CN117910917B - Logistics transportation process quality management system and method based on artificial intelligence - Google Patents
Logistics transportation process quality management system and method based on artificial intelligence Download PDFInfo
- Publication number
- CN117910917B CN117910917B CN202410310781.8A CN202410310781A CN117910917B CN 117910917 B CN117910917 B CN 117910917B CN 202410310781 A CN202410310781 A CN 202410310781A CN 117910917 B CN117910917 B CN 117910917B
- Authority
- CN
- China
- Prior art keywords
- logistics
- warehouse
- logistics warehouse
- order
- pheromone
- 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
- 238000000034 method Methods 0.000 title claims abstract description 63
- 230000008569 process Effects 0.000 title claims abstract description 38
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 25
- 238000003326 Quality management system Methods 0.000 title claims abstract description 10
- 239000000463 material Substances 0.000 claims abstract description 78
- 238000009826 distribution Methods 0.000 claims abstract description 25
- 239000003016 pheromone Substances 0.000 claims description 69
- 238000007726 management method Methods 0.000 claims description 31
- 241000257303 Hymenoptera Species 0.000 claims description 29
- 238000012544 monitoring process Methods 0.000 claims description 25
- 238000012545 processing Methods 0.000 claims description 20
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 230000000903 blocking effect Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 125000004122 cyclic group Chemical group 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 3
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000004321 preservation Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000001502 supplementing effect Effects 0.000 claims description 3
- 230000003442 weekly effect Effects 0.000 claims 1
- 230000006870 function Effects 0.000 description 16
- 230000005540 biological transmission Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of logistics management, and discloses a logistics transportation process quality management system and method based on artificial intelligence. Firstly, a proper position is selected from geographic information positions to establish a logistics warehouse, and a series of internet of things devices are installed in the warehouse to monitor and manage the logistics warehouse; when the system receives orders, each order is distributed to each logistics warehouse based on the geographical position of the order, and the logistics warehouse configures materials according to the demands of the orders; when the materials in the logistics warehouse do not meet the orders, the logistics warehouse can upload the logistics orders and are redistributed by the system; meanwhile, the logistics warehouse can carry out intelligent transportation and distribution according to the matched order; in the distribution process, an optimal path is selected based on an ant colony algorithm, and each time a node is reached, the feedback order distribution progress is reported to the system in real time, so that the management of the logistics transportation process is ensured.
Description
Technical Field
The invention relates to the technical field of logistics management (G06Q 10/08), in particular to a logistics transportation process quality management system and method based on artificial intelligence.
Background
With the continued development of computer technology, artificial intelligence is generally seen as an intelligent technology that involves machine learning, machine vision, natural language processing by robots, and automated control. With the development and application of artificial intelligence, china is transited from a traditional production mode to a technical production mode, and in recent years, the artificial intelligence technology has been widely applied to various aspects of society and has rapidly developed.
In the prior art, there are logistics management techniques based on artificial intelligence, including:
the Chinese patent with publication number CN114819783A discloses an intelligent logistics transportation management system, which specifically discloses: the system comprises a merchant client, a merchant management server, a plurality of local delivery site clients and merchant logistics carrier clients; the merchant client is used for receiving commodity orders submitted by users, returning the commodity orders submitted by the users and distributing addresses of the changed commodity orders submitted by the users, and transmitting the received relevant information about the commodity orders submitted by the users to the merchant management server; the merchant management server is used for receiving order information of the merchant client side for classification processing, then respectively making instructions on the classified information, and transmitting corresponding instruction information to the local delivery site client side and the merchant logistics carrier client side; and classifying, storing and monitoring all order information in real time. The logistics transportation management system can intelligently process the conditions of ordering, returning and changing addresses of users, and can monitor the conditions of order logistics in real time.
The Chinese patent with publication number CN109460951A discloses an intelligent logistics classification management system based on the Internet of things, and specifically discloses: the system comprises a registered user, a registration module, an auditing module, a cloud platform, a mail sending user, a direct sending module, an allocation module, a logistics transportation module, a registered transportation module, a first receiving point, a second registered transportation module, a second receiving point, an order release platform, a delivery identification module and a processor; according to the intelligent logistics classification management system, package orders are distributed to registered users, so that the problems that vehicles cannot be found in the existing logistics, vehicles cannot be found in the vehicles, and the configuration of vehicles and personnel of logistics companies in the logistics peak period is insufficient are solved; the second transportation user owner registers through the cloud platform, utilizes private car and public bus, can carry the commodity circulation parcel between county level and the rural area to solve rural commodity circulation staff and vehicle deficiency and lead to the slow problem of transportation.
Currently, with the rapid development of artificial intelligence technology, the problems faced by supply chain logistics companies are increasing. The intelligent development of the single express receiving points can not meet the requirements of diversification of customer demands, improvement of logistics efficiency and reduction of enterprise cost. Under the background, the construction of the intelligent logistics storage system is rapidly increased, however, in the operation process of the intelligent logistics storage system, the problems of slow data transmission, untimely logistics information transfer, untimely grasping of material states and the like exist.
Disclosure of Invention
(One) solving the technical problems
Aiming at the defects of the prior art, the invention provides a logistics transportation process quality management system and method based on artificial intelligence, which have the advantages of fast data transmission, timely logistics information circulation and the like, and solve the problems of slow data transmission, untimely logistics information circulation and untimely material state mastering.
(II) technical scheme
In order to solve the technical problems of slow data transmission, untimely logistics information circulation and untimely material state grasping, the invention provides the following technical scheme:
The embodiment discloses a logistics transportation process quality management method based on artificial intelligence, which specifically comprises the following steps:
S1, selecting proper positions based on geographic information positions to establish logistics warehouses, and installing and monitoring express receiving points of the Internet of things for each logistics warehouse; the building of the logistics warehouse at the selected proper position specifically comprises the following steps:
S11, constructing a topological map of a target logistics area;
S12, constructing a unit time operation cost set { C ij(T0) } of a two-stage logistics warehouse; the two-stage logistics warehouse comprises a distributed warehouse serving as a second-stage logistics warehouse and a terminal station serving as a first-stage logistics warehouse; wherein T 0 represents a unit time, i represents a level of the logistics warehouse, j represents a serial number of the logistics warehouse, and C ij(T0) represents a unit time operation cost of a j-th logistics warehouse of the i-th level;
s13, constructing a two-stage logistics network cost optimization function; the method specifically comprises the following steps:
s131, calibrating terminal stations serving as a primary logistics warehouse on a topological map of a target logistics area according to population and cell distribution of the target logistics area to obtain a terminal station set { S 1j }; constructing a community distributed bin set { S 2j } serving as a secondary logistics warehouse;
S132, setting a community distributed bin set { S 2j } as a unit element set, wherein the first single element is S 21(x21,y21), and constructing a first single element two-layer logistics network map:
S21→{S1j}
s133, optimizing the warehouse address of the first single-element two-layer logistics network based on a minimum cost function f min(S21→{S1j); the minimum cost function f min(S21→{S1j }) satisfies:
Wherein S (x 21,y21) is a topological distance function, and represents the topological distance from each terminal station when the community distributed bin is arranged at a coordinate point (x 21,y21), v represents the average distribution speed, and T 1 represents the average standing time of the articles;
x21＝x20+nΔx
y21＝y20+mΔy
Wherein x 20 and y 20 represent initial coordinate points, Δx and Δy represent cyclic step sizes respectively, n and m represent cyclic increments respectively, and are natural numbers which are increased from 1;
Circularly increasing n and m, and calculating a point of the first single-element two-layer logistics network to obtain a minimum value as a first single element optimal solution;
S134, determining the number of secondary logistics warehouses in a target logistics area according to the bearing capacity of a single secondary logistics warehouse, determining a community distributed warehouse set { S 2j } as a multi-element set, and circularly executing steps S132 and S133 to obtain a second single element and a third single element until the determination of the positions of all the secondary logistics warehouses is completed;
S2, realizing overall dynamic management of the stock quantity, the type, the position and the time of the materials in the logistics warehouse through the installed express receiving points of the monitoring Internet of things;
s3, when receiving the logistics order, carrying out preliminary classification processing on the logistics order according to the address of the logistics order;
s4, distributing the logistics orders subjected to the preliminary classification treatment to logistics warehouses at different positions;
S5, after receiving the physical order, the logistics warehouse performs material allocation based on the material demand in the logistics order;
s6, after material allocation is completed, carrying out allocation scheduling on orders based on the intelligent transportation allocation module;
S7, in the delivery process, carrying out transportation delivery based on a route preset by the intelligent transportation delivery module, and reporting to the intelligent traceability module when one transportation node is reached until the route end point is reached;
preferably, the method for realizing the overall dynamic management of the stock, the type, the position and the time of the materials in the logistics warehouse by the installed express receiving points of the monitoring internet of things comprises the following steps:
s21, monitoring the warehousing condition of each type of material in a logistics warehouse in real time, and recording the quantity, the type, the storage position and the time of each type of material;
s22, monitoring the preservation condition of each type of material in the logistics warehouse in real time, and replacing unqualified materials by the logistics warehouse when detecting that the quality unqualified problem exists in some types of materials in the logistics warehouse;
S23, monitoring the ex-warehouse condition of each type of material in the logistics warehouse in real time, and recording the quantity, the type and the time of each type of material.
Preferably, the preliminary sorting process of the logistics orders according to the addresses of the logistics orders includes the following steps:
Matching based on Euclidean distance between the logistics order address and the address of each logistics warehouse;
The Euclidean distance calculation formula:
Setting the address of the order a 1 to be (x 1,y1), the address of the logistics warehouse b 1 to be (x 2,y2), and the address of the logistics warehouse b i to be (x i,yi),d(a1,b1) is the Euclidean distance from the address of the order a 1 to the address of the logistics warehouse b 1, d (a1,bi) is the Euclidean distance from the address of the order a 1 to the address of the logistics warehouse b i, wherein the address set of the logistics warehouse is { b 1,b2,b3,...,bn }, n represents the nth logistics warehouse, and i represents the ith logistics warehouse in the logistics warehouse set;
Sequentially calculating Euclidean distance from an order a 1 address to each logistics warehouse in a logistics warehouse set, constructing a distance set { d }, and judging the logistics warehouse to which the order is to be distributed according to the Euclidean distance;
when d (a1,bi) =min { d }, order a 1 will be assigned to the ith logistics warehouse.
Preferably, the logistics warehouse performs material allocation based on the material demand in the logistics order after receiving the physical order, and the method comprises the following steps of:
s51, arranging orders based on the order receiving order sequence of the logistics warehouse;
s52, matching the material demands on the basis of the types of the materials in the logistics warehouse and the arranged orders in sequence;
S53, placing orders meeting the material demands into a completion queue, performing material allocation according to the order demands, placing orders not meeting the material demands into a blocking queue, and supplementing the logistics warehouse according to the unsatisfied conditions in the blocking queue;
and S54, when the logistics warehouse is arranged to be replenished, the logistics warehouse reports the blocking queue, and the order receiving processing module rearranges the physical warehouse to process the order.
Preferably, after the material allocation is completed, the intelligent transportation delivery module performs delivery scheduling on the order, including the following steps:
S61, setting initial values of related parameters based on an ant colony algorithm, setting the number of ants as Q, and setting the minimum value of the pheromone error rate as E 0;
S62, placing m ants on n vertexes, adopting a preferred initial value strategy, randomly generating k solutions, and selecting l paths with shortest path distance to leave pheromones;
S63, the kth ant moves to the next node according to the probability p k ij, the path length L of the kth ant is calculated, and the current solution is recorded;
S64, adopting a preferred path strategy; recording the path length of each ant according to the step S63, sequencing the path lengths, selecting S paths with the shortest paths to form a solution set, and modifying the track strength of the optimal S individuals according to the pheromone updating mode;
S65, when all ants in the ant colony select an optimal solution set through the step S64, calculating the optimal solution set through a neural network, calculating a pheromone error range, and when the pheromone error rate reaches a minimum value which is not more than the minimum value E 0 in the setting, indicating that the calculation is completed, exiting the program and outputting a result; otherwise, step S66 will be performed;
s66, when the pheromone error rate E > E 0, according to formulas (8), (9), (10) and (11), recalculating required data, updating the pheromone content on each path, and reducing the pheromone error rate of the ant colony in the path set by continuously updating the pheromone data;
S67, after the set iteration times and iteration trends are stabilized after the ant colony loop of S61 to S66, the round trip paths of all ants in the ant colony are considered as the optimal paths searched for at the present time.
Preferably, the setting the initial value of the relevant parameter based on the ant colony algorithm includes:
setting g express receiving points, c i＝(xi,yi), i=1, 2,3,..g, existing near the current logistics warehouse;
Wherein c i、cj represents the ith and jth express receiving points adjacent to the logistics warehouse, and (x i,yi)、(xj,yj) represents the node coordinates of two adjacent express receiving points;
The distance between the express receiving point c i and the express receiving point c j can be expressed as:
Further, a tabu table is set for each ant, the passing express receiving points are recorded, the first position in the tabu table is the express receiving point where the ant is located at the initial moment, when all the express receiving points are added into the tabu table, the fact that the ant walks all the express receiving points is indicated, one trip is completed, and the initialization of the pheromone function is set, namely:
Wherein ζ ij (0) represents the initial time pheromone concentration, and MS j represents the physical distribution warehouse resource service capability at the j time; c represents a constant;
After initialization, the task T of the completion queue is distributed to a virtual task pool to form MT, and the probability p after the ant k moves to the node x at the moment T is:
Wherein a k represents a node on which ant k can move next, ζ ij (t) represents the concentration of pheromone of a path from node i to node j at time t, and σ ij represents the reciprocal of the Euclidean distance between the nodes; alpha and beta respectively represent a pheromone heuristic factor and an expected heuristic factor; where the desired heuristic factor β is a decreasing function as a function of the number of iterations, namely:
wherein b is a constant, i is the number of current iterations of the algorithm;
further, the content of each path pheromone at the time t+n is adjusted as follows:
Wherein ρ represents the volatilization coefficient of the pheromone between time periods (t, t+n), and (1- ρ) represents the residual amount of the pheromone and the volatilization coefficient takes on a value range (0, 1);
Wherein ρ represents a pheromone volatilization coefficient, Δζ ij (t) represents the sum of the pheromone contents released by all ants on the connection path of the express receiving point i and the express receiving point j, and Δζ k ij (t) represents the pheromone content released by the kth ant between the express receiving point c i and the express receiving point c j in the current cycle;
the updating mode of the pheromone mainly comprises the following steps:
Ant circulation model
Ant number model
Ant density model
Where L k denotes a path that the kth ant passes in the midstream.
Preferably, the preferred initial value strategy is to select n random numbers generated by m ants, select pheromones in a better path to leave, set a current solution set of the ants as an initial point of the ants, calculate path lengths L k (k=1, 2,3,..m) of all ants when all ants move from a current node i to a next node j and set the next node as a current solution according to a probability p k ij, select L paths according to the preferred optimal path strategy, and carry the selected L paths into an pheromone updating mode to modify the gauge strength according to the strength ranking;
preferably, the calculating the optimal solution set through the neural network includes:
inputting the collected optimal selection set into a neural network, and setting a corresponding weight for each path in the optimal selection set based on the actual path round trip time;
Setting an input value of x i (i=1, 2,.. N), wherein an input weight value corresponding to each input value z i is w i, b is an offset, and the output result obtained after the input values are input into the neural network is:
Where f (·) is the corresponding activation function, z i represents the distance value in the most preferred set, and u represents the distance value after processing.
The embodiment also discloses a logistics transportation process quality management system based on artificial intelligence, which specifically comprises: the system comprises a logistics warehouse address selection module, a material management module, an order receiving and processing module, an intelligent transportation distribution module and an intelligent traceability module;
The logistics warehouse address selection module is used for selecting a proper position according to the geographic information position to establish a logistics warehouse;
The material management module is used for monitoring and managing the material quality and the material in-and-out condition of the physical warehouse in real time by installing and monitoring the express receiving points of the Internet of things in the physical warehouse;
the order receiving and processing module is used for receiving the logistics orders and processing the logistics orders to distribute the logistics orders to all logistics warehouses;
the intelligent transportation distribution module is used for carrying out distribution scheduling on the logistics orders arranged by the logistics warehouse, and uploading the progress in the distribution process to the intelligent traceability module in real time;
The intelligent traceability module is used for receiving the logistics order progress information from the intelligent transportation distribution module in real time and transmitting the logistics order progress information from the intelligent transportation distribution module to a user.
(III) beneficial effects
Compared with the prior art, the invention provides an artificial intelligence-based logistics transportation process quality management system and method, which have the following beneficial effects:
1. According to the method, an ant colony algorithm and a mode of correlation among all express receiving points nearby in a logistics warehouse are used for establishing a shortest path table among all express receiving points, routes of ants are recorded according to a mode of setting a tabu table for each ant, the path length of each ant is calculated, the pheromone concentration on each equipment path is updated according to an pheromone iteration formula, and the shortest path in iteration times is found in a continuous iteration mode.
2. According to the invention, through the processing of receiving orders by the system, comprehensive judgment is carried out according to the positions of the orders and the demands of the materials of the orders, a proper logistics warehouse is selected, and the materials required by the orders are distributed based on the shortest path obtained by an ant colony algorithm.
3. According to the invention, the real-time feedback of the logistics order delivery condition based on the arrival node in the physical delivery process improves the interactivity and the real-time performance of logistics delivery.
Drawings
Fig. 1 is a schematic structural diagram of a transportation process management flow according to 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.
The embodiment discloses a logistics transportation process quality management method based on artificial intelligence, which specifically comprises the following steps:
S1, selecting proper positions based on geographic information positions to establish logistics warehouses, and installing and monitoring express receiving points of the Internet of things for each logistics warehouse; the building of the logistics warehouse at the selected proper position specifically comprises the following steps:
S11, constructing a topological map of a target logistics area;
S12, constructing a unit time operation cost set { C ij(T0) } of a two-stage logistics warehouse; the two-stage logistics warehouse comprises a distributed warehouse serving as a second-stage logistics warehouse and a terminal station serving as a first-stage logistics warehouse; wherein T 0 represents a unit time, i represents a level of the logistics warehouse, j represents a serial number of the logistics warehouse, and C ij(T0) represents a unit time operation cost of a j-th logistics warehouse of the i-th level;
s13, constructing a two-stage logistics network cost optimization function; the method specifically comprises the following steps:
s131, calibrating terminal stations serving as a primary logistics warehouse on a topological map of a target logistics area according to population and cell distribution of the target logistics area to obtain a terminal station set { S 1j }; constructing a community distributed bin set { S 2j } serving as a secondary logistics warehouse;
S132, setting a community distributed bin set { S 2j } as a unit element set, wherein the first single element is S 21(x21,y21), and constructing a first single element two-layer logistics network map:
S21→{S1j}
s133, optimizing the warehouse address of the first single-element two-layer logistics network based on a minimum cost function f min(S21→{S1j); the minimum cost function f min(S21→{S1j }) satisfies:
Wherein S (x 21,y21) is a topological distance function, and represents the topological distance from each terminal station when the community distributed bin is arranged at a coordinate point (x 21,y21), v represents the average distribution speed, and T 1 represents the average standing time of the articles;
x21＝x20+nΔx
y21＝y20+mΔy
Wherein x 20 and y 20 represent initial coordinate points, Δx and Δy represent cyclic step sizes respectively, n and m represent cyclic increments respectively, and are natural numbers which are increased from 1;
Circularly increasing n and m, and calculating a point of the first single-element two-layer logistics network to obtain a minimum value as a first single element optimal solution;
S134, determining the number of secondary logistics warehouses in a target logistics area according to the bearing capacity of a single secondary logistics warehouse, determining a community distributed warehouse set { S 2j } as a multi-element set, and circularly executing steps S132 and S133 to obtain a second single element and a third single element until the determination of the positions of all the secondary logistics warehouses is completed;
S2, realizing overall dynamic management of the stock quantity, the type, the position and the time of the materials in the logistics warehouse through the installed express receiving points of the monitoring Internet of things;
further, the monitoring of the internet of things express receiving point realizes the overall dynamic management of the stock, the type, the position and the time of the materials in the logistics warehouse, and the method comprises the following steps:
s21, monitoring the warehousing condition of each type of material in a logistics warehouse in real time, and recording the quantity, the type, the storage position and the time of each type of material;
s22, monitoring the preservation condition of each type of material in the logistics warehouse in real time, and replacing unqualified materials by the logistics warehouse when detecting that the quality unqualified problem exists in some types of materials in the logistics warehouse;
s23, monitoring the ex-warehouse condition of each type of material in the logistics warehouse in real time, and recording the quantity, the type and the time of each type of material;
s3, when receiving the logistics order, carrying out preliminary classification processing on the logistics order according to the address of the logistics order;
Further, the preliminary sorting process for the logistics orders according to the addresses of the logistics orders comprises the following steps:
Matching based on Euclidean distance between the logistics order address and the address of each logistics warehouse;
The Euclidean distance calculation formula:
Setting the address of the order a 1 to be (x 1,y1), the address of the logistics warehouse b 1 to be (x 2,y2), and the address of the logistics warehouse b i to be (x i,yi),d(a1,b1) is the Euclidean distance from the address of the order a 1 to the address of the logistics warehouse b 1, d (a1,bi) is the Euclidean distance from the address of the order a 1 to the address of the logistics warehouse b i, wherein the address set of the logistics warehouse is { b 1,b2,b3,...,bn }, n represents the nth logistics warehouse, and i represents the ith logistics warehouse in the logistics warehouse set;
Sequentially calculating Euclidean distance from an order a 1 address to each logistics warehouse in a logistics warehouse set, constructing a distance set { d }, and judging the logistics warehouse to which the order is to be distributed according to the Euclidean distance;
When d (a1,bi) =min { d }, order a 1 will be assigned to the ith logistics warehouse;
s4, distributing the logistics orders subjected to the preliminary classification treatment to logistics warehouses at different positions;
S5, after receiving the physical order, the logistics warehouse performs material allocation based on the material demand in the logistics order;
Further, the logistics warehouse performs material allocation based on the material demand in the logistics order after receiving the physical order, and the method comprises the following steps:
s51, arranging orders based on the order receiving order sequence of the logistics warehouse;
s52, matching the material demands on the basis of the types of the materials in the logistics warehouse and the arranged orders in sequence;
S53, placing orders meeting the material demands into a completion queue, performing material allocation according to the order demands, placing orders not meeting the material demands into a blocking queue, and supplementing the logistics warehouse according to the unsatisfied conditions in the blocking queue;
S54, when the logistics warehouse is arranged to carry out replenishment, the logistics warehouse reports the blocking queue, and the order receiving processing module rearranges the physical warehouse to process the order;
s6, after material allocation is completed, carrying out allocation scheduling on orders based on the intelligent transportation allocation module;
further, after the material allocation is completed, the intelligent transportation delivery module is used for delivering and scheduling the orders, and the method comprises the following steps of:
S61, setting initial values of related parameters, wherein the number of ants is Q, and the minimum value of the error rate of the pheromone is E 0;
setting g express receiving points, c i＝(xi,yi), i=1, 2,3,..g, existing near the current logistics warehouse;
Wherein c i、cj represents the ith and jth express receiving points adjacent to the logistics warehouse, and (x i,yi)、(xj,yj) represents the node coordinates of two adjacent express receiving points;
The distance between the express receiving point c i and the express receiving point c j can be expressed as:
Further, a tabu table is set for each ant, the passing express receiving points are recorded, the first position in the tabu table is the express receiving point where the ant is located at the initial moment, when all the express receiving points are added into the tabu table, the fact that the ant walks all the express receiving points is indicated, one trip is completed, and the initialization of the pheromone function is set, namely:
Wherein ζ ij (0) represents the initial time pheromone concentration, and MS j represents the physical distribution warehouse resource service capability at the j time; c represents a constant;
After initialization, the task T of the completion queue is distributed to a virtual task pool to form MT, and the probability p after the ant k moves to the node x at the moment T is:
Wherein a k represents a node on which ant k can move next, ζ ij (t) represents the concentration of pheromone of a path from node i to node j at time t, and σ ij represents the reciprocal of the Euclidean distance between the nodes; alpha and beta respectively represent a pheromone heuristic factor and an expected heuristic factor; where the desired heuristic factor β is a decreasing function as a function of the number of iterations, namely:
wherein b is a constant, i is the number of current iterations of the algorithm;
further, the content of each path pheromone at the time t+n is adjusted as follows:
Wherein ρ represents the volatilization coefficient of the pheromone between time periods (t, t+n), and (1- ρ) represents the residual amount of the pheromone and the volatilization coefficient takes on a value range (0, 1);
Wherein ρ represents a pheromone volatilization coefficient, Δζ ij (t) represents the sum of the pheromone contents released by all ants on the connection path of the express receiving point i and the express receiving point j, and Δζ k ij (t) represents the pheromone content released by the kth ant between the express receiving point c i and the express receiving point c j in the current cycle;
Further, the pheromone updating mode mainly comprises the following steps:
Ant circulation model
Ant number model
Ant density model
Wherein L k represents a path that the kth ant passes in the midstream;
S62, placing m ants on n vertexes, adopting a preferred initial value strategy, randomly generating k solutions, and selecting l paths with shortest path distance to leave pheromones;
The preferred initial value strategy is to leave the pheromones in the paths with better selection on n generated random numbers of m ants, set the current solution set of the ants as their initial points, move all ants from the current node i to the next node j according to the probability p k ij, and set the next node as the current solution;
Calculating path lengths L k (k=1, 2, 3.. The m) of all ants, selecting L paths according to a preferred optimal path strategy, and carrying out sorting on the selected L paths according to the strength to modify the rule strength in a pheromone updating mode;
S63, the kth ant moves to the next node according to the probability p k ij, the path length L of the kth ant is calculated, and the current solution is recorded;
S64, adopting a preferred path strategy; recording the path length of each ant according to the step S63, sequencing the path lengths, selecting S paths with the shortest paths to form a solution set, and modifying the track strength of the optimal S individuals according to the pheromone updating mode;
S65, when all ants in the ant colony select an optimal solution set through the step S64, calculating the optimal solution set through a neural network, calculating a pheromone error range, and when the pheromone error rate reaches a minimum value which is not more than the minimum value E 0 in the setting, indicating that the calculation is completed, exiting the program and outputting a result; otherwise, step S66 will be performed;
further, the calculating the optimal solution set through the neural network includes:
inputting the collected optimal selection set into a neural network, and setting a corresponding weight for each path in the optimal selection set based on the actual path round trip time;
Setting an input value of x i (i=1, 2,.. N), wherein an input weight value corresponding to each input value z i is w i, b is an offset, and the output result obtained after the input values are input into the neural network is:
wherein, f (·) is a corresponding activation function, z i represents a distance value in the most preferred set, and u represents a distance value after processing;
s66, when the pheromone error rate E > E 0, according to formulas (8), (9), (10) and (11), recalculating required data, updating the pheromone content on each path, and reducing the pheromone error rate of the ant colony in the path set by continuously updating the pheromone data;
S67, after the set iteration times and iteration trends are stabilized after the ant colony loop of S61 to S66 is completed, determining the round trip paths of all ants in the ant colony as the optimal path searched at the present time;
S7, in the delivery process, carrying out transportation delivery based on a route preset by the intelligent transportation delivery module, and reporting to the intelligent traceability module when one transportation node is reached until the route end point is reached;
The embodiment also discloses a logistics transportation process quality management system based on artificial intelligence, which specifically comprises: the system comprises a logistics warehouse address selection module, a material management module, an order receiving and processing module, an intelligent transportation distribution module and an intelligent traceability module;
The logistics warehouse address selection module is used for selecting a proper position according to the geographic information position to establish a logistics warehouse;
The material management module is used for monitoring and managing the material quality and the material in-and-out condition of the physical warehouse in real time by installing and monitoring the express receiving points of the Internet of things in the physical warehouse;
the order receiving and processing module is used for receiving the logistics orders and processing the logistics orders to distribute the logistics orders to all logistics warehouses;
the intelligent transportation distribution module is used for carrying out distribution scheduling on the logistics orders arranged by the logistics warehouse, and uploading the progress in the distribution process to the intelligent traceability module in real time;
The intelligent traceability module is used for receiving the logistics order progress information from the intelligent transportation distribution module in real time and transmitting the logistics order progress information from the intelligent transportation distribution module to a user.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (9)
1. The logistics transportation process quality management method based on artificial intelligence is characterized by comprising the following steps of:
S1, selecting proper positions based on geographic information positions to establish logistics warehouses, and installing and monitoring express receiving points of the Internet of things for each logistics warehouse; the building of the logistics warehouse at the selected proper position specifically comprises the following steps:
S11, constructing a topological map of a target logistics area;
S12, constructing a unit time operation cost set { C ij(T0) } of a two-stage logistics warehouse; the two-stage logistics warehouse comprises a distributed warehouse serving as a second-stage logistics warehouse and a terminal station serving as a first-stage logistics warehouse; wherein T 0 represents a unit time, i represents a level of the logistics warehouse, j represents a serial number of the logistics warehouse, and C ij(T0) represents a unit time operation cost of a j-th logistics warehouse of the i-th level;
s13, constructing a two-stage logistics network cost optimization function; the method specifically comprises the following steps:
s131, calibrating terminal stations serving as a primary logistics warehouse on a topological map of a target logistics area according to population and cell distribution of the target logistics area to obtain a terminal station set { S 1j }; constructing a community distributed bin set { S 2j } serving as a secondary logistics warehouse;
S132, setting a community distributed bin set { S 2j } as a unit element set, wherein the first single element is S 21(x21,y21), and constructing a first single element two-layer logistics network map:
S21→{S1j}
s133, optimizing the warehouse address of the first single-element two-layer logistics network based on a minimum cost function f min(S21→{S1j); the minimum cost function f min(S21→{S1j }) satisfies:
Wherein S (x 21,y21) is a topological distance function, and represents the topological distance from each terminal station when the community distributed bin is arranged at a coordinate point (x 21,y21), v represents the average distribution speed, and T 1 represents the average standing time of the articles;
x21＝x20+nΔx
y21＝y20+mΔy
Wherein x 20 and y 20 represent initial coordinate points, Δx and Δy represent cyclic step sizes respectively, n and m represent cyclic increments respectively, and are natural numbers which are increased from 1;
Circularly increasing n and m, and calculating a point of the first single-element two-layer logistics network to obtain a minimum value as a first single element optimal solution;
S134, determining the number of secondary logistics warehouses in a target logistics area according to the bearing capacity of a single secondary logistics warehouse, determining a community distributed warehouse set { S 2j } as a multi-element set, and circularly executing steps S132 and S133 to obtain a second single element and a third single element until the determination of the positions of all the secondary logistics warehouses is completed;
S2, realizing overall dynamic management of the stock quantity, the type, the position and the time of the materials in the logistics warehouse through the installed express receiving points of the monitoring Internet of things;
s3, when receiving the logistics order, carrying out preliminary classification processing on the logistics order according to the address of the logistics order;
s4, distributing the logistics orders subjected to the preliminary classification treatment to logistics warehouses at different positions;
S5, after receiving the physical order, the logistics warehouse performs material allocation based on the material demand in the logistics order;
s6, after material allocation is completed, carrying out allocation scheduling on orders based on the intelligent transportation allocation module;
And S7, in the delivery process, carrying out transportation delivery based on a route preset by the intelligent transportation delivery module, and reporting to the intelligent traceability module every time a transportation node is reached until the route end point is reached.
2. The method for managing the quality of the logistics transportation process based on artificial intelligence according to claim 1, wherein the method for realizing the overall dynamic management of the stock, the type, the position and the time of the logistics warehouse through the installed monitoring internet of things express receiving point comprises the following steps:
s21, monitoring the warehousing condition of each type of material in a logistics warehouse in real time, and recording the quantity, the type, the storage position and the time of each type of material;
s22, monitoring the preservation condition of each type of material in the logistics warehouse in real time, and replacing unqualified materials by the logistics warehouse when detecting that the quality unqualified problem exists in some types of materials in the logistics warehouse;
S23, monitoring the ex-warehouse condition of each type of material in the logistics warehouse in real time, and recording the quantity, the type and the time of each type of material.
3. The method for quality management of a logistics transportation process based on artificial intelligence according to claim 1, wherein the preliminary sorting process of the logistics orders according to the addresses of the logistics orders comprises the steps of:
Matching based on Euclidean distance between the logistics order address and the address of each logistics warehouse;
The Euclidean distance calculation formula:
Setting the address of the order a 1 to be (x 1,y1), the address of the logistics warehouse b 1 to be (x 2,y2), and the address of the logistics warehouse b i to be (x i,yi),d(a1,b1) is the Euclidean distance from the address of the order a 1 to the address of the logistics warehouse b 1, d (a1,bi) is the Euclidean distance from the address of the order a 1 to the address of the logistics warehouse b i, wherein the address set of the logistics warehouse is { b 1,b2,b3,...,bn }, n represents the nth logistics warehouse, and i represents the ith logistics warehouse in the logistics warehouse set;
Sequentially calculating Euclidean distance from an order a 1 address to each logistics warehouse in a logistics warehouse set, constructing a distance set { d }, and judging the logistics warehouse to which the order is to be distributed according to the Euclidean distance;
when d (a1,bi) =min { d }, order a 1 will be assigned to the ith logistics warehouse.
4. The method for quality management of a logistics transportation process based on artificial intelligence according to claim 1, wherein the logistics warehouse performs the material allocation based on the material demand in the logistics order after receiving the physical order, comprising the steps of:
s51, arranging orders based on the order receiving order sequence of the logistics warehouse;
s52, matching the material demands on the basis of the types of the materials in the logistics warehouse and the arranged orders in sequence;
S53, placing orders meeting the material demands into a completion queue, performing material allocation according to the order demands, placing orders not meeting the material demands into a blocking queue, and supplementing the logistics warehouse according to the unsatisfied conditions in the blocking queue;
and S54, when the logistics warehouse is arranged to be replenished, the logistics warehouse reports the blocking queue, and the order receiving processing module rearranges the physical warehouse to process the order.
5. The method for quality management of a logistics transportation process based on artificial intelligence according to claim 1, wherein after the material allocation is completed, the order is dispatched based on the intelligent transportation and distribution module, comprising the following steps:
S61, setting initial values of related parameters based on an ant colony algorithm, setting the number of ants as Q, and setting the minimum value of the pheromone error rate as E 0;
based on the ant colony algorithm, setting initial values of the relevant parameters includes:
setting g express receiving points, c i＝(xi,yi), i=1, 2,3,..g, existing near the current logistics warehouse;
Wherein c i、cj represents the ith and jth express receiving points adjacent to the logistics warehouse, and (x i,yi)、(xj,yj) represents the node coordinates of two adjacent express receiving points;
The distance between the express receiving point c i and the express receiving point c j can be expressed as:
Setting a tabu table for each ant, recording the passing express receiving points, wherein the first position in the tabu table is the express receiving point where the ant is located at the initial moment, when all the express receiving points are added into the tabu table, indicating that the ant has passed through all the express receiving points, completing one-time weekly trip, and setting to initialize the pheromone function, namely:
Wherein ζ ij (0) represents the initial time pheromone concentration, and MS q represents the q time logistics warehouse resource service capability; c represents a constant;
After initialization, the task T of the completion queue is distributed to a virtual task pool to form MT, and the probability p after the ant k moves from the node i to the node j at the moment T is:
Wherein a k represents a node on which ant k can move next, ζ ij (t) represents the concentration of pheromone of a path from node i to node j at time t, and σ ij represents the reciprocal of the Euclidean distance between the nodes; alpha and beta respectively represent a pheromone heuristic factor and an expected heuristic factor; where the expected heuristic factor β is a decreasing function as a function of the number of iterations, p k ij represents the probability that ant k moves from node i to node j, i.e.:
wherein b is a constant, and e is the number of current iterations of the algorithm;
the content of each path pheromone at the time t+n is adjusted as follows:
ξij(t+n)＝(1-ρ)·ξij(t)+Δξij(t),ρ∈[0,1] (7)
Wherein ρ represents the volatilization coefficient of the pheromone between time periods (t, t+n), and (1- ρ) represents the residual amount of the pheromone and the volatilization coefficient takes on a value range (0, 1);
Wherein ρ represents a pheromone volatilization coefficient, Δζ ij (t) represents the sum of the pheromone contents released by all ants on the connection path of the express receiving point i and the express receiving point j, and Δζ k ij (t) represents the pheromone content released by the kth ant between the express receiving point c i and the express receiving point c j in the current cycle;
the updating mode of the pheromone mainly comprises the following steps:
Ant circulation model
Ant number model
Ant density model
Wherein L k represents a path that the kth ant passes in the midstream;
S62, placing m ants on n vertexes, adopting a preferred initial value strategy, randomly generating k solutions, and selecting l paths with shortest path distance to leave pheromones;
S63, the kth ant moves to the next node according to the probability p, calculates the path length L of the kth ant, and records the current solution;
S64, adopting a preferred path strategy; recording the path length of each ant according to the step S63, sequencing the path lengths, selecting S paths with the shortest paths to form a solution set, and modifying the track strength of the optimal S individuals according to the pheromone updating mode;
S65, when all ants in the ant colony select an optimal solution set through the step S64, then calculate the optimal solution set through a neural network, calculate a pheromone error range, and when the pheromone error rate reaches a minimum value which is not more than the minimum value of the pheromone error rate in the setting and is E 0, the completion of calculation is indicated, the program is exited, and a result is output; otherwise, step S66 will be performed;
s66, when the pheromone error rate E > E 0, according to formulas (8), (9), (10) and (11), recalculating required data, updating the pheromone content on each path, and reducing the pheromone error rate of the ant colony in the path set by continuously updating the pheromone data;
S67, after the set iteration times and iteration trends are stabilized after the ant colony loop of S61 to S66, the round trip paths of all ants in the ant colony are considered as the optimal paths searched for at the present time.
6. The method for quality management of logistics transportation process based on artificial intelligence according to claim 5, wherein the method comprises the following steps: the calculating the optimal solution set through the neural network comprises:
inputting the collected optimal selection set into a neural network, and setting a corresponding weight for each path in the optimal selection set based on the actual path round trip time;
Setting an input value of x i (i=1, 2,.. N), wherein an input weight value corresponding to each input value z i is w i, b is an offset, and the output result obtained after the input values are input into the neural network is:
Where f (·) is the corresponding activation function, z i represents the distance value in the most preferred set, and u represents the distance value after processing.
7. The method for quality management of logistics transportation process based on artificial intelligence according to claim 5, wherein the method comprises the following steps: the preferred initial value strategy is to leave the pheromones in the paths with the optimal values by using the n random numbers generated by m ants, set the current solution set of the ants as their initial points, calculate the path length L k (k=1, 2,3, the..m) of all ants when all ants move from the current node i to the next node j and set the next node as the current solution according to the probability p k ij, select L paths according to the preferred optimal path strategy, and carry the selected L paths into the pheromone updating mode to modify the regular moment strength according to the strength.
8. An artificial intelligence based logistics transportation process quality management system implementing the artificial intelligence based logistics transportation process quality management method of any one of claims 1-7 comprising: the system comprises a logistics warehouse address selection module, a material management module, an order receiving and processing module and an intelligent transportation distribution module;
The logistics warehouse address selection module is used for selecting a proper position according to the geographic information position to establish a logistics warehouse;
The material management module is used for monitoring and managing the material quality and the material in-and-out condition of the physical warehouse in real time by installing and monitoring the express receiving points of the Internet of things in the physical warehouse;
the order receiving and processing module is used for receiving the logistics orders and processing the logistics orders to distribute the logistics orders to all logistics warehouses;
The intelligent transportation delivery module is used for carrying out delivery scheduling on the logistics orders arranged by the logistics warehouse, and uploading the progress in the delivery process to the intelligent traceability module in real time.
9. The artificial intelligence based logistics transportation process quality management system of claim 8, further comprising an intelligent traceability module for receiving logistics order progress information from the intelligent transportation delivery module in real time and transmitting the logistics order progress information from the intelligent transportation delivery module to the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410310781.8A CN117910917B (en) | 2024-03-19 | 2024-03-19 | Logistics transportation process quality management system and method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410310781.8A CN117910917B (en) | 2024-03-19 | 2024-03-19 | Logistics transportation process quality management system and method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117910917A CN117910917A (en) | 2024-04-19 |
| CN117910917B true CN117910917B (en) | 2024-06-04 |
Family
ID=90685493
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410310781.8A Active CN117910917B (en) | 2024-03-19 | 2024-03-19 | Logistics transportation process quality management system and method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117910917B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103632208A (en) * | 2013-11-14 | 2014-03-12 | 北京锐安科技有限公司 | Quantitive analysis method for logistics transport distance and warehouse site selection method |
| CN112061711A (en) * | 2020-08-18 | 2020-12-11 | 西南交通大学 | Modular logistics transportation system and transportation method thereof |
| CN113112203A (en) * | 2021-04-14 | 2021-07-13 | 杭州拼便宜网络科技有限公司 | Multi-distribution center vehicle routing system based on hybrid ant colony algorithm |
| WO2022033500A1 (en) * | 2020-08-12 | 2022-02-17 | 久恒理树 | Distributed logistics system |
| CN115495859A (en) * | 2022-09-19 | 2022-12-20 | 上海交通大学 | Warehouse network planning and cost-effective method based on genetic algorithm |
| CN116308031A (en) * | 2023-01-31 | 2023-06-23 | 广州盖盟达工业品有限公司 | Multi-warehouse inventory allocation method for shortening warehouse cargo allocation walking path |
| CN117495236A (en) * | 2023-11-20 | 2024-02-02 | 国网浙江省电力有限公司物资分公司 | Scheduling method and device for electric power material warehouse |
-
2024
- 2024-03-19 CN CN202410310781.8A patent/CN117910917B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103632208A (en) * | 2013-11-14 | 2014-03-12 | 北京锐安科技有限公司 | Quantitive analysis method for logistics transport distance and warehouse site selection method |
| WO2022033500A1 (en) * | 2020-08-12 | 2022-02-17 | 久恒理树 | Distributed logistics system |
| CN112061711A (en) * | 2020-08-18 | 2020-12-11 | 西南交通大学 | Modular logistics transportation system and transportation method thereof |
| CN113112203A (en) * | 2021-04-14 | 2021-07-13 | 杭州拼便宜网络科技有限公司 | Multi-distribution center vehicle routing system based on hybrid ant colony algorithm |
| CN115495859A (en) * | 2022-09-19 | 2022-12-20 | 上海交通大学 | Warehouse network planning and cost-effective method based on genetic algorithm |
| CN116308031A (en) * | 2023-01-31 | 2023-06-23 | 广州盖盟达工业品有限公司 | Multi-warehouse inventory allocation method for shortening warehouse cargo allocation walking path |
| CN117495236A (en) * | 2023-11-20 | 2024-02-02 | 国网浙江省电力有限公司物资分公司 | Scheduling method and device for electric power material warehouse |
Non-Patent Citations (1)
| Title |
|---|
| 电子商务环境下的二级物流配送中心选址研究;刘芬;中国优秀硕士学位论文全文数据库经济与管理科学辑;20080515;J145-129 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117910917A (en) | 2024-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109034468B (en) | Logistics distribution path planning method with time window based on cuckoo algorithm | |
| US20240054444A1 (en) | Logistics scheduling method and system for industrial park based on game theory | |
| US20210312347A1 (en) | Dispatching distribution | |
| CN112418497B (en) | Material distribution path optimization method for manufacturing Internet of things | |
| CN103927643B (en) | A kind of method that large-scale order form treatment optimizes with Distribution path | |
| CN108965024A (en) | A kind of virtual network function dispatching method of the 5G network slice based on prediction | |
| Agrawal et al. | A collaborative ant colony algorithm to stochastic mixed-model U-shaped disassembly line balancing and sequencing problem | |
| Jahanshahi et al. | A deep reinforcement learning approach for the meal delivery problem | |
| WO2019090874A1 (en) | Single vehicle scheduling method for cargo collection and delivery | |
| CN109214756A (en) | Based on ant group algorithm and the complete vehicle logistics dispatching method and device of hierarchy optimization, storage medium, terminal | |
| CN104008428B (en) | Service of goods requirement forecasting and resource preferred disposition method | |
| Wang et al. | Distributionally robust chance-constrained programming for multi-period emergency resource allocation and vehicle routing in disaster response operations | |
| CN115759917A (en) | Logistics path planning method based on improved mixed ant colony algorithm | |
| CN113935452A (en) | Distribution center goods picking path planning method based on ant colony algorithm and genetic algorithm fusion | |
| CN113850550A (en) | Intelligent catering order dispatching method, storage medium and computer for college park | |
| Jiang | Solving multi-robot picking problem in warehouses: a simulation approach | |
| Peng et al. | A strawberry harvest‐aiding system with crop‐transport collaborative robots: Design, development, and field evaluation | |
| CN117314283A (en) | Material distribution method, device and system for mixed flow assembly workshop and storage medium | |
| CN114926109A (en) | Warehouse site selection method | |
| CN117910917B (en) | Logistics transportation process quality management system and method based on artificial intelligence | |
| CN117709836A (en) | Management system of digital logistics supply chain | |
| CN115222340A (en) | Goods scheduling management method based on intelligent warehousing and related device | |
| CN115423414A (en) | Tool and method for generating distribution scheme of goods space of maintenance equipment warehouse | |
| Harman et al. | Multi-agent task allocation for harvest management | |
| CN114707921A (en) | Agent distribution decision and inventory management optimization system based on GA-BP algorithm |
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 |