CN110264133A - Vehicle deploying method, apparatus, computer equipment and storage medium - Google Patents

Vehicle deploying method, apparatus, computer equipment and storage medium Download PDF

Info

Publication number
CN110264133A
CN110264133A CN201910504784.4A CN201910504784A CN110264133A CN 110264133 A CN110264133 A CN 110264133A CN 201910504784 A CN201910504784 A CN 201910504784A CN 110264133 A CN110264133 A CN 110264133A
Authority
CN
China
Prior art keywords
vehicle
order
address
purchase
history
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
CN201910504784.4A
Other languages
Chinese (zh)
Other versions
CN110264133B (en
Inventor
谢恩宁
刘玉春
叶旺旺
周星言
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.)
Zhejiang Dasou Vehicle Software Technology Co Ltd
Original Assignee
Zhejiang Dasou Vehicle Software Technology Co Ltd
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 Zhejiang Dasou Vehicle Software Technology Co Ltd filed Critical Zhejiang Dasou Vehicle Software Technology Co Ltd
Priority to CN201910504784.4A priority Critical patent/CN110264133B/en
Publication of CN110264133A publication Critical patent/CN110264133A/en
Application granted granted Critical
Publication of CN110264133B publication Critical patent/CN110264133B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06315—Needs-based resource requirements planning or analysis
    • 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
    • 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
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
    • G06Q30/0635—Processing of requisition or of purchase orders

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

This application involves a kind of vehicle deploying method, apparatus, computer equipment and storage mediums.Purchase vehicle order is not matched the described method includes: obtaining from order pond according to preset period of time；Extract the vehicle demand and Order Address not matched in purchase vehicle order；From vehicle pond search with vehicle demand is matched sells vehicle, and obtain vehicle-state and the warehouse address that can sell vehicle；By the warehouse address, the Order Address and the vehicle-state input time prediction model, each waiting time that can sell vehicle is obtained；Time prediction model is to complete order training according to history；The warehouse address, the Order Address and the waiting time are handled, the smallest vehicle delivery scheme of total waiting time is obtained；The vehicle of selling is scheduled and is dispensed according to vehicle delivery scheme.It accurately be estimated using the time that this method can spend vehicle delivery, so that the vehicle delivery scheme formulated is rationally reliable, realize that whole order rate of exceeding the time limit declines.

Description

Vehicle deploying method, apparatus, computer equipment and storage medium
Technical field
This application involves logistics technology, more particularly to a kind of vehicle deploying method, apparatus, computer equipment and deposit Storage media.
Background technique
After client and vehicle seller sign purchase vehicle order, vehicle seller needs according to order demand car spotting.Work as vehicle When the warehouse of seller is distributed in different cities, staff needs to manually select and search for for known warehouse, can not Multizone Auto-matching is fully achieved, the programs obtained in this way lack global planning, are easy to cause resource wrong Match, vehicle deploying low efficiency.
Summary of the invention
Based on this, it is necessary to which in view of the above technical problems, providing one kind can be according to order information and can selling vehicle storage Address carries out vehicle scheduling automatically, so as to shorten vehicle average scheduled time, the vehicle for making the efficiency of vehicle scheduling be improved Concocting method, device, computer equipment and storage medium.
A kind of vehicle deploying method, which comprises
It is obtained from order pond according to preset period of time and does not match purchase vehicle order；
Extract the vehicle demand and Order Address not matched in purchase vehicle order；
From vehicle pond search with the vehicle demand is matched sells vehicle, and obtain the vehicle-state that can sell vehicle and Warehouse address；
By the warehouse address, the Order Address and the vehicle-state input time prediction model, obtain each described The waiting time of vehicle can be sold；The time prediction model is to complete order training according to history；
The warehouse address, the Order Address and the waiting time are handled, total waiting time minimum is obtained Vehicle delivery scheme.
In one of the embodiments, it is described obtained from order pond according to preset period of time do not match purchase vehicle order it Before, further includes:
Receive the purchase vehicle order that client terminal is sent；
Extract the vehicle demand and Order Address in the purchase vehicle order；
It searches in the first vehicle supply range vehicle corresponding with Order Address pond and is matched with the vehicle demand Sell vehicle of registering the license, the vehicle-state for selling vehicle of registering the license is that vehicles identifications are identified with license plate and have been associated with；
When be not matched to it is described can sell register the license vehicle when, purchase vehicle order using the purchase vehicle order as not matching and store to ordering Dan Chizhong；
When be matched to it is described can sell register the license vehicle when, ordered according to the warehouse address for selling vehicle of registering the license and the purchase vehicle Single Order Address generates vehicle delivery scheme.
The warehouse address, the Order Address and the waiting time are handled in one of the embodiments, Obtain the smallest vehicle delivery scheme of total waiting time, comprising:
Using bipartite graph cum rights maximum matching algorithm or Hungary Algorithm to the warehouse address, the Order Address and The waiting time is handled, and the smallest vehicle delivery scheme of total waiting time is obtained.
The warehouse address, the Order Address and the waiting time are handled in one of the embodiments, Obtain the smallest vehicle delivery scheme of total waiting time, comprising:
Using the warehouse address and the Order Address as the node in bipartite graph, by the node in the bipartite graph it Between the waiting time as weight；
The maximum weight matching for seeking the bipartite graph, obtain total waiting time it is the smallest sell vehicle with purchase vehicle order it is corresponding Distribution project.
In one of the embodiments, the method also includes:
The information of vehicles of selling of warehousing management terminal transmission is received, the vehicle-state sold in information of vehicles is vehicle Mark has been associated with license plate mark；
It can sell information of vehicles corresponding second vehicle supply range according to license plate mark acquisition；
The Order Address vehicle for not matching purchase vehicle order corresponding with the second vehicle supply range is needed It asks and is matched with the information of vehicles of selling；
When it is described sell information of vehicles with it is described do not match purchase vehicle order it fails to match when, the information of vehicles of selling is deposited It stores up in vehicle pond；
When it is described sell information of vehicles with it is described do not match purchase vehicle order successful match when, sell information of vehicles according to described Warehouse address with it is described do not match purchase vehicle order the Order Address generate vehicle delivery scheme.
The building mode of the time prediction model in one of the embodiments, comprising:
The history for obtaining preset quantity completes order as sample training order；
Sample distribution information is extracted from the sample training order；
Machine learning training is carried out to the sample distribution information according to each sample training order, obtaining the time estimates mould Type.
Machine learning instruction is carried out to the sample distribution information according to each sample training order in one of the embodiments, Practice, obtain time prediction model, further includes:
It obtains the history different from the sample training order and completes order as assessment verifying order；
Extract history distribution information from assessment verifying order, history distribution information include history warehouse address, History Order address, history waiting time and history vehicle-state；
History warehouse address, History Order address and history vehicle-state are inputted into the time prediction model, obtained Verify the estimated time；
Verifying assessment, the evaluation criteria are carried out to the verifying estimated time and history waiting time by evaluation criteria For at least one of the mean value of absolute deviation, the variance of absolute deviation, the median of absolute deviation, R2 score value.
It is described after the acquisition can sell vehicle-state and the warehouse address of vehicle in one of the embodiments, also Include:
When can sell the quantity of vehicle described in the judgement and being less than the quantity for not matching purchase vehicle order, obtain current time with And lower single time in the purchase vehicle order；
The purchase vehicle order is ranked up according to the current time and the difference of lower single time；
The warehouse in the purchase vehicle order that the difference is stood out according to the quantity for selling vehicle Location, the Order Address and the vehicle-state input trained time prediction model, and the purchase vehicle order presses the difference It is arranged from big to small.
A kind of vehicle deploying device, which is characterized in that described device includes:
It purchases vehicle order and obtains module, do not match purchase vehicle order for obtaining from order pond according to preset period of time；
Order information extraction module, for extracting the vehicle demand and Order Address not matched in purchase vehicle order；
Vehicle search module can be sold, for from vehicle pond search with the vehicle demand is matched sells vehicle, and obtain Take the vehicle-state that can sell vehicle and warehouse address；
Waiting time estimates module, for the warehouse address, the Order Address and the vehicle-state to be inputted root The time prediction model that order training is completed according to history obtains each waiting time that can sell vehicle；
Distribution project generation module, for the warehouse address, the Order Address and at the waiting time Reason, obtains the smallest vehicle delivery scheme of total waiting time.
Described device in one of the embodiments, further include:
Order reception module, for receiving the purchase vehicle order of client terminal transmission；
Order information extraction module, for extracting vehicle demand and Order Address in the purchase vehicle order；
Order matching module, in the first vehicle supply range vehicle corresponding with the Order Address pond search and The vehicle demand is matched to sell vehicle of registering the license, and the vehicle-state for selling vehicle of registering the license is that vehicles identifications and license plate identify It has been associated with；
Order memory module, for when be not matched to it is described can sell register the license vehicle when, using the purchase vehicle order as not The storage of vehicle order is bought rations into order pond；
Vehicle deploying module, for when be matched to it is described can sell register the license vehicle when, according to the storehouse for selling vehicle of registering the license The Order Address of library address and the purchase vehicle order generates vehicle delivery scheme.
In another embodiment, the distribution project generation module includes:
Distribution project generation unit, for using bipartite graph cum rights maximum matching algorithm or Hungary Algorithm to the storehouse Library address, the Order Address and the waiting time are handled, and the smallest vehicle delivery scheme of total waiting time is obtained.
In wherein some embodiments, the distribution project generation module includes:
Bipartite graph drawing unit, for inciting somebody to action using the warehouse address and the Order Address as the node in bipartite graph The waiting time between node in the bipartite graph is as weight；
Scheme matches generation unit and it is the smallest to obtain total waiting time for seeking the maximum weight matching of the bipartite graph It can sell vehicle distribution project corresponding with purchase vehicle order.
Described device in one of the embodiments, further include:
Information of vehicles receiving module, it is described to sell vehicle for receiving the information of vehicles of selling of warehousing management terminal transmission Vehicle-state in information is that vehicles identifications have been associated with license plate mark；
It supplies range and obtains module, supplied for corresponding second vehicle of information of vehicles can be sold according to license plate mark acquisition To range；
Vehicle match module, for described not matching the Order Address is corresponding with the second vehicle supply range The vehicle demand of purchase vehicle order is matched with the information of vehicles of selling；
Vehicle storage module, for when it is described sell information of vehicles with it is described do not match purchase vehicle order it fails to match when, will It is described to sell information of vehicles storage into vehicle pond；
Vehicle deploying module, for when it is described sell information of vehicles with it is described do not match purchase vehicle order successful match when, root Vehicle delivery side is generated with the Order Address for not matching purchase vehicle order according to the warehouse address for selling information of vehicles Case.
The waiting time estimates module and includes: in one of the embodiments,
Training order acquiring unit, the history for obtaining preset quantity complete order as sample training order；
Sample distribution information extraction unit, for extracting sample distribution information from the sample training order；
Learning training unit, for carrying out machine learning instruction to the sample distribution information according to each sample training order Practice, obtains time prediction model.
In another embodiment, the waiting time estimates module and includes:
Assessment verifying order acquiring unit completes order conduct for obtaining the history different from the sample training order Assessment verifying order；
History distribution information extraction unit, for extracting history distribution information, history from assessment verifying order Distribution information includes history warehouse address, History Order address, history waiting time and history vehicle-state；
Waiting time estimates unit, for inputting history warehouse address, History Order address and history vehicle-state The time prediction model, is verified the estimated time；
Assessment unit is commented for carrying out verifying to the verifying estimated time and history waiting time by evaluation criteria Estimate, the evaluation criteria be the mean value of absolute deviation, the variance of absolute deviation, the median of absolute deviation, in R2 score value extremely Few one kind.
In some embodiments, described device further include:
Time-obtaining module, for working as the quantity that can sell vehicle described in judgement less than the quantity for not matching purchase vehicle order When, obtain lower single time in current time and the purchase vehicle order；
Order Sorting module, for according to the current time and the difference of lower single time to the purchase vehicle order into Row sequence；
MIM message input module, the purchase vehicle that the quantity for that can sell vehicle according to stands out the difference are ordered The warehouse address, the Order Address and the vehicle-state in list input trained time prediction model, the purchase Vehicle order is arranged from big to small by the difference.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing The step of device realizes the above method when executing the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor The step of above method is realized when row.
Above-mentioned vehicle deploying method, apparatus, computer equipment and storage medium, according to preset period of time from order pond Acquisition does not match purchase vehicle order；The input of warehouse address, Order Address and vehicle-state is trained according to history completion order Time prediction model obtains the waiting time that can respectively sell vehicle；Warehouse address, Order Address and waiting time are handled, The smallest vehicle delivery scheme of total waiting time is obtained, order is completed by history and obtains time prediction model, to vehicle delivery The time of cost is accurately estimated, so that the vehicle delivery scheme formulated is rationally reliable, realizes that whole order exceeds the time limit the steady of rate Drop is fixed, and realizes standardization, the full-automation of entire matching process.And above-mentioned vehicle deploying method has also set up and has stood Order of body, various dimensions deploys system, reduces the delivery duration of each purchase vehicle order, reduces the super of entire platform or company Phase risk, but also the totle drilling cost of vehicle transport reduces, the integral benefit for realizing entire platform or company is maximum.
Detailed description of the invention
Fig. 1 is the application scenario diagram of vehicle deploying method in one embodiment；
Fig. 2 is the flow diagram of vehicle deploying method in one embodiment；
Fig. 3 is the flow diagram of vehicle deploying method in one embodiment；
Fig. 4 is the flow diagram of vehicle deploying method in another embodiment；
Fig. 5 is the flow diagram of time prediction model building in another embodiment；
Fig. 6 is the flow diagram of time prediction model building in another embodiment；
Fig. 7 is that the order of vehicle deploying method in one embodiment delivers timeliness comparison diagram；
Fig. 8 is the structural block diagram of vehicle deploying device in one embodiment；
Fig. 9 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not For limiting the application.
Vehicle deploying method provided by the present application, can be applied in application environment as shown in Figure 1.Wherein, client is whole End 102 is communicated by network with server 104, and server 104 and warehousing management terminal 106 communicate to connect.Client terminal Purchase vehicle order is sent to server 104 by 102, and server 104 is stored in vehicle order is purchased in order pond；104 basis of server Preset period of time is obtained from order pond does not match purchase vehicle order；Server 104 extracts the vehicle not matched in purchase vehicle order Demand and Order Address；Server 104 is searched for from vehicle pond and vehicle demand is matched sells vehicle, and acquisition can sell vehicle Vehicle-state and warehouse address；Warehouse address, Order Address and vehicle-state are inputted and are ordered according to history completion by server 104 Singly trained time prediction model, obtains the waiting time that can respectively sell vehicle；Server 104 to warehouse address, Order Address and Waiting time is handled, and the smallest vehicle delivery scheme of total waiting time is obtained；Server 104 is according to vehicle delivery scheme pair Vehicle can be sold to be scheduled and dispense.Vehicle delivery scheme can be sent to management by server 104 can sell the storage pipe of vehicle Terminal 106 is managed, warehousing management terminal 106 can sell vehicle according to the allotment of vehicle delivery scheme.Wherein, client terminal 102 and storage Management terminal 106 can be, but not limited to be various personal computers, laptop, smart phone, tablet computer and portable Smart machine, server 104 can be realized with the server cluster of the either multiple server compositions of independent server.
In one embodiment, as shown in Fig. 2, providing a kind of vehicle deploying method, it is applied in Fig. 1 in this way It is illustrated for server 104, comprising the following steps:
Step 202, it is obtained from order pond according to preset period of time and does not match purchase vehicle order.
Server 104 is obtained from order pond according to preset period of time does not match purchase vehicle order.Preset period of time can To be previously set by the vehicle seller of management server, or set by system.Preset period of time can be set to 1~ It 10 days, can be adjusted according to order data.It is stored with what vehicle seller received from each client terminal 102 in order pond Purchase vehicle order is not matched, and it is not carry out matched purchase vehicle order with vehicles identifications that this, which does not match purchase vehicle order,.Purchase vehicle order at least The Order Address of the final delivery of vehicle demand and vehicle comprising vehicle needed for client, purchase vehicle order can also be marked comprising client Know.Customer ID can be the identity information etc. of client, have uniqueness.
Step 204, the vehicle demand and Order Address not matched in purchase vehicle order is extracted.
Server 104 extracts the vehicle demand and Order Address not matched in purchase vehicle order.Vehicle demand can be client Every configuration information, such as vehicle model, color, engine model of required vehicle etc..Order Address is the final delivery of vehicle Address, can be the sale shops or warehouse or other positions that client specifies.
Step 206, from vehicle pond search with the vehicle demand is matched sells vehicle, and obtain the vehicle that can sell vehicle State and warehouse address.
Vehicle pond be stored with vehicle seller hold and also not with customer order is matched sells information of vehicles.Information of vehicles Include vehicles identifications and vehicle configuration corresponding with vehicles identifications.Vehicles identifications are to distinguish the unique identification that can respectively sell vehicle, Vehicles identifications can be ID code of vehicle (VIN code).ID code of vehicle is determined according to national vehicle management standard, packet The information such as manufacturer, age, vehicle, body model and the code, engine code and assembling place of vehicle are contained.Vehicle is matched It sets and can be body color, wheelbase, engine power etc..
Vehicle-state has a variety of, and each vehicle corresponds to a kind of vehicle-state, and still, vehicle-state can be according to can sell vehicle Distribution state real-time update.For example, vehicle-state can be existing vehicle and vehicles identifications and license plate mark be associated with, existing vehicle and Vehicles identifications and license plate mark are not associated but into client development ticket, vehicle transport and vehicles identifications and license plate are identified and do not closed In connection, vehicle purchase and vehicles identifications and license plate mark are not associated etc..Warehouse address is the warehouse location that storage can sell vehicle Location.
Server 104 is searched for from vehicle pond and vehicle demand is matched sells vehicle, and obtains the vehicle that can sell vehicle State and warehouse address.Server can obtain vehicle configuration information according to VIN code, and by the vehicle of vehicle configuration information and order Demand is matched, and obtains vehicle-state and the warehouse address that can sell vehicle according to VIN code after successful match.Server root Can search for from vehicle pond according to an order can sell vehicle with vehicle demand matched at least one, can each sell information of vehicles It can also be matched at least one order.When vehicle configuration information includes vehicle demand, server judgement can sell vehicle With vehicle demand successful match；When vehicle configuration information does not include vehicle demand, server judgement can sell vehicle and vehicle and need Ask that it fails to match.
Step 208, it by the warehouse address, the Order Address and the vehicle-state input time prediction model, obtains To each waiting time for selling vehicle；The time prediction model is to complete order training according to history.
Warehouse address, Order Address and vehicle-state are inputted the time that order training is completed according to history by server 104 Prediction model obtains each waiting time that can sell vehicle.Time prediction model is the history completed in order according to history What Order Address, history warehouse address, history waiting time and the training of history vehicle-state obtained.Time prediction model obtains Waiting time include distribution time and formality time etc..Time of delivery is according to the distance between Order Address and warehouse address It is obtained with path.The formality time refers to that completing vehicle ownership transfer formality needs time for spending, different vehicle state and The formality time that different Order Address need to spend is different.
For example, when one do not match purchase vehicle order and it is multiple sell vehicle match when, server calculating can respectively sell vehicle and match It is sent to the waiting time of the Order Address for not matching purchase vehicle order.When multiple purchase vehicle order is not matched and multiple sell vehicle Timing, server calculate separately the waiting time that can respectively sell vehicle delivery to the Order Address for not matching purchase vehicle order respectively.When depositing Vehicle can be sold at one and does not match purchase vehicle order matching with multiple, and server calculating can sell vehicle delivery and order to purchase vehicle is not matched respectively The waiting time of single Order Address.
Step 210, the warehouse address, the Order Address and the waiting time are handled, is always waited Time the smallest vehicle delivery scheme.
Server 104 handles warehouse address, Order Address and waiting time, obtains the smallest vehicle of total waiting time Distribution project.Server 104 carries out bipartite graph processing to warehouse address, Order Address and waiting time, and according to bipartite graph Algorithm obtains the smallest vehicle delivery scheme of total waiting time.Vehicle delivery scheme closes vehicles identifications and purchase vehicle order Connection, and Distribution path is generated according to warehouse address and Order Address.
In one embodiment, the warehouse address, the Order Address and the waiting time are handled, is obtained The smallest vehicle delivery scheme of total waiting time, comprising: use bipartite graph cum rights maximum matching algorithm or Hungary Algorithm pair The warehouse address, the Order Address and the waiting time are handled, and the smallest vehicle delivery of total waiting time is obtained Scheme.
Server 104 can be handled warehouse address, Order Address and waiting time using bipartite graph algorithm, be obtained The smallest vehicle delivery scheme of total waiting time.Bipartite graph algorithm can be bipartite graph cum rights maximum matching algorithm or Hungary Algorithm etc..
Server 104 is scheduled and dispenses to that can sell vehicle according to vehicle delivery scheme.Server 104 can be by vehicle Distribution project, which is sent to management, can sell the warehousing management terminal 106 of vehicle, and warehousing management terminal 106 is according to vehicle delivery scheme tune With vehicle can be sold.
Above-mentioned vehicle deploying method obtains from order pond according to preset period of time and does not match purchase vehicle order；By warehouse Address, Order Address and vehicle-state input complete the trained time prediction model of order according to history, obtain respectively selling vehicle Waiting time；Warehouse address, Order Address and waiting time are handled, the smallest vehicle of total waiting time is obtained and matches Scheme to be sent, order is completed by history and obtains time prediction model, the time spent to vehicle delivery is accurately estimated, so that The vehicle delivery scheme of formulation is rationally reliable, realizes that whole order exceeds the time limit the decline of stablizing of rate, and realize and entirely matched Standardization, the full-automation of journey.And above-mentioned vehicle deploying method has also set up three-dimensional, various dimensions order allotment systems, The delivery duration for reducing each purchase vehicle order, reduces the risk of exceeding the time limit of entire platform or company, but also vehicle transport is total Cost reduces, and the integral benefit for realizing entire platform or company is maximum.
In one embodiment, purchase vehicle order is not matched as shown in figure 3, obtaining from order pond according to preset period of time Before, it has follow steps:
Step 302, the purchase vehicle order that client terminal is sent is received.
Server 104 receives the purchase vehicle order that client terminal 102 is sent.What client terminal 102 can be inputted according to client The vehicle demand of required vehicle and dispatching address generate purchase vehicle order, are then sent to server 104.
Step 304, the vehicle demand and Order Address in the purchase vehicle order are extracted.
Server 104 extracts vehicle demand and Order Address in purchase vehicle order.
Step 306, search and the vehicle in the first vehicle supply range vehicle corresponding with Order Address pond Demand is matched to sell vehicle of registering the license, and the vehicle-state for selling vehicle of registering the license is that vehicles identifications have been associated with license plate mark.
Can sell register the license vehicle be vehicle seller hold and also not with the matched vehicle of registering the license of customer order.Vehicle of registering the license can be sold Vehicle-state be that vehicles identifications and license plate are identified and be associated with.License plate mark can be license plate number.When vehicles identifications and license plate mark After knowledge has been associated with, the first vehicle supply range can be reduced in region corresponding with license plate mark.In order to avoid inventory, need and When matching can sell vehicle of registering the license.Server 104 searched in the first vehicle supply range vehicle corresponding with Order Address pond with Vehicle demand is matched to sell vehicle of registering the license.
Step 308, when be not matched to it is described can sell register the license vehicle when, purchase vehicle order using the purchase vehicle order as not matching It stores in order pond.
When server 104 be not matched to can sell register the license vehicle when, server 104 by purchase vehicle order as do not match purchase vehicle order Single storage waits matching next time into order pond.
Step 310, when be matched to it is described can sell register the license vehicle when, according to the warehouse address for selling vehicle of registering the license and institute The Order Address for stating purchase vehicle order generates vehicle delivery scheme.
When server 104 be matched to can sell register the license vehicle when, server 104 according to can sell the warehouse address of vehicle of registering the license with Purchase vehicle order Order Address generate vehicle delivery scheme, and according to vehicle delivery scheme to can sell vehicle of registering the license be scheduled with Dispatching.Vehicle delivery scheme can also be sent to management by server 104 can sell the warehousing management terminal 106 of vehicle, storage pipe Reason terminal 106 is scheduled and dispenses to that can sell vehicle of registering the license according to vehicle delivery scheme.
Above-mentioned vehicle deploying method, when server receives the purchase vehicle order of client terminal transmission, server is first the One vehicle supply range vehicle corresponding with Order Address pond first matches purchase vehicle order, and vehicle of registering the license can be sold by reducing Inventory time, but also vehicle management totle drilling cost reduces.
In one embodiment, the warehouse address, the Order Address and the waiting time are handled, is obtained The smallest vehicle delivery scheme of total waiting time, comprising the following steps: using the warehouse address and the Order Address as two Node in component, using the waiting time between the node in the bipartite graph as weight；Seek the bipartite graph Maximum weight matching, obtains that total waiting time is the smallest to sell vehicle and the corresponding distribution project of purchase vehicle order.
Server 104 obtains vehicle delivery scheme, bipartite graph cum rights maximum using bipartite graph cum rights maximum matching algorithm It can be Kuhn-Munkres algorithm etc. with algorithm.Server 104 is using warehouse address and Order Address as the section in bipartite graph Point, using the waiting time between the node in bipartite graph as weight.Server can be using warehouse address as bipartite graph In nodes X, using Order Address as the node Y in bipartite graph, will the waiting time as weight, construct the matrix of bipartite graph.
Server 104 can obtain total waiting time minimum according to the maximum weight matching that the matrix of bipartite graph seeks bipartite graph Sell vehicle and the corresponding distribution project of purchase vehicle order；Server 104 can also traverse bipartite graph.Matching in bipartite graph is The set on side, the side in the set do not have common node.If in all matchings of a bipartite graph, one of them matched each side Weight and maximum, then the matching be maximum weight matching.Server can traverse all combinations on side in bipartite graph, therefrom find out most Authority matching.After acquiring maximum weight matching, warehouse address and Order Address associated by the side in maximum weight matching can be given birth to Sell vehicle distribution project corresponding with purchase vehicle order at total waiting time is the smallest.
Above-mentioned vehicle deploying method, server can accurately obtain total waiting using bipartite graph cum rights maximum matching algorithm Time is the smallest to sell vehicle distribution project corresponding with purchase vehicle order, when further reducing the average delivery of each purchase vehicle order It is long, reduce the risk of exceeding the time limit of entire platform or company.
In one embodiment, as shown in figure 4, vehicle deploying method is further comprising the steps of:
Step 402, receive the transmission of warehousing management terminal sells information of vehicles, the vehicle shape sold in information of vehicles State is that vehicles identifications have been associated with license plate mark.
Server 104 receives the vehicle shape sold information of vehicles, can sell in information of vehicles that warehousing management terminal 106 is sent State is that vehicles identifications have been associated with license plate mark.Warehousing management terminal 106 can be held each with real-time update typing vehicle seller Information of vehicles.
Step 404, it can sell information of vehicles corresponding second vehicle supply range according to license plate mark acquisition.
Server 104 can sell information of vehicles corresponding second vehicle supply range according to license plate mark acquisition.License plate Mark is corresponding with province, city, and when vehicles identifications have been associated with license plate mark, the second vehicle supply range is and license plate identifies Corresponding city or province.
Step 406, the Order Address described do not match corresponding with the second vehicle supply range is purchased into vehicle order Vehicle demand matched with the information of vehicles of selling.
Server 104 by Order Address it is corresponding with the second vehicle supply range do not match purchase vehicle order vehicle demand with Information of vehicles can be sold to be matched.When Order Address includes the second vehicle supply range, server determines Order Address and the Two vehicle supply ranges are corresponding, for example, the second vehicle supply range is Hangzhou, Order Address is inhabitants in Xiaoshan XX road XX Number, Order Address includes the second vehicle supply range, and server determines that Order Address is corresponding with the second vehicle supply range.When can Sell information of vehicles include vehicle demand when, server judgement can sell information of vehicles with do not match purchase vehicle order successful match；When can When selling information of vehicles not comprising vehicle demand, server judgement can sell information of vehicles, and it fails to match with purchase vehicle order is not matched.
Step 408, when it is described sell information of vehicles with it is described do not match purchase vehicle order it fails to match when, sell vehicle for described The storage of information is into vehicle pond.
When can sell information of vehicles with do not match purchase vehicle order it fails to match when, server 104 can sell information of vehicles storage Into vehicle pond.
Step 410, when it is described sell information of vehicles with it is described do not match purchase vehicle order successful match when, sold according to described The warehouse address of information of vehicles generates vehicle delivery scheme with the Order Address for not matching purchase vehicle order.
When that can sell information of vehicles with purchase vehicle order successful match is not matched, server 104 is according to can sell information of vehicles Warehouse address and do not match purchase vehicle order Order Address generate vehicle delivery scheme, and according to vehicle delivery scheme to that can sell on Board vehicle is scheduled and dispenses.Information of vehicles, which can each be sold, to be matched with an order.
Above-mentioned vehicle deploying method, when server receives selling information of vehicles and can selling for warehousing management terminal transmission Vehicle is when registering the license vehicle, and server first determination can sell the second vehicle supply range of vehicle, and in time and Order Address is the The purchase vehicle order of two vehicle supply ranges is first matched, and the inventory time that can sell vehicle of registering the license is reduced, but also vehicle pipe Managing totle drilling cost reduces.
In one embodiment, as shown in figure 5, the building mode of time prediction model, comprising the following steps:
Step 502, the history for obtaining preset quantity completes order as sample training order.
The history that server 104 obtains preset quantity completes order as sample training order.It is vehicle that history, which completes order, Seller sells the History Order of each vehicle, including at least where history vehicle history warehouse address, History Order address, go through History waiting time and history vehicle-state.Preset quantity can complete quantity on order according to history and be set, and can also be System default setting.Preset quantity can be a numerical value, be also possible to the percentage that history completes quantity on order.
Step 504, sample distribution information is extracted from the sample training order.
Server 104 extracts sample distribution information from sample training order, and sample distribution information includes influencing vehicle Dispense each factor of waiting time.When sample distribution information may include sample warehouse address, sample Order Address, sample waiting Between and sample vehicle-state.
Step 506, machine learning training is carried out to the sample distribution information according to each sample training order, obtains the time Prediction model.
Server 104 carries out machine learning training to sample distribution information according to each sample training order, and it is pre- to obtain the time Estimate model.Server can obtain position-distance-dispatching according to each sample warehouse address, sample Order Address and date of delivery Association between time obtains state-according to each vehicle-state, Order Address, sample waiting time and sample time of delivery Association of the address-between the formality time.Server according between position-distance-distribution time association and state-address- Association settling time prediction model between the formality time.
Above-mentioned vehicle deploying method, not only allowing for the vehicle delivery time also contemplates vehicle transfer and needs the formality that spends Time has accurately estimated the waiting time.
In one embodiment, as shown in fig. 6, carrying out machine to the sample distribution information according to each sample training order Learning training obtains time prediction model, further comprising the steps of:
Step 602, it obtains the history different from the sample training order and completes order as assessment verifying order.
Server 104 obtains the history different from the sample training order and completes order as assessment verifying order.It comments Estimate verifying order and sample training order belongs to history and completes order, but assesses in verifying order and sample training order It is different that each history completes order.The quantity of assessment verifying order and the quantity of sample training order can be arranged in proportion, can also It is configured with system according to accuracy rate.
Step 604, history distribution information is extracted from assessment verifying order, history distribution information includes history storehouse Library address, History Order address, history waiting time and history vehicle-state.
Server 104 extracts history distribution information from assessment verifying order, and history distribution information may include history Warehouse address, History Order address, history waiting time and history vehicle-state.History distribution information also may include history The factor of the other influences waiting time such as date of delivery.
Step 606, history warehouse address, History Order address and history vehicle-state the input time are estimated into mould Type is verified the estimated time.
Server 104 estimates history warehouse address, History Order address and history vehicle-state the input time Model is verified the estimated time.
Step 608, verifying assessment is carried out to the verifying estimated time and history waiting time by evaluation criteria, it is described Evaluation criteria is at least one of the mean value of absolute deviation, the variance of absolute deviation, the median of absolute deviation, R2 score value.
Server 104 carries out verifying assessment, institute to the verifying estimated time and history waiting time by evaluation criteria Evaluation criteria is stated as at least one in the mean value of absolute deviation, the variance of absolute deviation, the median of absolute deviation, R2 score value Kind.Server first calculates the time difference between verifying estimated time and history waiting time, and calculates between each time difference Absolute deviation, and difference and absolute deviation are updated to the standard that time prediction model is obtained in calculation formula according to evaluation criteria True rate.When accuracy rate is greater than preset threshold, the verifying of time prediction model is qualified, not so needs to adjust corresponding model ginseng repeatedly Number, until model can meet corresponding standard.
The mean value of absolute deviation:
The variance of absolute deviation:
The median of absolute deviation:
R2 score value:
Wherein
Wherein, nsamplesRepresent the quantity of all assessment verifying orders, yiWithRespectively represent each assessment verifying order The history waiting time and verifying estimated time for being calculated with above-mentioned time prediction model.
The above difference evaluation criteria has carried out verifying assessment to model from different perspectives respectively, describes the confidence journey of model Degree.Wherein, the mean value of absolute deviation reflects the height of overall offset degree, but can occur to the assessment of abnormal data inclined Difference；For the variance of absolute deviation mainly in the comparable situation of mean value, variance is lower to may indicate that assessment errors are smaller；Absolutely partially Deviation in most cases is contemplated in the median of difference, but population deviation perhaps can be very big；R2 score value is also named the goodness of fit, Reflection is the variance of predicted value and the difference of true value variance, closer to 1 presentation class data from overall distribution It is consistent with prediction distribution.
In another embodiment, after the acquisition can sell vehicle-state and the warehouse address of vehicle, further include with Lower step: when can sell the quantity of vehicle described in the judgement and being less than the quantity for not matching purchase vehicle order, obtain current time with And lower single time in the purchase vehicle order；According to the current time and the difference of lower single time to the purchase vehicle order It is ranked up；The warehouse in the purchase vehicle order that the difference is stood out according to the quantity for selling vehicle Location, the Order Address and the vehicle-state input trained time prediction model, and the purchase vehicle order presses the difference It is arranged from big to small.
Server 104 judges whether the quantity that can sell vehicle is greater than the quantity for not matching purchase vehicle order.When server judges When the quantity that vehicle can be sold is greater than the quantity for not matching purchase vehicle order, server calculating can respectively sell vehicle the corresponding waiting time； When server 104 judges that the quantity that can sell vehicle is less than the quantity for not matching purchase vehicle order, server 104 obtains current time With lower single time in purchase vehicle order.Server 104 according to current time and the difference of lower single time to the purchase vehicle order into Row sequence, obtains Order Sorting result.Server 104 according to can sell the quantity of vehicle will be before difference comes in Order Sorting result The purchase vehicle order of column extracts, and the purchase vehicle order in Order Sorting result is arranged from big to small by difference.Service The warehouse address for not matching purchase vehicle order extracted, Order Address and vehicle-state input trained time are estimated mould by device Type.
It is long to avoid part order according to the dispatching that can be sold vehicle condition and adjust order in real time for above-mentioned vehicle deploying method Phase overstocks the risk that causes to exceed the time limit and increases, and sells a small amount of to vehicle priority match to the order that will exceed the time limit with relatively reasonable degree On guarantee that whole system rate of exceeding the time limit is minimum.
As shown in fig. 7, the order of history match result delivers timeliness are as follows: the order for completing 25% needs 11.54 days, completes 50% order needs 14.39 days, and the order for completing 75% needs 18.24 days average, longest finishing time needs 44.53 days. Timeliness is delivered using the order of Model Matching result in the present embodiment are as follows: the order for completing 25% needs 10.96 days, completes 50% Order need 13.18 days, the order for completing 75% needs average 15.99 days, and longest finishing time needs 35.68 days.It is above-mentioned Vehicle deploying method makes whole order exceed the time limit rate decline 20%, and whole duration maximum of delivering shortens 25%.
It should be understood that although each step in the flow chart of Fig. 2-6 is successively shown according to the instruction of arrow, These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-6 Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately It executes.
In one embodiment, as shown in figure 8, providing a kind of vehicle deploying device, comprising: purchase vehicle order obtains module 802, order information extraction module 804, vehicle search module 806 can be sold, the waiting time estimates module 808 and distribution project generate Module 810, in which:
It purchases vehicle order and obtains module 802, do not match purchase vehicle order for obtaining from order pond according to preset period of time.
Order information extraction module 804, for extracting the vehicle demand and Order Address not matched in purchase vehicle order.
Vehicle search module 806 can be sold, for from vehicle pond search with the vehicle demand is matched sells vehicle, and Obtain vehicle-state and the warehouse address that can sell vehicle.
Waiting time estimates module 808, for inputting the warehouse address, the Order Address and the vehicle-state Time prediction model obtains each waiting time that can sell vehicle；The time prediction model is to complete order according to history Trained.
Distribution project generation module 810, for being carried out to the warehouse address, the Order Address and the waiting time Processing, obtains the smallest vehicle delivery scheme of total waiting time.
In some embodiments, device further include order reception module, order information extraction module, order matching module, Order memory module and vehicle deploying module, in which:
Order reception module, for receiving the purchase vehicle order of client terminal transmission.
Order information extraction module, for extracting vehicle demand and Order Address in the purchase vehicle order.
Order matching module, in the first vehicle supply range vehicle corresponding with the Order Address pond search and The vehicle demand is matched to sell vehicle of registering the license, and the vehicle-state for selling vehicle of registering the license is that vehicles identifications and license plate identify It has been associated with.
Order memory module, for when be not matched to it is described can sell register the license vehicle when, using the purchase vehicle order as not The storage of vehicle order is bought rations into order pond.
Vehicle deploying module, for when be matched to it is described can sell register the license vehicle when, according to the storehouse for selling vehicle of registering the license The Order Address of library address and the purchase vehicle order generates vehicle delivery scheme.
In some embodiments, distribution project generation module 810 includes distribution project generation unit, in which:
Distribution project generation unit, for using bipartite graph cum rights maximum matching algorithm or Hungary Algorithm to the storehouse Library address, the Order Address and the waiting time are handled, and the smallest vehicle delivery scheme of total waiting time is obtained.
In another embodiment, distribution project generation module 810 includes that bipartite graph drawing unit and scheme matching generate list Member, in which:
Bipartite graph drawing unit, for inciting somebody to action using the warehouse address and the Order Address as the node in bipartite graph The waiting time between node in the bipartite graph is as weight.
Scheme matches generation unit and it is the smallest to obtain total waiting time for seeking the maximum weight matching of the bipartite graph It can sell vehicle distribution project corresponding with purchase vehicle order.
In one embodiment, device further includes information of vehicles receiving module, supply range acquisition module, vehicle match mould Block, vehicle storage module and vehicle deploying module, in which:
Information of vehicles receiving module, it is described to sell vehicle for receiving the information of vehicles of selling of warehousing management terminal transmission Vehicle-state in information is that vehicles identifications have been associated with license plate mark.
It supplies range and obtains module, supplied for corresponding second vehicle of information of vehicles can be sold according to license plate mark acquisition To range.
Vehicle match module, for described not matching the Order Address is corresponding with the second vehicle supply range The vehicle demand of purchase vehicle order is matched with the information of vehicles of selling.
Vehicle storage module, for when it is described sell information of vehicles with it is described do not match purchase vehicle order it fails to match when, will It is described to sell information of vehicles storage into vehicle pond.
Vehicle deploying module, for when it is described sell information of vehicles with it is described do not match purchase vehicle order successful match when, root Vehicle delivery side is generated with the Order Address for not matching purchase vehicle order according to the warehouse address for selling information of vehicles Case.
In one embodiment, it includes that order acquiring unit, sample distribution information is trained to mention that the waiting time, which estimates module 808, Take unit and learning training unit, in which:
Training order acquiring unit, the history for obtaining preset quantity complete order as sample training order.
Sample distribution information extraction unit, for extracting sample distribution information from the sample training order.
Learning training unit, for carrying out machine learning instruction to the sample distribution information according to each sample training order Practice, obtains time prediction model.
In one embodiment, it further includes assessment verifying order acquiring unit, history dispatching that the waiting time, which estimates module 808, Information extraction unit, waiting time estimate unit and assessment unit, in which:
Assessment verifying order acquiring unit completes order conduct for obtaining the history different from the sample training order Assessment verifying order.
History distribution information extraction unit, for extracting history distribution information, history from assessment verifying order Distribution information includes history warehouse address, History Order address, history waiting time and history vehicle-state.
Waiting time estimates unit, for inputting history warehouse address, History Order address and history vehicle-state The time prediction model, is verified the estimated time.
Assessment unit is commented for carrying out verifying to the verifying estimated time and history waiting time by evaluation criteria Estimate, the evaluation criteria be the mean value of absolute deviation, the variance of absolute deviation, the median of absolute deviation, in R2 score value extremely Few one kind.
In one embodiment, device further includes time-obtaining module, Order Sorting module and MIM message input module, In:
Time-obtaining module, for working as the quantity that can sell vehicle described in judgement less than the quantity for not matching purchase vehicle order When, obtain lower single time in current time and the purchase vehicle order；
Order Sorting module, for according to the current time and the difference of lower single time to the purchase vehicle order into Row sequence；
MIM message input module, the purchase vehicle that the quantity for that can sell vehicle according to stands out the difference are ordered The warehouse address, the Order Address and the vehicle-state in list input trained time prediction model, the purchase Vehicle order is arranged from big to small by the difference.
Specific about vehicle deploying device limits the restriction that may refer to above for vehicle deploying method, herein not It repeats again.Modules in above-mentioned vehicle deploying device can be realized fully or partially through software, hardware and combinations thereof.On Stating each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also store in a software form In memory in computer equipment, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction Composition can be as shown in Figure 9.The computer equipment include by system bus connect processor, memory, network interface and Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating The database of machine equipment is for storing vehicle pond data and order pond data.The network interface of the computer equipment is used for and outside Terminal by network connection communication.To realize a kind of vehicle deploying method when the computer program is executed by processor.
It will be understood by those skilled in the art that structure shown in Fig. 9, only part relevant to application scheme is tied The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, which is stored with Computer program, the processor perform the steps of when executing computer program
It is obtained from order pond according to preset period of time and does not match purchase vehicle order；
Extract the vehicle demand and Order Address not matched in purchase vehicle order；
From vehicle pond search with the vehicle demand is matched sells vehicle, and obtain the vehicle-state that can sell vehicle and Warehouse address；
By the warehouse address, the Order Address and the vehicle-state input time prediction model, obtain each described The waiting time of vehicle can be sold；The time prediction model is to complete order training according to history；
The warehouse address, the Order Address and the waiting time are handled, total waiting time minimum is obtained Vehicle delivery scheme.
In one embodiment, it realizes when processor executes computer program and is obtained from order pond according to preset period of time It before taking the step of not matching purchase vehicle order, is also used to: receiving the purchase vehicle order that client terminal is sent；Extract the purchase vehicle order In vehicle demand and Order Address；Search and institute in the first vehicle supply range vehicle corresponding with Order Address pond State that vehicle demand is matched to sell vehicle of registering the license, the vehicle-state for selling vehicle of registering the license is that vehicles identifications and license plate identify Association；When be not matched to it is described can sell register the license vehicle when, purchase vehicle order using the purchase vehicle order as not matching and store to order Chi Zhong；When be matched to it is described can sell register the license vehicle when, according to the warehouse address for selling vehicle of registering the license and the purchase vehicle order The Order Address generate vehicle delivery scheme.
In one embodiment, it realizes when processor executes computer program to the warehouse address, the Order Address It is handled with the waiting time, when obtaining the step of the smallest vehicle delivery scheme of total waiting time, is also used to: using two Component cum rights maximum matching algorithm or Hungary Algorithm to the warehouse address, the Order Address and the waiting time into Row processing, obtains the smallest vehicle delivery scheme of total waiting time.
In one embodiment, it realizes when processor executes computer program to the warehouse address, the Order Address It is handled with the waiting time, when obtaining the step of the smallest vehicle delivery scheme of total waiting time, is also used to: will be described Warehouse address and the Order Address are as the node in bipartite graph, when by the waiting between the node in the bipartite graph Between be used as weight；The maximum weight matching for seeking the bipartite graph, obtain total waiting time it is the smallest sell vehicle and purchase vehicle order Corresponding distribution project.
In one embodiment, it is also performed the steps of when processor executes computer program and receives warehousing management terminal What is sent sells information of vehicles, and the vehicle-state sold in information of vehicles is that vehicles identifications have been associated with license plate mark；Root It can sell information of vehicles corresponding second vehicle supply range according to described in license plate mark acquisition；By the Order Address and described second The corresponding vehicle demand for not matching purchase vehicle order of vehicle supply range is matched with the information of vehicles of selling；Work as institute State can sell information of vehicles with it is described do not match purchase vehicle order it fails to match when, sell information of vehicles storage to vehicle pond for described In；When it is described sell information of vehicles with it is described do not match purchase vehicle order successful match when, according to the storehouse for selling information of vehicles Library address generates vehicle delivery scheme with the Order Address for not matching purchase vehicle order.
In one embodiment, the step of realizing the building mode of time prediction model when processor executes computer program When, be also used to: the history for obtaining preset quantity completes order as sample training order；It is extracted from the sample training order Sample distribution information out；Machine learning training is carried out to the sample distribution information according to each sample training order, obtains the time Prediction model.
In one embodiment, it realizes according to each sample training order when processor executes computer program to the sample Distribution information carries out machine learning training, when obtaining the step of time prediction model, is also used to: acquisition is ordered with the sample training Single different history completes order as assessment verifying order；History distribution information is extracted from assessment verifying order, History distribution information includes history warehouse address, History Order address, history waiting time and history vehicle-state；By history Warehouse address, History Order address and history vehicle-state input the time prediction model, are verified the estimated time；It is logical It crosses evaluation criteria and verifying assessment is carried out to the verifying estimated time and history waiting time, the evaluation criteria is absolute deviation Mean value, the variance of absolute deviation, the median of absolute deviation, at least one of R2 score value.
In one embodiment, the vehicle-state of vehicle can be sold in the acquisition by realizing when processor executes computer program After the step of warehouse address, be also used to: the quantity that vehicle can be sold described in the judgement is less than the purchase vehicle order of not matching When quantity, lower single time in current time and the purchase vehicle order is obtained；When according to the current time and the lower list Between difference the purchase vehicle order is ranked up；Described in the difference stood out according to the quantity for selling vehicle The warehouse address, the Order Address and the vehicle-state purchased in vehicle order input trained time prediction model, The purchase vehicle order is arranged from big to small by the difference.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated Machine program performs the steps of when being executed by processor
It is obtained from order pond according to preset period of time and does not match purchase vehicle order；
Extract the vehicle demand and Order Address not matched in purchase vehicle order；
From vehicle pond search with the vehicle demand is matched sells vehicle, and obtain the vehicle-state that can sell vehicle and Warehouse address；
By the warehouse address, the Order Address and the vehicle-state input time prediction model, obtain each described The waiting time of vehicle can be sold；The time prediction model is to complete order training according to history；
The warehouse address, the Order Address and the waiting time are handled, total waiting time minimum is obtained Vehicle delivery scheme.
In one embodiment, it is realized when computer program is executed by processor according to preset period of time from order pond It is also used to before obtaining the step of not matching purchase vehicle order: receiving the purchase vehicle order that client terminal is sent；The purchase vehicle is extracted to order Vehicle demand and Order Address in list；In the first vehicle supply range vehicle corresponding with the Order Address pond search with The vehicle demand is matched to sell vehicle of registering the license, and the vehicle-state for selling vehicle of registering the license is that vehicles identifications and license plate identify It has been associated with；When be not matched to it is described can sell register the license vehicle when, purchase vehicle order using the purchase vehicle order as not matching and store to ordering Dan Chizhong；When be matched to it is described can sell register the license vehicle when, ordered according to the warehouse address for selling vehicle of registering the license and the purchase vehicle Single Order Address generates vehicle delivery scheme.
In one embodiment, computer program is realized when being executed by processor to the warehouse address, the order Location and the waiting time are handled, and obtain being also used to when the step of the smallest vehicle delivery scheme of total waiting time: being used Bipartite graph cum rights maximum matching algorithm or Hungary Algorithm are to the warehouse address, the Order Address and the waiting time It is handled, obtains the smallest vehicle delivery scheme of total waiting time.
In one embodiment, computer program is realized when being executed by processor to the warehouse address, the order Location and the waiting time are handled, and obtain being also used to when the step of the smallest vehicle delivery scheme of total waiting time: by institute Warehouse address and the Order Address are stated as the node in bipartite graph, by the waiting between the node in the bipartite graph Time is as weight；The maximum weight matching for seeking the bipartite graph obtains the smallest vehicle of selling of total waiting time and orders with purchase vehicle Single corresponding distribution project.
In one embodiment, it is also used to when computer program is executed by processor: receiving what warehousing management terminal was sent Information of vehicles can be sold, the vehicle-state sold in information of vehicles is that vehicles identifications have been associated with license plate mark；According to license plate Mark can sell information of vehicles corresponding second vehicle supply range described in obtaining；The Order Address and second vehicle are supplied It is matched to the corresponding vehicle demand for not matching purchase vehicle order of range with the information of vehicles of selling；It is sold when described Information of vehicles with it is described do not match purchase vehicle order it fails to match when, by it is described sell information of vehicles storage into vehicle pond；Work as institute State can sell information of vehicles with it is described do not match purchase vehicle order successful match when, according to the warehouse address for selling information of vehicles with The Order Address for not matching purchase vehicle order generates vehicle delivery scheme.
In one embodiment, the step of the building mode of time prediction model is realized when computer program is executed by processor Be also used to when rapid: the history for obtaining preset quantity completes order as sample training order；It is mentioned from the sample training order Take out sample distribution information；Machine learning training is carried out to the sample distribution information according to each sample training order, when obtaining Between prediction model.
In one embodiment, it realizes according to each sample training order when computer program is executed by processor to the sample This distribution information carries out machine learning training, obtains being also used to when the step of time prediction model: obtaining and the sample training The different history of order completes order as assessment verifying order；History is extracted with delivering letters from assessment verifying order Breath, history distribution information includes history warehouse address, History Order address, history waiting time and history vehicle-state；It will History warehouse address, History Order address and history vehicle-state input the time prediction model, are verified when estimating Between；Verifying assessment is carried out to the verifying estimated time and history waiting time by evaluation criteria, the evaluation criteria is exhausted To at least one of the mean value of deviation, the variance of absolute deviation, the median of absolute deviation, R2 score value.
In one embodiment, the vehicle shape of vehicle can be sold in the acquisition by realizing when computer program is executed by processor Be also used to after the step of state and warehouse address: the quantity that vehicle can be sold described in the judgement is less than the purchase vehicle order that do not match When quantity, lower single time in current time and the purchase vehicle order is obtained；When according to the current time and the lower list Between difference the purchase vehicle order is ranked up；Described in the difference stood out according to the quantity for selling vehicle The warehouse address, the Order Address and the vehicle-state purchased in vehicle order input trained time prediction model, The purchase vehicle order is arranged from big to small by the difference.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, To any reference of memory, storage, database or other media used in each embodiment provided herein, Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM (PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms, Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.

Claims (18)

1. a kind of vehicle deploying method, which comprises
It is obtained from order pond according to preset period of time and does not match purchase vehicle order；
Extract the vehicle demand and Order Address not matched in purchase vehicle order；
From vehicle pond search with the vehicle demand is matched sells vehicle, and obtain the vehicle-state and warehouse that can sell vehicle Address；
By the warehouse address, the Order Address and the vehicle-state input time prediction model, each described can sell is obtained The waiting time of vehicle；The time prediction model is to complete order training according to history；
The warehouse address, the Order Address and the waiting time are handled, the smallest vehicle of total waiting time is obtained Distribution project.
2. the method according to claim 1, wherein described obtain not from order pond according to preset period of time Before matching purchase vehicle order, further includes:
Receive the purchase vehicle order that client terminal is sent；
Extract the vehicle demand and Order Address in the purchase vehicle order；
In the first vehicle supply range vehicle corresponding with Order Address pond, search with the vehicle demand is matched can Vehicle of registering the license is sold, the vehicle-state for selling vehicle of registering the license is that vehicles identifications have been associated with license plate mark；
When be not matched to it is described can sell register the license vehicle when, purchase vehicle order using the purchase vehicle order as not matching and store to order pond In；
When be matched to it is described can sell register the license vehicle when, according to the warehouse address for selling vehicle of registering the license and the purchase vehicle order The Order Address generates vehicle delivery scheme.
3. the method according to claim 1, wherein described to the warehouse address, the Order Address and institute Stating the waiting time is handled, and the smallest vehicle delivery scheme of total waiting time is obtained, comprising:
Using bipartite graph cum rights maximum matching algorithm or Hungary Algorithm to the warehouse address, the Order Address and described Waiting time is handled, and the smallest vehicle delivery scheme of total waiting time is obtained.
4. the method according to claim 1, wherein described to the warehouse address, the Order Address and institute Stating the waiting time is handled, and the smallest vehicle delivery scheme of total waiting time is obtained, comprising:
It, will be between the node in the bipartite graph using the warehouse address and the Order Address as the node in bipartite graph The waiting time is as weight；
The maximum weight matching for seeking the bipartite graph, obtains that total waiting time is the smallest to be sold vehicle vehicle order is corresponding matches with purchase Send scheme.
5. the method according to claim 1, wherein the method also includes:
The information of vehicles of selling of warehousing management terminal transmission is received, the vehicle-state sold in information of vehicles is vehicles identifications It has been associated with license plate mark；
It can sell information of vehicles corresponding second vehicle supply range according to license plate mark acquisition；
By the Order Address vehicle demand for not matching purchase vehicle order corresponding with the second vehicle supply range with The information of vehicles of selling is matched；
When it is described sell information of vehicles with it is described do not match purchase vehicle order it fails to match when, sell information of vehicles storage by described and arrive In vehicle pond；
When it is described sell information of vehicles with it is described do not match purchase vehicle order successful match when, according to the storehouse for selling information of vehicles Library address generates vehicle delivery scheme with the Order Address for not matching purchase vehicle order.
6. the method according to claim 1, wherein the building mode of the time prediction model, comprising:
The history for obtaining preset quantity completes order as sample training order；
Sample distribution information is extracted from the sample training order；
Machine learning training is carried out to the sample distribution information according to each sample training order, obtains time prediction model.
7. according to the method described in claim 6, it is characterized in that, described dispense the sample according to each sample training order Information carries out machine learning training, obtains time prediction model, further includes:
It obtains the history different from the sample training order and completes order as assessment verifying order；
History distribution information is extracted from assessment verifying order, history distribution information includes history warehouse address, history Order Address, history waiting time and history vehicle-state；
History warehouse address, History Order address and history vehicle-state are inputted into the time prediction model, are verified Estimated time；
Verifying assessment is carried out to the verifying estimated time and history waiting time by evaluation criteria, the evaluation criteria is exhausted To at least one of the mean value of deviation, the variance of absolute deviation, the median of absolute deviation, R2 score value.
8. the method according to claim 1, wherein vehicle-state and the storehouse that vehicle can be sold in the acquisition After the address of library, further includes:
When can sell the quantity of vehicle described in the judgement and being less than the quantity for not matching purchase vehicle order, current time and institute are obtained State lower single time in purchase vehicle order；
The purchase vehicle order is ranked up according to the current time and the difference of lower single time, obtains Order Sorting knot Fruit；
The difference is stood out according to the quantity for selling vehicle the warehouse address in the purchase vehicle order, institute State Order Address and the vehicle-state and input trained time prediction model, the purchase vehicle order press the difference from greatly to It is small to be arranged.
9. a kind of vehicle deploying device, which is characterized in that described device includes:
It purchases vehicle order and obtains module, do not match purchase vehicle order for obtaining from order pond according to preset period of time；
Order information extraction module, for extracting the vehicle demand and Order Address not matched in purchase vehicle order；
Vehicle search module can be sold, for from vehicle pond search with the vehicle demand is matched sells vehicle, and obtaining can Sell vehicle-state and the warehouse address of vehicle；
Waiting time estimates module, for by the warehouse address, the Order Address and the vehicle-state input time it is pre- Estimate model, obtains each waiting time that can sell vehicle；The time prediction model is to complete order training according to history；
Distribution project generation module is obtained for handling the warehouse address, the Order Address and the waiting time To the smallest vehicle delivery scheme of total waiting time.
10. device according to claim 9, which is characterized in that described device further include:
Order reception module, for receiving the purchase vehicle order of client terminal transmission；
Order information extraction module, for extracting vehicle demand and Order Address in the purchase vehicle order；
Order matching module, in the first vehicle supply range vehicle corresponding with Order Address pond search for it is described Vehicle demand is matched to sell vehicle of registering the license, and the vehicle-state for selling vehicle of registering the license is that vehicles identifications have been closed with license plate mark Connection；
Order memory module, for when be not matched to it is described can sell register the license vehicle when, using the purchase vehicle order as not matching purchase Vehicle order is stored into order pond；
Vehicle deploying module, for when be matched to it is described can sell register the license vehicle when, according to the warehouse for selling vehicle of registering the license The Order Address of location and the purchase vehicle order generates vehicle delivery scheme.
11. device according to claim 9, which is characterized in that the distribution project generation module includes:
Distribution project generation unit, for using bipartite graph cum rights maximum matching algorithm or Hungary Algorithm to the warehouse Location, the Order Address and the waiting time are handled, and the smallest vehicle delivery scheme of total waiting time is obtained.
12. device according to claim 9, which is characterized in that the distribution project generation module includes:
Bipartite graph drawing unit will be described for using the warehouse address and the Order Address as the node in bipartite graph The waiting time between node in bipartite graph is as weight；
Scheme matches generation unit, for seeking the maximum weight matching of the bipartite graph, obtains that total waiting time is the smallest to be sold Vehicle distribution project corresponding with purchase vehicle order.
13. device according to claim 9, which is characterized in that described device further include:
Information of vehicles receiving module, it is described to sell information of vehicles for receiving the information of vehicles of selling of warehousing management terminal transmission In vehicle-state be that vehicles identifications and license plate are identified and be associated with；
It supplies range and obtains module, for that can sell information of vehicles corresponding second vehicle supply model according to license plate mark acquisition It encloses；
Vehicle match module, for described not matching purchase vehicle for the Order Address is corresponding with the second vehicle supply range The vehicle demand of order is matched with the information of vehicles of selling；
Vehicle storage module, for when it is described sell information of vehicles with it is described do not match purchase vehicle order it fails to match when, will be described Information of vehicles storage can be sold into vehicle pond；
Vehicle deploying module, for when it is described sell information of vehicles with it is described do not match purchase vehicle order successful match when, according to institute The warehouse address of information of vehicles can be sold by, which stating, generates vehicle delivery scheme with the Order Address for not matching purchase vehicle order.
14. device according to claim 9, which is characterized in that the waiting time estimates module and includes:
Training order acquiring unit, the history for obtaining preset quantity complete order as sample training order；
Sample distribution information extraction unit, for extracting sample distribution information from the sample training order；
Learning training unit is obtained for carrying out machine learning training to the sample distribution information according to each sample training order To time prediction model.
15. device according to claim 14, which is characterized in that the waiting time estimates module and includes:
Assessment verifying order acquiring unit completes order as assessment for obtaining the history different from the sample training order Verify order；
History distribution information extraction unit, for extracting history distribution information, history dispatching from assessment verifying order Information includes history warehouse address, History Order address, history waiting time and history vehicle-state；
Waiting time estimates unit, for will history warehouse address, History Order address and history vehicle-state input described in Time prediction model, is verified the estimated time；
Assessment unit, for carrying out verifying assessment, institute to the verifying estimated time and history waiting time by evaluation criteria Evaluation criteria is stated as at least one in the mean value of absolute deviation, the variance of absolute deviation, the median of absolute deviation, R2 score value Kind.
16. device according to claim 9, which is characterized in that described device further include:
Time-obtaining module, when the quantity for that can sell vehicle described in the judgement is less than the quantity for not matching purchase vehicle order, Obtain lower single time in current time and the purchase vehicle order；
Order Sorting module, for being arranged according to the current time and the difference of lower single time the purchase vehicle order Sequence；
MIM message input module, in the purchase vehicle order that the quantity for that can sell vehicle according to stands out the difference The warehouse address, the Order Address and the vehicle-state input trained time prediction model, the purchase vehicle is ordered Difference described in individual palpation is arranged from big to small.
17. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists In the step of processor realizes any one of claims 1 to 8 the method when executing the computer program.
18. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program The step of method described in any item of the claim 1 to 8 is realized when being executed by processor.
CN201910504784.4A 2019-06-12 2019-06-12 Vehicle allocation method and device, computer equipment and storage medium Active CN110264133B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910504784.4A CN110264133B (en) 2019-06-12 2019-06-12 Vehicle allocation method and device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910504784.4A CN110264133B (en) 2019-06-12 2019-06-12 Vehicle allocation method and device, computer equipment and storage medium

Publications (2)

Publication Number Publication Date
CN110264133A true CN110264133A (en) 2019-09-20
CN110264133B CN110264133B (en) 2022-04-19

Family

ID=67917736

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910504784.4A Active CN110264133B (en) 2019-06-12 2019-06-12 Vehicle allocation method and device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN110264133B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110992129A (en) * 2019-11-18 2020-04-10 浙江大搜车软件技术有限公司 Vehicle order matching method and device, computer equipment and storage medium
CN112990527A (en) * 2019-12-17 2021-06-18 金毛豆科技发展(北京)有限公司 Aging estimation method and device
CN113421039A (en) * 2021-05-21 2021-09-21 浙江大搜车融资租赁有限公司 Vehicle management method, device and equipment
CN115577815A (en) * 2022-10-09 2023-01-06 南京领行科技股份有限公司 Order processing method and device, electronic equipment and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107122836A (en) * 2017-04-14 2017-09-01 上海雷腾软件股份有限公司 A kind of method and apparatus for vehicle distribute leaflets
CN107886285A (en) * 2017-12-25 2018-04-06 康美药业股份有限公司 Supply and marketing management method, equipment and computer-readable recording medium
CN108197835A (en) * 2018-02-05 2018-06-22 北京航空航天大学 Method for allocating tasks, device, computer readable storage medium and electronic equipment
CN109544279A (en) * 2018-11-05 2019-03-29 广州大学 The commodity adaption system and method quickly delivered towards order
CN109583770A (en) * 2018-11-28 2019-04-05 清华四川能源互联网研究院 Vehicle dispatching method and device
CN109657820A (en) * 2018-10-23 2019-04-19 厦门大学 A kind of taxi matching process reserved

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107122836A (en) * 2017-04-14 2017-09-01 上海雷腾软件股份有限公司 A kind of method and apparatus for vehicle distribute leaflets
CN107886285A (en) * 2017-12-25 2018-04-06 康美药业股份有限公司 Supply and marketing management method, equipment and computer-readable recording medium
CN108197835A (en) * 2018-02-05 2018-06-22 北京航空航天大学 Method for allocating tasks, device, computer readable storage medium and electronic equipment
CN109657820A (en) * 2018-10-23 2019-04-19 厦门大学 A kind of taxi matching process reserved
CN109544279A (en) * 2018-11-05 2019-03-29 广州大学 The commodity adaption system and method quickly delivered towards order
CN109583770A (en) * 2018-11-28 2019-04-05 清华四川能源互联网研究院 Vehicle dispatching method and device

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
宋海洋: "基于JAVA的汽车销售订单管理系统", 《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》 *
蒋凡 等: "基于外卖物流配送大数据的调度系统", 《大数据》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110992129A (en) * 2019-11-18 2020-04-10 浙江大搜车软件技术有限公司 Vehicle order matching method and device, computer equipment and storage medium
CN112990527A (en) * 2019-12-17 2021-06-18 金毛豆科技发展(北京)有限公司 Aging estimation method and device
CN113421039A (en) * 2021-05-21 2021-09-21 浙江大搜车融资租赁有限公司 Vehicle management method, device and equipment
CN115577815A (en) * 2022-10-09 2023-01-06 南京领行科技股份有限公司 Order processing method and device, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN110264133B (en) 2022-04-19

Similar Documents

Publication Publication Date Title
CN110264133A (en) Vehicle deploying method, apparatus, computer equipment and storage medium
Kranenburg et al. A new partial pooling structure for spare parts networks
Atan et al. Assemble-to-order systems: A review
Silbermayr et al. A multiple sourcing inventory model under disruption risk
US11928647B2 (en) System and method to predict service level failure in supply chains
EP3070667A1 (en) Revenue management system and revenue management method
Yang et al. Service parts inventory control with lateral transshipment and pipeline stockflexibility
WO2001097135A2 (en) Event revenue management system
CN110135815B (en) Travel order monitoring method and device, computer equipment and storage medium
US20200175461A1 (en) Method and system for two-echelon inventory allocation
US20160180256A1 (en) History-based probability forecasting
CN112070423A (en) Stock pre-occupation method and device, electronic equipment and storage medium
CN102073940A (en) Station platform dynamic distribution method and system during on-line reservation of supplier
CN112381482A (en) Material management method and device, electronic equipment and storage medium
Jose et al. On a retrial production inventory system with vacation and multiple servers
CN111178830A (en) Cost accounting method and device, computer equipment and storage medium
US20200175531A1 (en) Method and system for reserving stock in a regional distribution center
Tunacan et al. The impact of information sharing on different performance indicators in a multi-level supply chain
KR20220020605A (en) Electronic logistics management system and logistics management method to manage safety inventory
US20170220970A1 (en) Storage area management system and storage area management method
JP2014026483A (en) Inter-shop commodity transfer method and program using causal information
JPH08137961A (en) Processing system and its managing method for information on product
CN110599100A (en) Warehouse goods space recommendation method and device for commodities
REMBULAN et al. An Integrated Model of Continuous Review Inventory and Vehicle Routing Problem with Time Windows
CN113822634A (en) Cold chain inventory allocation method and device, computer equipment and storage medium

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