CN118134204A - Multi-terminal logistics transportation task management method and system based on cloud computing - Google Patents
Multi-terminal logistics transportation task management method and system based on cloud computing Download PDFInfo
- Publication number
- CN118134204A CN118134204A CN202410529994.XA CN202410529994A CN118134204A CN 118134204 A CN118134204 A CN 118134204A CN 202410529994 A CN202410529994 A CN 202410529994A CN 118134204 A CN118134204 A CN 118134204A
- Authority
- CN
- China
- Prior art keywords
- logistics
- task
- robot
- orders
- machine learning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007726 management method Methods 0.000 title claims abstract description 25
- 238000010801 machine learning Methods 0.000 claims abstract description 74
- 238000000034 method Methods 0.000 claims abstract description 58
- 238000012163 sequencing technique Methods 0.000 claims abstract description 38
- 238000013178 mathematical model Methods 0.000 claims abstract description 10
- 238000012546 transfer Methods 0.000 claims description 123
- 238000012549 training Methods 0.000 claims description 52
- 238000010586 diagram Methods 0.000 claims description 43
- 230000006870 function Effects 0.000 claims description 37
- 238000009826 distribution Methods 0.000 claims description 25
- 238000013468 resource allocation Methods 0.000 claims description 24
- 230000008569 process Effects 0.000 claims description 19
- 239000013598 vector Substances 0.000 claims description 16
- 230000015654 memory Effects 0.000 claims description 13
- 230000004913 activation Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000013439 planning Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 210000002569 neuron Anatomy 0.000 claims description 6
- 238000010200 validation analysis Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 5
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 4
- 230000001174 ascending effect Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 description 7
- 238000012384 transportation and delivery Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 229910052744 lithium Inorganic materials 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 229910052987 metal hydride Inorganic materials 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- 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
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of logistics transportation task management, and discloses a multi-terminal logistics transportation task management method and system based on cloud computing, wherein the method comprises the following steps: collecting all logistics orders in real time, wherein the logistics orders comprise shortest carrying path distance from goods to task points, goods dependence, task limiting residual time and goods weight; inputting the collected logistics orders into a pre-constructed first machine learning model to output task priorities corresponding to the logistics orders; carrying out association sequencing on the logistics orders according to the descending order of the task priority, and generating a logistics order sequencing table; sequentially inputting the priorities of the first n logistics orders in the logistics order sequencing table into a priority-scanning radius mathematical model to obtain n scanning radii; according to the invention, the logistics orders are input to the first machine learning model to obtain the priority, so that the logistics orders have a sequencing basis, and when the order quantity is large, the logistics orders can be efficiently and preferentially scheduled.
Description
Technical Field
The invention relates to the technical field of logistics transportation task management, in particular to a multi-terminal logistics transportation task management method and system based on cloud computing.
Background
At present, manufacturing enterprises generate a large number of different types of logistics transportation tasks in the operation process. The traditional manual carrying mode can not meet the requirement of production efficiency, and potential safety hazard and labor cost increase are easy to occur. Meanwhile, china attaches importance to developing intelligent manufacturing, and promotes the improvement of the production automation level.
The present logistics transfer robots can use visual positioning technology to transfer multiple objects, and some multifunctional mobile logistics transfer robots can automatically plan paths and order to complete multiple operations according to task settings, for example, patent publication No. CN115373349a discloses a mobile transfer robot scheduling method and system, comprising: the MES/WMS system issues a demand task to the intelligent dynamic scheduling system; the scheduling plan module generates a scheduling plan according to the demand task; the task management module respectively acquires parameter information of each AGV trolley and generates specific dispatching tasks by combining a dispatching plan; the path planning module generates path planning, and gives an instruction to the corresponding AGV through the AGV management and control module; and the AGV trolley executes the dispatching task and feeds back an execution result to the MES/WMS system. The invention realizes interconnection and intercommunication with the MES/WMS system, realizes the dynamic scheduling coordination of a plurality of AGV trolleys, realizes optimal task allocation, path planning and traffic control, and the plurality of AGV trolleys are in multi-task parallel, operate efficiently and stably, improves the carrying and production efficiency, saves the cost and helps enterprises to realize the factory cost reduction and synergy requirements.
The technology does not disclose how to efficiently and preferentially schedule when the order quantity of the production end is large, and does not consider other information except whether the state of the logistics transfer robot is idle or not and the electric quantity, other information is dynamically changed, such as the remaining maximum endurance mileage of the logistics transfer robot, influence factors of the information are not only the electric quantity problem, the goods dependence relationship is complex, the task first-in first-out needs to be considered, but the task and the task may have a matching relationship, the goods priority is considered only by first-in first-out, the goods is too one-sided, the task time node is not considered, the date of delivery needs to be ensured, the task time cannot be infinitely long, and the task time is even limited, so that the defect can be caused after the task time.
Based on the cloud computing, the application provides a method and a system for managing a multi-terminal logistics transportation task.
Disclosure of Invention
The invention aims to provide a method and a system for managing a multi-terminal logistics transportation task based on cloud computing, which are used for solving the existing problems in the prior art, so that when the order quantity is large, the order is efficiently and preferentially arranged, real-time matching is carried out on goods according to the state of a logistics transportation robot and the goods dependency relationship, and the delivery date is ensured at a task time node, and the method for managing the multi-terminal logistics transportation task based on the cloud computing is provided for achieving the purposes, and comprises the following steps:
collecting all logistics orders in real time, wherein the logistics orders comprise shortest carrying path distance from goods to task points, goods dependence, task limiting residual time and goods weight;
inputting the collected logistics orders into a pre-constructed first machine learning model to output task priorities corresponding to the logistics orders; carrying out association sequencing on the logistics orders according to the descending order of the task priority, and generating a logistics order sequencing table;
Sequentially inputting the first n logistics order priorities of the logistics order sequencing table into a priority-scanning radius mathematical model to obtain n scanning radii, wherein the n scanning radii are in one-to-one correspondence with the n logistics orders, and sequentially drawing circles by taking the goods position coordinates corresponding to the logistics orders as the center and the scanning radii corresponding to the logistics orders as the radii to obtain n transportation resource distribution diagrams, and the logistics transportation robot in the transportation resource distribution diagram is an idle logistics transportation robot;
According to the n carrying resource allocation diagrams, state information of each logistics carrying robot corresponding to the n carrying resource allocation diagrams is obtained, the logistics carrying robots are ordered to generate a logistics carrying robot ordering table, and the final logistics carrying robots in the n carrying resource allocation diagrams are sequentially determined according to matching degree of logistics orders and the state information.
Further, the first machine learning model building method includes:
Dividing the collected logistics orders into training sets And validation set/>Two subsets, each subset containing a plurality of logistics orders; training set/>The number of logistics orders in (1) is the validation set/>8 Times the number of the logistics orders; utilize training set/>Training a first machine learning model, and judging the task priority corresponding to the logistics order; after training, give verification set/>And evaluating the performance of the first machine learning model to finally obtain the first machine learning model.
Further, the first machine learning model is a MIP network model, an input layer, an output layer and two hidden layers are arranged, the input layer is provided with a characteristic dimension of 4, the number of nodes of the input layer is 4, and the two hidden layers comprise a first hidden layer and a second hidden layer; the number of neurons of the first hidden layer is set to 128, creating a weight matrix，/>Size (128,4), initializing weights, creating bias vector/>，/>Size (128, 1), initialized to 0, output of input layer is/>With the ReLU function as the activation function, the ReLU function will output/>, to the first hidden layerActing to calculate the output/>, of the first hidden layer; ReLU function pairTake a non-negative value, i.e./>Greater than 0 then/>Remaining unchanged, otherwise, 0;
And/> The calculation formula is as follows:
；
；
the number of neurons of the second hidden layer is set to 64, and a weight matrix is created ，/>Size (64, 128), create bias vector/>，/>The size is (64, 1), and the ReLU function is used as an activation function again to act as the ReLU activation function of the first hidden layer; the number of output nodes is the number of label categories, the label categories represent priority, and the weight matrix/>Size (3, 64), bias/>Size (3, 1), softmax is used as the activation function of the output layer.
Further, training the built first machine learning model, wherein the training method comprises the following steps:
step 1, making a first machine learning model be Initializing a first machine learning model, wherein initialized parameters meet Gaussian distribution, and in the training process, the training set/>, is used for each timeRandom extraction/>Feeding the strip logistics order into a first machine learning model/>Let/>The order of the strip logistics is/>，/>The corresponding task priority is/>, in turnThe cross entropy loss corresponding to each training process is/>，/>The calculation formula of (2) is as follows:
；
In the method, in the process of the invention, Represents the/>Strip Logistics order, wherein/>Represents the/>Task priorities corresponding to the strip logistics orders,Represents the/>Predicting task priority of strip logistics order,/>Representing hyper-parameters,/>Representing regularization of the weights of the first hidden layer and the weights of the second hidden layer;
step 2, from the training set Random extraction of the middle iteration/>Feeding the strip logistics order into a first machine learning model/>In the training process, training a first machine learning model by using an Adam gradient descent optimization algorithm, wherein the learning rate is 0.001, and when the loss function/>When convergence is achieved, the first machine learning model stops training;
step 3, after training, in the verification set Performance evaluation was performed on the first machine learning model.
Further, the method for constructing the priority-scanning radius mathematical model comprises the following steps:
With priority level For input,/>For output,/>Is the scanning radius;
；
In the method, in the process of the invention, And/>All are preset proportional coefficients, and the values are all larger than 0.
Further, the state information includes a remaining maximum endurance mileage of the logistics transfer robot, a logistics transfer robot average speed data, logistics transfer robot coordinates and a logistics transfer robot load.
Further, the sorting method of the sorting table of the logistics transfer robot comprises the following steps:
planning the shortest paths from the position coordinates to the goods coordinates of the h logistics carrying robots in the carrying resource allocation diagram by utilizing an A-scale algorithm, and obtaining h shortest path distances;
And carrying out ascending sort on the h logistics transfer robots corresponding to the h shortest path distances to obtain a logistics transfer robot sorting table.
Further, the determining method for sequentially determining the final logistics transfer robots in the n transfer resource allocation diagrams according to the matching degree of the logistics order and the state information includes:
Step 11, performing label assignment on the r-th logistics transfer robot, wherein r is an integer larger than 0, an initial value of the assigned label is set to 0, binary calculation is adopted, the weight of the goods is compared with the load of the logistics transfer robot, if the weight of the goods is smaller than the load of the logistics transfer robot, the assigned value is increased by 1, otherwise, the value is returned to 0; comparing the shortest distance required by the logistics transfer robot to finish the task with the remaining maximum endurance mileage of the logistics transfer robot, if the shortest distance required by the logistics transfer robot to finish the task is smaller than the remaining maximum endurance mileage of the logistics transfer robot, adding 1, otherwise returning to 0; comparing the slowest speed of the logistics carrying robot for completing the task with the average speed data of the logistics carrying robot, if the slowest speed of the logistics carrying robot for completing the task is smaller than the average speed data of the logistics carrying robot, adding 1, otherwise returning to 0; the shortest distance required by the logistics transfer robot to complete the task is the sum of the shortest path distance from the logistics transfer robot to the goods and the shortest transfer path distance from the goods to the task point; the slowest speed of the logistics transfer robot for completing the task is the quotient of the shortest distance required by the logistics transfer robot for completing the task and the task limiting residual time;
Step 12, when the label of the logistics transfer robot is 11, the state information of the logistics transfer robot with the label of 11 is completely matched with the logistics order, the logistics transfer robot with the label of 11 is determined to be the final logistics transfer robot, and the step 14 is skipped; when the logistics transfer robot label is not 11, the assigned label is assigned to be 0, and the step 13 is skipped;
Step 13, let r=r+1, repeat step 11-step 12 until r=h, finish the cycle;
And 14, sending a carrying instruction to the logistics carrying robot with the label of 11, deleting the idle label of the logistics carrying robot, and assigning the assigned label to 0.
Further, when the logistics transfer robots in the transfer resource allocation diagrams centering on different cargo coordinates have occupancy conflicts, the logistics transfer robot with the highest priority is selected according to the priority of the cargoes, when the cargoes with the highest priority are allocated, if the logistics transfer robot with the occupancy conflicts has an assigned label of 0, and if idle labels exist, the logistics transfer robot with the highest priority enters the next-level priority cargo allocation.
Further, specific data of influencing factors of the remaining maximum endurance mileage of the logistics transfer robot comprise battery type, battery capacity, motor driving efficiency, battery charge and discharge states and environment temperature and humidity, the specific data of the influencing factors are input into a pre-constructed second machine learning model, and the remaining maximum endurance mileage of the logistics transfer robot is output;
The construction method of the second machine learning model comprises the following steps:
converting the specific data of a group of influencing factors and the residual maximum endurance mileage of the logistics transfer robot into a corresponding group of characteristic vectors;
Taking each group of feature vectors as input of a second machine learning model, wherein the second machine learning model takes the remaining maximum endurance mileage of the logistics transfer robot corresponding to the specific data of a group of influence factors as output, takes the remaining maximum endurance mileage of the logistics transfer robot actually corresponding to the specific data of a group of influence factors as a prediction target, and takes the loss function value of the minimized second machine learning model as a training target; and stopping training when the loss function value of the second machine learning model is smaller than or equal to a preset target loss value.
A multi-terminal logistics transportation task management system based on cloud computing implements the multi-terminal logistics transportation task management method based on cloud computing, and the system comprises the following steps:
the collection module is used for collecting all logistics orders in real time, wherein the logistics orders comprise shortest carrying path distance from goods to task points, goods dependence, task limiting residual time and goods weight;
The logistics order sequencing module inputs the collected logistics orders into a first pre-constructed machine learning model to output task priorities corresponding to the logistics orders; carrying out association sequencing on the logistics orders according to the descending order of the task priority, and generating a logistics order sequencing table;
The first distribution module is used for sequentially inputting the first n logistics order priorities of the logistics order sequencing table into a priority-scanning radius mathematical model to obtain n scanning radii, wherein the n scanning radii are in one-to-one correspondence with the n logistics orders, and circles are drawn sequentially by taking goods position coordinates corresponding to the logistics orders as the center and the scanning radii corresponding to the logistics orders as the radii to obtain n transportation resource distribution diagrams, and a logistics transportation robot in the transportation resource distribution diagram is an idle logistics transportation robot; the second allocation module is used for obtaining the state information of each logistics transfer robot corresponding to the n transfer resource allocation diagrams according to the n transfer resource allocation diagrams, sequencing the logistics transfer robots to generate a logistics transfer robot sequencing table, and sequentially determining the final logistics transfer robots in the n transfer resource allocation diagrams according to the matching degree of the logistics orders and the state information.
An electronic device comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the multi-terminal logistics transportation task management method based on cloud computing when executing the computer program.
A computer readable storage medium, on which a computer program is stored, which when executed implements the method for managing multi-terminal logistics transportation tasks based on cloud computing.
The invention discloses a cloud computing-based multi-terminal logistics transportation task management method and a cloud computing-based multi-terminal logistics transportation task management system, which have the technical effects and advantages that:
According to the invention, the logistics orders are input into the first machine learning model to obtain the priority, so that the logistics orders are provided with a sequencing basis, when the logistics orders are sequenced, the logistics orders can be efficiently and preferentially scheduled, the first machine learning model considers the complexity of the dependence relationship of the logistics orders (namely, the dependence relationship of goods corresponding to the logistics orders) and the time limit of tasks, so that the processing sequence of goods is more accurately distributed, and the available transport capacity resources of the logistics transport robot of partial goods with the front sequencing are determined through the priority, so that when the logistics orders are large, the system is not crowded, so that scheduling is problematic, and finally one-to-many screening is performed, so that the goods reach the destination within the limited time.
The invention can comprehensively schedule various types of tasks and is suitable for complex production scenes; the situation that when the order quantity of the logistics is large, efficient priority scheduling is needed is considered, and the allocation tasks are performed in batches, so that the work load of the system can reasonably and efficiently complete the allocation operation even under the condition of large order quantity; according to the state of the logistics transfer robot, matching with a logistics order in real time, so that the goods can be safely and efficiently transferred to a task point; the complexity of the cargo dependency relationship is considered, comprehensive analysis is performed, and the process flow can be smoothly completed;
The method solves the problem that the task distance is distributed to exceed the range to cause the planned failure, and reasonable path planning ensures that the task point distance is within the range, so that the task arrangement is not influenced by single range; the dynamic correction can be performed in real time according to actual conditions, and the change conditions can be well adapted; the path and the task sequence are planned in advance, and the scheduling execution is carried out according to the plan, so that disorder caused by single machine faults can be avoided; fully considering the task time node and ensuring that the task is successfully completed in the delivery date; the system is updated only by adjusting the model, so that the maintenance cost is low, the algorithm result can be traced, and the later optimization and problem diagnosis are convenient.
Drawings
FIG. 1 is a schematic diagram of a system for managing a multi-terminal logistics transportation task based on cloud computing;
fig. 2 is a schematic diagram of data transmission of a multi-terminal logistics transportation task management system based on cloud computing;
FIG. 3 is a flow chart of a method for managing a multi-terminal logistics transportation task based on cloud computing;
FIG. 4 is a schematic diagram of an electronic device of the present invention;
fig. 5 is a schematic diagram of a storage medium of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1 and fig. 2, the system for managing a multi-terminal logistics transportation task based on cloud computing, which is deployed in a cloud server and capable of remotely checking logistics order allocation data in real time, includes a collection module, a logistics order ordering module, a first allocation module and a second allocation module, wherein the modules are connected by wires and/or wirelessly to realize data transmission between the modules:
The collection module is used for collecting all logistics orders in real time, wherein the logistics orders comprise shortest carrying path distance from goods to task points, goods dependence, task limiting residual time and goods weight;
it should be appreciated that: the shortest carrying path distance between the goods coordinates and the goods to the task point is obtained based on the prior art equipment according to the goods coordinates and the goods to the task point, for example, a Goldmap can position the user in real time, navigation planning is carried out according to the place name input by the user and the user position, and the user is informed of the required time and distance while giving the shortest path to the user;
It should be noted that: the goods dependence refers to the relevance between goods, so that batch or matched treatment is required during transportation and installation of the goods, for example, mobile phone parts, different parts are required to be installed in sequence, and the follow-up parts can be installed after the front parts are installed; the heavy machinery is required to be assembled and disassembled by a crane, and when carrying out logistics transportation tasks, the transportation of the heavy machinery is required to be carried out together with the crane;
Specifically, the task limiting remaining time is known by the task limiting time, the task limiting time can be determined by a worker according to the specific application requirements of the goods, the specific numerical limitation is not made here, the task limiting time can be modified in real time, and when an emergency occurs, such as an order is urgent, and a certain piece of goods is required to be carried in an emergency, the system can react only by modifying the task limiting time;
the logistics order sequencing module inputs the collected logistics orders into a first pre-constructed machine learning model to output task priorities corresponding to the logistics orders; carrying out association sequencing on the logistics orders according to the descending order of the task priority, generating a logistics order sequencing table, and sending the logistics order sequencing table to a first distribution module;
The shorter the shortest conveying path distance from the goods to the task point is, the higher the priority is, the shorter the shortest conveying path distance from the goods to the task point is, the lower the time and the burden required for completing the task are, and therefore the higher the priority is, the more reasonable the priority is set; the stronger the cargo dependence is, the higher the priority is, the stronger the cargo dependence is, the larger the influence on downstream tasks is, and more tasks are influenced by incomplete or delayed tasks, so that the tasks with strong dependence are more reasonable to process preferentially; the shorter the task definition residual time is, the higher the priority is, the shorter the task definition residual time is, which means that the higher the pressure given by the task is, the more reasonable the priority treatment is; the lighter the weight of the goods is, the higher the priority is, the lighter the weight of the goods is, which means that the larger the range of the matched logistics carrying robot is, the distribution task is easier to complete, so that the pressure of the distribution task of the system is reduced, and the higher the priority is, the more reasonable the priority is set;
The method for constructing the first machine learning model comprises the following steps of;
Dividing the collected logistics orders into training sets And validation set/>Two subsets, each subset containing a plurality of logistics orders; training set/>The number of logistics orders in (1) is the validation set/>8 Times the number of the logistics orders; utilize training set/>Training a first machine learning model, and judging the task priority corresponding to the logistics order; in the collecting process, task priority is determined by a person skilled in the art according to specific application requirements, and is not limited by specific numerical values, and after training, a verification set/>Evaluating the performance of the first machine learning model to finally obtain the first machine learning model;
The first machine learning model is an MIP network model, an input layer, an output layer and two hidden layers are arranged, the input layer is provided with a characteristic dimension of 4, the number of nodes of the input layer is 4, and the two hidden layers comprise a first hidden layer and a second hidden layer; the number of neurons of the first hidden layer is set to 128, creating a weight matrix ，/>Size (128,4), initializing weights, creating bias vector/>，/>Size (128, 1), initialized to 0, output of input layer is/>With the ReLU function as the activation function, the ReLU function will output/>, to the first hidden layerActing to calculate the output/>, of the first hidden layer; ReLU function pair/>Take a non-negative value, i.e./>Greater than 0 then/>Remaining unchanged, otherwise, 0;
And/> The calculation formula is as follows:
；
；
the number of neurons of the second hidden layer is set to 64, and a weight matrix is created ，/>Size (64, 128), create bias vector/>，/>The size is (64, 1), and the ReLU function is used as an activation function again to act as the ReLU activation function of the first hidden layer; the number of output nodes is the number of label classes, which represent priorities, e.g. 0 is low priority, 1 is medium priority, 2 is high priority, weight matrix/>Size (3, 64), bias/>Size (3, 1), using Softmax as the activation function of the output layer;
after the first machine learning model is built, training the first machine learning model, wherein the training process comprises the following steps:
step 1, making a first machine learning model be Initializing a first machine learning model, wherein initialized parameters meet Gaussian distribution, and in the training process, the training set/>, is used for each timeRandom extraction/>Feeding the strip logistics order into a first machine learning model/>Let/>The order of the strip logistics is/>，/>The corresponding task priority is/>, in turnThe cross entropy loss corresponding to each training process is/>，/>The calculation formula of (2) is as follows:
；
In the above-mentioned description of the invention, Represents the/>Strip Logistics order, wherein/>Represents the/>Task priority corresponding to strip logistics order,/>Represents the/>Predicting task priority of strip logistics order,/>Representing hyper-parameters,/>Representing regularization of the weights of the first hidden layer and the weights of the second hidden layer;
step 2, from the training set Random extraction of the middle iteration/>Feeding the strip logistics order into a first machine learning model/>In the training process, an Adam gradient descent optimization algorithm is used for training the first machine learning model, the learning rate is 0.001, and the Adam algorithm is widely applied to the training process of the first machine learning model. The method combines the ideas of a momentum method and an adaptive learning rate, and can adaptively adjust the learning rate of each parameter, thereby accelerating the convergence speed and improving the optimization effect when the loss function/>When convergence is achieved, the first machine learning model stops training;
step 3, after training, in the verification set Performing performance evaluation on the first machine learning model;
in an actual scene, the first machine learning model judges the task priority corresponding to the material flow order in real time;
The first distribution module sequentially inputs the first n logistics order priorities of the logistics order sequencing table into a priority-scanning radius mathematical model to obtain n scanning radii, the n scanning radii are in one-to-one correspondence with the n logistics orders, n goods position coordinates corresponding to the logistics orders are sequentially established as centers, the scanning radii corresponding to the logistics orders are taken as radii to draw circles to obtain n carrying resource distribution diagrams, and a logistics carrying robot in the carrying resource distribution diagram is an idle logistics carrying robot, namely the idle logistics carrying robot is a logistics carrying robot which does not accept tasks;
n is an integer greater than 1 and is determined by one skilled in the art according to the specific application requirements and is not herein defined by specific values;
The method for constructing the priority-scanning radius mathematical model comprises the following steps:
With priority level For input,/>For output,/>Is the scanning radius;
；
And/> All are preset proportionality coefficients, and the values are all larger than 0 according to specific application requirements determined by a person skilled in the art;
The second distribution module is used for obtaining the state information of each logistics carrying robot in each carrying resource distribution diagram according to the n carrying resource distribution diagrams, sequencing the logistics carrying robots to generate a logistics carrying robot sequencing table, and sequentially determining the final logistics carrying robots in the n carrying resource distribution diagrams according to the matching degree of the logistics orders and the state information;
The state information comprises the remaining maximum endurance mileage of the logistics transfer robot, the average speed data of the logistics transfer robot, the logistics transfer robot coordinates and the logistics transfer robot load;
The method comprises the steps that the remaining maximum endurance mileage of a logistics transfer robot is influenced by multiple factors, specific data of influencing factors comprise battery type, battery capacity, motor driving efficiency, battery charge and discharge states, environment temperature and humidity, logistics transfer robot quality and cargo weight, the data are inaccurate when only single influencing factors are considered, and the fact that the remaining maximum endurance mileage of the logistics transfer robot has important influence on overall task scheduling is considered to analyze and predict; inputting specific data of the influencing factors into a pre-constructed second machine learning model, and outputting the remaining maximum endurance mileage of the logistics transfer robot;
The battery type is provided with parameters by manufacturers, and different types of batteries, such as lithium batteries or nickel-metal hydride batteries, influence the endurance mileage; specific data are acquired by a battery sensor according to the battery capacity, the motor driving efficiency and the battery charging and discharging state, the logistics carrying robot with larger battery capacity is used, the cruising distance is naturally longer, the efficiency of converting electric energy into mechanical energy by the motor directly influences the cruising mileage, and the capacity attenuation is influenced by the fact that the battery is charged for a plurality of times and discharged deeply, so that the cruising mileage is influenced; acquiring specific data of environmental humiture by a humiture sensor, wherein different environmental humiture can influence the capacity and the service life of a battery, thereby influencing the endurance mileage; the mass and the weight of the logistics transfer robot are obtained by a logistics transfer robot force sensor and a cargo force sensor to obtain specific data, and the lighter the total mass is, the more far the mileage can be run under the same electric quantity;
The construction method of the second machine learning model comprises the following steps:
converting the specific data of a group of influencing factors and the residual maximum endurance mileage of the logistics transfer robot into a corresponding group of characteristic vectors;
Taking each group of feature vectors as input of a second machine learning model, wherein the second machine learning model takes the remaining maximum endurance mileage of the logistics transfer robot corresponding to the specific data of a group of influence factors as output, takes the remaining maximum endurance mileage of the logistics transfer robot actually corresponding to the specific data of a group of influence factors as a prediction target, and takes the loss function value of the minimized second machine learning model as a training target; stopping training when the loss function value of the second machine learning model is smaller than or equal to a preset target loss value;
The second machine learning model loss function value is a mean square error;
By the formula of loss function Training a model for minimization purposes, loss function formula/>Loss function value for the second machine learning model, x is feature vector group number; m is the number of feature vector groups; /(I)Remaining maximum endurance mileage of logistics transfer robot corresponding to the x-th group of feature vectors,/>The method comprises the steps that the remaining maximum endurance mileage of the logistics transfer robot actually corresponding to the x-th group of feature vectors is obtained;
the sorting method of the sorting table of the logistics transfer robot comprises the following steps:
planning the shortest paths from the position coordinates to the goods coordinates of the h logistics carrying robots in the carrying resource allocation diagram by utilizing an A-scale algorithm, and obtaining h shortest path distances;
And carrying out ascending sort on the h logistics transfer robots corresponding to the h shortest path distances to obtain a logistics transfer robot sorting table.
According to the matching degree of the logistics orders and the state information, the determining method for sequentially determining the final logistics transfer robots in the n transfer resource allocation diagrams comprises the following steps:
Step 11, performing label assignment on the r-th logistics transfer robot, wherein r is an integer larger than 0, an initial value of the assigned label is set to 0, binary calculation is adopted, the weight of the goods is compared with the load of the logistics transfer robot, if the weight of the goods is smaller than the load of the logistics transfer robot, the assigned value is increased by 1, otherwise, the value is returned to 0; comparing the shortest distance required by the logistics transfer robot to finish the task with the remaining maximum endurance mileage of the logistics transfer robot, if the shortest distance required by the logistics transfer robot to finish the task is smaller than the remaining maximum endurance mileage of the logistics transfer robot, adding 1, otherwise returning to 0; comparing the slowest speed of the logistics carrying robot for completing the task with the average speed data of the logistics carrying robot, if the slowest speed of the logistics carrying robot for completing the task is smaller than the average speed data of the logistics carrying robot, adding 1, otherwise returning to 0;
it should be noted that: the shortest distance required by the logistics transfer robot to complete the task is the sum of the shortest path distance from the logistics transfer robot to the goods and the shortest transfer path distance from the goods to the task point; the shortest path distance from the logistics carrying robot to the goods is obtained by the same method as the shortest carrying path distance from the goods to the task point; the slowest speed of the logistics transfer robot for completing the task is the quotient of the shortest distance required by the logistics transfer robot for completing the task and the task limiting residual time;
Step 12, when the label of the logistics transfer robot is 11, the state information of the logistics transfer robot with the label of 11 is completely matched with the logistics order, the logistics transfer robot with the label of 11 is determined to be the final logistics transfer robot, and the step 14 is skipped; when the logistics transfer robot label is not 11, the assigned label is assigned to be 0, and the step 13 is skipped;
Step 13, let r=r+1, repeat step 11-step 12 until r=h, finish the cycle;
Step 14, sending a carrying instruction to the logistics carrying robot with the label of 11, deleting the idle label of the logistics carrying robot, and assigning the assigned label to 0;
It should be noted that: the method for judging whether the logistics transfer robot is in an idle state comprises the steps of giving an idle label to the logistics transfer robot which does not accept tasks; when the logistics transfer robots in the transfer resource allocation diagrams centering on different cargo coordinates have occupation conflicts, selecting the cargo corresponding to the highest priority to occupy the logistics transfer robots according to the priority of the cargo, and when the cargo with the highest priority has been allocated, if the logistics transfer robot with the occupation conflicts has an allocation label of 0 and has an idle label, entering the next-level priority cargo allocation logic;
The logistics orders are input to the first machine learning model to obtain priority, so that the logistics orders are provided with a sequencing basis, when the logistics orders are sequenced, the logistics orders can be efficiently and preferentially scheduled, the first machine learning model considers the complexity of the dependence relationship of the logistics orders (namely, the dependence relationship of goods corresponding to the logistics orders) and the time limit of tasks, so that the processing sequence of goods is more accurately distributed, and the available transport capacity resources of the logistics transfer robot for partial goods with the front sequencing are determined according to the priority.
Example 2
Referring to fig. 3, the method for managing a multi-terminal logistics transportation task based on cloud computing according to the present embodiment includes:
collecting all logistics orders in real time;
Inputting the collected logistics orders into a pre-constructed first machine learning model to output task priorities of corresponding cargoes; carrying out association sequencing on the logistics orders according to the descending order of the task priority to generate a logistics order sequencing table;
Sequentially inputting the first n logistics order priorities of the logistics order sequencing table into a priority-scanning radius mathematical model to obtain n scanning radii, wherein the n scanning radii are in one-to-one correspondence with the n logistics orders, and sequentially drawing circles by taking the goods position coordinates corresponding to the logistics orders as the center and the scanning radii corresponding to the logistics orders as the radii to obtain n transportation resource distribution diagrams, and the logistics transportation robot in the transportation resource distribution diagram is an idle logistics transportation robot;
According to the n carrying resource allocation diagrams, state information of each logistics carrying robot corresponding to the n carrying resource allocation diagrams is obtained, the logistics carrying robots are ordered to generate a logistics carrying robot ordering table, and the final logistics carrying robots in the n carrying resource allocation diagrams are sequentially determined according to matching degree of logistics orders and the state information.
Example 3
Referring to fig. 4, an electronic device 500 is also provided in accordance with yet another aspect of the present application. The electronic device 500 may include one or more processors and one or more memories. Wherein the memory has stored therein computer readable code which, when executed by the one or more processors, can perform a cloud computing based multi-terminal logistics transportation task management method as described above.
The method or system according to embodiments of the application may also be implemented by means of the architecture of the electronic device shown in fig. 4. As shown in fig. 4, the electronic device 500 may include a bus 501, one or more CPUs 502, a ROM503, a RAM504, a communication port 505 connected to a network, an input/output 506, a hard disk 507, and the like. A storage device in the electronic device 500, such as a ROM503 or a hard disk 507, may store a multi-terminal logistics transportation task management method based on cloud computing provided by the present application. Further, the electronic device 500 may also include a user interface 508. Of course, the architecture shown in fig. 4 is merely exemplary, and one or more components of the electronic device shown in fig. 4 may be omitted as may be desired in implementing different devices.
Example 4
Referring to FIG. 5, a computer readable storage medium 250 according to one embodiment of the application is shown. Computer readable storage medium 250 has stored thereon computer readable instructions. When the computer readable instructions are executed by the processor, a method for managing multi-terminal logistics transportation tasks based on cloud computing according to an embodiment of the present application described with reference to the above drawings may be performed. Storage medium 250 includes, but is not limited to, for example, volatile memory and/or nonvolatile memory. Volatile memory can include, for example, random Access Memory (RAM), cache memory (cache), and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (13)
1. A multi-terminal logistics transportation task management method based on cloud computing is characterized by comprising the following steps:
collecting all logistics orders in real time, wherein the logistics orders comprise shortest carrying path distance from goods to task points, goods dependence, task limiting residual time and goods weight;
inputting the collected logistics orders into a pre-constructed first machine learning model to output task priorities corresponding to the logistics orders; carrying out association sequencing on the logistics orders according to the descending order of the task priority, and generating a logistics order sequencing table;
Sequentially inputting the first n logistics order priorities of the logistics order sequencing table into a priority-scanning radius mathematical model to obtain n scanning radii, wherein the n scanning radii are in one-to-one correspondence with the n logistics orders, and sequentially drawing circles by taking the goods position coordinates corresponding to the logistics orders as the center and the scanning radii corresponding to the logistics orders as the radii to obtain n transportation resource distribution diagrams, and the logistics transportation robot in the transportation resource distribution diagram is an idle logistics transportation robot;
According to the n carrying resource allocation diagrams, state information of each logistics carrying robot corresponding to the n carrying resource allocation diagrams is obtained, the logistics carrying robots are ordered to generate a logistics carrying robot ordering table, and the final logistics carrying robots in the n carrying resource allocation diagrams are sequentially determined according to matching degree of logistics orders and the state information.
2. The cloud computing-based multi-terminal logistics transportation task management method of claim 1, wherein the constructing the first machine learning model method comprises:
Dividing the collected logistics orders into training sets And validation set/>Two subsets, each subset containing a plurality of logistics orders; training set/>The number of logistics orders in (1) is the validation set/>8 Times the number of the logistics orders; utilize training set/>Training a first machine learning model, and judging the task priority corresponding to the logistics order; after training, give verification set/>And evaluating the performance of the first machine learning model to finally obtain the first machine learning model.
3. The method for managing the logistics transportation task of the multi-terminal based on the cloud computing according to claim 2, wherein the first machine learning model is an MIP network model, an input layer, an output layer and two hidden layers are arranged, the input layer is provided with a feature dimension of 4, the node number of the input layer is 4, and the two hidden layers comprise a first hidden layer and a second hidden layer; the number of neurons of the first hidden layer is set to 128, creating a weight matrix，/>Size (128,4), initializing weight, creating bias vector，/>Size (128, 1), initialized to 0, output of input layer is/>With the ReLU function as the activation function, the ReLU function will output/>, to the first hidden layerActing to calculate the output/>, of the first hidden layer; ReLU function pair/>Take a non-negative value, i.e. ifGreater than 0 then/>Remaining unchanged, otherwise, 0;
And/> The calculation formula is as follows:
；
；
the number of neurons of the second hidden layer is set to 64, and a weight matrix is created ，/>Size (64, 128), create bias vector/>，/>The size is (64, 1), and the ReLU function is used as an activation function again to act as the ReLU activation function of the first hidden layer; the number of output nodes is the number of label categories, the label categories represent priority, and the weight matrix/>Size (3, 64), bias/>Size (3, 1), softmax is used as the activation function of the output layer.
4. A method for managing a multi-terminal logistics transportation task based on cloud computing according to claim 3, wherein the first machine learning model which is built is trained, and the training method comprises:
step 1, making a first machine learning model be Initializing a first machine learning model, wherein initialized parameters meet Gaussian distribution, and in the training process, the training set/>, is used for each timeRandom extraction/>Feeding the strip logistics order into a first machine learning model/>Let/>The order of the strip logistics is/>，/>The corresponding task priority is/>, in turnThe cross entropy loss corresponding to each training process is/>，/>The calculation formula of (2) is as follows:
；
In the method, in the process of the invention, Represents the/>Strip Logistics order, wherein/>Represents the/>Task priority corresponding to strip logistics order,/>Represents the/>Predicting task priority of strip logistics order,/>Representing hyper-parameters,/>Representing regularization of the weights of the first hidden layer and the weights of the second hidden layer;
step 2, from the training set Random extraction of the middle iteration/>Feeding the strip logistics order into a first machine learning model/>In the training process, training a first machine learning model by using an Adam gradient descent optimization algorithm, wherein the learning rate is 0.001, and when the loss function/>When convergence is achieved, the first machine learning model stops training;
step 3, after training, in the verification set Performance evaluation was performed on the first machine learning model.
5. The cloud computing-based multi-terminal logistics transportation task management method of claim 1, wherein the method for constructing the priority-scanning radius mathematical model comprises:
With priority level For input,/>For output,/>Is the scanning radius;
；
In the method, in the process of the invention, And/>All are preset proportional coefficients, and the values are all larger than 0.
6. The cloud computing-based multi-terminal logistics transportation task management method of claim 1, wherein the state information comprises a remaining maximum endurance mileage of the logistics transportation robot, logistics transportation robot average speed data, logistics transportation robot coordinates and logistics transportation robot load.
7. The cloud computing-based multi-terminal logistics transportation task management method of claim 6, wherein the sequencing method of the logistics transportation robot sequencing table comprises:
planning the shortest paths from the position coordinates to the goods coordinates of the h logistics carrying robots in the carrying resource allocation diagram by utilizing an A-scale algorithm, and obtaining h shortest path distances;
And carrying out ascending sort on the h logistics transfer robots corresponding to the h shortest path distances to obtain a logistics transfer robot sorting table.
8. The cloud computing-based multi-terminal logistics transportation task management method of claim 7, wherein the determining method for sequentially determining the final logistics transportation robots in the n transportation resource allocation diagrams according to the matching degree of the logistics orders and the state information comprises:
Step 11, performing label assignment on the r-th logistics transfer robot, wherein r is an integer larger than 0, an initial value of the assigned label is set to 0, binary calculation is adopted, the weight of the goods is compared with the load of the logistics transfer robot, if the weight of the goods is smaller than the load of the logistics transfer robot, the assigned value is increased by 1, otherwise, the value is returned to 0; comparing the shortest distance required by the logistics transfer robot to finish the task with the remaining maximum endurance mileage of the logistics transfer robot, if the shortest distance required by the logistics transfer robot to finish the task is smaller than the remaining maximum endurance mileage of the logistics transfer robot, adding 1, otherwise returning to 0; comparing the slowest speed of the logistics carrying robot for completing the task with the average speed data of the logistics carrying robot, if the slowest speed of the logistics carrying robot for completing the task is smaller than the average speed data of the logistics carrying robot, adding 1, otherwise returning to 0; the shortest distance required by the logistics transfer robot to complete the task is the sum of the shortest path distance from the logistics transfer robot to the goods and the shortest transfer path distance from the goods to the task point; the slowest speed of the logistics transfer robot for completing the task is the quotient of the shortest distance required by the logistics transfer robot for completing the task and the task limiting residual time;
Step 12, when the label of the logistics transfer robot is 11, the state information of the logistics transfer robot with the label of 11 is completely matched with the logistics order, the logistics transfer robot with the label of 11 is determined to be the final logistics transfer robot, and the step 14 is skipped; when the logistics transfer robot label is not 11, the assigned label is assigned to be 0, and the step 13 is skipped;
Step 13, let r=r+1, repeat step 11-step 12 until r=h, finish the cycle;
And 14, sending a carrying instruction to the logistics carrying robot with the label of 11, deleting the idle label of the logistics carrying robot, and assigning the assigned label to 0.
9. The cloud computing-based multi-terminal logistics transportation task management method of claim 8, wherein when the logistics transportation robots in the transportation resource allocation diagram centering on different cargo coordinates have occupancy conflicts, the logistics transportation robot with the highest priority is selected according to the priority of the cargo, when the cargo with the highest priority has been allocated, if the logistics transportation robot with the occupancy conflicts has an allocation label of 0, and if the logistics transportation robot with the occupancy conflicts has an idle label, the logistics transportation robot with the highest priority enters the next-level priority cargo allocation.
10. The cloud computing-based multi-terminal logistics transportation task management method of claim 6, wherein the specific data of the influence factors of the remaining maximum endurance mileage of the logistics transportation robot comprise battery type, battery capacity, motor driving efficiency, battery charge and discharge state and environment temperature and humidity, the specific data of the influence factors are input into a pre-constructed second machine learning model, and the remaining maximum endurance mileage of the logistics transportation robot is output;
The construction method of the second machine learning model comprises the following steps:
converting the specific data of a group of influencing factors and the residual maximum endurance mileage of the logistics transfer robot into a corresponding group of characteristic vectors;
Taking each group of feature vectors as input of a second machine learning model, wherein the second machine learning model takes the remaining maximum endurance mileage of the logistics transfer robot corresponding to the specific data of a group of influence factors as output, takes the remaining maximum endurance mileage of the logistics transfer robot actually corresponding to the specific data of a group of influence factors as a prediction target, and takes the loss function value of the minimized second machine learning model as a training target; and stopping training when the loss function value of the second machine learning model is smaller than or equal to a preset target loss value.
11. A cloud computing-based multi-terminal logistics transportation task management system, characterized in that the method for managing the multi-terminal logistics transportation task based on the cloud computing according to any one of claims 1 to 10 is implemented, and the system comprises:
the collection module is used for collecting all logistics orders in real time, wherein the logistics orders comprise shortest carrying path distance from goods to task points, goods dependence, task limiting residual time and goods weight;
The logistics order sequencing module inputs the collected logistics orders into a first pre-constructed machine learning model to output task priorities corresponding to the logistics orders; carrying out association sequencing on the logistics orders according to the descending order of the task priority, and generating a logistics order sequencing table;
the first distribution module is used for sequentially inputting the first n logistics order priorities of the logistics order sequencing table into a priority-scanning radius mathematical model to obtain n scanning radii, wherein the n scanning radii are in one-to-one correspondence with the n logistics orders, and circles are drawn sequentially by taking goods position coordinates corresponding to the logistics orders as the center and the scanning radii corresponding to the logistics orders as the radii to obtain n transportation resource distribution diagrams, and a logistics transportation robot in the transportation resource distribution diagram is an idle logistics transportation robot;
The second allocation module is used for obtaining the state information of each logistics transfer robot corresponding to the n transfer resource allocation diagrams according to the n transfer resource allocation diagrams, sequencing the logistics transfer robots to generate a logistics transfer robot sequencing table, and sequentially determining the final logistics transfer robots in the n transfer resource allocation diagrams according to the matching degree of the logistics orders and the state information.
12. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the computer program, implements a method for managing a multi-terminal logistics transportation task based on cloud computing as claimed in any one of claims 1-10.
13. A computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, and when the computer program is executed, the method for managing a multi-terminal logistics transportation task based on cloud computing according to any one of claims 1 to 10 is implemented.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410529994.XA CN118134204A (en) | 2024-04-29 | 2024-04-29 | Multi-terminal logistics transportation task management method and system based on cloud computing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410529994.XA CN118134204A (en) | 2024-04-29 | 2024-04-29 | Multi-terminal logistics transportation task management method and system based on cloud computing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118134204A true CN118134204A (en) | 2024-06-04 |
Family
ID=91230481
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410529994.XA Pending CN118134204A (en) | 2024-04-29 | 2024-04-29 | Multi-terminal logistics transportation task management method and system based on cloud computing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118134204A (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN205751263U (en) * | 2016-03-01 | 2016-11-30 | 江苏零浩网络科技有限公司 | Vehicle positioning system based on Logistics Information Platform |
| US20170300857A1 (en) * | 2016-04-18 | 2017-10-19 | Mitac International Corp. | Instantaneous logistics order processing system |
| CN110874700A (en) * | 2018-09-03 | 2020-03-10 | 菜鸟智能物流控股有限公司 | Logistics order matching method and device and electronic equipment |
| CN111738570A (en) * | 2020-06-05 | 2020-10-02 | 苏州华易通物流有限公司 | Logistics management system based on internet |
| CN112573058A (en) * | 2019-09-30 | 2021-03-30 | 深圳市海柔创新科技有限公司 | Goods taking method, carrying robot, processing terminal and intelligent warehousing system |
| CN113240362A (en) * | 2021-04-29 | 2021-08-10 | 北京京东振世信息技术有限公司 | Logistics order task processing method and device, electronic equipment and computer medium |
| CN113743868A (en) * | 2021-09-06 | 2021-12-03 | 广西职业技术学院 | Logistics cargo management device |
| CN114154921A (en) * | 2021-10-20 | 2022-03-08 | 浙江菜鸟供应链管理有限公司 | Logistics order processing method and device, electronic equipment and storage medium |
| CN114663021A (en) * | 2022-03-24 | 2022-06-24 | 上海东普信息科技有限公司 | Distribution method, device, equipment and storage medium of logistics order |
| US20220227582A1 (en) * | 2019-05-20 | 2022-07-21 | Autostore Technology AS | Method and control system for preparing orders of goods stored in an automated storage system |
| US20220245574A1 (en) * | 2019-11-05 | 2022-08-04 | Strong Force Vcn Portfolio 2019, Llc | Systems, Methods, Kits, and Apparatuses for Digital Product Network Systems and Biology-Based Value Chain Networks |
| CN115373349A (en) * | 2022-07-07 | 2022-11-22 | 深圳优制云工业互联网有限公司 | Mobile transfer robot scheduling method and system |
| CN116957268A (en) * | 2023-07-27 | 2023-10-27 | 深圳市云恋科技有限公司 | Logistics order automatic distribution method and device, electronic equipment and readable storage medium |
-
2024
- 2024-04-29 CN CN202410529994.XA patent/CN118134204A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN205751263U (en) * | 2016-03-01 | 2016-11-30 | 江苏零浩网络科技有限公司 | Vehicle positioning system based on Logistics Information Platform |
| US20170300857A1 (en) * | 2016-04-18 | 2017-10-19 | Mitac International Corp. | Instantaneous logistics order processing system |
| CN110874700A (en) * | 2018-09-03 | 2020-03-10 | 菜鸟智能物流控股有限公司 | Logistics order matching method and device and electronic equipment |
| US20220227582A1 (en) * | 2019-05-20 | 2022-07-21 | Autostore Technology AS | Method and control system for preparing orders of goods stored in an automated storage system |
| CN112573058A (en) * | 2019-09-30 | 2021-03-30 | 深圳市海柔创新科技有限公司 | Goods taking method, carrying robot, processing terminal and intelligent warehousing system |
| US20220245574A1 (en) * | 2019-11-05 | 2022-08-04 | Strong Force Vcn Portfolio 2019, Llc | Systems, Methods, Kits, and Apparatuses for Digital Product Network Systems and Biology-Based Value Chain Networks |
| CN111738570A (en) * | 2020-06-05 | 2020-10-02 | 苏州华易通物流有限公司 | Logistics management system based on internet |
| CN113240362A (en) * | 2021-04-29 | 2021-08-10 | 北京京东振世信息技术有限公司 | Logistics order task processing method and device, electronic equipment and computer medium |
| WO2022228132A1 (en) * | 2021-04-29 | 2022-11-03 | 北京京东振世信息技术有限公司 | Logistics order task processing method and apparatus, electronic device, and computer medium |
| CN113743868A (en) * | 2021-09-06 | 2021-12-03 | 广西职业技术学院 | Logistics cargo management device |
| CN114154921A (en) * | 2021-10-20 | 2022-03-08 | 浙江菜鸟供应链管理有限公司 | Logistics order processing method and device, electronic equipment and storage medium |
| CN114663021A (en) * | 2022-03-24 | 2022-06-24 | 上海东普信息科技有限公司 | Distribution method, device, equipment and storage medium of logistics order |
| CN115373349A (en) * | 2022-07-07 | 2022-11-22 | 深圳优制云工业互联网有限公司 | Mobile transfer robot scheduling method and system |
| CN116957268A (en) * | 2023-07-27 | 2023-10-27 | 深圳市云恋科技有限公司 | Logistics order automatic distribution method and device, electronic equipment and readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 胡小建;韦超豪;: "基于Canopy和k-means算法的订单分批优化", 合肥工业大学学报(自然科学版), no. 03, 28 March 2017 (2017-03-28), pages 414 - 419 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yuan et al. | Research on intelligent workshop resource scheduling method based on improved NSGA-II algorithm | |
| Nielsen et al. | A methodology for implementation of mobile robot in adaptive manufacturing environments | |
| CN110807236A (en) | Warehouse logistics simulation system based on multiple robots | |
| Lin et al. | Network model and effective evolutionary approach for AGV dispatching in manufacturing system | |
| Yang et al. | Modelling and production configuration optimization for an assembly shop | |
| Yu et al. | An intelligent energy management system for large-scale charging of electric vehicles | |
| Köchel et al. | Kanban optimization by simulation and evolution | |
| Chang et al. | Multi-objective real-time dispatching for integrated delivery in a Fab using GA based simulation optimization | |
| Jin et al. | Multi agv scheduling problem in automated container terminal | |
| Hani et al. | Simulation based optimization of a train maintenance facility | |
| Xilin et al. | Resource allocation optimization of equipment development task based on MOPSO algorithm | |
| Niu et al. | A novel multi-tasks chain scheduling algorithm based on capacity prediction to solve AGV dispatching problem in an intelligent manufacturing system | |
| Jiao et al. | Online joint optimization of pick order assignment and pick pod selection in robotic mobile fulfillment systems | |
| CN116613867B (en) | Wireless power transmission system for AGV and control method thereof | |
| CN112084580B (en) | AGV system optimization configuration method based on regression analysis and satisfaction function method | |
| Jin et al. | Joint scheduling of deferrable demand and storage with random supply and processing rate limits | |
| CN118134204A (en) | Multi-terminal logistics transportation task management method and system based on cloud computing | |
| CN116720703A (en) | AGV multi-target task scheduling method and system based on deep reinforcement learning | |
| Badakhshian et al. | Performance optimization of simultaneous machine and automated guided vehicle scheduling using fuzzy logic controller based genetic algorithm | |
| Fethi et al. | The effect of AGVs number on a flexible manufacturing system | |
| CN114707707A (en) | Method and system for scheduling AGV task based on improved genetic algorithm | |
| CN112598273A (en) | Intelligent transportation scheduling method, system, medium and electronic equipment | |
| Yuan et al. | Flow shop scheduling with auxiliary time based on simulation optimization | |
| Kaoud et al. | Scheduling of automated guided vehicles and machines in flexible manufacturing systems: a simulation study | |
| Deng et al. | A two-stage routing optimization model for yard trailers in container terminals under stochastic demand |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |