CN110210666A - Intelligent recommendation method, system and storage medium based on vehicle and goods matching - Google Patents

Intelligent recommendation method, system and storage medium based on vehicle and goods matching Download PDF

Info

Publication number
CN110210666A
CN110210666A CN201910466393.8A CN201910466393A CN110210666A CN 110210666 A CN110210666 A CN 110210666A CN 201910466393 A CN201910466393 A CN 201910466393A CN 110210666 A CN110210666 A CN 110210666A
Authority
CN
China
Prior art keywords
vehicle
goods
matching
cargo
rate
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.)
Granted
Application number
CN201910466393.8A
Other languages
Chinese (zh)
Other versions
CN110210666B (en
Inventor
凌海峰
傅怡
刘业政
姜元春
孙见山
孙春华
陈夏雨
钱洋
孙舫
杨雪儿
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hefei Luyang Technology Innovation Group Co.,Ltd.
Original Assignee
Hefei University of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hefei University of Technology filed Critical Hefei University of Technology
Priority to CN201910466393.8A priority Critical patent/CN110210666B/en
Publication of CN110210666A publication Critical patent/CN110210666A/en
Application granted granted Critical
Publication of CN110210666B publication Critical patent/CN110210666B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083—Shipping
    • G06Q10/0835—Relationships between shipper or supplier and carriers

Abstract

The present invention provides a kind of intelligent recommendation method, system and storage medium based on vehicle and goods matching, is related to logistics technology.The following steps are included: obtaining vehicle goods data；Default vehicle and goods matching rate；The rate of empty ride of preset vehicle transport cargo；The charging ratio of preset vehicle transport cargo；Matching income based on the rate of empty ride and the charging ratio preset vehicle；Vehicle and goods matching target is preset based on the matching rate and the matching income, maximizes the matching rate and the matching income weighted sum；The constraint condition of default vehicle goods supply-demand mode model；Vehicle goods supply-demand mode model is constructed based on the vehicle and goods matching target and the constraint condition；The optimal solution of the vehicle goods supply-demand mode model is obtained based on ant colony optimization method.The present invention solves the problems, such as newly " zero recommends " occur due to lacking historical data into the vehicle in market.

Description

Intelligent recommendation method, system and storage medium based on vehicle and goods matching
Technical field
The present invention relates to logistics technology, and in particular to a kind of intelligent recommendation method based on vehicle and goods matching, system and Storage medium.
Background technique
The high speed development of internet especially mobile Internet has pushed the adjustment and reconstruct of social resources.Logistic resources It shares as a shared economic branch in logistics field, mainly includes vehicle transport power and information of freight source, in recent years, logistics row There is the shared logistics upsurge based on vehicle and goods matching in industry, by sharing vehicle goods resource, realizes goods stock and freight demand Shared matching.
The existing method for solving the problems, such as vehicle goods supply-demand mode is mainly the vehicle and goods matching based on assessment indicator system.It is based on The vehicle and goods matching of assessment indicator system carries out vehicle and goods matching recommendation by obtaining a large amount of associated traffic data.
However will appear outstanding resource in the prior art and be always recommended, and the vehicle in market is had just enter into due to lacking history Data and cannot recommend, there is a situation where " zero recommend ".
Summary of the invention
(1) the technical issues of solving
In view of the deficiencies of the prior art, the intelligent recommendation method that the present invention provides a kind of based on vehicle and goods matching, system and Storage medium solves the problems, such as newly " zero recommends " occur due to lacking historical data into the vehicle in market.
(2) technical solution
In order to achieve the above object, the present invention is achieved by the following technical programs:
A kind of intelligent recommendation method based on vehicle and goods matching, the method are executed by computer, comprising the following steps:
S1, vehicle goods data are obtained, the vehicle goods data include: the transportation demand of Che Yuanfang transport capacity data, source of goods side Data, vehicle are at a distance from cargo, the distance of goods handling；
S2, vehicle and goods matching rate is preset based on vehicle number to be matched and cargo number to be matched；
Based on the vehicle at a distance from cargo and the distance preset vehicle of the goods handling transport cargo rate of empty ride； Charging ratio based on the transportation movement requirements data preset vehicle of the Che Yuanfang transport capacity data and source of goods side transport cargo； Matching income based on the rate of empty ride and the charging ratio preset vehicle；
Vehicle and goods matching target is preset based on the matching rate and the matching income, receives the matching rate and the matching The weighted sum of benefit maximizes；
The constraint condition of S3, default vehicle goods supply-demand mode model；
S4, vehicle goods supply-demand mode model is constructed based on the vehicle and goods matching target and the constraint condition, the vehicle goods supplies Need Matching Model for obtaining vehicle and goods matching scheme；
S5, the optimal solution that the vehicle goods supply-demand mode model is obtained based on ant colony optimization method, the optimal solution are optimal Vehicle and goods matching scheme.
Preferably, in step s 2, the default vehicle and goods matching rate, comprising:
One between setting vehicle and cargo matches are as follows:
All matching xkiThe matrix V CM of composition are as follows:
Vehicle and goods matching rate are as follows:
Wherein:
R is matching rate；
xkiOne between vehicle and cargo matches；
K is vehicle number to be matched；
I is cargo number to be matched.
Preferably, in step s 2, the matching income of the preset vehicle, comprising:
The rate of empty ride of preset vehicle transport cargo:
Wherein:
UR is rate of empty ride；
xkiOne between vehicle and cargo matches；
K is vehicle number to be matched；
I is cargo number to be matched；
DkiFor vehicle vkPresent position and cargo ciThe distance of position；
LiFor cargo ciDeparture place is at a distance from destination；
The charging ratio of preset vehicle transport cargo:
Wherein:
LR is charging ratio；
xkiOne between vehicle and cargo matches；
K is vehicle number to be matched；
I is cargo number to be matched；
bkFor the transport capacity of kth vehicle；
diFor the transportation demand of i-th of cargo；
The matching income of the vehicle are as follows:
O=w3UR+w4LR
Wherein:
O is matching income；
UR is vehicle rate of empty ride；
LR is vehicle loading rate；
w3It is platform policymaker to the preference of rate of empty ride index；
w4It is platform policymaker to the preference of charging ratio index；
w3、w4∈ [0,1], w3+w4=1.
Preferably, in step s 2, the vehicle and goods matching target are as follows:
Max Z=w1R+w2O
Wherein:
Max Z is indicated to maximize matching rate and is matched the weighted sum of income；
w1Preference of the platform policymaker to matching rate index；
w2Preference of the platform policymaker to matching proceeds indicatior；
R is matching rate；
O is matching income；
w1、w2∈ [0,1], w1+w2=1.
Preferably, the constraint condition includes:
Condition 1: each car at most matches MIA cargo indicates are as follows:
Condition 2: each cargo at most matches MKVehicle indicates are as follows:
The total weight for the cargo that 3 each car of condition is recommended is no more than g times of truckload, indicates are as follows:
Condition 4: the actual transportation time of cargo is no more than the delivery time that the owner of cargo requires, and indicates are as follows:
Condition 5: the weight for the cargo in each scheme that each car is recommended is no more than the load-carrying of vehicle, indicates are as follows:
Wherein:
xkiOne between vehicle and cargo matches；
K is vehicle number to be matched；
I is cargo number to be matched；
MIIt can the matched cargo number upper limit for each car；
MKIt can the matched vehicle number upper limit for each cargo；
G is vehicle transport ability spreading parameter；
bkFor the transport capacity of kth vehicle；
diFor the transportation demand of i-th of cargo；
DkiFor vehicle vkPresent position and cargo ciThe distance of position；
LiFor cargo ciDeparture place is at a distance from destination；
V is the travel speed of vehicle；
TiThe time of destination is sent to for source of goods side's requirement cargo.
Preferably, in step s 5, the acquisition methods of the optimal solution include:
A1, by parameter initialization, comprising: ant maximum number of iterations MaxIt, ant number nAnt；Optimal value bestZ is 0, optimal solution bestSol are the full 0 matrix of K row I column；
A2, the solution space for constructing ant colony optimization method, obtain the matching scheme of a-th of ant in nth iteration, thus To the optimal solution of preceding n times iteration；
A3, judge whether n >=3 are true, if so, executing step a4；Otherwise, step a5 is executed；
A4, judge whether first three generation is maturity state, if so, executing step a7；It is no to then follow the steps a5；
A5, looking for food in conjunction with bacterium is clustered with k-means；
A6, judge ant colony state, and be adjusted parameter according to state, execute step a8；
A7, parameter is adjusted by chaology；
After a8, an iteration, according to the match condition between vehicle goods, pheromones are updated；
A9, judge whether to reach maximum number of iterations, if not up to maximum number of iterations, n+1 is assigned to n, return The a2；Otherwise optimal solution is exported, as optimal vehicle and goods matching scheme.
Preferably, in the a2, comprising the following steps:
B1, initialization the number of iterations n=1；
B2, initialization ant number a=1；
B3, initialization vehicle number k=1；
B4, it accesses to cargo, is generated in nth iteration a-th using constraint condition 2, condition 4 and condition 5 one by one The v of antkVehicle is corresponding allows to participate in matched cargo set
B5, foundation vehicle vkWith cargo ciBetween pheromone concentration, calculate vehicle vkWith cargo ciBetween matching it is general Rate executes roulette algorithm, fromThe middle next cargo c of selectioniRecommend vkVehicle, until being unsatisfactory for constraint condition 1 and condition 3 its any one of i.e. stop；
B6, judge whether k < K is true, if so, k+1 is assigned to k, return to b4；Otherwise b7 is executed.
B7, the path according to ant, by connected vkAnd ciX in corresponding VCM matrixkiIt is assigned a value of xki=1, it obtains The matching scheme of a-th of ant, is denoted as in nth iteration
B8, the target function value for calculating a-th of ant in nth iterationIfThen willAssignment It, will be corresponding to bestZMatrix is assigned to bestSol；Otherwise b9 is executed；
B9, judge whether a < nAnt is true, if so, executing S3, a+1 is otherwise assigned to a, returns to b3.
A kind of intelligent recommendation method system based on vehicle and goods matching, the system comprises computer, the computer includes:
At least one storage unit；
At least one processing unit；
Wherein, at least one instruction is stored at least one described storage unit, at least one instruction is by described At least one processing unit is loaded and is executed to perform the steps of
S1, vehicle goods data are obtained, the vehicle goods data include: the transportation demand of Che Yuanfang transport capacity data, source of goods side Data, vehicle are at a distance from cargo, the distance of goods handling；
S2, vehicle and goods matching rate is preset based on vehicle number to be matched and cargo number to be matched；
Based on the vehicle at a distance from cargo and the distance preset vehicle of the goods handling transport cargo rate of empty ride； Charging ratio based on the transportation movement requirements data preset vehicle of the Che Yuanfang transport capacity data and source of goods side transport cargo； Matching income based on the rate of empty ride and the charging ratio preset vehicle；
Vehicle and goods matching target is preset based on the matching rate and the matching income, receives the matching rate and the matching The weighted sum of benefit maximizes；
The constraint condition of S3, default vehicle goods supply-demand mode model；
S4, vehicle goods supply-demand mode model is constructed based on the vehicle and goods matching target and the constraint condition, the vehicle goods supplies Need Matching Model for obtaining vehicle and goods matching scheme；
S5, the optimal solution that the vehicle goods supply-demand mode model is obtained based on ant colony optimization method, the optimal solution are optimal Vehicle and goods matching scheme.
Preferably, in step s 2, the vehicle and goods matching target are as follows:
Max Z=w1R+w2O
Wherein:
MaxZ is indicated to maximize matching rate and is matched the weighted sum of income；
w1Preference of the platform policymaker to matching rate index；
w2Preference of the platform policymaker to matching proceeds indicatior；
R is matching rate；
O is matching income；
w1、w2∈ [0,1], w1+w2=1.
A kind of computer readable storage medium is stored at least one instruction on the medium, at least described instruction by Processor is loaded and is executed to realize such as above-mentioned method.
(3) beneficial effect
The present invention provides a kind of intelligent recommendation method, system and storage medium based on vehicle and goods matching.With the prior art Compare, have it is following the utility model has the advantages that
The present invention presets vehicle and goods matching rate by obtaining vehicle goods data, based on vehicle goods data；Vehicle is preset based on vehicle goods data Transport cargo rate of empty ride and charging ratio, the matching income based on rate of empty ride and charging ratio preset vehicle；Based on matching rate and It matches income and presets vehicle and goods matching target, maximize matching rate and matching income weighted sum；Default vehicle goods supply-demand mode model Constraint condition；Vehicle goods supply-demand mode model is constructed based on vehicle and goods matching target and constraint condition；It is obtained based on ant colony optimization method The optimal solution of pick-up goods supply-demand mode model, optimal solution are optimal vehicle and goods matching scheme.The present invention is that user recommends multiple vehicles Source and the source of goods are conducive to the development of logistics activity in reality, avoid newly going out into the vehicle in market due to lacking historical data The case where existing " zero recommends ", so that vehicle goods both sides in part go on smoothly service interfacing in reality, so that the rate of empty ride of lorry is reduced, Social resources utilization rate maximizes.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with It obtains other drawings based on these drawings.
Fig. 1 is the flow chart of intelligent recommendation method of the one embodiment of the invention based on vehicle and goods matching；
Fig. 2 is the flow chart of intelligent recommendation method of the another embodiment of the present invention based on vehicle and goods matching；
Fig. 3 is the optimizing structural schematic diagram that ant colony optimization algorithm solves vehicle goods supply-demand mode problem in the embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, to the technology in the embodiment of the present invention Scheme is clearly and completely described, it is clear that and described embodiments are some of the embodiments of the present invention, rather than whole Embodiment.Based on the embodiments of the present invention, those of ordinary skill in the art are obtained without creative efforts The every other embodiment obtained, shall fall within the protection scope of the present invention.
The embodiment of the present application is solved by providing a kind of intelligent recommendation method, system and storage medium based on vehicle and goods matching Due to lacking historical data there is the problem of " zero recommend " in the new vehicle into market of having determined, realizes vehicle goods in part in reality Both sides go on smoothly service interfacing, to reduce the rate of empty ride of lorry, social resources utilization rate is maximized.
Technical solution in the embodiment of the present application is in order to solve the above technical problems, general thought is as follows:
The embodiment of the present invention presets vehicle and goods matching rate by obtaining vehicle goods data, based on vehicle goods data；Based on vehicle goods data Preset vehicle transports the rate of empty ride and charging ratio of cargo, the matching income based on rate of empty ride and charging ratio preset vehicle；Based on Vehicle and goods matching target is preset with rate and matching income, maximizes matching rate and matching income weighted sum；Default vehicle goods supply and demand Constraint condition with model；Vehicle goods supply-demand mode model is constructed based on vehicle and goods matching target and constraint condition；Based on ant group optimization Method obtains the optimal solution of vehicle goods supply-demand mode model, and optimal solution is optimal vehicle and goods matching scheme.The embodiment of the present invention is to use Multiple vehicle sources and the source of goods are recommended in family, are conducive to the development of logistics activity in reality, avoid newly entering the vehicle in market due to lacking Historical data and there is the case where " zero recommend " so that vehicle goods both sides in part go on smoothly service interfacing in reality, to reduce The rate of empty ride of lorry, social resources utilization rate maximize.
In order to better understand the above technical scheme, in conjunction with appended figures and specific embodiments to upper Technical solution is stated to be described in detail.
The existing method for solving vehicle goods supply-demand mode problem is broadly divided into semantic-based vehicle and goods matching and based on evaluation The vehicle and goods matching of index system is these two types of.Wherein semantic-based vehicle and goods matching needs to establish the semantic knowledge mould of vehicle goods information Type, but since existing logistics information lacks unified standardized administration, the reasoning process of model is complex, answers in reality It is wideless with range.Vehicle and goods matching based on assessment indicator system needs to obtain a large amount of associated traffic data, be easy to cause just into The case where entering the vehicle in market cannot recommend due to shortage index of correlation.
The embodiment of the present invention provides a kind of intelligent recommendation method based on vehicle and goods matching, as shown in Figure 1, the above method is by counting Calculation machine executes, comprising the following steps:
S1, vehicle goods data are obtained, the vehicle goods data include: the transportation demand of Che Yuanfang transport capacity data, source of goods side Data, vehicle are at a distance from cargo and the distance of goods handling；
S2, vehicle and goods matching rate is preset based on vehicle number to be matched and cargo number to be matched；
Based on the vehicle at a distance from cargo and the distance preset vehicle of the goods handling transport cargo rate of empty ride； Charging ratio based on the transportation movement requirements data preset vehicle of the Che Yuanfang transport capacity data and source of goods side transport cargo； Matching income based on the rate of empty ride and the charging ratio preset vehicle；
Vehicle and goods matching target is preset based on the matching rate and the matching income, receives the matching rate and the matching The weighted sum of benefit maximizes；
The constraint condition of S3, default vehicle goods supply-demand mode model；
S4, vehicle goods supply-demand mode model is constructed based on the vehicle and goods matching target and the constraint condition, the vehicle goods supplies Need Matching Model for obtaining vehicle and goods matching scheme；
S5, the optimal solution that the vehicle goods supply-demand mode model is obtained based on ant colony optimization method, the optimal solution are optimal Vehicle and goods matching scheme.
The embodiment of the present invention presets vehicle and goods matching rate by obtaining vehicle goods data, based on vehicle goods data；Based on vehicle goods data Preset vehicle transports the rate of empty ride and charging ratio of cargo, the matching income based on rate of empty ride and charging ratio preset vehicle；Based on Vehicle and goods matching target is preset with rate and matching income, maximizes matching rate and matching income weighted sum；Default vehicle goods supply and demand Constraint condition with model；Vehicle goods supply-demand mode model is constructed based on vehicle and goods matching target and constraint condition；Based on ant group optimization Method obtains the optimal solution of vehicle goods supply-demand mode model, and optimal solution is optimal vehicle and goods matching scheme.The embodiment of the present invention is to use Multiple vehicle sources and the source of goods are recommended in family, are conducive to the development of logistics activity in reality, avoid newly entering the vehicle in market due to lacking Historical data and there is the case where " zero recommend " so that vehicle goods both sides in part go on smoothly service interfacing in reality, to reduce The rate of empty ride of lorry, social resources utilization rate maximize.
Each step is illustrated below.
In step sl, vehicle goods data are obtained.Specifically, vehicle goods data include: vehicle source number formulary evidence, Che Yuanfang transport capacity Data, source of goods number formulary evidence, the transportation movement requirements data of source of goods side, vehicle are at a distance from cargo, the distance of goods handling.
Wherein, above-mentioned vehicle source number formulary evidence are as follows:
V={ v1,v2,...,vk,...,vK}
Wherein:
vkIndicate k-th of Che Yuanfang；
Above-mentioned Che Yuanfang transport capacity data are bk, k ∈ { 1,2 ..., K }
Above-mentioned source of goods number formulary evidence are as follows:
C={ c1,c2,...,ci,...,cI}
Wherein:
ciIndicate i-th of source of goods side；
Above-mentioned transportation movement requirements data is di, i ∈ { 1,2 ..., I }.
Set vehicle vkPresent position and cargo ciThe distance of position is Dki, cargo ciDeparture place and destination Distance Li。
In step s 2, specifically:
S201, vehicle and goods matching rate is preset based on vehicle number to be matched and cargo number to be matched；
Specifically, in embodiments of the present invention, defining the time T that source of goods side requires cargo to be sent to destinationi。
One between setting vehicle and cargo matches as xki；
By all matching xkiThe matrix V CM of composition is a matching scheme of vehicle and goods matching problem:
VCM is the matching scheme that each row vector corresponds to each vehicle, each column vector corresponds to each cargo fortune The matching scheme of defeated demand.
Define the calculation formula of VCM matching rate R are as follows:
Wherein:
xkiOne between vehicle and cargo matches；
K is vehicle number to be matched；
I is cargo number to be matched.
The matching income of S202, preset vehicle.
It specifically includes:
The rate of empty ride of S2021, preset vehicle transport cargo.
Wherein:
UR is rate of empty ride；
xkiOne between vehicle and cargo matches；
K is vehicle number to be matched；
I is cargo number to be matched；
DkiFor vehicle vkPresent position and cargo ciThe distance of position；
LiFor cargo ciDeparture place is at a distance from destination.
The charging ratio of S2022, preset vehicle transport cargo.
Wherein:
LR is charging ratio；
xkiOne between vehicle and cargo matches；
K is vehicle number to be matched；
I is cargo number to be matched；
bkFor the transport capacity of kth vehicle；
diFor the transportation demand of i-th of cargo.
The matching income of S2023, preset vehicle.
O=w3UR+w4LR (4)
Wherein:
O is matching income；
UR is vehicle rate of empty ride；
LR is vehicle loading rate；
w3It is platform policymaker to the preference of rate of empty ride index；
w4It is platform policymaker to the preference of charging ratio index；
w3、w4∈ [0,1], w3+w4=1.
S203, default vehicle and goods matching target.
Specifically, constructing the target letter of vehicle and goods matching model to maximize matching income and matching rate weighted sum as target Number:
Max Z=w1R+w2O (5)
Wherein:
MaxZ is the weighted sum for maximizing matching rate and matching income；
w1It is platform policymaker to the preference of matching rate index；
w2It is platform policymaker to the preference of matching proceeds indicatior；
R is VCM matching rate；
O is matching income；
And w1、w2∈ [0,1], w1+w2=1.
In step s3, the constraint condition of vehicle goods supply-demand mode model is preset.
Specifically include: the quantity Matching relationship of vehicle and cargo, cargo and vehicle load relationship, cargo requirement be sent to when Between.
Specifically, constraint condition are as follows:
Formula (6) indicates that each car at most matches MIA cargo；
Formula (7) indicates that each cargo at most matches MKVehicle；
The total weight that formula (8) is represented to the cargo of each car recommendation is no more than g times of truckload；
Formula (9) indicates that the actual transportation time of cargo is no more than the delivery time that the owner of cargo requires；
The weight for the cargo that formula (10) is represented in each scheme of each car recommendation is no more than the load-carrying of vehicle.
Wherein:
xkiOne between vehicle and cargo matches；
K is vehicle number to be matched；
I is cargo number to be matched；
MIIt can the matched cargo number upper limit for each car；
MKIt can the matched vehicle number upper limit for each cargo；
G is vehicle transport ability spreading parameter；
bkFor the transport capacity of kth vehicle；
diFor the transportation demand of i-th of cargo；
DkiFor vehicle vkPresent position and cargo ciThe distance of position；
LiFor cargo ciDeparture place is at a distance from destination；
V is the travel speed of vehicle；
TiThe time of destination is sent to for source of goods side's requirement cargo.
In step s 4, vehicle goods supply-demand mode model is constructed based on above-mentioned vehicle and goods matching target and above-mentioned constraint condition, on Vehicle goods supply-demand mode model is stated for obtaining vehicle and goods matching scheme.
In step s 5, optimal vehicle goods is obtained to above-mentioned vehicle goods supply-demand mode model solution based on ant colony optimization method With scheme.
Specifically, as shown in figure 3, method for solving the following steps are included:
A1, by parameter initialization；
Specifically, including: initialization ant maximum number of iterations MaxIt, ant number nAnt, the important journey of pheromones is defined Spend factor-alpha, heuristic function significance level factor-beta, pheromones volatilization factor ρ；Initializing optimal value bestZ is 0, optimal solution BestSol is the full 0 matrix of K row I column.
A2, the solution space for constructing ant colony optimization method, obtain the matching scheme of a-th of ant in nth iteration, thus To the optimal solution of preceding n times iteration；
Specifically, step a2 the following steps are included:
B1, initialization the number of iterations n=1；
B2, initialization ant number a=1；
B3, initialization vehicle number k=1；
B4, it accesses to cargo, is generated in nth iteration using constraint equation (7), formula (9) and formula (10) one by one The v of a-th of antkVehicle is corresponding allows to participate in matched cargo set
B5, foundation vehicle vkWith cargo ciBetween pheromone concentration, calculate vehicle vkWith cargo ciBetween matching it is general Rate executes roulette algorithm, fromThe middle next cargo c of selectioniRecommend vkVehicle, until being unsatisfactory for constraint condition Any one of its of formula (6) and formula (8) stops；
B6, judge whether k < K is true, if so, k+1 is assigned to k, return to b4；Otherwise b7 is executed.
B7, the path according to ant, by connected vkAnd ciX in corresponding VCM matrixkiIt is assigned a value of xki=1, it obtains The matching scheme of a-th of ant, is denoted as in nth iteration
B8, the target function value for calculating a-th of ant in nth iterationIfThen willAssignment It, will be corresponding to bestZMatrix is assigned to bestSol；Otherwise b9 is executed；
B9, judge whether a < nAnt is true, if so, executing a3, a+1 is otherwise assigned to a, returns to b3.
A3, judge whether n >=3 are true, if so, executing step a4；Otherwise, step a5 is executed；
A4, judge whether first three generation is maturity state, if so, executing step a7；It is no to then follow the steps a5；
A5, looking for food in conjunction with bacterium is clustered with k-means；The following steps are included:
C101, initialization bacterium number are S, and chemotactic number is Nc, and the maximum step number of one-way movement is Ns in chemotactic operation, The step-length that single bacterium advances is sc；
C102, by the matching result of nAnt ant of the n-th generationIt is separately converted to 1 row, The vector of K × I column, and nAnt row, the matrix sam of K × I column are formed, and be normalized；
C103,3 matching schemes are randomly selected from the sam matrix after normalized, and (a line is a match party Case), it is denoted as sam1,sam2,sam3, as 3 cluster centres；
C104, initialization chemotactic frequency n c=1；
C105, the current bacterial population s=1 of initialization；
C106, s-th of bacterium is initialized in present position P (s, nc)=[sam of n-th c times chemotactic1,sam2,sam3], P (s, nc) is the vector being spliced by 3 initial cluster centers；Each remaining matching scheme is calculated in sam matrix to 3 The Euclidean distance at a center, and the smallest central point of selected distance is included into such；All matching schemes are calculated to center where it The sum of the distance of point, is denoted as s-th of bacterium in the fitness value J (s, nc) of n-th c times chemotactic；
C107, s-th of bacterium is overturn using formula (11), obtains s-th of bacterium in the travelling side of n-th c times chemotactic To
Wherein；
Δ (s, nc) indicates s-th of bacterium [- the 1 of n-th c times chemotactic,1] random vector；
ΔT(s, nc) indicates the transposition of Δ (s, nc)；
C108, the unidirectional steps of random walk ns=0 of initialization；
C109, s-th of bacterium is obtained using formula (12) in the present position P (s, nc+1) of n-th c+1 times chemotactic:
Wherein:
C (s) is the one step of bacterium travelling；
P (s, nc) s-th of bacterium is in the present position of n-th c times chemotactic；
Swimming direction of s-th of bacterium in n-th c times chemotactic；
C110, fitness value J (s, nc+1) is calculated, and judges whether J (s, nc) < J (s, nc+1) is true, if so, then P (s, nc+1) is assigned to P (s, nc), J (s, nc+1) is assigned to J (s, nc)；Otherwise, ns=N is enableds；
C111, it enables ns+1 be assigned to ns, judges ns < NsIt is whether true, if so, then return step c109 is executed；It is no Then, step c112 is executed；
C112, it enables s+1 be assigned to s, judges whether s < S is true, if so, then return step c106 is executed；Otherwise, it holds Row step c113；
C113, it enables nc+1 be assigned to nc, judges nc < NcIt is whether true, if so, then return step c105 is executed；It is no Then, step c201 is executed；
C201, the minimum fitness value J (s, nc) by finally obtained s bacterium, therefrom choose the smallest fitness value It is denoted as Jbest (s, nc), corresponding bacterium position is denoted as Pbest (s, nc)；
Pbest (s, nc) is split as three cluster centres by c202 again, the initial center point as k-means cluster；
C203 initializes maximum number of iterations Maxgn；
C204 initializes the number of iterations gn=1；
C205 calculates in sam matrix that each scheme is to the distance of central point, and selected distance minimum value is included into such；
C206 recalculates the central point of every one kind；
C207 judges gn < Maxgn, if so, gn+1 is assigned to gn, otherwise return step c205 terminates to cluster, defeated Cluster result out.
A6, judge ant colony state, and be adjusted parameter according to state, execute step a8；The a6 the following steps are included:
D1, definition LS indicate largest cluster size, and SS indicates the smallest cluster size of scale, and Zbest is indicated most The scale of class where big target function value, the scale of class where Zworst indicates minimum target functional value；
D2, judge Zworst=LS, if so, being original state, parameter alpha, β, ρ are adjusted using formula (13)-(15) It is whole, and parameter value range α ∈ [0.1,1.5] is set, β ∈ [0.1,1.5], ρ ∈ [0.02,0.08], if the ginseng after adjustment Number exceeds the upper (lower) boundary of value range, then takes the upper (lower) boundary in corresponding section as value adjusted, execute step a8；It is no Then follow the steps d3；
α(n+1)=α(n)-(rand×1.2) (13)
β(n+1)=β(n)-(rand×1.0) (14)
ρ(n+1)=ρ(n)-(rand×0.1) (15)
Wherein:
Rand is the random number on [0,1] section；
D3, judge Zbest=LS, if so, being maturity state, parameter alpha, β, ρ are adjusted using formula (16)-(18) It is whole, execute step a8；It is no to then follow the steps d4；
α(n+1)=α(n)+(rand×1.2) (16)
β(n+1)=β(n)+(rand×1.0) (17)
ρ(n+1)=ρ(n)+(rand×0.1) (18)
D4, it is half ripe state, parameter alpha, β, ρ is adjusted using formula (19)-(21), executes step a8；
α(n+1)=α(n)-(rand×0.5) (19)
β(n+1)=β(n)-(rand×0.5) (20)
ρ(n+1)=ρ(n)-(rand×0.05) (21)。
A7, parameter is adjusted by chaology；The a7 the following steps are included:
E1, unitization processing is carried out respectively to parameter alpha, β, ρ；
E2, parameter alpha, β, ρ are adjusted using formula (22)-(24)；
α(n+1)=μ × α(n)×(1-α(n)) (22)
β(n+1)=μ × β(n)×(1-β(n)) (23)
ρ(n+1)=μ × ρ(n)×(1-ρ(n)) (24)
Wherein:
μ is attractor；
E3, it carries out the recovery operation after unitization processing respectively to parameter alpha, β, ρ, executes step a8.
After a8, an iteration, according to the match condition between vehicle goods, pheromones are updated；
A9, judge whether to reach maximum number of iterations, if not up to maximum number of iterations, n+1 is assigned to n, return The a2；Otherwise optimal solution is exported, as optimal vehicle and goods matching scheme.
A kind of intelligent recommendation system based on vehicle and goods matching is also proposed in the embodiment of the present invention, the system comprises calculating Machine, the computer include:
At least one storage unit；
At least one processing unit；
Wherein, at least one instruction is stored at least one described storage unit, at least one instruction is by described At least one processing unit is loaded and is executed to perform the steps of
S1, vehicle goods data are obtained, the vehicle goods data include: the transportation demand of Che Yuanfang transport capacity data, source of goods side Data, vehicle are at a distance from cargo and the distance of goods handling；
S2, vehicle and goods matching rate is preset based on vehicle number to be matched and cargo number to be matched；
Based on the vehicle at a distance from cargo and the distance preset vehicle of the goods handling transport cargo rate of empty ride； Charging ratio based on the transportation movement requirements data preset vehicle of the Che Yuanfang transport capacity data and source of goods side transport cargo； Matching income based on the rate of empty ride and the charging ratio preset vehicle；
Vehicle and goods matching target is preset based on the matching rate and the matching income, receives the matching rate and the matching The weighted sum of benefit maximizes；
The constraint condition of S3, default vehicle goods supply-demand mode model；
S4, vehicle goods supply-demand mode model is constructed based on the vehicle and goods matching target and the constraint condition, the vehicle goods supplies Need Matching Model for obtaining vehicle and goods matching scheme；
S5, the optimal solution that the vehicle goods supply-demand mode model is obtained based on ant colony optimization method, the optimal solution are optimal Vehicle and goods matching scheme.
It will be appreciated that above-mentioned recommender system provided in an embodiment of the present invention is corresponding with above-mentioned recommended method, it is related The part such as explanation, citing, beneficial effect of content can refer to the corresponding contents in the intelligent recommendation method based on vehicle and goods matching, It is not repeating herein.
The embodiment of the present invention also provides a kind of computer readable storage medium, is stored at least one in above-mentioned storage medium Instruction, an at least the above instruction are loaded by processor and are executed to realize such as the above method.
In conclusion compared with prior art, have it is following the utility model has the advantages that
The embodiment of the present invention presets vehicle and goods matching rate by obtaining vehicle goods data, based on vehicle goods data；Based on vehicle goods data Preset vehicle transports the rate of empty ride and charging ratio of cargo, the matching income based on rate of empty ride and charging ratio preset vehicle；Based on Vehicle and goods matching target is preset with rate and matching income, maximizes matching rate and matching income weighted sum；Default vehicle goods supply and demand Constraint condition with model；Vehicle goods supply-demand mode model is constructed based on vehicle and goods matching target and constraint condition；Based on ant group optimization Method obtains the optimal solution of vehicle goods supply-demand mode model, and optimal solution is optimal vehicle and goods matching scheme.The embodiment of the present invention is to use Multiple vehicle sources and the source of goods are recommended in family, are conducive to the development of logistics activity in reality, avoid newly entering the vehicle in market due to lacking Historical data and there is the case where " zero recommend " so that vehicle goods both sides in part go on smoothly service interfacing in reality, to reduce The rate of empty ride of lorry, social resources utilization rate maximize.
The embodiment of the present invention combines the chemotactic step that bacterium is looked for food with k-means algorithm, obtains to ant colony iteration Vehicle and goods matching scheme is clustered.Initial cluster center is adjusted by bacterium chemotactic, can prevent cluster from falling into local optimum, effectively Improve cluster result, be conducive to the judgement of subsequent ant colony state, improves vehicle goods Rapid matching.
The embodiment of the present invention carries out parameter adjustment, the initial shape according to locating for ant colony by the judgement based on ant colony state State, half ripe state, maturity state carry out the dynamic adjustment of different amplitudes to parameter alpha, β, ρ, so that algorithm fast convergence respectively To near globally optimal solution, effectively accelerate convergence rate.
The embodiment of the present invention is by carrying out parameter adjustment based on chaology, so that the parameter alpha of grey iterative generation, β, ρ are in A kind of pseudorandom state, prevents algorithm from falling into local optimum, enhances the ability of algorithm global search, improves vehicle goods quick Match, obtains optimum matching scheme.
It should be noted that through the above description of the embodiments, those skilled in the art can be understood that It can be realized by means of software and necessary general hardware platform to each embodiment.Based on this understanding, above-mentioned skill Substantially the part that contributes to existing technology can be embodied in the form of software products art scheme in other words, the calculating Machine software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including some instructions are used So that computer equipment (can be personal computer, server or the network equipment etc.) execute each embodiment or Method described in certain parts of person's embodiment.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that implementation of the invention Example can be practiced without these specific details.In some instances, well known method, structure is not been shown in detail And technology, so as not to obscure the understanding of this specification.
Herein, relational terms such as first and second and the like be used merely to by an entity or operation with it is another One entity or operation distinguish, and without necessarily requiring or implying between these entities or operation, there are any this reality Relationship or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to the packet of nonexcludability Contain, so that the process, method, article or equipment for including a series of elements not only includes those elements, but also including Other elements that are not explicitly listed, or further include for elements inherent to such a process, method, article, or device. In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including the element Process, method, article or equipment in there is also other identical elements.
The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to the foregoing embodiments Invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each implementation Technical solution documented by example is modified or equivalent replacement of some of the technical features；And these modification or Replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.

Claims (10)

1. a kind of intelligent recommendation method based on vehicle and goods matching, which is characterized in that the method is executed by computer, including following Step:
S1, obtain vehicle goods data, the vehicle goods data include: Che Yuanfang transport capacity data, source of goods side transportation movement requirements data, Vehicle is at a distance from cargo, the distance of goods handling；
S2, vehicle and goods matching rate is preset based on vehicle number to be matched and cargo number to be matched；
Based on the vehicle at a distance from cargo and the distance preset vehicle of the goods handling transport cargo rate of empty ride；It is based on The charging ratio of the transportation movement requirements data preset vehicle of the Che Yuanfang transport capacity data and source of goods side transport cargo；It is based on The matching income of the rate of empty ride and the charging ratio preset vehicle；
Vehicle and goods matching target is preset based on the matching rate and the matching income, makes the matching rate and the matching income Weighted sum maximizes；
The constraint condition of S3, default vehicle goods supply-demand mode model；
S4, vehicle goods supply-demand mode model, the vehicle goods supply and demand are constructed based on the vehicle and goods matching target and the constraint condition With model for obtaining vehicle and goods matching scheme；
S5, the optimal solution that the vehicle goods supply-demand mode model is obtained based on ant colony optimization method, the optimal solution are optimal vehicle goods Matching scheme.
2. recommended method as described in claim 1, which is characterized in that in step s 2, the default vehicle and goods matching rate, packet It includes:
One between setting vehicle and cargo matches are as follows:
All matching xkiThe matrix V CM of composition are as follows:
Vehicle and goods matching rate are as follows:
Wherein:
R is matching rate；
xkiOne between vehicle and cargo matches；
K is vehicle number to be matched；
I is cargo number to be matched.
3. recommended method as claimed in claim 2, which is characterized in that in step s 2, the matching of the preset vehicle is received Benefit, comprising:
The rate of empty ride of preset vehicle transport cargo:
Wherein:
UR is rate of empty ride；
xkiOne between vehicle and cargo matches；
K is vehicle number to be matched；
I is cargo number to be matched；
DkiFor vehicle vkPresent position and cargo ciThe distance of position；
LiFor cargo ciDeparture place is at a distance from destination；
The charging ratio of preset vehicle transport cargo:
Wherein:
LR is charging ratio；
xkiOne between vehicle and cargo matches；
K is vehicle number to be matched；
I is cargo number to be matched；
bkFor the transport capacity of kth vehicle；
diFor the transportation demand of i-th of cargo；
The matching income of the vehicle are as follows:
O=w3UR+w4LR
Wherein:
O is matching income；
UR is vehicle rate of empty ride；
LR is vehicle loading rate；
w3It is platform policymaker to the preference of rate of empty ride index；
w4It is platform policymaker to the preference of charging ratio index；
w3、w4∈ [0,1], w3+w4=1.
4. recommended method as claimed in claim 3, which is characterized in that in step s 2, the vehicle and goods matching target are as follows:
MaxZ=w1R+w2O
Wherein:
MaxZ is indicated to maximize matching rate and is matched the weighted sum of income；
w1Preference of the platform policymaker to matching rate index；
w2Preference of the platform policymaker to matching proceeds indicatior；
R is matching rate；
O is matching income；
w1、w2∈ [0,1], w1+w2=1.
5. recommended method as claimed in claim 4, which is characterized in that the constraint condition includes:
Condition 1: each car at most matches MIA cargo indicates are as follows:
Condition 2: each cargo at most matches MKVehicle indicates are as follows:
The total weight for the cargo that 3 each car of condition is recommended is no more than g times of truckload, indicates are as follows:
Condition 4: the actual transportation time of cargo is no more than the delivery time that the owner of cargo requires, and indicates are as follows:
Condition 5: the weight for the cargo in each scheme that each car is recommended is no more than the load-carrying of vehicle, indicates are as follows:
Wherein:
xkiOne between vehicle and cargo matches；
K is vehicle number to be matched；
I is cargo number to be matched；
MIIt can the matched cargo number upper limit for each car；
MKIt can the matched vehicle number upper limit for each cargo；
G is vehicle transport ability spreading parameter；
bkFor the transport capacity of kth vehicle；
diFor the transportation demand of i-th of cargo；
DkiFor vehicle vkPresent position and cargo ciThe distance of position；
LiFor cargo ciDeparture place is at a distance from destination；
V is the travel speed of vehicle；
TiThe time of destination is sent to for source of goods side's requirement cargo.
6. recommended method as claimed in claim 5, which is characterized in that in step s 5, the acquisition methods packet of the optimal solution It includes:
A1, by parameter initialization, comprising: ant maximum number of iterations MaxIt, ant number nAnt；Optimal value bestZ is 0, most Excellent solution bestSol is the full 0 matrix of K row I column；
A2, the solution space for constructing ant colony optimization method, obtain the matching scheme of a-th of ant in nth iteration, thus before obtaining The optimal solution of n times iteration；
A3, judge whether n >=3 are true, if so, executing step a4；Otherwise, step a5 is executed；
A4, judge whether first three generation is maturity state, if so, executing step a7；It is no to then follow the steps a5；
A5, looking for food in conjunction with bacterium is clustered with k-means；
A6, judge ant colony state, and be adjusted parameter according to state, execute step a8；
A7, parameter is adjusted by chaology；
After a8, an iteration, according to the match condition between vehicle goods, pheromones are updated；
A9, judge whether to reach maximum number of iterations, if not up to maximum number of iterations, n+1 is assigned to n, described in return a2；Otherwise optimal solution is exported, as optimal vehicle and goods matching scheme.
7. recommended method as claimed in claim 6, which is characterized in that in the a2, comprising the following steps:
B1, initialization the number of iterations n=1；
B2, initialization ant number a=1；
B3, initialization vehicle number k=1；
B4, it accesses one by one to cargo, generates a-th of ant in nth iteration using constraint condition 2, condition 4 and condition 5 VkVehicle is corresponding allows to participate in matched cargo set
B5, foundation vehicle vkWith cargo ciBetween pheromone concentration, calculate vehicle vkWith cargo ciBetween matching probability, execute Roulette algorithm, fromThe middle next cargo c of selectioniRecommend vkVehicle, until being unsatisfactory for constraint condition 1 and condition 3 its any one of i.e. stop；
B6, judge whether k < K is true, if so, k+1 is assigned to k, return to b4；Otherwise b7 is executed.
B7, the path according to ant, by connected vkAnd ciX in corresponding VCM matrixkiIt is assigned a value of xki=1, obtain n-th The matching scheme of a-th of ant, is denoted as in secondary iteration
B8, the target function value for calculating a-th of ant in nth iterationIfThen willIt is assigned to BestZ, will be correspondingMatrix is assigned to bestSol；Otherwise b9 is executed；
B9, judge whether a < nAnt is true, if so, executing S3, a+1 is otherwise assigned to a, returns to b3.
8. a kind of intelligent recommendation method system based on vehicle and goods matching, which is characterized in that the system comprises computer, the meter Calculation machine includes:
At least one storage unit；
At least one processing unit；
Wherein, be stored at least one instruction at least one described storage unit, at least one instruction by it is described at least One processing unit is loaded and is executed to perform the steps of
S1, obtain vehicle goods data, the vehicle goods data include: Che Yuanfang transport capacity data, source of goods side transportation movement requirements data, Vehicle is at a distance from cargo, the distance of goods handling；
S2, vehicle and goods matching rate is preset based on vehicle number to be matched and cargo number to be matched；
Based on the vehicle at a distance from cargo and the distance preset vehicle of the goods handling transport cargo rate of empty ride；It is based on The charging ratio of the transportation movement requirements data preset vehicle of the Che Yuanfang transport capacity data and source of goods side transport cargo；It is based on The matching income of the rate of empty ride and the charging ratio preset vehicle；
Vehicle and goods matching target is preset based on the matching rate and the matching income, makes the matching rate and the matching income Weighted sum maximizes；
The constraint condition of S3, default vehicle goods supply-demand mode model；
S4, vehicle goods supply-demand mode model, the vehicle goods supply and demand are constructed based on the vehicle and goods matching target and the constraint condition With model for obtaining vehicle and goods matching scheme；
S5, the optimal solution that the vehicle goods supply-demand mode model is obtained based on ant colony optimization method, the optimal solution are optimal vehicle goods Matching scheme.
9. recommender system as claimed in claim 8, which is characterized in that in step s 2, the vehicle and goods matching target are as follows:
Max Z=w1R+w2O
Wherein:
MaxZ is indicated to maximize matching rate and is matched the weighted sum of income；
w1Preference of the platform policymaker to matching rate index；
w2Preference of the platform policymaker to matching proceeds indicatior；
R is matching rate；
O is matching income；
w1、w2∈ [0,1], w1+w2=1.
10. a kind of computer readable storage medium, be stored at least one instruction on the medium, at least described instruction by Reason device is loaded and is executed to realize the method as described in claim 1.
CN201910466393.8A 2019-05-31 2019-05-31 Intelligent recommendation method, system and storage medium based on vehicle and goods matching Active CN110210666B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910466393.8A CN110210666B (en) 2019-05-31 2019-05-31 Intelligent recommendation method, system and storage medium based on vehicle and goods matching

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910466393.8A CN110210666B (en) 2019-05-31 2019-05-31 Intelligent recommendation method, system and storage medium based on vehicle and goods matching

Publications (2)

Publication Number Publication Date
CN110210666A true CN110210666A (en) 2019-09-06
CN110210666B CN110210666B (en) 2021-08-10

Family

ID=67789788

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910466393.8A Active CN110210666B (en) 2019-05-31 2019-05-31 Intelligent recommendation method, system and storage medium based on vehicle and goods matching

Country Status (1)

Country Link
CN (1) CN110210666B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111798172A (en) * 2020-05-26 2020-10-20 嘉兴亚航信息技术有限公司 Dangerous chemical transportation method based on idea of horse racing
CN113379356A (en) * 2021-07-02 2021-09-10 西北师范大学 Vehicle and goods matching method based on AHP-DBN
CN113705966A (en) * 2021-07-20 2021-11-26 重庆超体科技有限公司 Vehicle transportation scheduling method for meeting road load rate in closed plant area

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105976140A (en) * 2016-04-27 2016-09-28 大连海事大学 Real-time vehicle commodity matching method under large-scale streaming data environment
CN107862493A (en) * 2017-10-20 2018-03-30 广西大学 A kind of goods stock matching travels on the way the numerical value determination methods of goods nearby
CN109359771A (en) * 2018-10-11 2019-02-19 福建龙易配信息科技有限公司 A kind of line haul vehicle and goods matching algorithm based on big data

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105976140A (en) * 2016-04-27 2016-09-28 大连海事大学 Real-time vehicle commodity matching method under large-scale streaming data environment
CN107862493A (en) * 2017-10-20 2018-03-30 广西大学 A kind of goods stock matching travels on the way the numerical value determination methods of goods nearby
CN109359771A (en) * 2018-10-11 2019-02-19 福建龙易配信息科技有限公司 A kind of line haul vehicle and goods matching algorithm based on big data

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
凌海峰,谷俊辉: "带软时间窗的多车场开放式车辆调度", 《计算机工程与应用》 *
宋飞: "流式数据环境下车货信息匹配方法研究", 《中国优秀硕士学位论文全文数据库（电子期刊）经济与管理科学辑》 *
胡觉亮,邴聪,韩曙光: "基于TS算法的公路干线货运平台车货匹配研究", 《浙江理工大学学报(社会科学版)》 *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111798172A (en) * 2020-05-26 2020-10-20 嘉兴亚航信息技术有限公司 Dangerous chemical transportation method based on idea of horse racing
CN111798172B (en) * 2020-05-26 2023-07-18 嘉兴亚航信息技术有限公司 Dangerous chemical transportation method based on field-contraindicated horse racing concept
CN113379356A (en) * 2021-07-02 2021-09-10 西北师范大学 Vehicle and goods matching method based on AHP-DBN
CN113379356B (en) * 2021-07-02 2022-05-17 西北师范大学 Vehicle and goods matching method based on AHP-DBN
CN113705966A (en) * 2021-07-20 2021-11-26 重庆超体科技有限公司 Vehicle transportation scheduling method for meeting road load rate in closed plant area
CN113705966B (en) * 2021-07-20 2024-01-26 重庆超体科技有限公司 Vehicle transportation scheduling method for meeting road load rate in closed factory

Also Published As

Publication number Publication date
CN110210666B (en) 2021-08-10

Similar Documents

Publication Publication Date Title
Caggiani et al. A modular soft computing based method for vehicles repositioning in bike-sharing systems
CN110210666A (en) Intelligent recommendation method, system and storage medium based on vehicle and goods matching
WO2022262469A1 (en) Industrial park logistics scheduling method and system based on game theory
Caggiani et al. A dynamic simulation based model for optimal fleet repositioning in bike-sharing systems
CN107798423A (en) Vehicle path planning Simulation Experimental Platform based on multi-intelligence algorithm
CN109034481A (en) A kind of vehicle routing problem with time windows modeling and optimization method based on constraint planning
CN107977739A (en) Optimization method, device and the equipment in logistics distribution path
Tirado et al. Heuristics for dynamic and stochastic routing in industrial shipping
CN105976140A (en) Real-time vehicle commodity matching method under large-scale streaming data environment
CN108629503A (en) A kind of taxi based on deep learning is got on the bus the prediction technique of demand
Yao et al. Improved artificial bee colony algorithm for vehicle routing problem with time windows
CN107491836A (en) A kind of distribution method of order, device and electronic equipment
CN109359771A (en) A kind of line haul vehicle and goods matching algorithm based on big data
CN116227773A (en) Distribution path optimization method based on ant colony algorithm
CN109345296A (en) Common people&#39;s Travel Demand Forecasting method, apparatus and terminal
Bianchessi et al. Active fleet balancing in vehicle sharing systems via feedback dynamic pricing
Tian et al. Research on vehicle-cargo matching algorithm based on improved dynamic Bayesian network
CN117113608B (en) Cold-chain logistics network node layout method and equipment
Liu et al. A Multiobjective optimization model for continuous allocation of emergency rescue materials
CN117236541A (en) Distributed logistics distribution path planning method and system based on attention pointer network
CN116228069A (en) Inventory path planning method and device, electronic equipment and storage medium
CN116882883A (en) Power grid material distribution path planning method utilizing big data
CN111429237A (en) Order price determining method and device, server and storage medium
CN116187610A (en) Tobacco order vehicle distribution optimization method based on deep reinforcement learning
Ning et al. A novel method for dynamic vehicle routing problem

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
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20220119

Address after: 230001 floor 6, block B, blue diamond Shangjie, No. 335, Suixi Road, Bozhou road street, Luyang District, Hefei City, Anhui Province

Patentee after: Hefei Luyang Technology Innovation Group Co.,Ltd.

Address before: Tunxi road in Baohe District of Hefei city of Anhui Province, No. 193 230009

Patentee before: Hefei University of Technology