CN110188937A - Business hall business scale prediction technique, device, equipment and storage medium - Google Patents
Business hall business scale prediction technique, device, equipment and storage medium Download PDFInfo
- Publication number
- CN110188937A CN110188937A CN201910433414.6A CN201910433414A CN110188937A CN 110188937 A CN110188937 A CN 110188937A CN 201910433414 A CN201910433414 A CN 201910433414A CN 110188937 A CN110188937 A CN 110188937A
- Authority
- CN
- China
- Prior art keywords
- business hall
- grid
- business
- target
- net region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/043—Optimisation of two dimensional placement, e.g. cutting of clothes or wood
Abstract
The invention discloses a kind of business hall business scale prediction technique, device, equipment and storage mediums.This method is based on grid and big data technology, first determines that grid score value to the impact fraction of portfolio, is converted to grid to the impact factor of business hall portfolio later, to establish the relationship in business hall portfolio and radiation scope between grid by grid and grid.According to embodiments of the present invention, it can be improved the accuracy of business hall business scale prediction.
Description
Technical field
The invention belongs to field of communication technology more particularly to a kind of business hall business scale prediction technique, device, equipment and
Storage medium.
Background technique
Business hall carries to provide a user and opens an account, pays the fees, inquiring as an important window for showing good service
While service, also functions to publicity and attract the effect of more users.It is built as entity, business scale is newly to set up a battalion
Industry Room key factor.Business hall scale is excessive to will cause the wasting of resources;Business hall scale is too small not to have expected effect, investment
Output is disproportionate.
For the prediction of new business hall business scale, current method is periphery after being based on setting up new business hall in history
The ratio that channel is handled in user's change is foundation, calculates that newly-increased business hall rear perimeter edge user abandons original channel and goes to new business
A possibility that Room transacting business, to predict new business hall business scale.
The business hall business scale that the prediction technique of existing business hall business scale predicts is not accurate enough.
Summary of the invention
In order to solve at least one technical problem in above-mentioned, it is pre- that the embodiment of the present invention provides a kind of business hall business scale
Method, apparatus, equipment and storage medium are surveyed, can be improved the accuracy of business hall business scale prediction.
In a first aspect, the embodiment of the present invention provides a kind of business hall business scale prediction technique, method includes:
According to the location information of target business hall, multiple first grids in the first radiation scope of target business hall are determined
Region;Wherein, multiple first grid area domains are true based on gridding division is carried out to the corresponding target geographical area of location information
Fixed;
According to the corresponding operational indicator in each first grid area domain and operational indicator weight, each first grid area domain is determined
Grid score value;
According between the grid score value in each first grid area domain and target business hall and each first grid area domain
Distance determines each first grid area domain to the first portfolio impact factor of target business hall;
Multiple first portfolio impact factors are inputted to the Traffic prediction model pre-established, obtain target business hall
Traffic prediction result.
Second aspect, the embodiment of the invention provides a kind of business hall business scale prediction meanss, device includes:
First grid area domain determining module determines the of target business hall for the location information according to target business hall
Multiple first grid area domains in one radiation scope;Wherein, multiple first grid area domains are based on to the corresponding mesh of location information
It marks geographic area and carries out gridding division determination;
Grid score value determining module is used for according to the corresponding operational indicator of each first grid and operational indicator weight, really
The grid score value in fixed each first grid area domain;
First portfolio impact factor determining module, for the grid score value and mesh according to each first grid area domain
The distance between business hall and each first grid area domain are marked, determines each first grid area domain to the first industry of target business hall
Business amount impact factor;
Prediction module is obtained for multiple first portfolio impact factors to be inputted the Traffic prediction model pre-established
To the Traffic prediction result of target business hall.
The third aspect, the embodiment of the invention provides a kind of pre- measurement equipments of business hall business scale, and equipment includes: processor
And it is stored with the memory of computer program instructions;
Processor realizes the business hall business scale prediction technique such as first aspect when executing computer program instructions.
Fourth aspect, the embodiment of the invention provides a kind of computer readable storage medium, computer readable storage mediums
On be stored with computer program instructions, when computer program instructions are executed by processor realize as first aspect business hall business
Scale forecast method.
Business hall business scale prediction technique, device, equipment and the storage medium of the embodiment of the present invention, based on grid and greatly
Data technique first determines that grid score value to the impact fraction of portfolio, is converted to grid to business hall later by grid and grid
The impact factor of portfolio, to establish the relationship in business hall portfolio and radiation scope between grid.The present invention can mention
The accuracy of high business hall business scale prediction.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, will make below to required in the embodiment of the present invention
Attached drawing is briefly described, for those of ordinary skill in the art, without creative efforts, also
Other drawings may be obtained according to these drawings without any creative labor.
Fig. 1 is the flow diagram of business scale prediction technique in business hall provided in an embodiment of the present invention;
Fig. 2 is the positional diagram of business hall and net region provided in an embodiment of the present invention;
Fig. 3 is central point schematic diagram in net region provided in an embodiment of the present invention;
Fig. 4 is radiation scope schematic diagram in business hall provided in an embodiment of the present invention;
Fig. 5 is the structural schematic diagram of business scale prediction meanss in business hall provided in an embodiment of the present invention;
Fig. 6 is the structural schematic diagram of business scale pre- measurement equipment in business hall provided in an embodiment of the present invention.
Specific embodiment
The feature and exemplary embodiment of various aspects of the invention is described more fully below, in order to make mesh of the invention
, technical solution and advantage be more clearly understood, below in conjunction with drawings and the specific embodiments, the present invention is carried out further detailed
Description.It should be understood that specific embodiment described herein is only configured to explain the present invention, it is not configured as limiting this hair
It is bright.To those skilled in the art, the present invention can be in the case where not needing some details in these details
Implement.The description of embodiment is preferably managed just for the sake of being provided by showing example of the invention of the invention below
Solution.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence " including ... ", it is not excluded that including
There is also other identical elements in the process, method, article or equipment of the element.
It is predicted for new business hall business scale, a kind of method is the periphery user based on after setting up new business hall in history
The ratio that channel is handled in change is foundation, and after calculating newly-increased business hall, periphery user abandons original channel and goes to new business hall
A possibility that transacting business, to predict new business hall business scale.
However, position data and business handling channel data dependent on periphery user when establishing business hall in history.By
In the magnanimity of communication data and the finiteness of storage medium, user's history position and business handling channel data difficulty are obtained very
Greatly, or at all it can not obtain.Allow to obtain complete data, communication service also with very big change has occurred several years ago
Change, previous business model and user behavior are also to remain to be discussed for current reference value.In addition, if only considering new battalion
The industry Room shunts the existing business handling amount (set business) for runing business hall after starting operation, without considering because of new battalion
The portfolio (potential business) set up and publicized and newly increase in the industry Room, the prediction result of the business scale of obtained new business hall
It is also not accurate enough.
In order to solve at least one technical problem in above-mentioned, the embodiment of the invention provides a kind of business hall business scales
Prediction technique, device, equipment and computer storage medium.It is provided for the embodiments of the invention business hall business rule first below
Mould prediction technique is introduced.
Fig. 1 shows the flow diagram of business scale prediction technique in business hall provided in an embodiment of the present invention.Such as Fig. 1 institute
Show, business scale prediction technique in business hall provided in an embodiment of the present invention the following steps are included:
S110 determines multiple in the first radiation scope of target business hall according to the location information of target business hall
One net region;Wherein, multiple first grid area domains are based on to the progress gridding of location information corresponding target geographical area
Divide determination;
S120 determines each first net according to the corresponding operational indicator in each first grid area domain and operational indicator weight
The grid score value in lattice region;
S130, according to the grid score value in each first grid area domain and target business hall and each first grid area domain
The distance between, determine each first grid area domain to the first portfolio impact factor of target business hall;
Multiple first portfolio impact factors are inputted the Traffic prediction model pre-established by S140, obtain target battalion
The Traffic prediction result in the industry Room.
In the present invention, target business hall can be newly-increased business hall, and business hall may include the communicating business Room, battalion, bank
Industry Room etc..
According to embodiments of the present invention, the portfolio for the target business hall predicted is the industry after the stable operation of target business hall
Business amount had both included that target business hall shunts the portfolio that periphery has business hall, and had also included setting up and declaring because of target business hall
The portfolio for passing and newly increasing.
In S110, according to the location information of target business hall, in the first radiation scope of target business hall is determined
One net region, comprising:
According to the location information of target business hall, the net region where target business hall is determined;
According to the net region where target business hall, multiple first nets in the first radiation scope of target business hall are determined
Lattice region;Wherein, the first radiation scope is centered on the net region where target business hall, is half with the first preset length
The range of diameter.
First radiation scope can also by when centered on the coordinate points of target business hall, using the first preset length as radius
Range.
Below to net region, first grid area domain where the location information of target business hall, target business hall etc. into
Row is described in detail.
<location information of business hall>
As an example, target geographical area is determined with the location information of target business hall, for example, with target business hall
Affiliated city also can according to need the other suitable administrative regions of selection or geographic range made as target geographical area
For target geographical area.Further, it is possible to use GIS-Geographic Information System (Geographic Information System, GIS) work
Tool or other tools, the two-dimensional plane coordinate location information of target business hall being converted into target geographical area.Target battalion
The location information in the industry Room can be indicated with coordinate points, for example, by the address of the specific verbal description of target business hall (for example, xx
The city street xx xx) or longitude and latitude description position be converted into plane coordinate point.In the present invention, target business hall and existing
The location information of business hall all can be plane coordinate point.
<net region where target business hall>
Before determining the net region where target business hall, the present invention can also include carrying out to target geographical area
Gridding divides, and obtains multiple net regions;According to the corresponding operational indicator in each net region and operational indicator weight, determine
The grid score value of each net region;According to the maximum net region of grid score value, the location information of target business hall is determined.
Net region can be understood as GIS grid, i.e., target geographical area progress gridding is divided it using GIS tool
The multiple net regions obtained afterwards.Net region can be indicated with alphabetical G, can be the square area that side length is L, L's takes
Value range can be (0.05-1) KM.
Grid score value indicates with letter I, to influence portfolio as foundation, stream of people's feature, the prosperity of determining net region
The grid score value that degree, service coverage amount, rival etc. index are calculated, the higher net region of score are more valuable
Value.The determination method of grid score value is described in detail in S120.Net region and net region in target geographical area
Corresponding grid score value can be used as the addressing foundation of newly-increased business hall, can determine target geographical area according to grid score value height
The interior most suitable grid for establishing new business hall.
In embodiments of the present invention, target business can be improved as the addressing foundation of target business hall using grid score value
The portfolio in the Room, and reduce cost.
The relationship of business hall and net region includes three kinds of relationships as shown in Figure 2: business hall is in net region, business
The Room on the intersection of net region (Fig. 2 be on lateral intersection), business hall on the intersection point of net region.
If business hall in net region, is based on minimum distance principle, the center of the net region where business hall
Point and business hall coordinate points distance are most short.If business hall is on the intersection or intersection point of net region, with a distance from business hall most
There are two or more for new net region.
Wherein, as shown in figure 3, the central point of net region can be calculated with four vertex of net region.Such as Fig. 3 institute
Show, (x1,y1)、(x1,y2)、(x2,y1)、(x2,y2) be respectively a net region four vertex, if center point coordinate be (x,
Y), then x=(x1+x2)/2, y=(y1+y2)/2。
According to above-mentioned analysis, by taking existing business hall as an example, according to the location information of existing business hall, existing business hall is determined
The net region at place;Wherein, if the quantity of the net region nearest with existing business hall is there are multiple, according to preset rules
Determine the net region where existing business hall.The method of net region may include walking as follows where determining existing business hall
It is rapid:
Step 1, all existing business hall H in target geographical area are obtained1,H2,…,HpAnd its position coordinates;
Step 2, net region in target geographical area is traversed, according in existing business hall position coordinates and net region
The distance between heart point determines the net region and its number H nearest from existing business hall1(n1:G11,G12,…,G1n1),H2
(n2:G21,G22,…,G2N2),…,Hp(np:Gp1,Gp2,…,Gpnp), wherein ni is the nearest grid in from i-th existing business hall
The number in region;
Step 3, the net region nearest from existing business hall of traversal step 2 and number be as a result, i=1,2 ..., p, if
Ni=1, i.e., net region nearest from existing business hall only exist one, then net region Gi1It is exactly existing business hall place
Net region, by existing business hall and affiliated net region to (Hi,Gi) it is deposited into results set;If ni > 1, from existing
The nearest net region in business hall have it is multiple, then by business hall and corresponding net region information Hi(ni:Gi1,Gi2,…,Gini)
It is deposited into set undetermined;
Step 4, whether judging result set and set undetermined are empty, if results set is not empty, collection undetermined is combined into sky,
Illustrate the net region where all existing business halls all it has been determined that algorithm terminates;If results set is empty, collection undetermined
Conjunction is not empty, then illustrates that all existing business halls are on the intersection or intersection point of net region, then go to step 5;If result
Set is not that empty, undetermined set is not sky, illustrates that the existing business hall of a part is on the intersection or intersection point of net region, then turns
Step 6;Results set is that the situation that empty, undetermined collection is combined into sky does not occur;
Step 5, results set is that empty, undetermined set is not empty, illustrates that all existing business halls are in net region
On intersection or intersection point.At this point, traversing set undetermined from the beginning to the end, grid regions where existing business hall are determined as follows
Domain: existing business hall is on two net region transverse direction intersections, then selects lower section net region as where existing business hall
Net region;Existing business hall is on the intersection of two net regions longitudinal direction, then select left net region as have business
Net region where the Room;Existing business hall then selects lower left net region as existing business hall on the intersection point of net region
The net region at place.By existing business hall and affiliated net region to (Hi,Gi) store and arrive results set, algorithm terminates;
Step 6, an existing business hall H in set undetermined is readi(ni:Gi1,Gi2,…,Gini), traversing result set
In existing business hall, wherein calculate the fixed existing business hall nearest with existing business hall Hi distance undetermined, if
There are multiple fixed existing business halls are all nearest at a distance from Hi, then take any one have business hall as with Hi distance
Nearest existing business hall, is denoted as H*.H* is calculated separately to the nearest net region G of existing business hall Hi undeterminedi1,Gi2,…,
GiniDistance.Since H* is not on intersection or intersection point, so H* to net region Gi1,Gi2,…,GiniDistance not phase certainly
Deng.It selects net region wherein farthest with a distance from H* as the existing affiliated net region business hall Hi undetermined, is as a result stored in
Results set;
Step 7, step 5 is repeated, until set undetermined is emptying;
Especially, it should be noted that it is possible that two existing business halls belong to the same net region in calculated result
The case where.Has the phenomenon that business hall belongs to the same net region if there is two or more, then by this grid
Existing business hall in region, which merges, is considered as 1 existing business hall, and the aggregate value of stable portfolio has battalion after being used as merging
The portfolio in the industry Room.
It is above-mentioned only with existing business hall as an example, the determination of the net region where target business hall can also use it is upper
State method.
The method of determination of net region, can traverse all grid regions where the business hall provided according to embodiments of the present invention
Domain, it is all same for avoiding net region where different business halls, and then can be improved the accurate of business hall Traffic prediction
Property.
<first grid area domain>
The determination in multiple first grid area domains in the first radiation scope of target business hall can be, with target business hall
Centered on the net region at place, using L=n*l as the radiation radius of target business hall, the first radiation of delineation target business hall
A first grid area domain N=(2n+1) * (2n+1) in range forms net region sequence G1,G2,…,GN。
As shown in figure 4, net region where the H of business hall is G13, radiation radius L=2*l, first in the first radiation scope
Net region is 25, respectively G1,G2,….,G25。
In embodiments of the present invention, multiple first grids in the first radiation scope of target business hall can accurately be determined
Region, and then improve the accuracy of target business hall business scale prediction.
In S120, grid score value can be calculated using index method of weighting.Index of correlation understands according to business and index
Screening technique (including the methods of correlation analysis, factorial analysis, principal component analysis, attribute selection) is determining, index weights foundation
Index (including the importance marking based on comentropy, the importance marking based on correlation, is based on Geordie to the importance of target
A variety of methods such as the importance marking of coefficient (Gini coefficient, GINI)) it determines.
As an example, it is based on telecommunication service understanding and operational indicator screening technique, gives the reality as described in table 1
Apply example traffic index and operational indicator weight.Operational indicator data can derive from mobile BMO data, investigational data, crawl
Public data.The meaning represented according to operational indicator is different, and Base Case operational indicator has been generalized into three ranks, each
The operational indicator of rank is obtained by the operational indicator of its next rank and corresponding Weight, first order operational indicator
Grid score value has been determined with its weight.Specific formula for calculation is as follows:
Wherein, I is grid score value, IndexiIt is i-th of first class index,It is the weight of i-th of first class index, m is one
Grade index number, IndexijIt is j-th of two-level index under i-th of first class index,It is j-th two under i-th of first class index
The weight of grade index, miIt is two-level index number, Index under i-th of first class indexijkIt is j-th two under i-th of level-one refers to
K-th of three-level index under grade index,It is k-th of three-level index power under j-th of two-level index under i-th of level-one refers to
Weight, mijIt is the three-level index number under j-th of two-level index under i-th of level-one refers to.
Table 1
In S130, the distance between target business hall and each first grid area domain can be net where target business hall
The distance between any point in any point and each first grid area domain in lattice region.It preferably, is target business hall institute
Net region central point between the central point in each first grid area domain at a distance from.It can more accurately determine each
First portfolio impact factor of the first grid area domain to target business hall.
According to distance value from small to large sequentially resequence first grid area domain, equidistant net region is according to up time
Needle direction (upper, right, under, left) determines collating sequence, and obtained net region sequence is still denoted as G1,G2,…,GN, corresponding distance
Sequence is denoted as d1, d2 ..., dN;First portfolio impact factor of each first grid area domain to target business hall is denoted as f1,
f2,…,fN, circular is as follows:
If first grid area domain is only in the first radiation scope of target business hall, the first grid area domain is to target
First portfolio impact factor expression formula (3) of business hall is as follows:
fj=Ij/dj (3)
Wherein IjIt is the grid score value in j-th of first grid area domain, djIt is j-th of first grid area domain to target business hall
Distance.
If business hall is not only being runed in the first radiation scope of target business hall, while again in first grid area domain
The second radiation scope in, it is assumed that first grid area domain is simultaneously in the second radiation scope that p0 has runed business hall, then the
One net region is as follows to the expression formula (4) of target business hall impact factor:
In S140, the first portfolio impact factor is denoted as f1,f2,…,fNInput the Traffic prediction mould pre-established
Type obtains the portfolio of target business hall.
Specifically, Traffic prediction model rule of thumb can be directly arranged.Preferably, according to Traffic prediction model
The portfolio of existing business hall in the affiliated geographic area in target business hall and the second net region are to the second of existing business hall
Portfolio impact factor and the prediction model established;Wherein, the second net region is in the second radiation scope of existing business hall
Net region, centered on the second radiation scope is the net region where having business hall, with the second preset length for half
The range of diameter.Traffic prediction model is established based on the existing business hall portfolio currently runed, so that Primary Stage Data
Collection becomes more easy and possible.
Further, the establishment process of Traffic prediction model may include: the grid according to each second net region
Score value and the distance between existing business hall and each second net region, determine each second net region to have battalion
The second portfolio impact factor in the industry Room;To have the portfolio of business hall and each second portfolio impact factor as sample number
According to establishing Traffic prediction model using preset algorithm.
Specifically, the establishment process of Traffic prediction model may comprise steps of:
Step 1, target geographical area delimited with target business hall position, such as takes the affiliated city in target business hall for target
Manage region;
Step 2, by ArcGIS tool, target geographical area is divided into the net region of L × L size, to grid regions
Domain is numbered and calculates the grid score value of net region;
Step 3, it according to the attributed region of target business hall, filters out current also in the existing of operation in target geographical area
Business hall, it is assumed that have p also in the existing business hall of operation in target geographical area, H is numbered to existing business hall1,
H2,…,Hp;
Step 4, the stabilization portfolio V that step 3 selects existing business hall is calculated1,V2,…,Vp, stablize portfolio V and calculate public affairs
Formula (5) is as follows:
Wherein, ViIt is i-th also in the stable portfolio in the existing business hall of operation, q is tracking months, vijAlso for i-th
The existing business hall of operation the jth moon actual volume;
Step 5, using ArcGIS tool or other tools, the existing business hall address information for the operation that step 3 is selected
It is converted to coordinate points (x1,y1),(x2,y2),…,(xp,yp);
Step 6, the net region G where the existing business hall for the operation that step 3 is selected is determined1,G2,…,Gp, specific side
Method can be the method for determination of the net region where the target business hall of foregoing description.
It step 7, is existing business hall radiation radius with L=n*l, step 6 has net region G where business hall1,
G2,…,GpBased on, draw a circle to approve the second net region in the second radiation scope of the existing business hall of each operation.According to radiation
Radius defines L=n*l it is found that the second net region quantity in the second radiation scope of the existing business hall of each operation is N
=(2n+1) * (2n+1).Therefore grid sequence (the G in the second radiation scope of the existing business hall of p operation is obtained11,
G12,…,G1N),(G21,G22,…,G2N),…,(Gp1,Gp2,…,GpN);
Step 8, it using plane two o'clock range formula, calculates the second determining net region of step 7 and corresponding radiation is existing
The distance definition of the distance of business hall, the second net region and existing business hall is the central point of the second net region and has battalion
The distance between the central point of net region where the industry Room, wherein the net region where existing business hall is determined at a distance from itself
Justice is l0=l/10.Obtain the grid and business hall distance sequence (d in the second radiation scope of operation business hall11,d12,…,
d1N),(d21,d22,…,d2N),…,(dp1,dp2,…,dpN).The distance between plane two o'clock formula (6) is as follows:
Wherein, PA, PBIt is the two o'clock in plane, coordinate is respectively (xA,yA) and (xB,yB)。
Step 9, according to step 8 run existing business hall at a distance from the second net region in the second radiation scope from
The second grid in second radiation scope of the existing business hall of the small operation obtained to big sequence rearrangement step 7 and 8
Regional sequence and corresponding distance sequence, with equidistant second net region in existing business hall according to clockwise (it is upper,
It is right, under, it is left) determine collating sequence.The grid sequence and distance sequence of obtained rearrangement, can continue to use original label side
Method (G11,G12,…,G1N),(G21,G22,…,G2N),…,(Gp1,Gp2,…,GpN) and (d11,d12,…,d1N),(d21,d22,…,
d2N),…,(dp1,dp2,…,dpN), wherein di1≤ di2≤ ...≤diN, i=1,2 ..., p.According to existing business hall and second
Second net region G known to the definition of distance between net region1j,G2j,…,GpjIt is arrived respectively radiates existing business hall H1,
H2,…,HpBe equidistant, i.e. d1j=d2j=...=dpj, j=1,2 ..., N.
Step 10, battalion is had to radiation according to the grid score value of the second net region in step 2,9 and the second net region
The distance in the industry Room calculates second portfolio impact factor of second net region to existing business hall, note in step 9 grid sequence
For (f11,f12,…,f1N),(f21,f22,…,f2N),…,(fp1,fp2,…,fpN).Second portfolio impact factor calculation method
It is as follows:
If this second in the second radiation scope of the existing business hall that second net region is only runed at one
Second portfolio impact factor of the existing business hall that net region radiates it is grid score value divided by second net region
With existing business hall distance, it may be assumed that
fij=Ij/dij (7)
Wherein IjIt is j-th of mesh index in the i-th business hall radiation scope;
If second net region is simultaneously in the second radiation scope that two or more have business hall, false
If the second net region j is in p0 operation business hall H1,H2,…Hp0In radiation scope, then second net region is to wherein i-th
A existing business hall impact factor are as follows:
Step 11, by the second portfolio impact factor according to grid with a distance from business hall from closely to remote sequence sort.
H1(V1:f11,f12,…,f1N),H2(V2:f21,f22,…,f2N),…,Hp(Vp:fp1,fp2,…,fpN) as step 9 institute
It states, the net region sequence (G in the existing business hall radiation scope of operation11,G12,…,G1N),(G21,G22,…,G2N),…,
(Gp1,Gp2,…,GpN) in come the net region of each subsequence same position being equidistant to corresponding radiation business hall,
That is net region G1j,G2j,…,Gpj(j=1,2 ..., N) its radiation business hall H is arrived respectively1,H2,…,HpBe equidistant.Cause
This can define N number of variable g according to position number of the net region in subsequence1,g2,…,gN, using this N number of variable as
Independent variable, the existing business hall portfolio of operation is as independent variable, with Hi(Vi:fi1,fi2,…,fiN), i=1,2 ..., p are sample
Notebook data establishes regressive prediction model.Linear Regression Forecasting Model result is as follows:
V=a1g1+a2g2+…+aNgN+a0 (9)
Wherein, gjIt is the independent variable of the mesh definition of jth position in the existing business hall grid sequence of operation, ajJ-th certainly
Variation coefficient, a0It is constant.
It, can also be using various regression analyses such as generalized regression, neural net regression, support vector machines in addition to linear regression
Algorithm is modeled.
In embodiments of the present invention, net region is defined to the impact factor of radiation business hall, to establish grid regions
Relational model between domain and business hall portfolio, using the relational model, be the portfolio of the target business hall of prediction not only
Include the portfolio for shunting the other channels in its periphery after target business hall is runed, also includes setting up and declaring for target business hall
The portfolio for passing and newly increasing.
Fig. 5 is the structural schematic diagram of business scale prediction meanss in business hall provided in an embodiment of the present invention.As described in Figure 5,
Business scale prediction meanss in business hall provided in an embodiment of the present invention comprise the following modules:
First grid area domain determining module 201 determines target business hall for the location information according to target business hall
Multiple first grid area domains in first radiation scope;Wherein, multiple first grid area domains are based on corresponding to location information
Target geographical area carries out gridding and divides determination;
Grid score value determining module 202 is used for according to the corresponding operational indicator of each first grid and operational indicator weight,
Determine the grid score value in each first grid area domain;
First portfolio impact factor determining module 203, for the grid score value according to each first grid area domain, and
The distance between target business hall and each first grid area domain determine each first grid area domain to the first of target business hall
Portfolio impact factor;
Prediction module 204, for multiple first portfolio impact factors to be inputted the Traffic prediction model pre-established,
Obtain the Traffic prediction result of target business hall.
Business scale prediction meanss in business hall provided in an embodiment of the present invention are based on grid and big data technology, first determine
Grid and grid to the impact fraction of portfolio, later by grid score value be converted to influence of the grid to business hall portfolio because
Son, to establish the relationship in business hall portfolio and radiation scope between grid.The present invention can be improved business hall business rule
The accuracy of mould prediction.
In one embodiment, first grid area domain determining module 201 is specifically used for:
According to the location information of target business hall, the net region where target business hall is determined;
According to the net region where target business hall, multiple first in the first radiation scope of target business hall are determined
Net region;Wherein, the first radiation scope is to be with the first preset length centered on the net region where target business hall
The range of radius.
In embodiments of the present invention, multiple first grids in the first radiation scope of target business hall can accurately be determined
Region, and then improve the accuracy of target business hall business scale prediction.
In one embodiment, the first portfolio impact factor determining module 203 is specifically used for:
The distance between target business hall and each first grid area domain include the net region where target business hall
The distance between the central point of central point and each first grid area domain.
In embodiments of the present invention, it can more accurately determine each first grid area domain to the first industry of target business hall
Business amount impact factor.
In one embodiment, prediction module 204 is specifically used for:
Traffic prediction model is according to the portfolio of the existing business hall in the affiliated geographic area in target business hall and the
The prediction model that the second portfolio impact factor of existing business hall is established in two net regions;Wherein, the second net region
To have the net region in the second radiation scope of business hall, the second radiation scope is to have the grid regions where business hall
Centered on domain, using the second preset length as the range of radius.
In embodiments of the present invention, Traffic prediction mould is established based on the existing business hall portfolio currently runed
Type, so that the collection of Primary Stage Data becomes more easy and possible.
In one embodiment, prediction module 204 is specifically used for:
According between the grid score value of each second net region and existing business hall and each second net region
Distance determines each second net region to the second portfolio impact factor of existing business hall;
To have the portfolio of business hall and each second portfolio impact factor as sample data, built using preset algorithm
Vertical portfolio prediction model.
In embodiments of the present invention, net region is defined to the impact factor of radiation business hall, to establish grid regions
Relational model between domain and business hall portfolio, using the relational model, be the portfolio of the target business hall of prediction not only
Include the portfolio for shunting the other channels in its periphery after target business hall is runed, also includes setting up and declaring for target business hall
The portfolio for passing and newly increasing.
In one embodiment, prediction module 204 is specifically used for:
According to the location information of existing business hall, the net region where existing business hall is determined;Wherein, if with having battalion
The quantity of the nearest net region in the industry Room then determines the net region where existing business hall there are multiple according to preset rules.
The method of determination of net region, can traverse all grid regions where the business hall provided according to embodiments of the present invention
Domain, it is all same for avoiding net region where different business halls, and then can be improved the accurate of business hall Traffic prediction
Property.
In one embodiment, first grid area domain determining module 201 is specifically used for:
Gridding division is carried out to target geographical area, obtains multiple net regions;
According to the corresponding operational indicator in each net region and operational indicator weight, the grid point of each net region is determined
Value;
According to the maximum net region of grid score value, the location information of target business hall is determined.
In embodiments of the present invention, target business can be improved as the addressing foundation of target business hall using grid score value
The portfolio in the Room, and reduce cost.
Fig. 6 is the structural schematic diagram of business scale pre- measurement equipment in business hall provided in an embodiment of the present invention.
In business hall, the pre- measurement equipment of business scale may include processor 301 and be stored with depositing for computer program instructions
Reservoir 302.
Specifically, above-mentioned processor 301 may include central processing unit (CPU) or specific integrated circuit
(Application Specific Integrated Circuit, ASIC), or may be configured to implement implementation of the present invention
One or more integrated circuits of example.
Memory 302 may include the mass storage for data or instruction.For example it rather than limits, memory
302 may include hard disk drive (Hard Disk Drive, HDD), floppy disk drive, flash memory, CD, magneto-optic disk, tape or logical
With the combination of universal serial bus (Universal Serial Bus, USB) driver or two or more the above.It is closing
In the case where suitable, memory 302 may include the medium of removable or non-removable (or fixed).In a suitable case, it stores
Device 302 can be inside or outside synthesized gateway disaster tolerance equipment.In a particular embodiment, memory 302 is nonvolatile solid state
Memory.In a particular embodiment, memory 302 includes read-only memory (ROM).In a suitable case, which can be
ROM, programming ROM (PROM), erasable PROM (EPROM), the electric erasable PROM (EEPROM), electrically rewritable of masked edit program
The combination of ROM (EAROM) or flash memory or two or more the above.
Processor 301 is by reading and executing the computer program instructions stored in memory 302, to realize above-mentioned implementation
Any one business hall business scale prediction technique in example.
In one example, business scale pre- measurement equipment in business hall may also include communication interface 303 and bus 310.Wherein,
As shown in fig. 6, processor 301, memory 302, communication interface 303 connect by bus 310 and complete mutual communication.
Communication interface 303 is mainly used for realizing in the embodiment of the present invention between each module, device, unit and/or equipment
Communication.
Bus 310 includes hardware, software or both, and the component of the pre- measurement equipment of business hall business scale is coupled to each other one
It rises.For example it rather than limits, bus may include accelerated graphics port (AGP) or other graphics bus, enhancing industrial standard frame
Structure (EISA) bus, front side bus (FSB), super transmission (HT) interconnection, Industry Standard Architecture (ISA) bus, infinite bandwidth interconnection,
Low pin count (LPC) bus, memory bus, micro- channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-
Express (PCI-X) bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association part (VLB) bus or
The combination of other suitable buses or two or more the above.In a suitable case, bus 310 may include one
Or multiple buses.Although specific bus has been described and illustrated in the embodiment of the present invention, the present invention considers any suitable bus
Or interconnection.
The pre- measurement equipment of business hall business scale can execute the business hall business scale prediction side in the embodiment of the present invention
Method, to realize business hall business scale prediction technique and device in conjunction with Fig. 1 and Fig. 5 description.
In addition, in conjunction with the business hall business scale prediction technique in above-described embodiment, the embodiment of the present invention can provide one kind
Computer storage medium is realized.Computer program instructions are stored in the computer storage medium;The computer program instructions
Any one business hall business scale prediction technique in above-described embodiment is realized when being executed by processor.
It should be clear that the invention is not limited to specific configuration described above and shown in figure and processing.
For brevity, it is omitted here the detailed description to known method.In the above-described embodiments, several tools have been described and illustrated
The step of body, is as example.But method process of the invention is not limited to described and illustrated specific steps, this field
Technical staff can be variously modified, modification and addition after understanding spirit of the invention, or suitable between changing the step
Sequence.
Functional block shown in structures described above block diagram can be implemented as hardware, software, firmware or their group
It closes.When realizing in hardware, it may, for example, be electronic circuit, specific integrated circuit (ASIC), firmware appropriate, insert
Part, function card etc..When being realized with software mode, element of the invention is used to execute program or the generation of required task
Code section.Perhaps code segment can store in machine readable media program or the data-signal by carrying in carrier wave is passing
Defeated medium or communication links are sent." machine readable media " may include any medium for capableing of storage or transmission information.
The example of machine readable media includes electronic circuit, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), soft
Disk, CD-ROM, CD, hard disk, fiber medium, radio frequency (RF) link, etc..Code segment can be via such as internet, inline
The computer network of net etc. is downloaded.
It should also be noted that, the exemplary embodiment referred in the present invention, is retouched based on a series of step or device
State certain methods or system.But the present invention is not limited to the sequence of above-mentioned steps, that is to say, that can be according in embodiment
The sequence referred to executes step, may also be distinct from that the sequence in embodiment or several steps are performed simultaneously.
The above description is merely a specific embodiment, it is apparent to those skilled in the art that,
For convenience of description and succinctly, the system, module of foregoing description and the specific work process of unit can refer to preceding method
Corresponding process in embodiment, details are not described herein.It should be understood that scope of protection of the present invention is not limited thereto, it is any to be familiar with
Those skilled in the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or substitutions,
These modifications or substitutions should be covered by the protection scope of the present invention.
Claims (10)
1. a kind of business hall business scale prediction technique characterized by comprising
According to the location information of target business hall, multiple first grids in the first radiation scope of the target business hall are determined
Region;Wherein, the multiple first grid area domain is based on to the location information corresponding target geographical area progress grid
Change and divides determination;
According to the corresponding operational indicator in each first grid area domain and operational indicator weight, each first grid is determined
The grid score value in region;
According to the grid score value in each first grid area domain and the target business hall and each first grid area
The distance between domain determines each first grid area domain to the first portfolio impact factor of the target business hall;
Multiple first portfolio impact factors are inputted into the Traffic prediction model pre-established, obtain the target business
The Traffic prediction result in the Room.
2. business scale prediction technique in business hall according to claim 1, which is characterized in that described according to target business hall
Location information, determine the first grid area domain in the first radiation scope of the target business hall, comprising:
According to the location information of target business hall, the net region where the target business hall is determined;
According to the net region where the target business hall, determine multiple in the first radiation scope of the target business hall
First grid area domain;Wherein, first radiation scope is centered on the net region where the target business hall, with the
One preset length is the range of radius.
3. business scale prediction technique in business hall according to claim 1, which is characterized in that the target business hall and each
Central point and each institute of the distance between a described first grid area domain including the net region where the target business hall
State the distance between the central point in first grid area domain.
4. business scale prediction technique in business hall according to claim 1, which is characterized in that the Traffic prediction model
For according to the portfolio of the existing business hall in the affiliated geographic area in target business hall and the second net region to it is described
The prediction model for having the second portfolio impact factor of business hall and establishing;Wherein, second net region is described existing
Net region in second radiation scope of business hall, second radiation scope are with the grid where the existing business hall
Centered on region, using the second preset length as the range of radius.
5. business scale prediction technique in business hall according to claim 4, which is characterized in that the Traffic prediction model
Establishment process include:
According to the grid score value of each second net region and the existing business hall and each second grid regions
The distance between domain determines each second net region to the second portfolio impact factor of the existing business hall;
Using the portfolio of the existing business hall and each second portfolio impact factor as sample data, pre- imputation is utilized
Method establishes Traffic prediction model.
6. business scale prediction technique in business hall according to claim 1, which is characterized in that the method also includes:
According to the location information of the existing business hall, the net region where the existing business hall is determined;Wherein, if with institute
The quantity of the nearest net region in existing business hall is stated there are multiple, then where determining the existing business hall according to preset rules
Net region.
7. business scale prediction technique in business hall according to claim 1, which is characterized in that the method also includes:
Gridding division is carried out to the target geographical area, obtains multiple net regions;
According to the corresponding operational indicator in each net region and operational indicator weight, the net of each net region is determined
Lattice score value;
According to the maximum net region of grid score value, the location information of the target business hall is determined.
8. a kind of business hall business scale prediction meanss, which is characterized in that described device includes:
First grid area domain determining module determines the of the target business hall for the location information according to target business hall
Multiple first grid area domains in one radiation scope;Wherein, the multiple first grid area domain is based on to the location information
Corresponding target geographical area carries out gridding and divides determination;
Grid score value determining module, for according to the corresponding operational indicator of each first grid and operational indicator weight, really
The grid score value in fixed each first grid area domain;
First portfolio impact factor determining module, for the grid score value according to each first grid area domain, Yi Jisuo
The distance between target business hall and each first grid area domain are stated, determines each first grid area domain to the mesh
Mark the first portfolio impact factor of business hall;
Prediction module is obtained for multiple first portfolio impact factors to be inputted the Traffic prediction model pre-established
To the Traffic prediction result of the target business hall.
9. a kind of pre- measurement equipment of business hall business scale, which is characterized in that the equipment includes: processor and is stored with calculating
The memory of machine program instruction;
The processor realizes the business hall industry as described in claim 1-7 any one when executing the computer program instructions
Business scale forecast method.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program instruction realizes the business as described in claim 1-7 any one when the computer program instructions are executed by processor
Room business scale prediction technique.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910433414.6A CN110188937B (en) | 2019-05-23 | 2019-05-23 | Business hall business scale prediction method, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910433414.6A CN110188937B (en) | 2019-05-23 | 2019-05-23 | Business hall business scale prediction method, device, equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110188937A true CN110188937A (en) | 2019-08-30 |
CN110188937B CN110188937B (en) | 2021-10-29 |
Family
ID=67717431
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910433414.6A Active CN110188937B (en) | 2019-05-23 | 2019-05-23 | Business hall business scale prediction method, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110188937B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150235319A1 (en) * | 2014-02-14 | 2015-08-20 | Nathan A. Tidd | Method for selecting equity investments using quantitative multi-factor models of the relationship between common business characteristics and current stock prices |
CN105956721A (en) * | 2016-06-15 | 2016-09-21 | 南京林洋电力科技有限公司 | Method for predicting business scale of business hall by utilizing big data |
CN106384250A (en) * | 2016-09-13 | 2017-02-08 | 百度在线网络技术(北京)有限公司 | Site selection method and device |
CN109543909A (en) * | 2018-11-27 | 2019-03-29 | 平安科技(深圳)有限公司 | Prediction technique, device and the computer equipment of vehicle caseload |
-
2019
- 2019-05-23 CN CN201910433414.6A patent/CN110188937B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150235319A1 (en) * | 2014-02-14 | 2015-08-20 | Nathan A. Tidd | Method for selecting equity investments using quantitative multi-factor models of the relationship between common business characteristics and current stock prices |
CN105956721A (en) * | 2016-06-15 | 2016-09-21 | 南京林洋电力科技有限公司 | Method for predicting business scale of business hall by utilizing big data |
CN106384250A (en) * | 2016-09-13 | 2017-02-08 | 百度在线网络技术(北京)有限公司 | Site selection method and device |
CN109543909A (en) * | 2018-11-27 | 2019-03-29 | 平安科技(深圳)有限公司 | Prediction technique, device and the computer equipment of vehicle caseload |
Also Published As
Publication number | Publication date |
---|---|
CN110188937B (en) | 2021-10-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103134505B (en) | Path planning system and method thereof | |
CN103077604B (en) | traffic sensor management method and system | |
CN103270509B (en) | For geographical data bank being converted into the method for map tile data base, equipment and computer program | |
CN105069047B (en) | A kind of search method and device of geography information | |
CN106681996B (en) | The method and apparatus for determining interest region in geographic range, point of interest | |
CN110298553A (en) | A kind of National land space planing method, system and equipment based on GIS | |
CN106570595A (en) | Subway station position selection method and system based on space big data | |
CN105674994A (en) | Driving route acquisition method and device and navigation equipment | |
JP2001504965A (en) | Using multiple cost levels for route discovery computation | |
CN107194525A (en) | A kind of down town appraisal procedure based on mobile phone signaling | |
Buczkowska et al. | A comparison of euclidean distance, travel times, and network distances in location choice mixture models | |
CN103049829B (en) | Integrated fusion method of urban and rural passenger line network and hub station | |
CN107506433A (en) | Urban development space general layout Scene Simulation system | |
CN104636457B (en) | A kind of method and device of location finding cognition | |
CN109544690A (en) | Shared bicycle trip influence factor recognition methods, system and storage medium | |
CN107547154A (en) | A kind of method and device for establishing video traffic prediction model | |
CN106408110A (en) | Method and system for scenic spot locking | |
CN110020224A (en) | Correlating method, device, equipment and the medium of map interest point data | |
CN112819659A (en) | Tourist attraction development and evaluation method | |
CN112651546A (en) | Bus route optimization method and system | |
CN104361255A (en) | Simulation method for urban expansion through modified cellular automaton | |
Halim et al. | On finding optimum commuting path in a road network: a computational approach for smart city traveling | |
CN108806254B (en) | Method and device for identifying urban traffic corridor and computer readable storage medium | |
CN107655490A (en) | Hotspot path based on mobile subscriber track segmentation and most hot search finds method | |
CN111008730B (en) | Crowd concentration prediction model construction method and device based on urban space structure |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |