CN111047102B - Express delivery route optimization method based on elite-driven particle swarm algorithm - Google Patents
Express delivery route optimization method based on elite-driven particle swarm algorithm Download PDFInfo
- Publication number
- CN111047102B CN111047102B CN201911306510.0A CN201911306510A CN111047102B CN 111047102 B CN111047102 B CN 111047102B CN 201911306510 A CN201911306510 A CN 201911306510A CN 111047102 B CN111047102 B CN 111047102B
- Authority
- CN
- China
- Prior art keywords
- particle
- optimization
- optimal
- particles
- express delivery
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
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"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/008—Artificial life, i.e. computing arrangements simulating life based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0835—Relationships between shipper or supplier and carriers
- G06Q10/08355—Routing methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Robotics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
An express delivery route optimization method based on elite-driven particle swarm optimization belongs to the field of combination of machine learning and logistics technology. According to the method, the pre-condition of transportation is determined by setting the parameters of the express delivery end, road network data is obtained through an electronic map to obtain the existing path information, constraint conditions for limiting a logistics scheme are formulated according to order data and delivery requirements, the solution space of the delivery scheme is determined through an enumeration method, and finally an optimal logistics delivery plan meeting all requirements is searched through PSO-ED.
Description
Technical Field
The invention belongs to the technical field of machine learning and logistics, and provides a model for searching an optimal express delivery route by using an improved particle swarm algorithm, which can quickly and effectively find an optimal delivery scheme so as to help express enterprises to realize quick and efficient delivery service.
Background
Efficient delivery is a precondition for survival and development of express enterprises. Today, where electronic commerce is actively developed, only one urban express enterprise has millions of goods to be delivered every day. Unreasonable distribution paths will bring significant losses to the enterprise. The reasonable planning of the delivery path by using the computer technology is a necessary choice for the express enterprises to realize the rapid and efficient delivery service. However, path planning is a complex multi-objective task that takes into account both the cost of delivery and customer satisfaction, as well as the different requirements for delivering the goods, such as the urgent delivery of fresh fruit and the careful transportation of fragile items. In the face of such a complex multi-objective optimization problem, it is not appropriate to only give one set of plans. The method provides a plurality of feasible schemes and alternative schemes for examining the distribution problem based on different angles for enterprises to select, and is an ideal function which the express management system should have.
In recent years, computer technology has rapidly developed, and particle swarm optimization (PSO, particle Swarm Optimization) proposed by Kennedy and Eberhart in 1995 is a population-based evolutionary computing algorithm. The algorithm attracts attention of many scholars and researchers in the last 20 years due to the simple concept, easy implementation and low computational overhead. PSOs have proven to be effective and powerful in the face of complex optimization problems. Nowadays, PSOs have been successfully used in a wide variety of fields, such as power systems, engineering, neural networks, etc.
The PSO algorithm can be utilized to effectively complete multi-target optimizing tasks. According to the method, all influence factors in the express delivery path planning are comprehensively considered, so that an optimal scheme is quickly and efficiently sought. However, conventional PSO algorithms tend to produce premature convergence (especially in dealing with complex multimodal search problems) and have poor local optimality. The PSO algorithm falls into a local minimum mainly due to the loss of diversity of the population in the search space and the fact that each particle in the population is close to a globally optimal particle, thus falling into a locally optimal solution. Therefore, the learning model of the traditional PSO algorithm needs to be improved, the diversity of the population is increased, and meanwhile, the complexity of the algorithm is reduced as much as possible, so that the problem of optimizing the distribution path is better solved.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides an express delivery route optimization method based on an elite-driven particle swarm algorithm (Particle Swarm Optimization driven by Elite, PSO-ED).
