CN114492934A - Method and device for selecting addresses of warehouse - Google Patents

Method and device for selecting addresses of warehouse Download PDF

Info

Publication number
CN114492934A
CN114492934A CN202111600398.9A CN202111600398A CN114492934A CN 114492934 A CN114492934 A CN 114492934A CN 202111600398 A CN202111600398 A CN 202111600398A CN 114492934 A CN114492934 A CN 114492934A
Authority
CN
China
Prior art keywords
warehouse
information
call
demand
vector set
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.)
Withdrawn
Application number
CN202111600398.9A
Other languages
Chinese (zh)
Inventor
李晓宇
刘大成
刘坤
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.)
Nanjing Suning Software Technology Co ltd
Original Assignee
Nanjing Suning 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 Nanjing Suning Software Technology Co ltd filed Critical Nanjing Suning Software Technology Co ltd
Priority to CN202111600398.9A priority Critical patent/CN114492934A/en
Publication of CN114492934A publication Critical patent/CN114492934A/en
Priority to CA3184567A priority patent/CA3184567C/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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 OR CALCULATING; 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
    • G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Evolutionary Biology (AREA)
  • Game Theory and Decision Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Genetics & Genomics (AREA)
  • Artificial Intelligence (AREA)
  • Finance (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Physiology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Educational Administration (AREA)
  • Accounting & Taxation (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application relates to a method and a device for selecting addresses of warehouses, the prepared information of at least one predetermined alternative warehouse and each demand place is obtained, the calling information of the at least one alternative warehouse is generated through a preset model according to the prepared information, the preset model can comprehensively evaluate the availability of the alternative warehouse in combination with cost and time effectiveness to obtain more optimal calling information, the address of a target warehouse is selected according to the calling information, the address of the calling warehouse can be reasonably selected, the logistics distribution efficiency is improved, the logistics inventory backlog is reduced, and the efficient operation of a logistics system is ensured.

Description

Method and device for selecting addresses of warehouse
Technical Field
The application relates to the technical field of warehouse logistics, in particular to a method and a device for selecting a warehouse site.
Background
With the rise of online markets worldwide, online transactions provide a convenient and efficient way for customers and retailers. To support the plethora of transaction services on-line, on-line retailers need to provide a supply chain network to provide more efficient services. Along with the development of the logistics industry and the retail industry, the selection of the warehouse location can greatly affect the operation cost and efficiency. How to optimize warehouse site selection of a logistics system which is one of key links in a supply chain network is one of key factors for improving the logistics transportation quality and efficiency.
At present, a 'factor specific gravity method' or a 'gravity center method' is generally adopted for warehouse address selection, and the problem of regional concentration of warehouse addresses selected according to the methods due to unreasonable logistics planning and layout causes low logistics distribution efficiency and unsmooth operation of a logistics system, thereby causing huge waste of logistics resources.
Disclosure of Invention
Therefore, it is necessary to provide a method and an apparatus for selecting a warehouse address to reasonably select and call the address of the warehouse, improve the logistics distribution efficiency, reduce the backlog of the logistics warehouse, and ensure the efficient operation of the logistics system.
In a first aspect, a method for addressing a warehouse is provided, the method comprising:
acquiring the preparation information of at least one predetermined alternative warehouse and each demand place;
generating calling information of at least one alternative warehouse through a preset model according to the preparation information;
and selecting the address of the target warehouse according to the calling information.
In a possible implementation manner, generating, by using a preset model, invocation information of at least one alternative warehouse according to the preparation information includes:
generating a calling vector of at least one alternative warehouse according to the preparation information;
and generating calling information of at least one alternative warehouse through a preset model according to the calling vector.
In a possible implementation manner, generating, by using a preset model, invocation information of at least one candidate warehouse according to an invocation vector includes:
inputting the calling vectors into a preset model, and randomly selecting at least one calling vector to obtain a first calling vector set;
randomly selecting two calling vectors from the first calling vector set, and correspondingly exchanging elements in the two calling vectors with the same cross probability to obtain a second calling vector set;
adjusting the calling vectors in the second calling vector set through the user-defined mutation operator to obtain a third calling vector set;
and performing genetic algorithm iteration for preset times on the first call vector set and the third call vector set to generate call information of at least one alternative warehouse.
In one possible implementation, the genetic algorithm iteration comprises:
combining the third call vector set and the first call vector set to obtain a fourth call vector set;
performing fast non-dominated sorting on the call vectors in the fourth call vector set, and selecting the call vectors in the first layer pareto frontier as a fifth call vector set;
randomly taking out K call vectors from the fifth call vector set, and reserving the call vectors meeting preset conditions to obtain a sixth call vector set;
randomly selecting two calling vectors from the sixth calling vector set, and correspondingly exchanging elements in the two calling vectors with the same cross probability to obtain a seventh calling vector set;
and adjusting the call vector in the seventh call vector set as the call information of the at least one alternative warehouse through the custom mutation operator.
In a possible implementation manner, adjusting the call vectors in the second call vector set by a custom mutation operator to obtain a third call vector set includes:
randomly selecting n first warehouses from at least one alternative warehouse, wherein n is more than 0 and less than m, and m is the number of the preset selected warehouses;
randomly selecting m-n second warehouses from the remaining alternative warehouses of the at least one alternative warehouse;
determining an optional warehouse corresponding to each demand place according to the call vector of the demand place corresponding to the first warehouse and the call vector of the demand place corresponding to the second warehouse;
and adjusting the values of all elements of the call vectors in the second call vector set to a preset range according to the optional warehouse corresponding to each demand place to obtain a third call vector set.
In one possible implementation manner, after selecting the address of the target repository according to the call information, the method further includes:
determining demand place sets with discontinuous space according to the preparation information of the target warehouse and the demand places corresponding to the target warehouse;
calculating the product value of the number of the target warehouses corresponding to all demand places in the demand place set;
and when the product value is larger than a first threshold value or smaller than a second threshold value, determining the warehouse opening address of the warehouse corresponding to the demand place set according to the preparation information of the target warehouse corresponding to the demand place set and the demand place set.
In one possible implementation, the preparation information includes cost information of at least one alternative warehouse and each demand place; acquiring the predetermined preparation information of at least one alternative warehouse and each demand place, wherein the preparation information comprises the following steps:
acquiring historical cost information and historical order information of an existing warehouse and each demand place;
acquiring first coverage information of an existing warehouse and each demand place and second coverage information of at least one alternative warehouse and each demand place;
and fitting the cost information of the at least one alternative warehouse and each demand place according to the historical cost information, the historical order information, the first coverage information and the second coverage information.
In one possible implementation manner, the preparation information comprises transportation timeliness of at least one alternative warehouse and each demand place; acquiring the predetermined preparation information of at least one alternative warehouse and each demand place, wherein the preparation information comprises the following steps:
acquiring order transportation time of an existing warehouse and each demand place;
and fitting the transportation timeliness of at least one alternative warehouse and each demand place according to the historical order information, the order transportation time, the first coverage information and the second coverage information.
In one possible implementation, the method further includes:
and displaying the position of the target warehouse in a terminal display area according to the address of the target warehouse.
In a second aspect, there is provided an apparatus for addressing a warehouse, the apparatus comprising:
the acquisition module is used for acquiring the predetermined preparation information of at least one alternative warehouse and each demand place;
the generating module is used for generating calling information of the at least one alternative warehouse through a preset model according to the preparation information;
and the selection module is used for selecting the address of the target warehouse according to the calling information.
According to the method and the device for selecting the warehouse address, the predetermined preparation information of at least one alternative warehouse and each demand place is obtained, the calling information of the at least one alternative warehouse is generated through the preset model according to the preparation information, the preset model can comprehensively evaluate the availability of the alternative warehouse in combination with cost and time effectiveness to obtain better calling information, the address of the target warehouse is selected according to the calling information, the address of the calling warehouse can be reasonably selected, the logistics distribution efficiency is improved, the logistics inventory backlog is reduced, and the efficient operation of a logistics system is ensured.
Drawings
FIG. 1 is a schematic flow chart of a method for locating a warehouse according to an embodiment of the present application;
FIG. 2 is a block diagram of a warehouse location device in an embodiment of the present application;
FIG. 3 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In the existing warehouse site selection method, the site selection of the optimal warehouse is usually carried out by a factor specific gravity method or a gravity center method. In the factor-specific gravity method, a decision maker needs to consider various factors, such as natural factors, operating environment factors, infrastructure conditions, types of logistics centers, types of commodities and the like. The factors are used as the basis of warehouse site selection, a qualitative analysis method is mostly adopted for primary site selection, a plurality of warehouse sites are roughly selected, quantitative analysis and quantitative comparison are considered, and a better scheme is finally obtained. The gravity center method is a simulation method, which considers the demand place and the warehouse in the logistics system as the logistics system distributed in a certain plane range, respectively considers the demand quantity and the resource quantity of each point as the weight of the object, and finds the coordinate point with the minimum total transportation cost as the optimal warehouse site.
The technical scheme hides many problems, for example, logistics planning and layout are unreasonable, and the problem of regional concentration is easy to occur, and merchants build logistics centers locally and want to build local warehouses into domestic first-class warehouse bases, so that the problem of logistics heat is caused, and meanwhile, the problem of division of departments is caused, so that the logistics management efficiency is low, the logistics system is not smooth in operation, and the like.
In order to solve the problem of the prior art, the embodiment of the application provides a method and a device for warehouse address selection. The method for selecting a warehouse site provided by the embodiment of the present application is first described below.
Fig. 1 is a schematic flow chart illustrating a method for locating a warehouse according to an embodiment of the present application. As shown in fig. 1, the method may include the steps of:
s110, obtaining the predetermined preparation information of at least one alternative warehouse and each demand place.
In the conventional logistics system, a central warehouse (RDC) and a front warehouse (FDC) are provided, the RDC is a Distribution Center which performs Distribution service to users in a plurality of provincial areas with strong radiation capability and stock preparation, and the FDC is a front logistics Center which is built in an important area below a Regional warehouse Center. The location selection and membership of the RDCs and FDCs determines the overall transportation cost and delivery timeliness.
According to the logistics business requirements, the alternative warehouse address and the warehouse type which can be constructed by each place are preferentially determined, and according to the difference of the business requirements, each place can be used as an alternative of FDC or an alternative of RDC, or can be used as an alternative of two types of warehouses at the same time. And simultaneously, determining the demand place of the alternative warehouse to be served according to the logistics business demand.
And acquiring the preparation information of at least one predetermined alternative warehouse and each demand place through the historical information of the logistics system, wherein the preparation information comprises order information, transportation time, transportation cost, coverage relation and other information.
And S120, generating calling information of at least one alternative warehouse through a preset model according to the preparation information.
The preset model is a multi-objective optimization model with constraint conditions and a genetic algorithm, wherein the constraint conditions comprise:
warehouse type: warehouses are divided into two categories, RDCs and FDCs. A single RDC may have multiple dependent FDCs, and an FDC may have only one corresponding RDC. The optional range of RDC coverage requirements must be within the scope of their corresponding RDC.
The coverage relationship is as follows: each warehouse has its own coverage area and cannot serve the demand places outside its coverage area. The warehouse is a unit of demand place, one demand place can only have one warehouse, and the warehouse type can only be one of RDC and FDC. Each warehouse can cover multiple places of need, and as long as one place of need is covered, the warehouse is called, and all places of need have only one warehouse to cover.
Warehouse dependencies: within the optional scope, there may be an overlap in the dependencies between RDCs and FDCs, whether FDCs are enabled and to which RDCs the FDC belongs are also within the decision scope. The target warehouse must have RDC bins, and cannot be all FDCs. Similarly, the called FDC bin must have a corresponding RDC bin call.
And the preset model generates calling information of at least one alternative warehouse according to the preparation information by adopting two objective functions of formula (1) and formula (2). Wherein, formula (1) represents maximizing the aging, and formula (2) represents minimizing the cost.
Figure BDA0003432935720000061
Wherein odpiRepresents the ratio of the next day of the j-th candidate warehouse to the n demand places, at this time, i belongs to [ (j-1) n +1, jn]，j∈[1，m]；oq_mniRepresents the order quantity of the jth candidate warehouse to n demand places, at the moment, i belongs to [ (j-1) n +1, jn]，j∈[1，m]；xiThe coverage information of the jth candidate warehouse to the n demand places is represented, oq represents the order quantity of the n demand places, m represents the number of the candidate warehouses, and n represents the number of the demand places.
Figure BDA0003432935720000062
Wherein,
Figure BDA0003432935720000063
denotes the invocation of the ith warehouse candidate, ic denotes the initial inventory cost, iwn denotes the initial inventory quantity, triIndicating the transfer rate, weight, from RDC to FDC at the ith demand locationiIndicating the weight of the cargo at the ith demand location, oriRepresenting the operation rate from RDC to FDC of the ith demand site, pni representing the parcel number of the ith demand site, freightiRepresents the transportation cost and the operation cost, x, of the ith alternative warehouse covering the corresponding demand placeiAnd representing the coverage information of the corresponding demand place of the ith alternative warehouse.
The call information is a collection of multiple call vectors, which can be expressed as:
X＝[x1，...，xn，xn+1，...，xn×(m-1)+1，...，xm×n]
wherein X represents a call vector, m represents the number of alternative warehouses, n represents the number of demand places, and XiAnd representing coverage information of the alternative warehouse to the demand site. x is the number ofi0 means no coverage, xi1 denotes RDC warehouse coverage, xiTable 2 (the two tables)An FDC warehouse overlay is shown.
In some embodiments, generating, according to the preparation information, invocation information of the at least one alternative repository through a preset model includes:
generating a calling vector of at least one alternative warehouse according to the preparation information;
and generating calling information of at least one alternative warehouse through a preset model according to the calling vector.
The preparation information comprises alternative warehouse types, addresses of alternative warehouses, coverage information of the alternative warehouses to various demand places, transportation timeliness, cost information and the like. According to the preparation information, vectors of different categories can be generated to form a calling vector.
And the dimension of the vector formed by the proportion of the next day of each alternative warehouse covering all the demand places is m multiplied by n, the element value is-1, and the fact that the warehouse can not cover the corresponding demand place is shown. The element value is greater than or equal to 0, which indicates that the warehouse can cover the corresponding demand place. The specific element value represents the proportion of the order which can reach the next day to reach the grade in the order of the current demand. For example, 0.6 indicates that when an alternative warehouse covers a demand site, 60% of all orders in the demand site can be fulfilled for the next day.
And a vector consisting of cost information, wherein the dimension is m multiplied by n, and the vector represents the transportation cost and the operation cost of the warehouse covering the corresponding demand place.
And a vector consisting of the order quantity, with n dimensions, represents the order quantity of each demand place.
And a vector consisting of the cargo weights, wherein the dimensionality is n-dimensionality and represents the cargo weight corresponding to the order representing each demand place.
And a vector consisting of the package quantity, wherein the dimensionality is n-dimensional, and the vector represents the package quantity corresponding to the order of each demand place.
And a vector consisting of the coverage information, with the dimension of m multiplied by n, represents the coverage condition of the alternative warehouse to each demand place.
And (3) acquiring all vectors of the variable data participating in the formula (1) and the formula (2), wherein the vectors are not listed one by one, inputting the vectors into a preset model, and inputting a better calling scheme by the preset model through a series of calculations.
S130, selecting the address of the target warehouse according to the calling information.
Analyzing the calling information, obtaining which warehouses need to be called as target warehouses and the type of each called warehouse, if an FDC warehouse is called, which RDC warehouse the FDC warehouse belongs to, which demand places each warehouse specifically covers, and the like. The specific analysis process is as follows:
the 1 st to n th elements in the calling vector X represent the coverage of the 1 st candidate bin to all n demand places, the n +1 st to 2n th elements represent the coverage of the 2 nd candidate bin to all n demand places, and so on, each n element represents the coverage of one warehouse to n demand places. If all the n elements corresponding to a warehouse are zero, the warehouse is not called. Otherwise, if any element is not zero, the warehouse is called.
For an invoked warehouse, the values of non-zero elements in n elements corresponding to the warehouse are necessarily the same. If the value is 1, the warehouse is an RDC warehouse; if the value is 2, the warehouse is an FDC warehouse.
If the FDC bin exists, selecting an attribution scheme with the lowest cost according to the bin opening condition of the RDC bin to which the FDC bin can be attributed, the actual FDC bin covering city condition, the allocation cost from different alternative RDC bins to the FDC bin and the transportation cost, and determining which RDC bin the FDC bin belongs specifically.
The position corresponding to the non-zero element in the n elements corresponding to the warehouse represents the demand place covered by the warehouse.
And selecting a target warehouse according to the analysis result, and determining the address of the target warehouse.
In the embodiment of the application, the preset preparation information of at least one alternative warehouse and each demand place is obtained, the calling information of the at least one alternative warehouse is generated through the preset model according to the preparation information, the preset model can comprehensively evaluate the availability of the alternative warehouse in combination with cost and timeliness to obtain better calling information, and the address of the target warehouse is selected according to the calling information, so that the address of the calling warehouse can be reasonably selected, the logistics distribution efficiency is improved, the logistics inventory backlog is reduced, and the efficient operation of a logistics system is ensured.
In some embodiments, generating, according to the call vector, call information of the at least one candidate warehouse through a preset model includes:
inputting the calling vectors into a preset model, and randomly selecting at least one calling vector to obtain a first calling vector set;
randomly selecting two calling vectors from the first calling vector set, and correspondingly exchanging elements in the two calling vectors with the same cross probability to obtain a second calling vector set;
adjusting the call vectors in the second call vector set through the custom mutation operator to obtain a third call vector set;
and performing genetic algorithm iteration for preset times on the first call vector set and the third call vector set to generate call information of at least one alternative warehouse.
The preset model solves the calling vector through a genetic algorithm, and the genetic algorithm comprises three core operators of selection, intersection and variation. Firstly, randomly initializing a call vector to obtain a first call vector set. And then, generating a second call vector set by adopting a uniformly distributed crossover operator for the first call vector set, namely randomly selecting two call vectors from the first call vector set, and correspondingly exchanging elements in the two call vectors with the same crossover probability to obtain the second call vector set. And finally, adjusting the call vectors in the second call vector set through the user-defined mutation operator to obtain a third call vector set. And performing genetic algorithm iteration on the first call vector set and the third call vector set until reaching a preset number, and outputting a final call vector set as call information of at least one alternative warehouse. The preset times can be selected according to data obtained from experimental experience, so that the iteration effect is optimal.
In some embodiments, the genetic algorithm iteration comprises:
combining the third call vector set and the first call vector set to obtain a fourth call vector set;
performing fast non-dominated sorting on the call vectors in the fourth call vector set, and selecting the call vectors in the first layer pareto frontier as a fifth call vector set;
randomly taking out K call vectors from the fifth call vector set, and reserving the call vectors meeting preset conditions to obtain a sixth call vector set;
randomly selecting two calling vectors from the sixth calling vector set, and correspondingly exchanging elements in the two calling vectors with the same cross probability to obtain a seventh calling vector set;
and adjusting the call vector in the seventh call vector set as the call information of the at least one alternative warehouse through the custom mutation operator.
And combining the third call vector set and the first call vector set to obtain a fourth call vector set, so that the number of elements in the new call vector set is doubled. And (3) processing the calling vectors through a championship selection operator, performing playback sampling, taking K vectors from the total at one time, taking the optimal vectors from the vectors for reservation, and repeating the operation for several times according to the number of the vectors needing to be reserved to obtain a sixth calling vector set.
And then, processing a sixth calling vector by adopting a uniformly distributed crossover operator, randomly selecting two calling vectors from a sixth calling vector set, forming the two calling vectors into paired vectors, correspondingly exchanging elements in the paired vectors with the same crossover probability, determining the positions of the elements exchanged in the calling vectors by the crossover probability, and correspondingly exchanging the elements in the paired vectors with the same crossover probability, namely exchanging the elements at the same positions in the paired vectors to obtain a new calling vector, thereby forming a seventh calling vector set.
Finally, the calling vectors in the seventh calling vector set are adjusted through the mutation operator pair. There are many common mutation operators available, such as: basic potential variation, uniform variation, boundary variation, non-uniform variation, Gaussian approximation variation, and the like. However, the existing general mutation operator cannot guarantee that the mutated individuals hit a feasible space, and under the condition of more and stricter constraint conditions, a larger population scale and evolution times need to be set, so that it is possible to guarantee that the individuals meeting the constraint exist in the final population. This process not only consumes a large amount of resources to solve, but also does not guarantee that a solution that meets the constraints can be derived.
In order to obtain the calling information more practically, the calling vector in the seventh calling vector set is adjusted by a user-defined mutation operator, the constraint condition of the preset model is set to be the optional range of each element of the calling vector, the elements of each calling vector are in the optional range, random mutation is carried out according to the mutation probability, and the calling information of at least one alternative warehouse is obtained. And if the iteration times do not reach the preset times, taking the adjusted seventh calling vector set as initial data of the next iteration to continue to calculate.
The user-defined mutation operator in the embodiment of the application can correspond to complex constraint conditions, so that the calling vector processed by the mutation operator can meet the constraint conditions certainly, the mode that in an original algorithm, a vector set is filtered through the constraint conditions is changed, the probability that the calling vector hits a feasible region in the evolution process is improved, especially under the condition that the constraint conditions are complex, the integral iteration times can be effectively reduced on the premise that calling information is ensured, and the algorithm solving efficiency is improved.
In some embodiments, adjusting the call vectors in the second call vector set by the custom mutation operator to obtain a third call vector set includes:
randomly selecting n first warehouses from at least one alternative warehouse, wherein n is more than 0 and less than m, and m is the number of the preset selected warehouses;
randomly selecting m-n second warehouses from the remaining alternative warehouses of the at least one alternative warehouse;
determining an optional warehouse corresponding to each demand place according to the call vector of the demand place corresponding to the first warehouse and the call vector of the demand place corresponding to the second warehouse;
and adjusting the values of all elements of the call vectors in the second call vector set to a preset range according to the optional warehouse corresponding to each demand place to obtain a third call vector set.
When the user-defined mutation operator is calculated, firstly, a calling vector participating in mutation calculation is selected, and the number m of the preset selection warehouse and the value of the mutation probability are determined, wherein the value of the mutation probability can be selected according to actual requirements, and is not limited here.
And then randomly selecting n first warehouses from at least one alternative warehouse, and enabling the value of n to be smaller while ensuring that the n first warehouses can cover all places with demands as much as possible.
And randomly selecting m-n alternative warehouses from the rest alternative warehouses, so that the number of the alternative warehouses participating in mutation is equal to the number m of the preset selection warehouses.
According to m randomly selected alternative warehouses, taking demand places as units, counting the optional warehouses corresponding to each demand place, wherein the time effectiveness of the optional warehouse positions is optimal or the cost is lowest.
Randomly selecting any value between 0 and 1 to compare with the variation probability, if the any value is smaller than the variation probability, indicating that the calling vector participating in the variation calculation does not need to be varied, checking each element of the calling vector, and adjusting the three aspects of no warehouse coverage in a demand place, multiple warehouse coverage in the demand place and no preset optional range of a warehouse covering the demand place, so as to ensure that the calling warehouse must cover the demand place where the calling warehouse is located. And adjusting the value of the calling vector to be within a preset range according to the adjustment condition and storing the adjusted calling vector to a third calling vector set.
If any value is larger than the mutation probability, it is indicated that the call vectors participating in the mutation calculation need to be mutated, in each demand place, a warehouse is randomly selected in the selectable warehouse, the warehouse must cover the demand place where the warehouse is located, and the adjusted call vectors are stored in a third call vector set.
The user-defined mutation operator is added with a process of checking and adjusting the legality (conforming to the constraint) of the calling vector in one step, namely, whether the values of all elements of all the calling vectors are legal is checked, if not, a value is randomly selected in an optional value range, so that the diversity of the calling vectors is ensured, all the calling vectors are also ensured to conform to the model constraint, the solving efficiency of the genetic algorithm is greatly improved, and the calling information is more accurate and reasonable.
In some embodiments, after selecting the address of the target repository based on the call information, the method further comprises:
determining demand place sets with discontinuous space according to the preparation information of the target warehouse and the demand places corresponding to the target warehouse;
calculating the product value of the number of the target warehouses corresponding to all demand places in the demand place set;
and when the product value is larger than a first threshold value or smaller than a second threshold value, determining the warehouse opening address of the warehouse corresponding to the demand place set according to the preparation information of the target warehouse corresponding to the demand place set and the demand place set.
In the calling scheme, there may be a spatial discontinuity of the city group covered by the warehouse, and there are many reasons for this result, which may be:
data problem: because the data is subsequently brought into the data calculated by the model, the data is derived from manual statistics and model fitting, and errors are inevitable. Thus possibly resulting in a city that is relatively far from warehouse a instead having a relatively good time efficiency or a relatively low cost. This is a situation that may cause the coverage city of warehouse a to be spatially discontinuous.
Pareto optimal: the time efficiency of selecting warehouse A in a city is better, and the cost of selecting warehouse B is lower, so that both the two options are feasible from the multi-target optimization perspective, but the spatial discontinuity phenomenon can be caused by selecting warehouse A in a city.
Aiming at the problems, the spatial continuity optimization is carried out on the calling scheme, and the specific logic is as follows: finding out demand places with discontinuous space based on whether warehouses corresponding to adjacent demand places are consistent or not, dividing the demand places into isolated demand place sets according to a communication relation, and then selecting an optimal warehouse to cover the demand place set from all target warehouses of a single demand place set.
The demand place set with discontinuous space refers to a demand place which does not include the warehouse in a plurality of adjacent demand places in the coverage range of the same warehouse, and the plurality of adjacent demand places are called as demand place sets with discontinuous space, and each demand place is an isolated demand place.
Firstly, a calling vector to be optimized is randomly selected from calling information, a demand place set with discontinuous space is determined according to preparation information of demand places corresponding to a target warehouse and the target warehouse in the calling vector, and specifically, the demand place set with discontinuous space is determined according to coverage information of the demand places corresponding to the target warehouse and the target warehouse.
And calculating a product value of the number of the target warehouses corresponding to all demand places in the demand place set, and determining the warehouse opening address of the warehouse corresponding to the demand place set according to the preparation information of the target warehouse corresponding to the demand place set and the demand place set when the product value is greater than a first threshold value or smaller than a second threshold value.
The first threshold may be set to 0 and the second threshold may be set to a larger constant, such as 1000, when the product value is greater than 0, indicating that there are multiple alternative warehouses on demand, which may be warehouse selected. When the product value is less than 1000, the coverage scheme which needs to be explored subsequently is moderate, the calculation efficiency is high, at the moment, all possible coverage schemes in the demand place set are traversed, the coverage schemes comprise warehouse types, transportation timeliness, cost information and the like, an optimal coverage scheme is selected on the premise that the spatial continuity is guaranteed, elements of the call vector are adjusted according to the coverage scheme, and the optimized call vector is output.
When the product value is 0, it indicates that there is a demand site without a target warehouse, which cannot be warehouse-selected. When the product value is larger than 1000, the coverage schemes needing to be explored subsequently are too many, the calculation efficiency is low, at the moment, no proper optimization scheme exists, and the call vector is discarded.
The optimized calling information effectively solves the phenomenon that the urban group covered by the warehouse is discontinuous in space, so that a calling scheme obtained according to the calling information is more feasible.
In some embodiments, the provisioning information includes cost information for at least one alternative warehouse with each demand site; acquiring the predetermined preparation information of at least one alternative warehouse and each demand place, wherein the preparation information comprises the following steps:
acquiring historical cost information and historical order information of an existing warehouse and each demand place;
acquiring first coverage information of an existing warehouse and each demand place and second coverage information of at least one alternative warehouse and each demand place;
and fitting the cost information of the at least one alternative warehouse and each demand place according to the historical cost information, the historical order information, the first coverage information and the second coverage information.
The existing warehouse refers to all called warehouses in the logistics system. According to the actual order condition of a certain past time period, historical order information of each demand place is counted, wherein the historical order information comprises information such as order quantity, cargo weight and package quantity. Historical order information is obtained, and a data basis is provided for obtaining a more accurate and higher-reliability calling scheme.
According to the existing warehouse calling scheme and the existing warehouse city covering scheme, historical cost information generated when the existing warehouse covers each demand place is counted, wherein the historical cost information comprises transportation cost information and operation cost information.
Since the coverage of a warehouse is limited, it is impossible for a warehouse to cover all cities across the country. In order to improve the performance of subsequent calculation and avoid unnecessary calculation, the maximum coverage of each alternative warehouse to each demand place needs to be determined.
The first coverage information comprises an existing warehouse coverage demand place, an existing warehouse non-coverage demand place and the distance between the existing warehouse and the demand place, and the second coverage information comprises an alternative warehouse coverage demand place, an alternative warehouse non-coverage demand place and the distance between the alternative warehouse and the demand place.
In the process of generating the calling information through the preset model, the cost information of at least one alternative warehouse and each demand place is indispensable data, but the data is unknown and needs to be evaluated through historical data of the existing warehouse and each demand place.
The method for evaluating the cost information of the alternative warehouse and each demand place comprises the following steps: and (distance, order quantity and cost) data structures are constructed, the cost is used as target _ value, namely the target value, the distance and the order quantity are used as features, the historical order information is used as training samples, and the fitting model is trained. According to the first coverage information and the second coverage information, the distance between the alternative warehouse and each demand place and the order quantity can be counted, the distance is used as a sample characteristic, and the cost information of the at least one alternative warehouse and each demand place is obtained through a fitting model.
In some embodiments, the preparation information includes transportation age of the at least one alternative warehouse with each demand site; acquiring the predetermined preparation information of at least one alternative warehouse and each demand place, wherein the preparation information comprises the following steps:
acquiring order transportation time of an existing warehouse and each demand place;
and fitting the transportation timeliness of at least one alternative warehouse and each demand place according to the historical order information, the order transportation time, the first coverage information and the second coverage information.
The transportation aging is the ratio of the number of orders reached in the next day of a certain demand place to the total number of orders in the demand place, and the higher the ratio is, the better the aging is. The overall aging is the aging of each demand place, and weighted average is performed according to the order quantity.
The order quantity of the existing warehouse and each demand place is obtained through historical order information, meanwhile, the order transportation time of the existing warehouse and each demand place is obtained, the quantity of orders arriving on the same day and the quantity of orders arriving on the next day of each demand place are determined according to the order transportation time, and the historical transportation timeliness of each demand place is calculated.
Since it is unknown to estimate the transportation aging of the alternative warehouse and each demand location, it is necessary to estimate and obtain the transportation aging according to the historical data of the existing warehouse and each demand location, and train the fitting model by using the distance as feature, that is, the characteristic, the aging as target _ value, that is, the target value, and the historical transportation aging of each demand location covered by the existing warehouse as a training sample. And then counting the distance from each alternative warehouse to each demand place by using the first coverage information, inputting the distance serving as a characteristic into a fitting model, and calculating the transportation timeliness of at least one alternative warehouse and each demand place.
In some embodiments, the method further comprises: and displaying the position of the target warehouse in a terminal display area according to the address of the target warehouse.
And combining the calling scheme, and converting the terminal display area into a map to display the position of the target warehouse according to the address of the target warehouse, so that the user can more intuitively and clearly see the selected and called warehouse and the coverage condition of each warehouse.
It should be understood that, although the steps in the flowchart of fig. 1 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 1 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
In some embodiments, as shown in fig. 2, there is provided a warehouse addressing device 200, comprising: an obtaining module 210, a generating module 220, and a selecting module 230, wherein:
an obtaining module 210, configured to obtain predetermined preparation information of at least one alternative warehouse and each demand location;
a generating module 220, configured to generate, according to the preparation information, call information of the at least one alternative warehouse through a preset model;
and a selecting module 230, configured to select an address of the target warehouse according to the call information.
In the embodiment of the application, the address of the calling warehouse can be reasonably selected, the logistics distribution efficiency is improved, the logistics inventory backlog is reduced, and the efficient operation of a logistics system is ensured.
In some embodiments, the generating module 220 is specifically configured to:
generating a calling vector of at least one alternative warehouse according to the preparation information;
and generating calling information of at least one alternative warehouse through a preset model according to the calling vector.
In some embodiments, the generating module 220 is specifically configured to:
inputting the calling vectors into a preset model, and randomly selecting at least one calling vector to obtain a first calling vector set;
randomly selecting two calling vectors from the first calling vector set, and correspondingly exchanging elements in the two calling vectors with the same cross probability to obtain a second calling vector set;
adjusting the calling vectors in the second calling vector set through the user-defined mutation operator to obtain a third calling vector set;
and performing fast non-dominant sequencing on the call vectors in the third call vector set, and selecting the call vector in the first layer pareto frontier as the call information of at least one alternative warehouse.
In some embodiments, the generating module 220 is specifically configured to:
randomly selecting n first warehouses from at least one alternative warehouse, wherein n is more than 0 and less than m, and m is the number of the preset selected warehouses;
randomly selecting m-n second warehouses from the remaining alternative warehouses of the at least one alternative warehouse;
determining an optional warehouse corresponding to each demand place according to the call vector of the demand place corresponding to the first warehouse and the call vector of the demand place corresponding to the second warehouse;
and adjusting the values of all elements of the call vectors in the second call vector set to a preset range according to the optional warehouse corresponding to each demand place to obtain a third call vector set.
In some embodiments, the apparatus further comprises: a determining device 240, configured to determine a demand place set with discontinuous space according to the preparation information of the demand places corresponding to the target warehouse and the target warehouse after selecting the address of the target warehouse according to the call information;
calculating the product value of the number of the target warehouses corresponding to all demand places in the demand place set;
and when the product value is larger than a first threshold value or smaller than a second threshold value, determining the warehouse opening address of the warehouse corresponding to the demand place set according to the preparation information of the target warehouse corresponding to the demand place set and the demand place set.
In some embodiments, the provisioning information includes cost information for at least one alternative warehouse with each demand site; the obtaining module 210 is specifically configured to:
acquiring historical cost information and historical order information of an existing warehouse and each demand place;
acquiring first coverage information of an existing warehouse and each demand place and second coverage information of at least one alternative warehouse and each demand place;
and fitting the cost information of the at least one alternative warehouse and each demand place according to the historical cost information, the historical order information, the first coverage information and the second coverage information.
In some embodiments, the preparation information includes transportation age of the at least one alternative warehouse with each demand site; the obtaining module 210 is specifically configured to:
acquiring order transportation time of an existing warehouse and each demand place;
and fitting the transportation timeliness of at least one alternative warehouse and each demand place according to the historical order information, the order transportation time, the first coverage information and the second coverage information.
In some embodiments, the apparatus further comprises a presentation module 250 for:
and displaying the position of the target warehouse in a terminal display area according to the address of the target warehouse.
For the specific definition of the warehouse location device, reference may be made to the above definition of the warehouse location method, and details are not described here. The modules in the warehouse addressing device can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In some embodiments, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 3. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing warehouse call data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of addressing a warehouse.
Those skilled in the art will appreciate that the architecture shown in fig. 3 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In some embodiments, there is provided a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor when executing the computer program implementing the steps of:
acquiring the preparation information of at least one predetermined alternative warehouse and each demand place;
generating calling information of at least one alternative warehouse through a preset model according to the preparation information;
and selecting the address of the target warehouse according to the calling information.
In some embodiments, the processor, when executing the computer program, further performs the steps of: generating calling information of at least one alternative warehouse through a preset model according to the preparation information, wherein the calling information comprises: generating a calling vector of at least one alternative warehouse according to the preparation information; and generating calling information of at least one alternative warehouse through a preset model according to the calling vector.
In some embodiments, the processor, when executing the computer program, further performs the steps of: generating calling information of at least one alternative warehouse through a preset model according to the calling vector, wherein the calling information comprises: inputting the calling vectors into a preset model, and randomly selecting at least one calling vector to obtain a first calling vector set; randomly selecting two calling vectors from the first calling vector set, and correspondingly exchanging elements in the two calling vectors with the same cross probability to obtain a second calling vector set; adjusting the calling vectors in the second calling vector set through the user-defined mutation operator to obtain a third calling vector set; and performing genetic algorithm iteration for preset times on the first call vector set and the third call vector set to generate call information of at least one alternative warehouse.
In some embodiments, the processor, when executing the computer program, further performs the steps of: combining the third call vector set and the first call vector set to obtain a fourth call vector set; performing fast non-dominated sorting on the call vectors in the fourth call vector set, and selecting the call vectors in the first layer pareto frontier as a fifth call vector set; randomly taking out K call vectors from the fifth call vector set, and reserving the call vectors meeting preset conditions to obtain a sixth call vector set; randomly selecting two calling vectors from the sixth calling vector set, and correspondingly exchanging elements in the two calling vectors with the same cross probability to obtain a seventh calling vector set; and adjusting the call vector in the seventh call vector set as the call information of the at least one alternative warehouse through the custom mutation operator.
In some embodiments, the processor, when executing the computer program, further performs the steps of: adjusting the call vectors in the second call vector set through the user-defined mutation operator to obtain a third call vector set, which comprises the following steps: randomly selecting n first warehouses from at least one alternative warehouse, wherein n is more than 0 and less than m, and m is the number of the preset selected warehouses; randomly selecting m-n second warehouses from the remaining alternative warehouses of the at least one alternative warehouse; determining an optional warehouse corresponding to each demand place according to the call vector of the demand place corresponding to the first warehouse and the call vector of the demand place corresponding to the second warehouse; and adjusting the values of all elements of the call vectors in the second call vector set to a preset range according to the optional warehouse corresponding to each demand place to obtain a third call vector set.
In some embodiments, the processor, when executing the computer program, further performs the steps of: after selecting the address of the target repository according to the call information, the method further comprises: determining demand place sets with discontinuous space according to the preparation information of the target warehouse and the demand places corresponding to the target warehouse; calculating the product value of the number of the target warehouses corresponding to all demand places in the demand place set; and when the product value is larger than a first threshold value or smaller than a second threshold value, determining the warehouse opening address of the warehouse corresponding to the demand place set according to the preparation information of the target warehouse corresponding to the demand place set and the demand place set.
In some embodiments, the processor when executing the computer program further performs the steps of: the preparation information comprises cost information of at least one alternative warehouse and each demand place; acquiring the predetermined preparation information of at least one alternative warehouse and each demand place, wherein the preparation information comprises the following steps: acquiring historical cost information and historical order information of an existing warehouse and each demand place; acquiring first coverage information of an existing warehouse and each demand place and second coverage information of at least one alternative warehouse and each demand place; and fitting the cost information of the at least one alternative warehouse and each demand place according to the historical cost information, the historical order information, the first coverage information and the second coverage information.
In some embodiments, the processor when executing the computer program further performs the steps of: the preparation information comprises the transportation time limit of at least one alternative warehouse and each demand place; acquiring the predetermined preparation information of at least one alternative warehouse and each demand place, wherein the preparation information comprises the following steps: acquiring order transportation time of an existing warehouse and each demand place; and fitting the transportation timeliness of at least one alternative warehouse and each demand place according to the historical order information, the order transportation time, the first coverage information and the second coverage information.
In some embodiments, the processor, when executing the computer program, further performs the steps of: the method further comprises the following steps: and displaying the position of the target warehouse in a terminal display area according to the address of the target warehouse.
In some embodiments, there is provided a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
acquiring predetermined preparation information of at least one alternative warehouse and each demand place;
generating calling information of at least one alternative warehouse through a preset model according to the preparation information;
and selecting the address of the target warehouse according to the calling information.
In some embodiments, the computer program when executed by the processor further performs the steps of: generating calling information of at least one alternative warehouse through a preset model according to the preparation information, wherein the calling information comprises: generating a calling vector of at least one alternative warehouse according to the preparation information; and generating calling information of at least one alternative warehouse through a preset model according to the calling vector.
In some embodiments, the computer program when executed by the processor further performs the steps of: generating calling information of at least one alternative warehouse through a preset model according to the calling vector, wherein the calling information comprises: inputting the calling vectors into a preset model, and randomly selecting at least one calling vector to obtain a first calling vector set; randomly selecting two calling vectors from the first calling vector set, and correspondingly exchanging elements in the two calling vectors with the same cross probability to obtain a second calling vector set; adjusting the calling vectors in the second calling vector set through the user-defined mutation operator to obtain a third calling vector set;
and performing genetic algorithm iteration for preset times on the first call vector set and the third call vector set to generate call information of at least one alternative warehouse.
In some embodiments, the computer program when executed by the processor further performs the steps of: combining the third call vector set and the first call vector set to obtain a fourth call vector set; performing fast non-dominated sorting on the call vectors in the fourth call vector set, and selecting the call vectors in the first layer pareto frontier as a fifth call vector set; randomly taking out K call vectors from the fifth call vector set, and reserving the call vectors meeting preset conditions to obtain a sixth call vector set; randomly selecting two calling vectors from the sixth calling vector set, and correspondingly exchanging elements in the two calling vectors with the same cross probability to obtain a seventh calling vector set; and adjusting the call vector in the seventh call vector set as the call information of the at least one alternative warehouse through the custom mutation operator.
In some embodiments, the computer program when executed by the processor further performs the steps of: adjusting the call vectors in the second call vector set through the user-defined mutation operator to obtain a third call vector set, which comprises the following steps: randomly selecting n first warehouses from at least one alternative warehouse, wherein n is more than 0 and less than m, and m is the number of the preset selected warehouses; randomly selecting m-n second warehouses from the remaining alternative warehouses of the at least one alternative warehouse; determining an optional warehouse corresponding to each demand place according to the call vector of the demand place corresponding to the first warehouse and the call vector of the demand place corresponding to the second warehouse; and adjusting the values of all elements of the call vectors in the second call vector set to a preset range according to the optional warehouse corresponding to each demand place to obtain a third call vector set.
In some embodiments, the computer program when executed by the processor further performs the steps of: after selecting the address of the target repository according to the call information, the method further comprises: determining demand place sets with discontinuous space according to the preparation information of the target warehouse and the demand places corresponding to the target warehouse; calculating the product value of the number of the target warehouses corresponding to all demand places in the demand place set; and when the product value is larger than a first threshold value or smaller than a second threshold value, determining the warehouse opening address of the warehouse corresponding to the demand place set according to the preparation information of the target warehouse corresponding to the demand place set and the demand place set.
In some embodiments, the computer program when executed by the processor further performs the steps of: the preparation information comprises cost information of at least one alternative warehouse and each demand place; acquiring the predetermined preparation information of at least one alternative warehouse and each demand place, wherein the preparation information comprises the following steps: acquiring historical cost information and historical order information of an existing warehouse and each demand place; acquiring first coverage information of an existing warehouse and each demand place and second coverage information of at least one alternative warehouse and each demand place; and fitting the cost information of the at least one alternative warehouse and each demand place according to the historical cost information, the historical order information, the first coverage information and the second coverage information.
In some embodiments, the computer program when executed by the processor further performs the steps of: the preparation information comprises the transportation time limit of at least one alternative warehouse and each demand place; acquiring the predetermined preparation information of at least one alternative warehouse and each demand place, wherein the preparation information comprises the following steps: acquiring order transportation time of an existing warehouse and each demand place; and fitting the transportation timeliness of at least one alternative warehouse and each demand place according to the historical order information, the order transportation time, the first coverage information and the second coverage information.
In some embodiments, the computer program when executed by the processor further performs the steps of: the method further comprises the following steps: and displaying the position of the target warehouse in a terminal display area according to the address of the target warehouse.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (10)

1.一种仓库选址的方法，其特征在于，所述方法包括：1. a method for warehouse site selection, characterized in that the method comprises: 获取预先确定的至少一个备选仓库与各个需求地的预备信息；Obtain the pre-determined at least one alternative warehouse and the preparatory information of each demand place; 根据所述预备信息，通过预设模型生成所述至少一个备选仓库的调用信息；generating call information of the at least one candidate warehouse by using a preset model according to the preliminary information; 根据所述调用信息，选择目标仓库的地址。According to the calling information, the address of the target warehouse is selected. 2.根据权利要求1所述的方法，其特征在于，所述根据所述预备信息，通过预设模型生成所述至少一个备选仓库的调用信息，包括：2 . The method according to claim 1 , wherein, according to the preliminary information, generating the calling information of the at least one candidate warehouse by using a preset model, comprising: 2 . 根据所述预备信息，生成所述至少一个备选仓库的调用向量；generating a call vector of the at least one candidate warehouse according to the preliminary information; 根据所述调用向量，通过所述预设模型生成所述至少一个备选仓库的调用信息。According to the invocation vector, invocation information of the at least one candidate warehouse is generated by using the preset model. 3.根据权利要求2所述的方法，其特征在于，所述根据所述调用向量，通过所述预设模型生成所述至少一个备选仓库的调用信息，包括：3 . The method according to claim 2 , wherein, generating the call information of the at least one candidate warehouse by using the preset model according to the call vector, comprising: 3 . 将所述调用向量输入所述预设模型随机选择至少一个所述调用向量，得到第一调用向量集合；Inputting the call vector into the preset model to randomly select at least one call vector to obtain a first call vector set; 从所述第一调用向量集合中随机选择两个调用向量，并将所述两个调用向量中的元素以相同的交叉概率对应交换，得到第二调用向量集合；Two invocation vectors are randomly selected from the first invocation vector set, and elements in the two invocation vectors are correspondingly exchanged with the same cross probability to obtain a second invocation vector set; 通过自定义变异算子调整所述第二调用向量集合中的调用向量，得到第三调用向量集合；Adjust the call vector in the second call vector set by the self-defined mutation operator to obtain the third call vector set; 对所述第一调用向量集合和所述第三调用向量集合进行预设次数的遗传算法迭代，生成所述至少一个备选仓库的调用信息。Perform a preset number of genetic algorithm iterations on the first call vector set and the third call vector set to generate call information of the at least one candidate warehouse. 4.根据权利要求3所述的方法，其特征在于，所述遗传算法迭代包括：4. The method of claim 3, wherein the genetic algorithm iteration comprises: 合并所述第一调用向量集合和所述第三调用向量集合，得到第四调用向量集合；combining the first call vector set and the third call vector set to obtain a fourth call vector set; 对所述第四调用向量集合中的调用向量进行快速非支配排序，选取第一层帕累托前沿中的调用向量作为第五调用向量集合；Perform fast non-dominant sorting on the call vectors in the fourth call vector set, and select the call vectors in the Pareto frontier of the first layer as the fifth call vector set; 从所述第五调用向量集合中随机取出K个调用向量，保留符合预设条件的调用向量，得到第六调用向量集合；Randomly take out K call vectors from the fifth call vector set, retain call vectors that meet the preset conditions, and obtain the sixth call vector set; 从所述第六调用向量集合中随机选择两个调用向量，并将所述两个调用向量中的元素以相同的交叉概率对应交换，得到第七调用向量集合；Two invocation vectors are randomly selected from the sixth invocation vector set, and the elements in the two invocation vectors are correspondingly exchanged with the same cross probability to obtain the seventh invocation vector set; 通过自定义变异算子调整所述第七调用向量集合中的调用向量作为所述至少一个备选仓库的调用信息。The call vector in the seventh call vector set is adjusted by a user-defined mutation operator as call information of the at least one candidate warehouse. 5.根据权利要求3所述的方法，其特征在于，所述通过自定义变异算子调整所述第二调用向量集合中的调用向量，得到第三调用向量集合，包括：5. The method according to claim 3, wherein, adjusting the call vector in the second call vector set by a self-defined mutation operator to obtain a third call vector set, comprising: 从所述至少一个备选仓库中随机选取n个第一仓库，其中，0<n<m，m为预设选择仓库个数；Randomly select n first warehouses from the at least one candidate warehouse, wherein 0<n<m, m is the number of preset selection warehouses; 从所述至少一个备选仓库的剩余备选仓库中随机选取m-n个第二仓库；randomly select m-n second warehouses from the remaining candidate warehouses of the at least one candidate warehouse; 根据所述第一仓库对应需求地的调用向量，以及所述第二仓库对应需求地的调用向量，确定每个需求地对应的可选仓库；According to the call vector corresponding to the demand place of the first warehouse, and the call vector of the second warehouse corresponding to the demand place, determine the optional warehouse corresponding to each demand place; 根据每个需求地对应的可选仓库，对所述第二调用向量集合中调用向量的所有元素的取值调整到预设范围，得到第三调用向量集合。According to the optional warehouse corresponding to each requirement, the values of all elements of the invocation vector in the second invocation vector set are adjusted to a preset range to obtain a third invocation vector set. 6.根据权利要求5所述的方法，其特征在于，根据所述调用信息，选择目标仓库的地址之后，所述方法还包括：6. The method according to claim 5, wherein, after selecting the address of the target warehouse according to the calling information, the method further comprises: 根据所述目标仓库与所述目标仓库对应需求地的预备信息，确定空间不连续的需求地集合；According to the target warehouse and the preparatory information of the corresponding demand places of the target warehouse, determine the set of demand places with discontinuous space; 计算所述需求地集合中所有需求地对应目标仓库的数量的乘积值；Calculate the product value of the quantity of all the demand places in the demand place set corresponding to the number of target warehouses; 当所述乘积值大于第一阈值或者小于第二阈值时，根据所述需求地集合与所述需求地集合对应目标仓库的预备信息，确定所述需求地集合对应仓库的地址。When the product value is greater than the first threshold or less than the second threshold, the address of the warehouse corresponding to the demand set is determined according to the demand set and the preparatory information of the target warehouse corresponding to the demand set. 7.根据权利要求1所述的方法，其特征在于，所述预备信息包括所述至少一个备选仓库与各个需求地的成本信息；所述获取预先确定的至少一个备选仓库与各个需求地的预备信息，包括：7 . The method according to claim 1 , wherein the preliminary information comprises cost information of the at least one candidate warehouse and each demand place; and the acquiring the predetermined at least one candidate warehouse and each demand place. 8 . Preliminary information, including: 获取现有仓库与各个需求地的历史成本信息和历史订单信息；Obtain historical cost information and historical order information of existing warehouses and various demand locations; 获取所述现有仓库与各个需求地的第一覆盖信息，以及所述至少一个备选仓库与各个需求地的第二覆盖信息；acquiring first coverage information of the existing warehouse and each demand place, and second coverage information of the at least one candidate warehouse and each demand place; 根据所述历史成本信息、所述历史订单信息、所述第一覆盖信息和所述第二覆盖信息，拟合所述至少一个备选仓库与各个需求地的成本信息。According to the historical cost information, the historical order information, the first coverage information and the second coverage information, the cost information of the at least one candidate warehouse and each demand place is fitted. 8.根据权利要求7所述的方法，其特征在于，预备信息包括所述至少一个备选仓库与各个需求地的运输时效；所述获取预先确定的至少一个备选仓库与各个需求地的预备信息，包括：8 . The method according to claim 7 , wherein the preparation information includes the transportation time limit of the at least one alternative warehouse and each demand place; the obtaining the pre-determined at least one alternative warehouse and the preparation of each demand place. 9 . information, including: 获取所述现有仓库与各个需求地的订单运输时间；Obtain the order transportation time between the existing warehouse and each demand place; 根据所述历史订单信息、所述订单运输时间、所述第一覆盖信息和所述第二覆盖信息，拟合所述至少一个备选仓库与各个需求地的运输时效。According to the historical order information, the order transportation time, the first coverage information and the second coverage information, the transportation timeliness between the at least one candidate warehouse and each demand place is fitted. 9.根据权利要求1所述的方法，其特征在于，所述方法还包括：9. The method of claim 1, wherein the method further comprises: 根据所述目标仓库的地址，在终端显示区域展示所述目标仓库的位置。According to the address of the target warehouse, the location of the target warehouse is displayed in the terminal display area. 10.一种仓库选址的装置，其特征在于，所述装置包括：10. A device for warehouse location selection, characterized in that the device comprises: 获取模块，用于获取预先确定的至少一个备选仓库与各个需求地的预备信息；an acquisition module, used to acquire the pre-determined at least one candidate warehouse and the preparatory information of each demand place; 生成模块，用于根据所述预备信息，通过预设模型生成所述至少一个备选仓库的调用信息；a generating module, configured to generate call information of the at least one candidate warehouse by using a preset model according to the preliminary information; 选择模块，用于根据所述调用信息，选择目标仓库的地址。The selection module is used for selecting the address of the target warehouse according to the calling information.
CN202111600398.9A 2021-12-24 2021-12-24 Method and device for selecting addresses of warehouse Withdrawn CN114492934A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202111600398.9A CN114492934A (en) 2021-12-24 2021-12-24 Method and device for selecting addresses of warehouse
CA3184567A CA3184567C (en) 2021-12-24 2022-12-21 Method and device for selecting addresses of warehouse

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111600398.9A CN114492934A (en) 2021-12-24 2021-12-24 Method and device for selecting addresses of warehouse

Publications (1)

Publication Number Publication Date
CN114492934A true CN114492934A (en) 2022-05-13

Family

ID=81496424

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111600398.9A Withdrawn CN114492934A (en) 2021-12-24 2021-12-24 Method and device for selecting addresses of warehouse

Country Status (2)

Country Link
CN (1) CN114492934A (en)
CA (1) CA3184567C (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115907598A (en) * 2022-11-07 2023-04-04 杭州巨灵兽智能科技有限公司 Supply chain transportation network planning method, device, equipment and storage medium

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN120764950A (en) * 2025-07-03 2025-10-10 军事科学院系统工程研究院后勤科学与技术研究所 Material storage layout method and device

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105373909A (en) * 2015-12-04 2016-03-02 江苏省现代企业信息化应用支撑软件工程技术研发中心 Logistics dispensing center addressing method based on simulation software
US20170206621A1 (en) * 2016-01-14 2017-07-20 Alibaba Group Holding Limited Systems and Methods for Determining the Effectiveness of Warehousing
CN107092979A (en) * 2017-04-07 2017-08-25 东南大学 Consider the transport network system in saving site selecting method of carbon emission
CN109102868A (en) * 2018-08-13 2018-12-28 中南大学 The site selecting method of medical emergency facility after a kind of shake
CN109377265A (en) * 2018-09-21 2019-02-22 金蝶蝶金云计算有限公司 Site selecting method, device, equipment and storage medium
CN109636002A (en) * 2018-11-13 2019-04-16 深圳大学 A kind of site selecting method and system of the Cold Chain Logistics home-delivery center based on goods damage
CN112215530A (en) * 2019-07-11 2021-01-12 北京京东尚科信息技术有限公司 Warehouse selection method and device

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105373909A (en) * 2015-12-04 2016-03-02 江苏省现代企业信息化应用支撑软件工程技术研发中心 Logistics dispensing center addressing method based on simulation software
US20170206621A1 (en) * 2016-01-14 2017-07-20 Alibaba Group Holding Limited Systems and Methods for Determining the Effectiveness of Warehousing
CN107092979A (en) * 2017-04-07 2017-08-25 东南大学 Consider the transport network system in saving site selecting method of carbon emission
CN109102868A (en) * 2018-08-13 2018-12-28 中南大学 The site selecting method of medical emergency facility after a kind of shake
CN109377265A (en) * 2018-09-21 2019-02-22 金蝶蝶金云计算有限公司 Site selecting method, device, equipment and storage medium
CN109636002A (en) * 2018-11-13 2019-04-16 深圳大学 A kind of site selecting method and system of the Cold Chain Logistics home-delivery center based on goods damage
CN112215530A (en) * 2019-07-11 2021-01-12 北京京东尚科信息技术有限公司 Warehouse selection method and device

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115907598A (en) * 2022-11-07 2023-04-04 杭州巨灵兽智能科技有限公司 Supply chain transportation network planning method, device, equipment and storage medium

Also Published As

Publication number Publication date
CA3184567C (en) 2025-05-13
CA3184567A1 (en) 2023-06-24

Similar Documents

Publication Publication Date Title
Shi et al. Analytics for cross‐border e‐commerce: inventory risk management of an online fashion retailer
Hajipour et al. A multi-objective harmony search algorithm to optimize multi-server location–allocation problem in congested systems
CN114926305B (en) Power material control method, device, computer equipment, and storage medium
Carrillo et al. Can tightness in the housing market help predict subsequent home price appreciation? Evidence from the United States and the Netherlands
CN104008428B (en) Service of goods requirement forecasting and resource preferred disposition method
CN114091993A (en) Warehouse site selection method, device, equipment and storage medium
CN111353094A (en) Information pushing method and device
CN114492934A (en) Method and device for selecting addresses of warehouse
CN111353794B (en) Data processing method, supply chain scheduling method and device
Zhou et al. Parcel locker location problem with selectable volume sizes and heterogeneous customers in the last mile delivery
Ekren et al. Enhancing e-grocery order fulfillment: improving product availability, cost, and emissions in last-mile delivery
Ko An intelligent, empty container dispatching system model using fuzzy set theory and genetic algorithm in the context of industry 4.0
CN109978241B (en) Method and device for determining charging load of electric automobile
CN118982262A (en) A method, system and storage medium for enterprise digital transformation management
CN115049158A (en) Method, system, storage medium and terminal for predicting running state of urban system
JP7144945B2 (en) Sales forecast simulation device, sales forecast simulation method and sales forecast simulation program
CN114254845A (en) Warehouse site selection method and device, computer equipment and storage medium
CN111353797B (en) Resource allocation method, device and electronic equipment
CN115712775A (en) Product recommendation method and device, computer equipment and storage medium
Gao et al. Optimizing matching radius for ride-hailing systems with dual-replay-buffer deep reinforcement learning
Kong et al. Demand-predictive storage assignment mechanism for flower auction centers
Ge et al. Proactive Two‐Level Dynamic Distribution Routing Optimization Based on Historical Data
CN119417345A (en) A logistics decision-making method and system for enterprise sales and delivery based on large models
CN115943399A (en) Generation method, generation device, program, information processing method, and information processing device
CN119398653A (en) Warehouse site selection method, device, 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
WW01 Invention patent application withdrawn after publication
WW01 Invention patent application withdrawn after publication

Application publication date: 20220513