CN109377265A - Site selecting method, device, equipment and storage medium - Google Patents
Site selecting method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN109377265A CN109377265A CN201811107197.3A CN201811107197A CN109377265A CN 109377265 A CN109377265 A CN 109377265A CN 201811107197 A CN201811107197 A CN 201811107197A CN 109377265 A CN109377265 A CN 109377265A
- Authority
- CN
- China
- Prior art keywords
- address
- value
- destination address
- indicate
- demand
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0204—Market segmentation
- G06Q30/0205—Location or geographical consideration
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of site selecting methods.This method comprises: obtaining the first predictive information;First predictive information includes the article demand information of each location point;The characteristic information of each location point is determined according to first predictive information;The characteristic information includes user's characteristic information and environmental characteristic information;According to the characteristic information and objective optimization model, destination address is determined;Article demand Maximum Value and cost of consumed resource in the corresponding address cover of the objective optimization model is minimum.The site selecting method accuracy that the application proposes is higher.
Description
Technical field
The present invention relates to big data application field more particularly to a kind of site selecting method, device, equipment and storage mediums.
Background technique
With the development of big data technology, the application of big data has been deep into the every aspect of people's life, especially exists
Commercial field is especially prominent.Wherein, the address choice of business shops is become using big data realization now more popular
Mode.
Currently, being mainly based upon the senior practitioner of industry or experts and scholars' official communication to the address choice method of business shops
The step analysis of inquiry and fuzzy synthetic appraisement method, i.e., by related fields expert according to its experience to the correlative factor of addressing
Importance is made an appraisal, and obtains the comprehensive score of each preselected address in conjunction with analytic hierarchy process (AHP) and fuzzy synthetic appraisement method,
It is obtained determining the address that appropriateness is optimal according to comprehensive score.
But above-mentioned site selecting method excessively relies on artificial experience, accuracy is lower.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide method, the dress that one kind can effectively improve addressing accuracy
It sets, computer equipment and storage medium.
In a first aspect, a kind of site selecting method, which comprises
Obtain the first predictive information;First predictive information includes the article demand information of each location point;
The characteristic information of each location point is determined according to first predictive information;The characteristic information includes user spy
Reference breath and environmental characteristic information;
According to the characteristic information and objective optimization model, destination address is determined;The objective optimization model is correspondingly
Article demand Maximum Value and cost of consumed resource in the coverage area of location is minimum.
It is described in one of the embodiments, that destination address is determined according to the characteristic information and objective optimization model, packet
It includes:
The input parameter of the objective optimization model is determined according to the characteristic information;The input parameter is for assisting choosing
Location;
Using preset intelligent optimization algorithm, according to objective optimization model described in the input parametric solution, obtain described
Destination address.
The objective optimization model includes objective function and constraint condition in one of the embodiments,;The constraint item
Part is for constraining the objective function, so that the article demand Maximum Value and resource consumption of objective function output
Cost minimization.
In one of the embodiments, the objective function for obtain article demand Maximum Value value and resource consumption at
This minimum value;
The constraint condition include the following:
The coverage area of the destination address is not more than the radiation scope of user's management ability;
The distance between demand address and the destination address are less than the radius of the coverage area;The demand address is
Address in the coverage area;
The cost of consumed resource of the destination address is less than user's available resources;
The destination address is the address in alternative library;The alternative library includes according to the alternative of characteristic information generation
Address.
The objective function includes in one of the embodiments,With
Wherein, M indicates article demand value;I is 1 any integer value into n, and i indicates demand addressing point, n therein
Indicate the number for the demand addressing point that preselected area includes;J is 1 any integer value into l, and j is with indicating the target
Location point, l therein indicate the number for the destination address point that preselected area includes;xi,jIndicate that the target addressing point j is covered equal to 1
Cover demand the address points i, xi,jIndicate that the target addressing point j is not covered with the demand address points i equal to 0;viIndicate the
Value index nember on the corresponding line of the described demand address points of i, wjIt indicates to be worth under the corresponding line of j-th of target addressing point and refer to
Number;U indicates cost of consumed resource, yjIndicate that point j is the target addressing point, y equal to 1jIndicate that point j is not the target equal to 0
Addressing point, cjIndicate the cost of consumed resource coefficient of the target addressing point j, δjIndicate user in j-th of target addressing point
Carry out affection index when resource consumption;
The constraint condition includes Rj-Fk>=0, j=1,2 ... l;Wherein, RjIndicate the covering half of the target addressing point j
Diameter, FkFor the radiation scope of k-th of user's management ability;K is 1 any integer value into h, and k indicates user's individual,
In h indicate the number of user's individual;
The constraint condition includesWherein, ei=(lati,loni) indicate
The coordinate of the demand address points i, latiIndicate the latitude value of the demand address points i, loniIndicate the demand address points i
Longitude, dj=(latj,lonj) indicate the coordinate of the target addressing point j, latjIndicate the latitude of the target addressing point j
Angle value, lonjIndicate the longitude of the target addressing point j, dis (ei,dj) indicate described coordinate eiWith described coordinate dj's
Euclidean distance;
The third constraint condition includescjIndicate the resource consumption of the target addressing point j at
This, γkIndicate the rent cost coefficient of k-th of user, CkIndicate the maximum resource consumption value of k-th of user;
The constraint condition includes Y={ d1,d2,…dm};Wherein, Y is the alternative library of addressing point, d1,d2,.....dmFor
Alternative address in alternative library;M therein is integer value, and m indicates the number of the alternative address in the alternative library.
It is described in one of the embodiments, to use preset intelligent optimization algorithm, according to input parametric solution institute
Objective optimization model is stated, the destination address is obtained, comprising:
The first candidate site set is encoded using preset coding method, obtains the second candidate site set;Institute
Stating the second candidate site set includes multiple candidate site coordinates;
By in the second candidate site set each candidate site coordinate and the input parameter, it is excellent to input the target
Change in model, obtains the first output result;The first output result includes article demand value and cost of consumed resource;
According to the first output result and default fitness value, the destination address is obtained;The fitness includes institute
State article demand Maximum Value value and the cost of consumed resource minimum value.
It is described according to the first output result and default fitness value in one of the embodiments, obtain the mesh
Mark address, comprising:
If the first output result meets the default fitness value, by the corresponding candidate of the first output result
Address coordinate is determined as the destination address;
If the first output result is unsatisfactory for the default fitness value, according to preset genetic algorithm, described the
Two candidate site set and the objective optimization model, obtain the destination address;The third candidate site set includes not
Meet the candidate site coordinate of the default fitness value.
It is described according to preset genetic algorithm, the second candidate site set and described in one of the embodiments,
Objective optimization model obtains the destination address, comprising:
According to default operator, the second candidate site set is pre-processed, obtains third candidate site set;Institute
Stating default operator includes at least one of selection operator, crossover operator and mutation operator;
By in the third candidate site set each candidate site coordinate and the input parameter, it is excellent to input the target
Change in model, obtains the second output result;
According to the second output result and the default fitness value, the destination address is obtained.
It is described according to preset genetic algorithm, the second candidate site set and described in one of the embodiments,
Objective optimization model obtains the destination address, comprising:
According to the preset genetic algorithm and preset iterated conditional, the second candidate site set is iterated
It calculates, determines destination address;The iterated conditional includes preset the number of iterations, or, in the second candidate site set
Similarity threshold between address and the destination address.
In one of the embodiments, the method also includes:
Recommendation list is generated according to the characteristic information and the destination address;The characteristic information includes user's finance letter
Breath, commercial circle information and User action log.
Second aspect, a kind of addressing device, described device include:
Module is obtained, for obtaining the first predictive information;First predictive information includes the article of each location point
Demand information;
First determining module, for determining the characteristic information of each location point according to first predictive information;It is described
Characteristic information includes user's characteristic information and environmental characteristic information;
Second determining module, for determining destination address according to the characteristic information and objective optimization model;The target
Article demand Maximum Value and cost of consumed resource in the corresponding address cover of Optimized model is minimum.
The third aspect, a kind of computer equipment, including memory and processor, the memory are stored with computer journey
Sequence, the processor perform the steps of when executing the computer program
Obtain the first predictive information;First predictive information includes the article demand information of each location point;
The characteristic information of each location point is determined according to first predictive information;The characteristic information includes user spy
Reference breath and environmental characteristic information;
According to the characteristic information and objective optimization model, destination address is determined;The objective optimization model is correspondingly
Article demand Maximum Value and cost of consumed resource in the coverage area of location is minimum.
Fourth aspect, a kind of computer readable storage medium are stored thereon with computer program, the computer program quilt
Processor performs the steps of when executing
Obtain the first predictive information;First predictive information includes the article demand information of each location point;
The characteristic information of each location point is determined according to first predictive information;The characteristic information includes user spy
Reference breath and environmental characteristic information;
According to the characteristic information and objective optimization model, destination address is determined;The objective optimization model is correspondingly
Article demand Maximum Value and cost of consumed resource in the coverage area of location is minimum.
The site selecting method that the application proposes, computer equipment obtain the first predictive information;First predictive information includes each
The article demand information of a location point;The characteristic information of each position point is determined according to the first predictive information;Characteristic information includes using
Family characteristic information and environmental characteristic information;According to characteristic information and objective optimization model, destination address is determined;Objective optimization model
Article demand Maximum Value and cost of consumed resource in corresponding address cover is minimum.In this site selecting method, due to
The objective optimization model that computer equipment is constructed according to characteristic information, the article demand value in corresponding address cover is most
Big and cost of consumed resource is minimum, is optimal result by the destination address that the object module determines, moreover, the addressing side therefore
Method does not depend on artificial experience, so the accuracy of calculation result is higher.
Detailed description of the invention
Fig. 1 is the schematic diagram of internal structure for the computer equipment that one embodiment provides;
Fig. 2 is a kind of flow chart for site selecting method that one embodiment provides;
Fig. 3 is the flow chart of the implementation of S103 in Fig. 2 embodiment;
Fig. 4 is the flow chart of the implementation of S202 in Fig. 3 embodiment;
Fig. 5 is the flow chart of the implementation of S303 in Fig. 4 embodiment;
Fig. 6 is the flow chart of the implementation of S402 in Fig. 5 embodiment;
Fig. 7 is the recommender system schematic diagram that one embodiment provides;
Fig. 8 is the flow diagram for the recommender system that one embodiment provides;
Fig. 9 is the schematic diagram for the addressing device that one embodiment provides.
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 to explain the application, and do not have to
In restriction the application.
A kind of site selecting method provided by the embodiments of the present application is applicable to all kinds of terminal devices, server etc.;Wherein, terminal
Equipment can be, but not limited to be various mainframe computers, personal computer, laptop, smart phone, tablet computer and just
Take formula wearable device.By taking computer equipment as an example, site selecting method provided by the embodiments of the present application can be applied to as shown in Figure 1
In computer equipment.The computer equipment includes processor, the memory, network interface, display screen connected by system bus
And input unit.Wherein, the processor of the computer equipment is for providing calculating and control ability.The storage of the computer equipment
Device includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system and computer program.
The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The computer is set
Standby network interface is used to communicate with external terminal by network connection.To realize when the computer program is executed by processor
A kind of site selecting method.The display screen of the computer equipment can be liquid crystal display or electric ink display screen, the computer
The input unit of equipment can be the touch layer covered on display screen, be also possible to the key being arranged on computer equipment shell,
Trace ball or Trackpad can also be external keyboard, Trackpad or mouse etc..
It will be understood by those skilled in the art that structure shown in Fig. 1, 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.
Currently, realizing using traditional site selecting method to the address choice of business shops, artificial experience is excessively relied on, accurately
Property is lower.The application provides a kind of site selecting method, it is intended to solve the problems, such as that the site selecting method accuracy of the prior art is lower.
Technical solution of the present invention is described in detail with specifically embodiment below.These specific implementations below
Example can be combined with each other, and the same or similar concept or process may be repeated no more in certain embodiments.
Fig. 2 is a kind of flow chart for site selecting method that one embodiment provides.What is involved is computer equipments for the present embodiment
In conjunction with predictive information and characteristic information, the detailed process of address choice is carried out using the objective optimization model of building.This method
Executing subject is computer equipment.As shown in Fig. 2, method includes the following steps:
S101, the first predictive information is obtained;First predictive information includes the article demand information of each location point.
Wherein, each location point refers to each shops address preselected in estimation range.Article demand information refers to
When selling article on specific shops address, actual demand amount, demand frequency of the client to article.First predictive information refers to
Demand, demand frequency in estimation range on each preselected shops address to article.First predictive information can be with
It resolves to obtain according to prediction model.
In the present embodiment, computer equipment is obtained from database, or is crawled using the network information, available each
The history sales volume data of full category commodity on a location point, life cycle of commodities feature, geographical feature information, real-time commodity need
The data such as regular information are sought, using these information as the first predictive information.Alternatively, computer equipment can use some prediction sides
Method establishes prediction model, then by the history sales volume data of the full category commodity on each above-mentioned location point, life cycle of commodities
The data such as feature, geographical feature information, real-time demand for commodity rule information are input in prediction model, and the first prediction is calculated
Information.The construction method for the prediction model that the present embodiment is related to can be using classical statistics model prediction method, popular machine
At least one of device learning method, high-end deep learning method method, or the integration algorithm of these types of method, this implementation
Example is without limitation.
S102, the characteristic information that each position point is determined according to the first predictive information;Characteristic information includes user's characteristic information
With environmental characteristic information.
Wherein, characteristic information is for indicating user, commercial circle, community, traffic, environment, geographical location etc. and shops's address phase
The information of pass.User's characteristic information can indicate that objective cluster analysis information, flow of the people information, user's financial information etc. are related to user
One or more information;Environmental characteristic information can indicate that commercial circle, community, traffic, environment, geographical location, shops's resource disappear
One or more information relevant to environment scene such as consumption finance.These information can be by computer equipment from historical data base
It obtains, or is crawled by computer equipment by the network information.
It in the present embodiment, optionally, can be further according to the spy when computer equipment gets characteristic information
Reference ceases construction feature database, and this feature database is used to store user's characteristic information and environmental characteristic information.For example, calculating
Machine equipment can sell the type of article according to shops and demand estimates out the objective group portrait information for buying the article, Yi Jike
The finance purchase information of group.
S103, according to characteristic information and objective optimization model, determine destination address;It covers the corresponding address of objective optimization model
Article demand Maximum Value and cost of consumed resource within the scope of lid is minimum.
Wherein, objective optimization model is used to solve destination address according to characteristic information, enables the destination address solved
Meet the article demand Maximum Value in corresponding address cover and cost of consumed resource is minimum.Article demand value refers to
Client refers to the cost of running a shop of shops to the demand of article, cost of consumed resource.
In the present embodiment, it can be covered previously according to a large amount of user's characteristic information and the big characteristic information of environment with address
Article demand Maximum Value and the conditions such as cost of consumed resource minimum within the scope of lid is as constraint condition, using model construction side
Method constructs the objective optimization model, computer equipment according to current characteristic information and the objective optimization model pre-established,
Solve optimal destination address, and article demand Maximum Value and resource consumption in the range of the destination address is covered
Cost minimization.For example, computer equipment calculates an optimal shops address according to objective optimization model, then the optimal shops
Location may be implemented with the maximum amount of commodity of the smallest cost sale of running a shop.
In above-described embodiment, computer equipment obtains the first predictive information;First predictive information includes each location point
Article demand information;The characteristic information of each position point is determined according to the first predictive information;Characteristic information includes user characteristics letter
Breath and environmental characteristic information;According to characteristic information and objective optimization model, destination address is determined;Objective optimization model is correspondingly
Article demand Maximum Value and cost of consumed resource in the coverage area of location is minimum.In this site selecting method, since computer is set
The standby objective optimization model constructed according to characteristic information, article demand Maximum Value and resource in corresponding address cover
Consuming cost is minimum, is optimal result by the destination address that the object module determines, moreover, the site selecting method does not depend on therefore
Artificial experience, so the accuracy of calculation result is higher.
Fig. 3 is the flow chart of the implementation of S103 in Fig. 2 embodiment.The embodiment what is involved is computer equipment according to
The detailed process of the objective optimization model solving target address of foundation.On the basis of the above embodiments, as shown in figure 3, it is above-mentioned
S103 " according to the characteristic information and objective optimization model, determines destination address ", may include steps of:
S201, the input parameter that objective optimization model is determined according to characteristic information;Input parameter is for assisting addressing.
Wherein, objective optimization model is multiple-objection optimization equation, commonly used in solving the optimization problem of multiple target.And it is somebody's turn to do
The optimal solution of multiple-objection optimization equation is defined as the forward position pareto solution, the i.e. destination address of the present embodiment selection.According to above-mentioned defeated
Enter parameter building objective optimization model, i.e. multiple-objection optimization equation, so that computer equipment can be by resolving multiple-objection optimization
Equation obtains the forward position pareto solution, to determine the optimal destination address selected.
In the present embodiment, input parameter may include target addressing point, demand address points, target addressing point covering demand
Value index nember under value index nember, the corresponding line of target addressing point on the index of location point, the line of demand address points, target addressing point
The covering half of the affection index, target addressing point of cost of consumed resource coefficient, user when target addressing point carries out resource consumption
Diameter, the radiation scope of customer consumption level, the coordinate of demand address points, the coordinate of target addressing point, demand address points coordinate
Euclidean distance, the rent cost coefficient of user, the maximum resource consumption value of user between the coordinate of target addressing point and/or
Alternative address etc. in alternative library, wherein the cost of consumed resource coefficient of target addressing point is used for indicating cost coefficient of running a shop
The radiation scope of the family level of consumption is used to indicate that the financial level index of user, the maximum resource of user to be consumed for indicating user
Finance it is horizontal can pay maximum put into.These input parameters can be determined according to characteristic information, for example, demand address points
Line on value index nember can be calculated by the characteristic informations such as the spending amount of relative article, quantity, frequency on line.Example again
Such as, value index nember can be believed by the features such as traffic, flow of the people, commercial circle, community's value under line under the corresponding line of target addressing point
Breath is calculated.
S202, using preset intelligent optimization algorithm, according to input parametric solution objective optimization model, with obtaining target
Location.
Wherein, intelligent optimization algorithm is the intelligent method for solving above-mentioned multi-objective optimization question, may include losing
At least one of the intelligent optimization algorithms such as propagation algorithm, particle swarm algorithm, ant group algorithm algorithm.
In the present embodiment, by preselected area multiple candidate sites and above-mentioned input parameter, be brought into objective optimization mould
It is resolved in type, obtains calculation result, then the calculation result is compared analysis with default result, if the calculation result accords with
Close default result, then the corresponding candidate site of the calculation result is determined as destination address, if the calculation result do not meet it is default
As a result, then using preset intelligent optimization algorithm, further optimization processing is carried out to the calculation result, after optimization processing
Calculation result is brought into objective optimization model again and is resolved, and obtains new calculation result, further according to the new solution
It calculates result and determines destination address.
Illustratively, the objective optimization model that above-described embodiment is related to includes objective function and constraint condition;Constrain item
Part is for constraining objective function, so that the article demand Maximum Value and cost of consumed resource of objective function output are most
It is small.
Illustratively, the objective function in objective optimization model is for obtaining article demand Maximum Value value and resource consumption
Cost minimum;Objective function can specifically include following relational expression (1) and relational expression (2):
Wherein, M indicates article demand value;I is 1 any integer value into n, and i indicates demand addressing point, n therein
Indicate the number for the demand addressing point that preselected area includes;J is 1 any integer value into l, and j is with indicating the target
Location point, l therein indicate the number for the destination address point that preselected area includes;xi,jIndicate that the target addressing point j is covered equal to 1
Cover demand the address points i, xi,jIndicate that the corresponding point j of the target addressing point is not covered with the demand address points i equal to 0;
viIndicate value index nember on the corresponding line of i-th of demand address points, wjIndicate the corresponding line of j-th of target addressing point
Lower value index nember;U indicates cost of consumed resource, yjIndicate that point j is the target addressing point, y equal to 1jIt is not equal to 0 expression point j
The target addressing point, cjIndicate the cost of consumed resource coefficient of the target addressing point j, δjIndicate user in j-th of mesh
Affection index when addressing point carries out resource consumption is marked, which can indicate user for target addressing point region
Tendency degree, the height for being inclined to degree can be expressed with weighted value.For example, user in In Guangzhou Area for selecting
The tendency degree of location is relatively high, then weighted value can be 0.8, and the tendency degree for carrying out addressing in Beijing area is compared
Low, then weighted value can be 0.2.
Illustratively, the constraint condition in objective optimization model includes following 4 constraint condition:
First constraint condition: the coverage area of destination address is not more than the radiation scope of customer consumption level, the constraint
The relational expression (3) that condition includes:
Rj-Fk>=0, j=1,2 ... l (3);
Wherein, RjIndicate the covering radius of target addressing point j, FkFor the radiation scope of k-th of user's management ability.K is 1
Any integer value into h, k indicate that user's individual, h therein indicate the number of user's individual;
Second constraint condition: the distance between demand address and destination address are less than the radius of the coverage area;It needs
Ask address for the address in coverage area, the relational expression (4) which includes:
Wherein, ei=(lati,loni) indicate the coordinate of the demand address points i, latiIndicate the demand address points i
Latitude value, loniIndicate the longitude of the demand address points i, dj=(latj,lonj) indicate the target addressing point j's
Coordinate, latjIndicate the latitude value of the target addressing point j, lonjIndicate the longitude of the target addressing point j, dis (ei,
dj) indicate described coordinate eiWith described coordinate djEuclidean distance;
Third constraint condition: the cost of consumed resource of destination address is less than user's available resources, which includes
Relational expression (5):
Wherein, cjIndicate the cost of consumed resource of target addressing point j, γkIndicate the rent cost coefficient of k-th of user, Ck
Indicate the maximum resource consumption value of k-th of user.
4th constraint condition: destination address is the address in alternative library;Alternative library includes raw according to the characteristic information
At alternative address, the relational expression (6) which includes:
Y={ d1,d2,...dm} (6);
Wherein, Y is the alternative library of addressing point, d1,d2,.....dmFor the alternative address in alternative library.M therein is integer
Value, m indicate the number of the alternative address in alternative library.
In above-described embodiment, the input parameter of objective optimization model is determined according to characteristic information;Input parameter is for assisting
Addressing;Destination address is obtained according to input parametric solution objective optimization model using preset intelligent optimization algorithm.In the choosing
During location, objective optimization model is solved using intelligent optimization algorithm, can be solved in certain area coverage optimally
Location, so as to improve the accuracy of preselected destination address, so that the destination address selected more meets the need of user
It asks.
On the basis of above-described embodiment completes building Model for Multi-Objective Optimization, following embodiment is related to according to objective optimization
Model carries out the process of multiple-objection optimization solution using intelligent optimization algorithm.
Fig. 4 is the flow chart of the implementation of S202 in Fig. 3 embodiment.What is involved is computer equipment uses for the embodiment
Preset intelligent optimization algorithm solves objective optimization model, obtains the process of optimal destination address.As shown in figure 4, above-mentioned
S202 " uses preset intelligent optimization algorithm, according to input parametric solution objective optimization model, obtain destination address ", can wrap
Include following steps:
S301, the first candidate site set is encoded using preset coding method, obtains the second candidate site collection
It closes;Second candidate site set includes multiple candidate site coordinates.
Wherein, the first candidate site set includes the address information of multiple location points within the scope of preselected area.Second waits
Selecting address set includes multiple candidate site coordinates, and address coordinate therein is the latitude and longitude coordinates in geographical location.Preset volume
Code method can use binary coding mode, alternatively it is also possible to using ranks coding mode.
Illustratively, ranks coding mode is used in the present embodiment, which is the longitude and latitude based on geographical location
The coded representation method for spending feature, so that higher by the destination address precision that the coding mode solves.Its specific side encoded
Method are as follows: the grid of one r × u of setting, the grid representation preselected area range, r indicate the corresponding maximum dimension of preselected area range
Angle value, u indicate the corresponding maximum longitude of the preselected area range.Spatial position of the grid cell q on the grid is expressed as q
(a, b), grid cell q indicate corresponding of address coordinate.Wherein, a is the line number of grid cell q, i.e. dimension values, b is
The row number of grid cell q, i.e. longitude, 1≤a≤r, 1≤b≤u.When the preset coding method of use is to the first candidate site
After set is encoded, the second obtained candidate site set g may include p candidate site coordinate, i.e. p grid cell q,
Second candidate site set g can specifically be indicated are as follows: g (a1,b1;a2,b2;.......;ap,bp), wherein it is small to be more than or equal to 1 by p
In equal to r × u.
S302, by the second candidate site set each candidate site coordinate and input parameter, input objective optimization model
In, obtain the first output result;First output result includes article demand value and cost of consumed resource.
In the present embodiment, by the second candidate site set g (a1,b1;a2,b2;.......;ap,bp), and get each
Parameter is inputted, relational expression is brought intoWithIt solves, obtains including the first defeated of M and U
Result out.M indicates article demand value, and U indicates cost of consumed resource.
S303, result and default fitness value are exported according to first, obtains destination address;Default fitness value includes article
Demand Maximum Value value and cost of consumed resource minimum value.
Wherein, default fitness value is the preset value that can satisfy desired fitness pre-set.It is described suitable
Response is during computer equipment is using intelligent optimization algorithm search optimal solution, for measuring the superiority and inferiority of search result
Assess parameter.Fitness usually is solved to obtain by fitness function, and the fitness function that this implementation uses is above-mentioned relation formulaWith
In the present embodiment, when computer equipment gets the default fitness value, using this preset fitness value as
The standard parameter for assessing destination address superiority and inferiority is compared the first output result got and default fitness value, thus
Judge whether meet article demand Maximum Value, the smallest constraint condition of cost of consumed resource with the first output result.
Optionally, Fig. 5 is the flow chart of the implementation of S303 in Fig. 4 embodiment.What is involved is computers for the embodiment
Equipment determines the process of destination address according to the first output result.As shown in figure 5, method includes the following steps:
If S401, the first output result meet the default fitness value, by the corresponding candidate ground of the first output result
Location coordinate is determined as destination address.
In the present embodiment, default fitness value includes the preset value and cost of consumed resource preset value of article demand value,
When the article demand value in the first output result is more than or equal to the preset value of article demand value, and the first output result
In cost of consumed resource when being less than or equal to cost of consumed resource preset value, will be sat with the first corresponding candidate site of output result
Mark is determined as destination address, the optimal destination address as selected.
If S402, the first output result are unsatisfactory for default fitness value, according to preset genetic algorithm, the second candidate ground
Location set and objective optimization model, obtain destination address.
Wherein, there are three types of the case where the first output result are unsatisfactory for default fitness value, the first is the first output result
In article demand value be less than article demand value preset value, and simultaneously first output result in cost of consumed resource it is big
In cost of consumed resource preset value;It is for second that article demand value in first output result is less than the pre- of article demand value
If value, and the cost of consumed resource in the first output result is less than or equal to cost of consumed resource preset value;The third is first defeated
The article demand value in result is more than or equal to the preset value of article demand value out, and first exports the resource consumption in result
Cost is greater than cost of consumed resource preset value.
In the present embodiment, in the case where the first output result is unsatisfactory for default fitness value, need using preset something lost
Propagation algorithm further optimizes each candidate site coordinate in the second candidate site set, the candidate after being optimized
Address set, further according to after optimization candidate site set and objective optimization model set the goal really again address, thus
To the candidate site coordinate that can satisfy default fitness value.For example, using genetic algorithm to the address in the second candidate collection
Coordinate optimizes processing, generates new address coordinate, then the new address coordinate is substituted into objective optimization model again and is carried out
It resolves, judges whether the new address coordinate meets article demand Maximum Value, money according to the output result of objective optimization model
The smallest constraint condition of source consuming cost, so that it is determined that destination address.
Optionally, the step S303 in Fig. 2 embodiment is " according to preset genetic algorithm, the second candidate site set and mesh
Mark Optimized model, obtain the destination address ", can also include: according to preset genetic algorithm and preset iterated conditional, it is right
Second candidate site set is iterated calculating, determines destination address;The iterated conditional includes preset the number of iterations, or,
The similarity threshold between address and destination address in second candidate site set.
Wherein, iterated conditional is used to indicate computer equipment using genetic algorithm, changes to the second candidate site set
Generation corresponding stopping criterion for iteration when calculating.The stopping criterion for iteration may include preset the number of iterations, or, the second candidate ground
The similarity threshold between address and destination address in the set of location.The number of iterations therein can be the threshold pre-set
Value, optionally, the number of iterations can also carry out customized according to artificial empirical value.Similarity threshold indicates the second candidate site collection
The similarity degree between address and destination address in conjunction, similarity threshold can be customized in advance according to actual needs.
It, can be using default when computer equipment gets the second candidate site set by coding in the present embodiment
Genetic algorithm calculating is iterated to the second candidate site set, obtain iterative calculation result.If the iterative calculation result is full
(the number of iterations has reached the address in default the number of iterations or the second candidate site set when the preset iterated conditional of foot
Similarity between destination address has reached similarity threshold), then terminate iterative calculation;If iterative calculation result is unsatisfactory for pre-
If iterated conditional when, then continue to iterate to calculate, until iterate to calculate result can satisfy preset iterated conditional until, with most
The iterative calculation result for realizing output eventually is optimal result, that is, it is the smallest to meet article demand Maximum Value, cost of consumed resource
User demand target.
It is if the first output result meets the default fitness value, the first output result is corresponding in above-described embodiment
Candidate site coordinate be determined as destination address;If the first output result is unsatisfactory for the default fitness value, according to default
Genetic algorithm, the second candidate site set and the objective optimization model, obtain the destination address.Due in the mistake
Cheng Zhong, the superiority-inferiority of candidate site is assessed according to default fitness value, and the candidate site that will meet default fitness value is true
It is set to destination address, the candidate site for being unsatisfactory for default fitness value is optimized into processing, so that with obtaining optimal target
Location, so the accuracy of the destination address obtained using this method is higher.
Optionally, Fig. 6 is the flow chart of 402 implementation in Fig. 5 embodiment.What is involved is step " roots for the embodiment
According to preset genetic algorithm, the second candidate site set and objective optimization model, obtain destination address " process.Such as Fig. 6 institute
Show, method includes the following steps:
S501, basis preset operator, pre-process to the second candidate site set, obtain third candidate site set;
Default operator includes at least one of selection operator, crossover operator and mutation operator.
Wherein, the mapping relations on one function space to another function space of operator representation are preset, the present embodiment relates to
And mapping relations of the default operator arrived between the second candidate site set and third candidate site set.Specific pre- imputation
Son may include at least one of operators such as selection operator, crossover operator and mutation operator, or all including these three calculations
Son.
Illustratively, selection operator carries out selection operation for realizing to each candidate site, to realize in addressing space
Each candidate site for being included is screened.Method particularly includes: first each candidate site in the second candidate site set is carried out
Each candidate site in second candidate site set is carried out the arrangement of sequencing according to the height of grade by classification processing, then
The crowding distance between each neighboring candidate address in the second candidate site set is calculated, is carried out first according to the size of crowding distance
The preceding N number of candidate site of rehearsal is finally selected in the arrangement of sequence afterwards in the candidate site set arranged, and N is positive whole
Number.Wherein, crowding distance refers to the distance between neighboring candidate address, can be calculated by objective function.Crowding distance
Bigger, candidate site is more excellent;The higher grade of candidate site, and candidate site is more excellent.
Illustratively, crossover operator is used to carry out cross processing to each candidate site in the second candidate site set, with
Realize the local area deep-searching to addressing space.The present embodiment realizes crossover operation, specific side using the method for two point recombination
Method are as follows: two candidate sites are randomly selected in the second candidate site set swaps position, the time after forming new intersection
Select address set.Optionally, also the present embodiment can also use other recombination methods, for example, three candidate sites of random selection,
The place-exchange for then carrying out three candidate sites, can be selected, the present embodiment according to actual needs about recombination method
It is without limitation.
Illustratively, mutation operator is used to carry out variation processing to each candidate site in the second candidate site set, with
Meet the requirement in actual environment with variation.The present embodiment realizes mutation operation, tool using the method for single-point variation
Body method are as follows: a candidate site is randomly selected in the second candidate site set as location point to be made a variation, then this
Another candidate site is randomly selected in two candidate site set and replaces location point to be made a variation, and completes mutation operation.It is optional
Ground, mutation operation can also realize mutation operation using the method for multiple spot variation, as long as can satisfy the item of practical mutation probability
Part.The present embodiment is without limitation.
In the present embodiment, selection operator can be respectively adopted after getting the second candidate site set in computer equipment
Selection operation is carried out to the second candidate site set, crossover operation is carried out to the second candidate site set using crossover operator, is adopted
Mutation operator operation is carried out to the second candidate site set with mutation operator, to realize the pretreatment to the second candidate site set
Operation achievees the purpose that optimize the second candidate site set.Optionally, computer equipment is getting the second candidate site set
Afterwards, can also simultaneously using selection operator to the second candidate site set carry out selection operation, using crossover operator to selection after
The second candidate site set carry out crossover operation, made a variation using mutation operator to the second candidate site set after intersection
Operator operation, for the sequencing between above-mentioned operator, can be handled, the present embodiment does not limit this in any combination
System.
S502, by third candidate site set each candidate site coordinate and input parameter, input objective optimization model
In, obtain the second output result.
In the present embodiment, third candidate site collection is combined into the optimum results of the second candidate site set.By the candidate ground of third
Each input parameter that location is gathered and got, is brought into relational expressionWithIt is asked
Solution, obtain include M and U second export result.
S503, result and default fitness value are exported according to second, obtains destination address.
The acquisition process for the destination address that the present embodiment is related to may refer to step S303 in above-described embodiment,
S401,S402.Its concrete methods of realizing is consistent, does not do burdensome explanation herein.
In above-described embodiment, computer equipment pre-processes the second candidate site set, obtains according to default operator
Third candidate site set;Default operator includes at least one of selection operator, crossover operator and mutation operator;Third is waited
Each candidate site coordinate and input parameter in address set are selected, inputs in objective optimization model, obtains the second output result;Root
According to the second output result and default fitness value, destination address is obtained;Destination address is carried out using intelligent optimization algorithm herein
During resolving, since default operator is to advanced optimize processing to each candidate site in the second candidate site set,
So higher by the destination address precision that this method obtains.
In one embodiment, computer equipment can also wrap after calculating destination address according to objective optimization model
It includes: recommendation list is generated according to characteristic information and destination address;Characteristic information includes user's financial information, commercial circle information and user
User behaviors log.
In the present embodiment, realizes to be generated according to characteristic information and destination address using recommender system as shown in Figure 7 and recommend
List.The system includes processing module, property data base, resolves address database, user journal module, client, Yong Hujiao
Mutual interface, recommending module.Processing module is used for the first predictive information that basis is got and determines characteristic information, and processing module is also used
In calculating destination address according to objective optimization model and characteristic information;Property data base be used for storage feature information, including with
Family financial information, commercial circle information;Address database is resolved for storing what computer equipment was calculated according to objective optimization model
Multiple destination addresses.User journal module is used to store the user behaviors log information of user, for example, user is clear in a certain period of time
Look at webpage when the information relevant to article such as purchase type of goods, the interest dabbled.User interface is used for computer
Equipment crawls the user behaviors log information of user according to user interface.Client is provided by user interface to computer equipment
User information.Recommending module user combines user's financial information, commercial circle information, the user behaviors log information of user, to resolving address
Multiple destination addresses in database are further optimized processing, to generate the destination address after new optimization, and to push away
The form for recommending list is shown.It is specific to show that picture may include multiple optimal destination addresses, it can show and calculate
In display area in the display screen of machine equipment, user is facilitated to check.
Using recommender system as shown in Figure 7, realizes and recommendation list, such as Fig. 8 are generated according to characteristic information and destination address
It is shown, it may include steps of:
S601, user journal module crawl the behavior letter that client is retained on a user interface by user interface
Breath, and send the behavioural information of the user to recommending module.
S602, processing module determine characteristic information according to the first predictive information got, and this feature information is stored
In characteristic information library.
S603, processing module calculate destination address according to objective optimization model and characteristic information, and by the destination address
It is stored in and resolves in address database.
S604, recommending module obtain destination address from resolving address database respectively, obtain from characteristic information library special
Reference breath.
S605, recommending module are according to the behavioural information and characteristic information of the user got, to the destination address got
Further optimization processing is carried out, to generate the recommendation list of optimal objective address.
In above-described embodiment, computer equipment can also be according to spy after calculating destination address according to objective optimization model
Reference breath and destination address generate recommendation list;The characteristic information includes user's financial information, commercial circle information and user behavior
Log.This step, which is realized, advanced optimizes processing to destination address, in conjunction with user's financial information, commercial circle information and user's row
The address in recommendation list generated for log, can more meet user demand, to improve the site selecting method of the application proposition
Accuracy, and in the form of recommendation list show on a computing device, can be used family more intuitively know it is selected
Destination address content.
It should be understood that although each step in the flow chart of Fig. 2-8 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. 2-8
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.
Fig. 9 is the schematic diagram for the addressing device that one embodiment provides, as shown in figure 9, described device includes: acquisition module
11, the first determining module 12 and the second determining module 13, in which:
Module 11 is obtained, for obtaining the first predictive information;First predictive information includes the object of each location point
Product demand information;
First determining module 12, for determining the characteristic information of each location point according to first predictive information;Institute
Stating characteristic information includes user's characteristic information and environmental characteristic information;
Second determining module 13, for determining destination address according to the characteristic information and objective optimization model;The mesh
It marks the article demand Maximum Value in the corresponding address cover of Optimized model and cost of consumed resource is minimum.
Specific about addressing device limits the restriction that may refer to above for site selecting method, and details are not described herein.
Modules in above-mentioned addressing device can be realized fully or partially through software, hardware and combinations thereof.Above-mentioned each module can
It is embedded in the form of hardware or independently of in the processor in computer equipment, computer can also be stored in a software form and set
In memory in standby, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is also provided, which includes memory, processor and deposit
Store up the computer program that can be run on a memory and on a processor, wherein processor is realized as above when executing described program
State any one site selecting method in each embodiment.
The computer equipment, when processor executes program, by realizing such as any one choosing in the various embodiments described above
Location method, so as to improve the accuracy of addressing.
In one embodiment, a kind of storage medium is also provided, computer program is stored thereon with, wherein the program quilt
It realizes when processor executes such as any one site selecting method in the various embodiments described above.Wherein, the storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random
AccessMemory, RAM) etc..The computer storage medium, the computer program of storage include as above-mentioned each by realizing
The process of the embodiment of site selecting method, so as to improve the accuracy of addressing.
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), increase
Strong 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 embodiments described above only express several embodiments of the present invention, and 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 inventive concept of the premise, various modifications and improvements can be made, these belong to protection of the invention
Range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (13)
1. a kind of site selecting method, which is characterized in that the described method includes:
Obtain the first predictive information;First predictive information includes the article demand information of each location point;
The characteristic information of each location point is determined according to first predictive information;The characteristic information includes user characteristics letter
Breath and environmental characteristic information;
According to the characteristic information and objective optimization model, destination address is determined;It covers the corresponding address of the objective optimization model
Article demand Maximum Value and cost of consumed resource within the scope of lid is minimum.
2. the method according to claim 1, wherein described according to the characteristic information and objective optimization model,
Determine destination address, comprising:
The input parameter of the objective optimization model is determined according to the characteristic information;The input parameter is for assisting addressing;
The target is obtained according to objective optimization model described in the input parametric solution using preset intelligent optimization algorithm
Address.
3. according to the method described in claim 2, it is characterized in that, the objective optimization model includes objective function and constraint item
Part;The constraint condition is for constraining the objective function, so that the article demand value of objective function output
Maximum and cost of consumed resource is minimum.
4. according to the method described in claim 3, it is characterized in that, the objective function is for obtaining article demand Maximum Value
Value and cost of consumed resource minimum value;
The constraint condition include the following:
The coverage area of the destination address is not more than the radiation scope of user's management ability;
The distance between demand address and the destination address are less than the radius of the coverage area;The demand address is described
Address in coverage area;
The cost of consumed resource of the destination address is less than user's available resources;
The destination address is the address in alternative library;The alternative library includes being generated alternatively according to the characteristic information
Location.
5. according to the method described in claim 4, it is characterized in that, the objective function includes
With
Wherein, M indicates article demand value;I is 1 any integer value into n, and i indicates that demand addressing point, n therein indicate
The number for the demand addressing point that preselected area includes;J is 1 any integer value into l, and j indicates the destination address point,
L therein indicates the number for the destination address point that preselected area includes;xi,jIt is indicated equal to 1 described in the target addressing point j covering
Demand address points i, xi,jIndicate that the target addressing point j is not covered with the demand address points i equal to 0;viIndicate i-th of institute
State value index nember on the corresponding line of demand address points, wjIndicate value index nember under the corresponding line of j-th of target addressing point;U
Indicate cost of consumed resource, yjIndicate that point j is the target addressing point, y equal to 1jIndicate that point j is not the target addressing equal to 0
Point, cjIndicate the cost of consumed resource coefficient of the target addressing point j, δjIndicate that user carries out in j-th of target addressing point
Affection index when resource consumption;
The constraint condition includes Rj-Fk>=0, j=1,2 ... l;Wherein, RjIndicate the covering radius of the target addressing point j, Fk
For the radiation scope of k-th of user's management ability;K is 1 any integer value into h, and k indicates user's individual, h therein
Indicate the number of user's individual;
The constraint condition includesWherein, ei=(lati,loni) described in expression
The coordinate of demand address points i, latiIndicate the latitude value of the demand address points i, loniIndicate the warp of the demand address points i
Angle value, dj=(latj,lonj) indicate the coordinate of the target addressing point j, latjIndicate the latitude value of the target addressing point j,
lonjIndicate the longitude of the target addressing point j, dis (ei,dj) indicate described coordinate eiWith described coordinate djIt is European
Distance;
The constraint condition includesWherein, cjIndicate the cost of consumed resource of the target addressing point j,
γkIndicate the rent cost coefficient of k-th of user, CkIndicate the maximum resource consumption value of k-th of user;
The constraint condition includes Y={ d1,d2,…dm};Wherein, Y is the alternative library of addressing point, d1,d2,.....dmIt is alternative
Alternative address in library;M therein is integer value, and m indicates the number of the alternative address in the alternative library.
6. method according to claim 4 or 5, which is characterized in that it is described to use preset intelligent optimization algorithm, according to institute
Objective optimization model described in input parametric solution is stated, the destination address is obtained, comprising:
The first candidate site set is encoded using preset coding method, obtains the second candidate site set;Described
Two candidate site set include multiple candidate site coordinates;
By in the second candidate site set each candidate site coordinate and the input parameter, input the objective optimization mould
In type, the first output result is obtained;The first output result includes article demand value and cost of consumed resource;
According to the first output result and default fitness value, the destination address is obtained;The default fitness value includes
The article demand Maximum Value value and the cost of consumed resource minimum value.
7. according to the method described in claim 6, it is characterized in that, described according to the first output result and default fitness
Value, obtains the destination address, comprising:
If the first output result meets the default fitness value, by the corresponding candidate site of the first output result
Coordinate is determined as the destination address;
If the first output result is unsatisfactory for the default fitness value, waited according to preset genetic algorithm, described second
Address set and the objective optimization model are selected, the destination address is obtained.
8. the method according to the description of claim 7 is characterized in that it is described according to preset genetic algorithm, it is described second candidate
Address set and the objective optimization model, obtain the destination address, comprising:
According to default operator, the second candidate site set is pre-processed, obtains third candidate site set;It is described pre-
Imputation attached bag includes at least one of selection operator, crossover operator and mutation operator;
By in the third candidate site set each candidate site coordinate and the input parameter, input the objective optimization mould
In type, the second output result is obtained;
According to the second output result and the default fitness value, the destination address is obtained.
9. the method according to the description of claim 7 is characterized in that it is described according to preset genetic algorithm, it is described second candidate
Address set and the objective optimization model, obtain the destination address, comprising:
According to the preset genetic algorithm and preset iterated conditional, meter is iterated to the second candidate site set
It calculates, determines destination address;The iterated conditional includes preset the number of iterations, or, the ground in the second candidate site set
Similarity threshold between location and the destination address.
10. method according to claim 1-5, which is characterized in that the method also includes:
Recommendation list is generated according to the characteristic information and the destination address;The characteristic information include user's financial information,
Commercial circle information and User action log.
11. a kind of addressing device, which is characterized in that described device includes:
Module is obtained, for obtaining the first predictive information;First predictive information includes the article demand of each location point
Information;
First determining module, for determining the characteristic information of each location point according to first predictive information;The feature
Information includes user's characteristic information and environmental characteristic information.
Second determining module, for determining destination address according to the characteristic information and objective optimization model;The objective optimization
Article demand Maximum Value and cost of consumed resource in the corresponding address cover of model is minimum.
12. 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 10 the method when executing the computer program.
13. 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 one of claims 1 to 10 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811107197.3A CN109377265A (en) | 2018-09-21 | 2018-09-21 | Site selecting method, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811107197.3A CN109377265A (en) | 2018-09-21 | 2018-09-21 | Site selecting method, device, equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109377265A true CN109377265A (en) | 2019-02-22 |
Family
ID=65402283
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811107197.3A Pending CN109377265A (en) | 2018-09-21 | 2018-09-21 | Site selecting method, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109377265A (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110414746A (en) * | 2019-08-07 | 2019-11-05 | 软通动力信息技术有限公司 | Crowd's wound space opens up address choice method, apparatus, equipment and storage medium |
CN110675189A (en) * | 2019-09-20 | 2020-01-10 | 东北大学 | Unmanned shelf location method based on Wide & Deep model and genetic algorithm |
CN111145452A (en) * | 2019-12-31 | 2020-05-12 | 中国银行股份有限公司 | Site selection method and device for self-service cash recycling machine capable of taking train tickets |
CN111339965A (en) * | 2020-02-28 | 2020-06-26 | 深圳前海微众银行股份有限公司 | Farm site selection method, farm site selection device, farm site selection equipment and computer readable storage medium |
CN111383052A (en) * | 2020-03-04 | 2020-07-07 | 深圳市丰巢科技有限公司 | Intelligent cabinet site selection model modeling method and device, server and storage medium |
CN111610494A (en) * | 2020-05-27 | 2020-09-01 | 武汉理工大学 | VTS radar configuration signal coverage optimization method |
WO2020186646A1 (en) * | 2019-03-21 | 2020-09-24 | 深圳市丰巢科技有限公司 | Site selection method and device for locker, server and storage medium |
CN111754143A (en) * | 2019-03-26 | 2020-10-09 | 顺丰科技有限公司 | Method and device for selecting address of material flow point, computer equipment and readable storage medium |
CN112257167A (en) * | 2020-10-30 | 2021-01-22 | 贝壳技术有限公司 | Method and device for determining article placement scheme based on genetic algorithm |
CN113076621A (en) * | 2020-09-04 | 2021-07-06 | 中移(上海)信息通信科技有限公司 | Reference station network address selection method and device, electronic equipment and computer storage medium |
CN113283680A (en) * | 2021-07-20 | 2021-08-20 | 北京世纪好未来教育科技有限公司 | Address selection method, device, equipment and storage medium thereof |
CN113762683A (en) * | 2020-11-25 | 2021-12-07 | 北京京东振世信息技术有限公司 | Method and device for site selection of store |
CN113763098A (en) * | 2020-12-21 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Method and device for determining an item |
CN114520979A (en) * | 2021-12-22 | 2022-05-20 | 浙江高信技术股份有限公司 | Lamp post communication system comprising transfer module and transfer module installation prediction method |
CN114926072A (en) * | 2022-06-01 | 2022-08-19 | 广西中烟工业有限责任公司 | Point selection method and device for cigarette point of sale and electronic equipment |
CN116645141A (en) * | 2023-06-07 | 2023-08-25 | 广州数说故事信息科技有限公司 | Multi-dimensional feature-fused chain store site selection recommendation method |
-
2018
- 2018-09-21 CN CN201811107197.3A patent/CN109377265A/en active Pending
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020186646A1 (en) * | 2019-03-21 | 2020-09-24 | 深圳市丰巢科技有限公司 | Site selection method and device for locker, server and storage medium |
CN111754143A (en) * | 2019-03-26 | 2020-10-09 | 顺丰科技有限公司 | Method and device for selecting address of material flow point, computer equipment and readable storage medium |
CN110414746A (en) * | 2019-08-07 | 2019-11-05 | 软通动力信息技术有限公司 | Crowd's wound space opens up address choice method, apparatus, equipment and storage medium |
CN110675189A (en) * | 2019-09-20 | 2020-01-10 | 东北大学 | Unmanned shelf location method based on Wide & Deep model and genetic algorithm |
CN110675189B (en) * | 2019-09-20 | 2022-12-13 | 东北大学 | Unmanned goods shelf site selection method based on Wide & Deep model and genetic algorithm |
CN111145452A (en) * | 2019-12-31 | 2020-05-12 | 中国银行股份有限公司 | Site selection method and device for self-service cash recycling machine capable of taking train tickets |
CN111339965A (en) * | 2020-02-28 | 2020-06-26 | 深圳前海微众银行股份有限公司 | Farm site selection method, farm site selection device, farm site selection equipment and computer readable storage medium |
CN111383052A (en) * | 2020-03-04 | 2020-07-07 | 深圳市丰巢科技有限公司 | Intelligent cabinet site selection model modeling method and device, server and storage medium |
CN111610494A (en) * | 2020-05-27 | 2020-09-01 | 武汉理工大学 | VTS radar configuration signal coverage optimization method |
CN111610494B (en) * | 2020-05-27 | 2022-08-19 | 武汉理工大学 | VTS radar configuration signal coverage optimization method |
CN113076621A (en) * | 2020-09-04 | 2021-07-06 | 中移(上海)信息通信科技有限公司 | Reference station network address selection method and device, electronic equipment and computer storage medium |
CN112257167A (en) * | 2020-10-30 | 2021-01-22 | 贝壳技术有限公司 | Method and device for determining article placement scheme based on genetic algorithm |
CN112257167B (en) * | 2020-10-30 | 2022-03-29 | 贝壳找房(北京)科技有限公司 | Method and device for determining article placement scheme based on genetic algorithm |
CN113762683A (en) * | 2020-11-25 | 2021-12-07 | 北京京东振世信息技术有限公司 | Method and device for site selection of store |
CN113763098A (en) * | 2020-12-21 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Method and device for determining an item |
CN113283680A (en) * | 2021-07-20 | 2021-08-20 | 北京世纪好未来教育科技有限公司 | Address selection method, device, equipment and storage medium thereof |
CN114520979A (en) * | 2021-12-22 | 2022-05-20 | 浙江高信技术股份有限公司 | Lamp post communication system comprising transfer module and transfer module installation prediction method |
CN114520979B (en) * | 2021-12-22 | 2024-02-09 | 浙江高信技术股份有限公司 | Lamp post communication system comprising transfer module and transfer module installation prediction method |
CN114926072A (en) * | 2022-06-01 | 2022-08-19 | 广西中烟工业有限责任公司 | Point selection method and device for cigarette point of sale and electronic equipment |
CN116645141A (en) * | 2023-06-07 | 2023-08-25 | 广州数说故事信息科技有限公司 | Multi-dimensional feature-fused chain store site selection recommendation method |
CN116645141B (en) * | 2023-06-07 | 2024-02-27 | 广州数说故事信息科技有限公司 | Multi-dimensional feature-fused chain store site selection recommendation method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109377265A (en) | Site selecting method, device, equipment and storage medium | |
Sharma et al. | Survey of stock market prediction using machine learning approach | |
Amiri | Project selection for oil-fields development by using the AHP and fuzzy TOPSIS methods | |
Park et al. | Using Bayesian Kriging for spatial smoothing in crop insurance rating | |
Ghazalli et al. | Development of an AHP–CBR evaluation system for remanufacturing: end-of-life selection strategy | |
Güller et al. | Simulation-based optimization for a capacitated multi-echelon production-inventory system | |
CN109767038A (en) | Crop yield prediction technique, device and computer readable storage medium | |
Frini et al. | Making decisions in a sustainable development context: A state-of-the-art survey and proposal of a multi-period single synthesizing criterion approach | |
Karimi et al. | An application of fuzzy-logic and grey-relational ANP-based SWOT in the ceramic and tile industry | |
Goswami et al. | Evaluation of the best smartphone model in the market by integrating fuzzy-AHP and PROMETHEE decision-making approach | |
Chuu | An investment evaluation of supply chain RFID technologies: A group decision-making model with multiple information sources | |
Peña-Guzmán et al. | Forecasting Water Demand in Residential, Commercial, and Industrial Zones in Bogotá, Colombia, Using Least‐Squares Support Vector Machines | |
CN105096152A (en) | Commodity popularity-based operation execution method and device | |
Wang et al. | A branch-and-price approach to the share-of-choice product line design problem | |
CN106846163A (en) | A kind of electric power payment channel overall analysis system | |
US20130166459A1 (en) | Invention valuation and scoring system | |
CN115358549A (en) | Method, apparatus, device, medium and program product for provider hologram creation | |
Noori | Developing a CBR system for marketing mix planning and weighting method selection using fuzzy AHP | |
Lin et al. | Intelligent prediction of the construction cost of substation projects using support vector machine optimized by particle swarm optimization | |
Liao et al. | Compromise solutions for stochastic multicriteria acceptability analysis with uncertain preferences and nonmonotonic criteria | |
Ravulapati et al. | A reinforcement learning approach to stochastic business games | |
CN107424026A (en) | Businessman's reputation evaluation method and device | |
CN116402528A (en) | Power data processing system | |
CN116823300A (en) | Cross-border electronic commerce intelligent line selection system based on machine learning | |
Kuo et al. | Subpopulation preference adjective non-dominated sorting genetic algorithm for multi-objective capacity expansion for matured fabs |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190222 |
|
RJ01 | Rejection of invention patent application after publication |