The technical scheme of the invention is as follows:
step 1, setting express delivery end parameters, wherein the express delivery end parameters comprise distributed point information, distribution point information, express delivery content information and transport means;
step 2, acquiring road network data from an electronic map provider of a third party;
specifically, the road network data in the step 2 includes traffic line positions, road physical geometric features, historical traffic data and road charging information, and correspondingly, the search space of the distribution scheme in the step 5 includes traffic line positions, road physical geometric features, historical traffic data, road charging information, basic distribution tasks, constraint conditions and optimization targets processed based on an enumeration method. Information such as road network data, transportation means, distribution points and distribution points is automatically quantized into discrete digital information by the system.
specifically, the order data in step 3 includes: the type of the article to be delivered, the order requirement, the total weight of the article and the destination. The order input module is mainly used for acquiring order information, and comprises the following steps: time constraints generated according to customer requirements; vehicle constraints are generated according to the types of the articles, whether the express delivery (such as the electronic equipment containing the lithium battery cannot be air-borne, fragile articles need to be taken and put lightly, cannot be stacked randomly and cannot run bumpy roads in land transportation) needs to be carefully handled or not, and the like.
Step 4, determining at least one optimization target from a preset optimization target set, and presenting the optimization target in the fitness function to obtain an objective function to be optimized; the optimization targets include: the cost is lowest, the time is shortest, and business points are dispatched in time;
and 5, processing the road network data in the step 2, the basic distribution tasks and the constraint conditions in the step 3 based on an enumeration method to acquire a search space of a distribution scheme. The search space comprises a transportation route, a transportation tool, a distributed point and a distribution point; a dispatcher's delivery route;
and 6, searching an optimal solution by using an elite driving particle swarm algorithm based on an objective function to be optimized, wherein the specific process is as follows:
and (3) adjusting the weights of all parts of the objective function to be optimized by using the optimization targets selected in the step (4), if the optimization targets are the shortest in time, the weights of the parts representing the time are increased, and the optimization function containing three optimization targets can be expressed as follows:
F(x)＝αf(x)+βg(x)+γh(x)(1)
wherein f (x) is a cost module, g (x) is a time module, and h (x) is a business point instant dispatch module. Then searching an optimal solution by using an elite driving particle swarm method, wherein the elite driving particle swarm method has the following formula:
wherein t is iteration count and time step; c 1 ，c 2 ，c 3 Is a learning factor, namely, the deviation weight of social learning, neighborhood learning and self-learning is adjusted; r is (r) 1 ，r 2 ，r 3 Is subject to [0,1 ]]Random numbers uniformly distributed in the interval ensure that the searching process has randomness and can cover the whole searching space; w represents inertial weight, which means how much the speed of the current time step inherits the speed of the last time step; x is the position of each particle, and the position of each particle represents express route information, wherein the express route information comprises a transportation route, a transportation tool, a distributed point, a distribution point and a distribution route of a distributor; v is the respective speed of the particles, and the time step of each iteration is 1, namely the displacement of the particles can be considered, and the particles are driven by the displacement to jump from the current solution to another solution; i, j are the particle labels and the dimension labels, respectively; the gbest is the optimal position searched by all the current particles, namely the global optimal particle; the pbest is the optimal position searched by each current particle, and the nbest is the optimal position searched by each neighbor of the current particle, namely the neighbor optimal particle.
ggr and ngr are gravitation coefficients of global optimal particles and neighborhood optimal particles to each particle, and the specific calculation formula is as follows:
wherein dist represents the distance between the current particle and the global optimal particle and the neighborhood optimal particle, respectively. dist (dist) gmax Is the maximum Euclidean distance of the entire search space, dist nmax The maximum distance that the neighborhood optimal particles can influence is the maximum and minimum search positions of each dimension are given by quantized road network information:
dist nmax for the influence range of the neighborhood optimal particles, the gravitation coefficient is inversely proportional to the square of the distance between particles, and the gravitation coefficient is also in accordance with Newton's calculation of the gravitation, and the gravitation coefficient calculated by the formula (4) (5) is always in the interval [0.5, 1)]A number of the pairs.
The invention has the beneficial effects that: according to the method, the pre-condition of transportation is determined by setting the parameters of the express delivery end, road network data is obtained through an electronic map to obtain the existing path information, constraint conditions for limiting a logistics scheme are formulated according to order data and delivery requirements, the solution space of the delivery scheme is determined through an enumeration method, and finally an optimal logistics delivery plan meeting all requirements is searched through PSO-ED.
Drawings
Fig. 1 is a schematic flow chart of the present invention.
FIG. 2 is a schematic diagram of the gravitational coefficient in PSO-ED.
FIG. 3 is a schematic diagram of a simulated express delivery optimization route.
Detailed description of the preferred embodiments
According to the specific description of each step, the input express delivery requirement is simulated on the acquired road network information, and the performance of the elite driving particle swarm search algorithm and the performance of the traditional particle swarm search algorithm provided by the invention are compared. The road network information includes detailed road network information of Beijing, hebei and Shandong. The road conditions in the Beijing part are congested, express delivery to Shandong is required to pass through a charged expressway and pass through Hebei if going to land, and air transportation can be selected if the Beijing is far away from the Shandong part, so that simulation experiments are carried out in the three regions. We simulated 200 express delivery routes including common items, electronic products that cannot be air transported, fragile items, high value products, etc., and randomly assigned one or more optimization objectives for these express delivery.
The following is a specific simulation experiment, and is shown in fig. 3.
Step 1, setting express delivery end parameters, wherein the express delivery end parameters comprise distributed point information, distribution point information, express delivery content information and transport means; the parameters of the express delivery end are recorded into the system by a worker after collecting the mail information of the customer; the information of the distributed points and the distribution points is dynamically updated to prevent the distribution points from being completely distributed in time due to excessive express delivery, and the position information of the distributed points and the distribution points are marked on the electronic map; the article information includes the volume, weight and type of the articles, wherein the type information of each article is stored in the system in advance, and corresponds to the characteristic data of each article, such as fragility, moisture susceptibility or limiting transportation means or road selection for some reasons, and the volume and weight information also can limit transportation means (the factors such as weight limit, height limit and capacity of vehicles or planes need to be considered). After the parameters are input, the background returns the order number of the order;
step 2, acquiring road network data from an electronic map provider of a third party; the road network data is accessed directly through an interface opened by a network map provider (a third party such as a Goldmap), and when the travel time of a certain section of journey needs to be calculated, the length of a specific section of journey and the traffic condition at the corresponding moment are accessed and calculated as external initial parameter data. The express delivery at each business point is transported to the collection and distribution points of each city by the transport vehicle, and then sorted according to the difference of destinations and the difference of transport means given by the system, where the system also considers whether each train number/flight is effectively utilized, i.e. whether express packages are transported as much as possible. When the utilization rate of a certain train number/flight is insufficient, express packages with high priority are transported to the next distributed point in advance, packages with low priority wait until the next day and packages with the next day are transported together, and the priorities of the express packages with high priority are correspondingly increased due to time.
And step 3, acquiring order data, and generating basic distribution tasks and constraint conditions according to the order data. If the salesman finishes submitting the express delivery end parameters in the step 1, the background will be automatic. The basic distribution tasks as in fig. 3 are: express delivery is sent from Beijing foreign language university bird post to hospitals in the Shandong Zaozhuang city platform village district from the Beijing city sea lake district, and the parcel weight is 2kgThe package size is 0.1×0.1 x 0.1m 3 . The constraint conditions are as follows: fragile articles, the next day of arrival, high value articles.
Step 4, determining at least one optimization target from a preset optimization target set, wherein the determined optimization target is the shortest in time, and the optimization target is presented in an optimization function, namely the size of a parameter beta is increased in the example, and then alpha and gamma are set to be 1, beta is set to be 5, and the optimization function is that:
F(x)＝1×f(x)+5×g(x)+1×h(x) (7)
and 5, generating a search space of the distribution scheme by the background according to the road network data, the basic distribution task and the constraint conditions which are acquired in the step. The search space comprises a transportation route, a transportation tool, a distributed point, a distribution point and a distribution route of a distributor;
and step 6, initializing particle parameters by using a PSO-ED algorithm and iterating after obtaining the search space, and trying to find a global optimal solution. The time overhead of the process is affected by the complexity of the problem, so that an upper limit solving time can be set manually, or the current obtained optimal scheme can be manually stopped and output in the solving process. In this set of experiments we set the upper solution limit time for the single task to 10 seconds.
When the dispatcher receives a plurality of dispatching tasks, the system also generates an optimal dispatching route.
Simulation results show that the express route optimization based on elite-driven particle swarm algorithm has better optimizing performance than the express route optimization based on the traditional particle swarm algorithm, and the time cost of the two algorithms is approximate under the condition of the same iteration times. Because the gravitation coefficient is introduced, the convergence rate of the elite-driven particle swarm algorithm is improved by 30%, and in each express route optimization task, the score of the optimal solution found by the elite-driven particle swarm algorithm is more than or equal to that of the optimal solution found by the traditional particle swarm algorithm. Therefore, the invention can effectively solve the problem of optimization of the delivery route and find a better express route.
While the preferred embodiment of the present invention has been described in detail, the present invention is not limited to the embodiments, and those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention, and these equivalent modifications or substitutions are included in the scope of the present invention as defined in the appended claims.
Claims (2)
1. The express delivery route optimization method based on elite-driven particle swarm optimization is characterized by comprising the following steps:
step 1, setting express delivery end parameters, wherein the express delivery end parameters comprise distributed point information, distribution point information, express delivery content information and transport means;
step 2, acquiring road network data from an electronic map provider of a third party;
step 3, acquiring order data, and generating basic distribution tasks and constraint conditions according to the order data;
step 4, determining at least one optimization target from a preset optimization target set, and presenting the optimization target in the fitness function to obtain an objective function to be optimized; the optimization targets include: the cost is lowest, the time is shortest, and business points are dispatched in time;
step 5, processing the road network data in the step 2, the basic distribution tasks and the constraint conditions in the step 3 based on an enumeration method to obtain a search space of a distribution scheme; the search space comprises a transportation route, a transportation tool, a distributed point and a distribution point; a dispatcher's delivery route;
and 6, searching an optimal solution by using an elite driving particle swarm algorithm based on an objective function to be optimized, wherein the specific process is as follows:
and (3) adjusting the weight of each part of the objective function to be optimized by using the optimization target selected in the step (4), and then searching an optimal solution by using an elite driving particle swarm method, wherein the elite driving particle swarm method has the following formula:
wherein t is an iteration count; c 1 To adjust the social learning factor c 2 To adjust the neighbor learning factor c 3 To adjust the self-learning factor; r is (r) 1 ，r 2 ，r 3 Is subject to [0,1 ]]Random numbers uniformly distributed in the interval ensure that the searching process has randomness and can cover the whole searching space; w represents inertial weight, which means how much the speed of the current time step inherits the speed of the last time step; x is the position of each particle, and the position of each particle represents express route information, wherein the express route information comprises a transportation route, a transportation tool, a distributed point, a distribution point and a distribution route of a distributor; v is the respective speed of the particles, and the time step of each iteration is 1, namely the displacement of the particles can be considered, and the particles are driven by the displacement to jump from the current solution to another solution; i, j are the particle labels and the dimension labels, respectively; the gbest is the optimal position searched by all the current particles, namely the global optimal particle; the pbest is the optimal position searched by each current particle, and the nbest is the optimal position searched by each neighbor of the current particle, namely the neighbor optimal particle;
ggr and ngr are gravitation coefficients of global optimal particles and neighborhood optimal particles to each particle, and the specific calculation formula is as follows:
wherein dist represents the distance between the current particle and the global optimal particle and the neighborhood optimal particle respectively; dist (dist) gmax Is the maximum Euclidean distance of the entire search space, dist nmax Is the maximum distance that the neighborhood optimal particles can affect, each dimensionThe maximum and minimum search positions of (1) are given by quantized road network information:
where d represents the dimension of the search space; max (max) i Representing the maximum value taken by the particle in the ith dimension; min i Representing the minimum taken by the particle in the ith dimension;
dist nmax for the influence range of the neighborhood optimal particles, the gravitation coefficient is inversely proportional to the square of the distance between particles, and the gravitation coefficient is also in accordance with Newton's calculation of the gravitation, and the gravitation coefficient calculated by the formula (4) (5) is always in the interval [0.5, 1)]A number of the pairs.
2. The express delivery route optimization method based on elite driving particle swarm optimization according to claim 1, wherein the optimization objective selected in step 4 is used for adjusting the weights of each part of the objective function to be optimized, and the optimization function comprising three optimization objectives can be expressed as:
F(x)＝αf(x)+βg(x)+γh(x)(6)
where α is a cost target weight, f (x) is a cost target, β is a time target weight, g (x) is a time target, γ is a business point immediate dispatch target weight, and h (x) is a business point immediate dispatch target.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911306510.0A CN111047102B (en) | 2019-12-18 | 2019-12-18 | Express delivery route optimization method based on elite-driven particle swarm algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911306510.0A CN111047102B (en) | 2019-12-18 | 2019-12-18 | Express delivery route optimization method based on elite-driven particle swarm algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111047102A CN111047102A (en) | 2020-04-21 |
| CN111047102B true CN111047102B (en) | 2023-05-30 |
Family
ID=70237496
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911306510.0A Active CN111047102B (en) | 2019-12-18 | 2019-12-18 | Express delivery route optimization method based on elite-driven particle swarm algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111047102B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112529305A (en) * | 2020-12-16 | 2021-03-19 | 北京交通大学 | Express item acquisition sequence prediction method based on deep learning |
| CN117195484B (en) * | 2023-08-08 | 2024-05-03 | 广东贝能达交通设备有限公司 | Rail transit management method and system |
| CN117113608B (en) * | 2023-10-23 | 2024-02-13 | 四川港投新通道物流产业投资集团有限公司 | Cold-chain logistics network node layout method and equipment |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103971160B (en) * | 2014-05-05 | 2017-02-15 | 北京航空航天大学 | particle swarm optimization method based on complex network |
| CN106682682A (en) * | 2016-10-20 | 2017-05-17 | 北京工业大学 | Method for optimizing support vector machine based on Particle Swarm Optimization |
| CN109063899A (en) * | 2018-07-06 | 2018-12-21 | 上海大学 | Vehicle transport method and device for planning, electronic equipment and readable storage medium storing program for executing |
| CN109726863A (en) * | 2018-12-26 | 2019-05-07 | 深圳市北斗智能科技有限公司 | A kind of material-flow method and system of multiple-objection optimization |
-
2019
- 2019-12-18 CN CN201911306510.0A patent/CN111047102B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111047102A (en) | 2020-04-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111047102B (en) | Express delivery route optimization method based on elite-driven particle swarm algorithm | |
| US20210312347A1 (en) | Dispatching distribution | |
| CN107918849A (en) | A kind of intelligent scheduling device and method of electronic logistics van | |
| CN107038496A (en) | Paths planning method and system are delivered in a kind of unmanned plane express delivery automatically | |
| Luo et al. | A last-mile drone-assisted one-to-one pickup and delivery problem with multi-visit drone trips | |
| CN107909228B (en) | Dynamic vehicle goods receiving and dispatching path planning method and device based on modular factor calculation | |
| CN111563709A (en) | Intelligent logistics cargo link cargo collection method and system | |
| CN115471153A (en) | New rural wisdom logistics management system | |
| CN112613812B (en) | Express delivery transmission system for dispatching route planning based on public transport dispatching control system | |
| Iliopoulou et al. | Route planning for a seaplane service: The case of the Greek Islands | |
| CN112418475A (en) | Logistics path planning method and device, electronic equipment and storage medium | |
| CN116384853B (en) | Digital twin intelligent logistics management method and device | |
| Gupta et al. | Multi-objective fuzzy vehicle routing problem: a case study | |
| CN112150060A (en) | Ant colony algorithm-based emergency medical material distribution optimization method | |
| JP2004217340A (en) | Transport plan preparing system and method thereof | |
| Kłodawski et al. | Route planning with dynamic information from the EPLOS system | |
| CN111539674A (en) | Order combining method for logistics transportation of engineering machinery rental scene | |
| CN117114541B (en) | Emergency supply method and system for electric power materials | |
| Ermagan et al. | Machine Learning-enhanced Column Generation Approach for Express Shipments with Autonomous Robots and Public Transportation | |
| CN116750390B (en) | Method, device, equipment and medium for processing logistics objects in storage nodes | |
| Ma et al. | The stochastic and dynamic vehicle routing problem: A literature review | |
| Liyanage et al. | A Capacitated Vehicle Routing Problem Model for Stationery Industry | |
| Hu et al. | Energy-efficient dispatching solution in an automated air cargo terminal | |
| Zhang | Lifting the Efficiency of Food Delivery with Drone Resupply | |
| Liu et al. | Drone scheduling in a hexagon‐based delivery network with multiple fulfillment centers |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |