maximum value N of m ant iteration times required to be traversed _max Messaging tau on each path at the initial time _ij (0) =τ (0), pheromone probability coefficient ρ, pheromone heuristic factor α, self heuristic quantity factor β, total information quantity Q, and the like. Establishing a tabu list J ^k And ensures that there are no addresses in the table at this time.

Step 2, randomly arranging m ants on n addresses, wherein each address is distributed with at most one ant, and storing address information of the m ants into a tabu list J ^k 。

In practical application, m ants are sent to n addresses, namely, the information left by the ants when vehicles pass through during dispatching of each address is actually obtained, so that the information on n addresses is summarized after the ants traverse all addresses, and in the traversing process, after each traversing of an address, the ants need to store the address information into a tabu list, and the situation that the ants repeatedly traverse the addresses and influence the summarization of final information is avoided.

In this embodiment, when traversing n addresses, and after completing one address traversal, the ant selects the next address by calculating probability, where the probability calculation rule is:

wherein,,

for the probability that ant k selects address j from address i at time t, k represents the kth ant, τ _ij (t) represents the pheromone concentration, eta of the address i, j at the t-th moment _ij Representing visibility from address i to address j, L ^k Representing the total cost (or distance) of ant k going through a loop (or iteration) lock going through the path,>

is the pheromone change of ant k from address i to address j.

Further, after a path optimization model is obtained through training according to historical data, the model is used for planning a delivery path of the express delivery of the courier on the same day, a specific planning flow is shown in fig. 3, and the method comprises the following steps:

301. acquiring express mail information to be processed by a current salesman, and position information of a distribution center where the current salesman is located and vehicle information of a currently available vehicle of the distribution center;

302. analyzing all express mail information which is responsible for the salesmen to obtain corresponding express mail order information and a dispatching address set, and numbering each dispatching address in the dispatching address set;

303. Counting the total distribution amount of the order information to be processed by the salesman;

in this embodiment, taking a dispatch order as an example, since there is a difference in the amount of goods in different orders, the specific amount of goods can be calculated by weight or by volume, and the loading weight of a vehicle is fixed.

In the step, when the total delivery volume of the orders of the salesmen is counted, optionally, selecting one-day delivery orders for counting, firstly classifying the orders, for example, counting according to the volume if the orders are small pieces of documents; if the large-piece express mail is counted according to the volume, the volume is converted into the occupation of the volume after the volume and the weight are counted, and therefore the counting of the total delivery amount of the order information is completed.

304. Selecting at least one vehicle meeting loading requirements from the available vehicles according to the total distribution amount;

in this embodiment, the loading requirements include a selected maximum load of the vehicle that is greater than or equal to the total delivered-quantity; in the process of selecting vehicles according to the total distribution amount, besides taking the loading weight of the vehicles as consideration, the type of the vehicles, such as vehicles with the same loading amount, is also considered, and the vehicle with smaller fuel consumption is selected, wherein the consideration index can be selected according to the current road condition in practical application.

Of course, it is also possible to select vehicles with a loading weight equal to the total delivery amount, and in practical applications, there is also a need to leave room for the subsequent increase of the delivery order, and the selection can be made by setting a fluctuation range, for example, a vehicle with a loading weight of 25 kg can be selected.

In practical application, the method can further comprise selecting vehicles according to the dispatch area information of the operators, selecting small trucks such as flat trucks for the address area with convenient traffic, and selecting cars such as minibuses for the area with inconvenient traffic.

305. Taking the distribution center as an origin, and respectively traversing the at least one vehicle through all the dispatch addresses in the dispatch address set by the path optimization model to obtain a plurality of logistics lines;

in this embodiment, the location information of the origin of the selected at least one vehicle is set as the location information of the distribution center, and the distribution address set is traversed by using the principle of the ant colony algorithm based on the location information, so as to obtain a plurality of logistics routes.

In this embodiment, the dispatch address set may be traversed by at least one vehicle, as shown in fig. 4, specifically by the following procedure:

3051. Setting an origin of each of the at least one vehicle as location information of the distribution center;

3052. randomly selecting one vehicle from the at least one vehicle as a first vehicle;

3053. selecting a dispatch address from the dispatch address set as a first dispatch address based on the first vehicle;

3054. traversing path information between the distribution center and the first dispatch address through the path optimization model, and storing the first dispatch address into a preset tabu list;

3055. after the traversal of the dispatch addresses is completed, selecting the next dispatch address from the dispatch address set to traverse and store the tabu list;

3056. after traversing all the dispatch addresses in the dispatch address set, clearing the tabu list, and planning an optimal logistics route between the salesman and the first vehicle based on all path information obtained by traversing;

3057. and selecting a second vehicle from the rest vehicles to traverse the dispatch address set, and outputting a corresponding optimal logistics line. Until all vehicle traversal plans are completed, step 306 is performed.

In practical application, after a vehicle is selected from at least one vehicle, a dispatch address is randomly selected from a dispatch address set allowed by the vehicle to carry out traversal, namely, traversal is carried out from a distribution center to the selected address through a path optimization model, namely, traversal is carried out on a path from the distribution center to the selected address through a model simulation ant, specifically, real-time driving records between the two parts can be traversed through navigation software, the concentration of pheromones on a corresponding path is obtained through the number of vehicles traversing between the two parts, so that an optimal path between the two parts is calculated, in practical application, in traversal, statistics is carried out on driving records of a truck preferentially, so that the response of the driving time and the driving road condition left by the truck is obtained, so that the condition of traffic and the driving road on the corresponding path is calculated, so that an optimal section of logistics line is output, after the output of the path is completed, the dispatch address is taken as the starting point of the vehicle, the next dispatch address is selected from the rest dispatch addresses until the whole dispatching address set is completed, and the optimal logistics line is obtained after the whole vehicle is recombined.

In this step, for the last output several logistic routes, the optimal route set of each vehicle obtained by traversing the dispatch address set for all vehicles selected in step 304 is referred to as an optimal route set formed.

306. Calculating unit distribution cost of each logistics line in the plurality of logistics lines, and determining matching parameters between the salesmen and corresponding vehicles based on the unit distribution cost;

307. and planning an optimal logistics line corresponding to the salesman according to the matching parameters.

In this embodiment, when selecting the next dispatch address, traversing is performed by using a path optimization model, specifically selecting the next dispatch address from the dispatch address set by means of probability calculation, and optionally selecting one with the largest probability, or selecting two or three of the route segments traversed, and selecting one of the route segments traversed, in practical application, selecting a route segment with the shortest time, the shortest route and the largest delivery volume by means of setting constraint conditions by using a mathematical model.

In this embodiment, for selecting according to the probability, specifically, according to a preset probability conversion rule, calculating the probability that the first vehicle passes through each dispatch address, selecting one dispatch address with the highest probability as the first dispatch address, where the probability conversion rule is as follows:

In conclusion, the path optimization model constructed by the ant colony algorithm optimizes the package-sending path of the salesman, so that the solution of the complex optimization problem with higher practicability is realized, and the planned path has higher practicability, thereby meeting the requirements of various practical applications.

Furthermore, by utilizing the ant colony algorithm, the optimal route of the pick-up or delivery and the optimal adaptation information of the salesmen and the vehicles are automatically and efficiently calculated, thereby realizing the maximization of benefits, greatly improving the matching degree of the vehicles and the salesmen and reducing the logistics distribution cost.

Referring to fig. 5, a server is used as a logistics route planning device for detailed description, and another embodiment of the logistics route planning method in the embodiment of the present invention includes:

501. acquiring express mail information to be processed by a current salesman, and position information of a distribution center where the current salesman is located and vehicle information of a currently available vehicle of the distribution center;

the server receives a request of sending or receiving a piece triggered by a salesman on an APP, obtains the piece information of the salesman needing to send or receive the piece in the current time period from a logistics database according to the request, obtains the current position of the salesman through a positioning technology, determines a distribution center closest to the salesman based on the position, takes the distribution center as an originating point of sending or receiving the piece, and then inquires vehicle information of a vehicle which can be currently called by the salesman from a system of the distribution center.

502. Analyzing all express mail information which is responsible for the salesmen to obtain corresponding express mail order information and a dispatching address set, and numbering each dispatching address in the dispatching address set;

specifically, the server obtains all the express mail information required to be dispatched by the salesman at the current time from the dispatch database, extracts the order number and the dispatch address from the express mail information through a text and picture identification technology, and numbers the dispatch addresses of all the express mail. Furthermore, in the numbering process, navigation software can be used for automatically navigating and calculating the distance, the numbering is performed based on the sequencing of the distance, and then the compiled dispatch addresses are formed into a set.

503. Taking the vehicle information, the order information and the delivery address set as constraint conditions of logistics route planning, and calculating matching parameters between the salesmen and available vehicles by using a path optimization model;

504. planning an optimal logistics line corresponding to the salesman according to the matching parameters;

505. new order information of the network points passing through the optimal object flow line is obtained at fixed time;

in this embodiment, the new order information is a pick-up order or a dispatch order, for this step, the adjustment of the logistics path of the salesman is achieved by combining with the situation of the website order and dynamically sensing pick-up or dispatch, so that the control of the re-dispatch of the salesman to the greatest extent can be achieved, optionally, when the new order is received on the logistics system, the salesman is selected and allocated by judging the dispatch website where the order is located, if the order is just the website served by the salesman, the type of the order is further determined, the current route adjustment strategy for the salesman is set based on the type, if the dispatch order is selected, the planning in the going of the route of the salesman is preferentially selected, and if the dispatch order is selected, the return route of the salesman is preferentially selected and adjusted.

In this embodiment, when a new order is acquired at regular time, the new order may be selected and acquired by positioning the dispatch of the salesman, for example, a timer is set, the dispatch software of the salesman is set to acquire at regular time, and meanwhile, whether the salesman reaches the current logistics line to obtain the dispatch address needs to be monitored, if yes, the timer is triggered to acquire whether the new order exists on the website where the dispatch address exists, if yes, the new order is read and pushed to the salesman, and whether the salesman needs to receive the new order is determined.

506. Judging whether the new order information belongs to an order on the optimal commodity circulation line;

507. if yes, the new order information is embedded into the optimal logistics line according to the path optimization model.

In this embodiment, before outputting the optimal line, determining the type of the express mail information, where the type includes a pick-up and a send-out, if the express mail is picked up, the line of the output return section is preferentially selected to pick up the express mail, and if the express mail is taken out, the express mail is output according to the current road condition; if the route is the route, the route of the output route is selected to be the route in a centralized way, and the return route is output according to the current road condition.

In practical application, when the current logistics line is adjusted by using the path optimization model, the uncoded part of the current logistics line is decoded by a genetic algorithm to obtain a dispatch address set, and the steps 502-503 are repeated to perform path optimization planning to obtain the current optimal logistics line.

Of course, the output logistics line can also be evaluated by combining with the mathematical model, specifically, whether the logistics line meets the constraint condition in the mathematical model is judged, and in the process of judging whether the constraint condition is met, comparison consideration can be performed according to the priority in the constraint condition in the mathematical model, for example: and evaluating the conditions in the path according to the sequence of time window > cargo capacity > distance > cost, and directly outputting the corresponding logistics line after the evaluation is passed.

In this embodiment, if the constraint condition is set, the constraint condition includes at least one of the following:

freight volume constraint conditions of corresponding delivery tasks under various route grades;

vehicle quantity constraint conditions corresponding to different cargo quantities;

a difference constraint condition of a straight line distance between a delivery starting point and a delivery ending point and the total distance of a delivery line;

Decision variable uniqueness constraint conditions in the distribution process;

distributing time window constraint conditions;

loading limit constraints on the distribution line;

transportation cost constraints.

Further, the genetic algorithm is used for extracting the gene individuals from partial routes which are not completed in the current logistics route, so that a plurality of dispatch addresses are obtained;

and sequentially encoding the extracted plurality of dispatch addresses and the dispatch addresses in the new order to form an initial solution, wherein the dispatch addresses in the initial solution and the dispatch addresses are in a neighborhood relationship.

And then, based on an ant colony algorithm, each dispatch address in the initial solution is respectively in butt joint with the dispatch address where the business is located, one dispatch address with the optimal probability is selected as the next dispatch address through a probability conversion rule, a distribution network between the next dispatch address and the current dispatch address is formed, and the optimal line of the line in the distribution network is traversed through simulation ants.

By implementing the method, the learning of path planning experience based on a learning mode of a machine algorithm can be realized, the input of manual operation can be reduced, the matching degree of people and vehicles is improved, meanwhile, orders of network points in the lines are monitored in real time to adjust the lines in real time, rescheduling of service personnel is realized, the distribution logistics cost of express mail is reduced, the efficiency of picking up and dispatching the express mail is improved, and complaints of clients are avoided.

In this embodiment, for a business person, in the process of logistics transportation, the processed express mail information includes two types of package and dispatch, the logistics route planning method provided in the present application may perform planning processing for an individual dispatch route, or may perform planning processing for a route of package alone, or may be hybrid processing, as shown in fig. 6, the package is taken as a main line, and the package is taken as an auxiliary hybrid service form to describe, where the processing steps specifically include:

601. acquiring an unprocessed dispatch order of the day, which is distributed to the salesman by the logistics system, according to the dispatch departure time reported by the salesman;

602. extracting delivery addresses and delivery time in the delivery order to obtain a delivery address set and a delivery time sequence;

603. acquiring vehicle information which can be allocated by a salesman at an originating place according to the distribution originating place selected by the salesman;

in the step, the obtained vehicle information comprises the number of vehicles which can be allocated, the maximum loading weight of each vehicle, the running time, the running distance and the like, in practical application, the loading weight of the vehicle is determined based on the vehicle specification by identifying the vehicle specification and the historical running record of the vehicle for each called at the starting place, the maximum running distance and the specified running time of the vehicle are calculated based on the historical running record, in the screening process, whether each vehicle can run at the distribution time in the dispatch order is firstly judged according to the specified running time, so that a first vehicle set is selected, and if the specific starting time of a judging line and the time of returning to the distribution starting place are within the specified running time of the vehicle, the vehicle is determined to be the vehicle which can be called by a service person.

And then carrying out further screening by using the loading weight based on the first vehicle set, and finally carrying out final screening by using the form route of the vehicle, wherein in the final screening, whether the maximum route from the delivery starting address to the furthest delivery task can be completed by the oil quantity reserved by the vehicle can be determined based on the relation between the driving route and the oil consumption in the driving record of the vehicle.

604. Traversing the distribution address set and the distribution time sequence through a path optimization model adopting an ant colony algorithm principle, and outputting an optimal distribution line;

in this step, for implementation of step 604, whether the time from the vehicle to each dispatch address accords with the distribution time sequence may be calculated by creating an initial route, if so, the initial route is taken as a planning basis of the distribution route, traversal adjustment is performed on each section of route in the initial route by using a path optimization model, specifically, route between every two dispatch addresses is re-planned by using ant colony traversal principle in the model, and of course, the time to reach the dispatch address cannot be increased when the constraint condition of traversal planning is met, and on this basis, it is determined how best to travel by simulating the pheromone left by ants for vehicle travel between two places, that is, low cost, short distance, and the like, so as to output the final distribution route.

In this embodiment, the order processing of the logistics is not receiving after the task amount is reached, but each website receives a new order at any time, and at this time, the real-time dispatch may not be completed due to departure or missing of the salesman, so as to solve the problem, in this embodiment, the step of dispatching the salesman who is dispatching the piece around to adjust is provided, which includes the following steps:

605. the logistics route planning device monitors that a new delivery order is received by a website and obtains the new delivery order;

606. acquiring current positioning information of a salesman;

the step is specifically that the GPS positioning system in the logistics new route planning device is called to traverse the card punching information recorded by the website where the new order is located by the salesman so as to judge whether the proper salesman is called, if yes, step 607 is executed.

607. Judging whether the positioning information is consistent with the position information of the distribution center;

608. if the new order information is consistent, executing the step of judging whether the new order information belongs to the order on the optimal commodity line;

and when the order belongs to the optimal logistics line, embedding the new order information into the optimal logistics line according to the path optimization model, executing step 609, and otherwise returning to step 606.

609. If the addresses are inconsistent, an unprocessed dispatch address is selected from the dispatch address set to form a second dispatch address set;

610. and taking the positioning information as an origin of the vehicle, and planning a logistics line for the second dispatch address set by utilizing the path optimization model.

Through the steps, the express delivery route of the salesman is planned by utilizing the route optimization model trained by the ant colony algorithm, and the route planning optimization is realized by utilizing the algorithm model, and because the algorithm model has the characteristics of self-organization, parallel calculation and positive feedback search, the calculated express delivery or delivery route can meet the matching degree between the salesman and the vehicle to the greatest extent, and the delivery route is determined by adopting a scientific and reasonable method, so that the satisfaction degree of the customer to the logistics delivery service can be enhanced, the delivery cost of a logistics enterprise is reduced, and the delivery efficiency is improved.

Meanwhile, new order conditions of all the sites are detected in real time to call the service personnel to realize dispatch, so that the rescheduling strength of the service personnel is improved, the actual loading and transporting capacity of each vehicle is increased, the dispatch number of express mail is reduced, and the logistics cost is further reduced.

The method for planning a logistics route in the embodiment of the present invention is described above, and the device for planning a logistics route in the embodiment of the present invention is described below, referring to fig. 7, where an implementation manner of the device for planning a logistics route in the embodiment of the present invention includes:

the collecting module 71 is configured to obtain information of a express to be processed by a current salesman, and position information of a distribution center where the current salesman is located and vehicle information of a vehicle currently available in the distribution center;

the parsing module 72 is configured to parse all pieces of express information that are responsible for the salesman, obtain corresponding order information of the express and a group address set, and number each group address in the group address set;

the model analysis module 73 is configured to calculate a matching parameter between the salesman and the available vehicle by using the vehicle information, the order information and the group address set as constraint conditions of logistics route planning and using a path optimization model, where the path optimization model is a model obtained by training logistics history processing information through an ant colony algorithm;

and the route generation module 74 is used for planning an optimal logistics route corresponding to the salesman according to the matching parameters.

According to the device, the ant colony algorithm is adopted to train logistics historical processing information classified according to the operators, a path optimization model is obtained, corresponding express mail order information, express mail addresses and distributable vehicle information are extracted from express mail information to be processed by the operators in the path planning process, the information is used as constraint conditions of a planned path, the path optimization model is utilized to calculate matching parameters between the operators and the vehicle information, and optimal path planning is carried out based on the matching parameters, so that the logistics line is optimized according to the relation between the vehicle information and the express mail processed by the operators, the maximum loading of the vehicles is realized, the matching degree of people and vehicles is improved, meanwhile, the efficiency of distributing the express mail is improved, and the logistics distribution cost of a single operator is reduced.

The embodiment of the logistics route planning device according to the present invention is not described in detail herein.

Referring to fig. 8, in another embodiment of the present invention, a logistics route planning apparatus includes:

Wherein the model analysis module 73 comprises:

a statistics unit 731, configured to count total delivery amounts of order information to be processed by the salesman;

a selecting unit 732 configured to select at least one vehicle satisfying a loading requirement from the available vehicles according to the total delivery amount, the loading requirement including a maximum load of the selected vehicles being greater than or equal to the total delivery amount;

an analysis unit 733, configured to traverse the at least one vehicle through the path optimization model by using the distribution center as an origin, and obtain a plurality of logistics routes;

A calculating unit 734, configured to calculate a unit distribution cost of each of the plurality of logistics routes, and determine a matching parameter between the salesman and the corresponding vehicle based on the unit distribution cost.

Optionally, the analysis unit 733 is specifically configured to:

Optionally, the logistics route planning apparatus further comprises an optimizing module 75, which is specifically configured to:

Wherein the optimization module 75 is further configured to:

acquiring current positioning information of the salesman;

In this embodiment, the logistics route planning apparatus further includes a model training module 76, specifically configured to:

In practical applications, fig. 7-8 above describe the logistics route planning apparatus in the embodiment of the present invention in detail from the point of view of the modularized functional entity, and the logistics route planning device in the embodiment of the present invention is described in detail from the point of view of hardware processing.

Fig. 9 is a schematic structural diagram of an entity device of a logistics route planning apparatus according to the present invention, where the logistics route planning apparatus 2000 may generate relatively large differences according to actual requirements, actual configurations or performances, and may include, for example, one or more processors (central processing units, CPU) 2010 (for example, one or more processors) and a memory 2020, one or more storage media 2030 (for example, one or more mass storage devices) storing application programs 2033 or data 2032. The storage means used by the memory 1020 and the storage medium 2030 may be short-lived storage or persistent storage. The program stored on storage medium 2030 may include modules (not shown) of functionality provided by one or more embodiments, each of which may include a series of instruction operations for logistics line planning apparatus 2000. Still further, the processor 2010 may be configured to communicate with the storage medium 2030, and execute a series of instruction operations in the storage medium 2030 on the logistics route planning apparatus 2000, where the series of instruction corresponds to the function implemented by the logistics route planning method provided in the above embodiment.

The logistics planning apparatus 2000 may also include one or more power supplies 2040, one or more wired or wireless network interfaces 2050, one or more input/output interfaces 2060, and/or one or more operating systems 2031, such as Windows Server, mac OS X, unix, linux, freeBSD, etc. It will be appreciated by those skilled in the art that the logistics planning apparatus structure illustrated in fig. 9 does not constitute a unique limitation of the logistics planning apparatus, and in practical applications it may comprise more or less components than illustrated, or some components may be combined, or a different arrangement of components.

The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, or a volatile computer readable storage medium, in which a computer program (i.e. instructions) is stored, which when executed on a computer, cause the computer to perform the steps of the method for logistics route planning, optionally by a processor on the computer.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method of logistic route planning, the method comprising:

Planning an optimal logistics line corresponding to the salesman according to the matching parameters;

after the optimal logistics line corresponding to the salesman is planned according to the matching parameters, the method further comprises the following steps:

if yes, embedding the new order information into the optimal logistics line according to the path optimization model;

the embedding the new order information into the optimal logistics line according to the path optimization model comprises the following steps:

performing decoding processing on partial unfinished lines in the current logistics line through a genetic algorithm to obtain a dispatch address set, and performing path optimization planning processing to obtain the current optimal logistics line;

evaluating the output logistics lines by combining the mathematical model, and directly outputting the corresponding logistics lines after the evaluation is passed;

extracting a gene individual from partial unfinished lines in the current logistics line through the genetic algorithm to obtain a plurality of dispatch addresses;

Sequentially encoding the extracted plurality of dispatch addresses and the dispatch addresses in the new order to form an initial solution, wherein the dispatch addresses in the initial solution and the dispatch addresses are in a neighborhood relationship;

and respectively butting each dispatch address in the initial solution with the dispatch address where the business is located based on an ant colony algorithm, selecting one dispatch address with optimal probability as the next dispatch address through a probability conversion rule, forming a distribution network between the next dispatch address and the current dispatch address, and traversing the optimal line of the line in the distribution network through simulating ants.

2. The method of claim 1, wherein the calculating the matching parameters between the salesman and the available vehicles using the vehicle information, the order information, and the group address set as constraints for the logistics route planning and the path optimization model comprises:

3. The method of claim 2, wherein using the distribution center as an origin, traversing the at least one vehicle over all of the dispatch addresses in the dispatch address set based on the path optimization model, respectively, to obtain a plurality of logistics routes comprises:

4. A method of route planning according to claim 3 wherein said selecting a dispatch address from said dispatch address set based on said first vehicle as a first dispatch address comprises:

5. The method according to claim 1, further comprising, after the new order information of the dots passed on the optimal commodity line is obtained at the timing, before the determining whether the new order information belongs to the order on the optimal commodity line:

Acquiring current positioning information of the salesman;

6. The logistics route planning method of claim 1, comprising training to obtain the path optimization model by:

7. A logistics route planning device, characterized in that the logistics route planning device comprises:

the line generation module is used for planning an optimal logistics line corresponding to the salesman according to the matching parameters;

the optimizing module is used for acquiring new order information of the network points passing through the optimal commodity line at regular time, wherein the new order information is a member-collecting order or a member-sending order; judging whether the new order information belongs to an order on the optimal commodity circulation line; if yes, embedding the new order information into the optimal logistics line according to the path optimization model;

The optimizing module is also used for carrying out decoding processing on partial unfinished lines in the current logistics line through a genetic algorithm to obtain a delivery address set, and carrying out path optimizing planning processing to obtain the current optimal logistics line; evaluating the output logistics lines by combining the mathematical model, and directly outputting the corresponding logistics lines after the evaluation is passed; extracting a gene individual from partial unfinished lines in the current logistics line through the genetic algorithm to obtain a plurality of dispatch addresses; sequentially encoding the extracted plurality of dispatch addresses and the dispatch addresses in the new order to form an initial solution, wherein the dispatch addresses in the initial solution and the dispatch addresses are in a neighborhood relationship; and respectively butting each dispatch address in the initial solution with the dispatch address where the business is located based on an ant colony algorithm, selecting one dispatch address with optimal probability as the next dispatch address through a probability conversion rule, forming a distribution network between the next dispatch address and the current dispatch address, and traversing the optimal line of the line in the distribution network through simulating ants.

8. A logistics route planning apparatus, characterized in that the logistics route planning apparatus comprises: a memory and at least one processor, the memory having instructions stored therein, the memory and the at least one processor being interconnected by a line;

The at least one processor invokes the instructions in the memory to cause the logistics route planning apparatus to perform the logistics route planning method of any one of claims 1-6.

9. A computer readable storage medium having a computer program stored thereon, wherein the computer program when executed by a processor implements the logistics route planning method of any one of claims 1-6.