CN110188937B - Business hall business scale prediction method, device, equipment and storage medium - Google Patents
Business hall business scale prediction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN110188937B CN110188937B CN201910433414.6A CN201910433414A CN110188937B CN 110188937 B CN110188937 B CN 110188937B CN 201910433414 A CN201910433414 A CN 201910433414A CN 110188937 B CN110188937 B CN 110188937B
- Authority
- CN
- China
- Prior art keywords
- grid
- business hall
- area
- traffic
- target
- 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.)
- Active
Links
Images
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 business scale prediction method, a business scale prediction device, business scale prediction equipment and a storage medium for a business hall. The method is based on the grid and big data technology, firstly determining the grid and the influence value of the grid on the business volume, and then converting the grid value into the influence factor of the grid on the business volume of the business hall, thereby establishing the relationship between the business volume of the business hall and the grid in the radiation range. According to the embodiment of the invention, the accuracy of business scale prediction of the business hall can be improved.
Description
Technical Field
The invention belongs to the technical field of communication, and particularly relates to a business scale prediction method, a business scale prediction device, business scale prediction equipment and a storage medium.
Background
The business hall is used as an important window for displaying high-quality services, bears services such as account opening, payment and inquiry and the like for users, and plays a role in propaganda and attracting more users. As a physical building, the business scale is an important factor for newly establishing a business hall. The too large scale of the business hall can cause resource waste; too small a business hall size does not have the expected effect, and the input and output are not proportional.
Aiming at the prediction of the business scale of a new business hall, the conventional method is based on that after the new business hall is established historically, the proportion of transacting channels is changed by peripheral users, and the possibility that the peripheral users abandon the original channels to switch to the new business hall to transact the business after the new business hall is added is calculated, so that the business scale of the new business hall is predicted.
The business scale of the business hall predicted by the existing business scale prediction method of the business hall is not accurate enough.
Disclosure of Invention
In order to solve at least one of the above technical problems, embodiments of the present invention provide a business hall business scale prediction method, device, apparatus, and storage medium, which can improve the accuracy of business hall business scale prediction.
In a first aspect, an embodiment of the present invention provides a business scale prediction method for a business hall, where the method includes:
determining a plurality of first grid areas in a first radiation range of the target business hall according to the position information of the target business hall; the first grid areas are determined by carrying out grid division on a target geographic area corresponding to the position information;
determining the grid value of each first grid area according to the service index corresponding to each first grid area and the service index weight;
determining a first traffic influence factor of each first grid area on the target business hall according to the grid value of each first grid area and the distance between the target business hall and each first grid area;
and inputting the plurality of first traffic influence factors into a pre-established traffic prediction model to obtain a traffic prediction result of the target business hall.
In a second aspect, an embodiment of the present invention provides a business scale prediction apparatus for a business hall, where the apparatus includes:
the first grid area determining module is used for determining a plurality of first grid areas in a first radiation range of the target business hall according to the position information of the target business hall; the first grid areas are determined by carrying out grid division on a target geographic area corresponding to the position information;
the grid score determining module is used for determining the grid score of each first grid area according to the service index and the service index weight corresponding to each first grid;
the first traffic influence factor determining module is used for determining first traffic influence factors of the first grid areas on the target business hall according to the grid values of the first grid areas and the distances between the target business hall and the first grid areas;
and the prediction module is used for inputting the plurality of first traffic influence factors into a pre-established traffic prediction model to obtain a traffic prediction result of the target business hall.
In a third aspect, an embodiment of the present invention provides a business hall traffic scale prediction apparatus, where the apparatus includes: a processor and a memory storing computer program instructions;
the processor, when executing the computer program instructions, implements a business hall traffic dimensioning method as in the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the business hall business scale prediction method according to the first aspect is implemented.
The business hall service scale prediction method, device, equipment and storage medium of the embodiment of the invention are based on grids and big data technology, firstly determine the grids and the influence scores of the grids on the service volume, and then convert the grid scores into the influence factors of the grids on the service volume of the business hall, thereby establishing the relationship between the service volume of the business hall and the grids in the radiation range. The method and the device can improve the accuracy of business scale prediction of the business hall.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments of the present invention will be briefly described below, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a business scale prediction method for a business hall according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a location relationship between a business hall and a grid area according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of the center point of a grid area provided by an embodiment of the present invention;
FIG. 4 is a schematic view of the radiation range of a business hall provided by an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a business scale prediction apparatus of a business hall according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a business size prediction apparatus of a business hall according to an embodiment of the present invention.
Detailed Description
Features and exemplary embodiments of various aspects of the present invention will be described in detail below, and in order to make objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the present invention.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Aiming at the prediction of the business scale of a new business hall, one method is based on that after the new business hall is established historically, peripheral users change the channel handling proportion, and the possibility that the peripheral users abandon the original channel to be transferred to the new business hall for business handling after the new business hall is newly added is calculated, so that the business scale of the new business hall is predicted.
However, it relies on location data and business transaction channel data of surrounding users when the business hall is historically established. Due to the massive nature of communication data and the limitation of storage media, the difficulty in acquiring the historical position of the user and the data of the business handling channel is high, or the data cannot be acquired at all. Even if complete data can be obtained, the communication service changes greatly from a few years ago, and the past service mode and the user behavior are questionable for the current reference value. In addition, if only the business handling capacity (established business) of the existing business hall in operation is divided after the new business hall starts to operate, but not the new increased business capacity (potential business) due to the establishment and promotion of the new business hall, the obtained prediction result of the business scale of the new business hall is not accurate enough.
In order to solve at least one technical problem, embodiments of the present invention provide a business hall business scale prediction method, device, apparatus, and computer storage medium. First, a business hall business scale prediction method provided by the embodiment of the present invention will be described below.
Fig. 1 is a schematic flow chart illustrating a business size prediction method for a business hall according to an embodiment of the present invention. As shown in fig. 1, the business hall business scale prediction method provided by the embodiment of the present invention includes the following steps:
s110, determining a plurality of first grid areas in a first radiation range of the target business hall according to the position information of the target business hall; the first grid areas are determined by carrying out grid division on a target geographic area corresponding to the position information;
s120, determining grid values of the first grid areas according to the service indexes and the service index weights corresponding to the first grid areas;
s130, determining first traffic influence factors of each first grid area on the target business hall according to the grid score of each first grid area and the distance between the target business hall and each first grid area;
and S140, inputting the plurality of first traffic influence factors into a pre-established traffic prediction model to obtain a traffic prediction result of the target business hall.
In the invention, the target business hall can be a newly added business hall, and the business hall can comprise a communication business hall, a bank business hall and the like.
According to the embodiment of the invention, the predicted business volume of the target business hall is the business volume of the target business hall after the target business hall operates stably, and the predicted business volume not only comprises the business volume of the peripheral existing business hall shunted by the target business hall, but also comprises the business volume which is newly increased due to the establishment and propaganda of the target business hall.
In S110, determining a first grid area within a first radiation range of the target business hall according to the location information of the target business hall includes:
determining a grid area where the target business hall is located according to the position information of the target business hall;
determining a plurality of first grid areas in a first radiation range of the target business hall according to the grid areas of the target business hall; the first radiation range is a range which takes a grid area where the target business hall is located as a center and takes a first preset length as a radius.
The first radiation range may be a range centered on a coordinate point of the target business hall and having a first preset length as a radius.
The position information of the target business hall, the mesh area where the target business hall is located, the first mesh area, and the like will be described in detail below.
< location information of office >
As an example, the target geographic area is determined by the location information of the target business hall, for example, a city to which the target business hall belongs is used as the target geographic area, and other suitable administrative areas or geographic areas can be selected as the target geographic area according to needs. In addition, Geographic Information System (GIS) tools or other tools may be used to convert the location Information of the target business hall into two-dimensional planar coordinates within the target Geographic area. The location information of the target business hall may be represented by coordinate points, for example, by converting the location of a specific literal description of the target business hall (e.g., xx street xx number xx city) or longitude and latitude description into plane coordinate points. In the invention, the position information of the target business hall and the existing business hall can be plane coordinate points.
< grid area where target Business office is located >
Before determining the grid area where the target business hall is located, the method can also comprise the steps of carrying out gridding division on the target geographic area to obtain a plurality of grid areas; determining the grid value of each grid area according to the service index corresponding to each grid area and the service index weight; and determining the position information of the target business hall according to the grid area with the maximum grid score.
The grid area can be understood as a GIS grid, i.e., a plurality of grid areas obtained by meshing and dividing the target geographic area with a GIS tool. The grid region may be represented by the letter G, and may be a square region with a side length L, and the value range of L may be (0.05-1) KM.
The grid score is expressed by letter I, and is calculated according to the indexes of people flow characteristics, blooming degree, service coverage, competitors and the like of the determined grid region based on the influence on the service volume, and the grid region with higher score is more valuable. The method of determining the grid score is explained in detail in S120. The grid area in the target geographic area and the grid score corresponding to the grid area can be used as a site selection basis of the newly added business hall, and the grid which is most suitable for establishing the new business hall in the target geographic area can be determined according to the grid score.
In the embodiment of the invention, the grid score is used as the address selection basis of the target business hall, so that the service volume of the target business hall can be improved, and the cost is reduced.
The relationship of the business hall to the grid area includes three relationships as shown in fig. 2: the business hall is in the grid area, the business hall is on the intersection line of the grid area (on the transverse intersection line in fig. 2), and the business hall is on the intersection point of the grid area.
If the business hall is in the grid area, the distance between the center point of the grid area where the business hall is located and the coordinate point of the business hall is shortest based on the principle of the shortest distance. If the business hall is on the intersection line or intersection point of the grid areas, two or more grid areas exist which are the newest distance from the business hall.
Wherein, as shown in fig. 3, the center point of the mesh region may be calculated with four vertices of the mesh region. As shown in FIG. 3, (x)1,y1)、(x1,y2)、(x2,y1)、(x2,y2) Each of the four vertices of a mesh region is defined as x, y, and x is (x, y)1+x2)/2，y＝(y1+y2)/2。
According to the analysis, taking the existing business hall as an example, determining the grid area where the existing business hall is located according to the position information of the existing business hall; if the number of the grid areas nearest to the existing business hall is multiple, the grid area where the existing business hall is located is determined according to a preset rule. The method for determining the grid area where the existing business hall is located can comprise the following steps:
step 1, acquiring all existing business halls H in a target geographic area1,H2,…,HpAnd its position coordinates;
step 2, traversing the grid areas in the target geographic area, and determining the grid areas closest to the existing business hall and the number H of the grid areas according to the distance between the position coordinates of the existing business hall and the central point of the grid areas1(n1:G11,G12,…,G1n1),H2(n2:G21,G22,…,G2N2),…,Hp(np:Gp1,Gp2,…,Gpnp) Wherein ni is the number of grid areas closest to the ith existing business hall;
step 3, traversing the grid areas and the number results of the grid areas nearest to the existing business hall in the step 2, wherein i is 1,2, …, p, if ni is 1, namely only one grid area exists in the grid areas nearest to the existing business hall, the grid area Gi1Namely, the grid area where the existing business hall is located is paired with the grid area where the existing business hall and the grid area belong to (H)i,Gi) Storing the result set; if ni>1, if there are more than one grid area nearest to the business hall, then the business hall and the corresponding grid area information Hi(ni:Gi1,Gi2,…,Gini) Storing the data into a pending set;
step 4, judging whether the result set and the to-be-determined set are empty, if the result set is not empty and the to-be-determined set is empty, indicating that all grid areas where the existing business halls are located are determined, and ending the algorithm; if the result set is empty and the set to be determined is not empty, all the existing business halls are positioned on the intersecting line or the intersecting point of the grid area, and then the step 5 is executed; if the result set is not empty and the set to be determined is not empty, indicating that a part of the existing business halls are positioned on the intersecting line or the intersecting point of the grid area, turning to step 6; the condition that the result set is empty and the undetermined set is empty does not occur;
and 5, indicating that all the existing business halls are positioned on the intersecting line or the intersecting point of the grid area when the result set is empty and the pending set is not empty. At this time, the undetermined set is traversed from beginning to end, and the grid area where the business hall exists is determined according to the following method: if the existing business hall is positioned on the transverse intersection line of the two grid areas, the grid area below is selected as the grid area where the existing business hall is positioned; if the existing business hall is located on the vertical intersection line of the two grid areas, the left grid area is selected as the grid area where the existing business hall is located; and if the existing business hall is positioned at the intersection point of the grid areas, selecting the grid area at the lower left as the grid area where the existing business hall is positioned. Will have business hall and its belongedMesh region pair (H)i,Gi) Storing the result set, and finishing the algorithm;
step 6, reading an existing business hall H in the pending seti(ni:Gi1,Gi2,…,Gini) And traversing the existing business halls in the result set, wherein a determined existing business hall closest to the pending existing business hall Hi is calculated, and if a plurality of determined existing business halls are closest to the Hi, taking any one of the determined existing business halls as the existing business hall closest to the Hi and marking as H. Respectively calculating H to the nearest grid region G of the pending existing business hall Hii1,Gi2,…,GiniThe distance of (c). H is not on the intersection line or point, so H is to grid region Gi1,Gi2,…,GiniMust not be equal. Selecting the grid area farthest from H as the grid area to which the pending business hall Hi belongs, and storing the result into a result set;
step 7, repeating the step 5 until the pending set becomes empty;
it should be noted that, in the calculation result, it may happen that two existing business halls belong to the same grid area. If two or more existing business halls belong to the same grid area, the existing business halls in the grid area are merged and regarded as 1 existing business hall, and the total value of the stable business volume of the existing business halls is regarded as the business volume of the merged existing business hall.
The above-mentioned existing business hall is taken as an example only, and the above-mentioned method can be adopted for determining the grid area where the target business hall is located.
According to the determination method of the grid areas where the business hall is located, provided by the embodiment of the invention, all grid areas can be traversed, the grid areas where different business halls are located are prevented from being the same, and the accuracy of business hall traffic prediction can be further improved.
< first mesh region >
The first grid areas within the first radiation range of the target business hall may be determined by centering on the grid area where the target business hall is locatedL is the radiation radius of the target business hall, and defines N is the (2N +1) × (2N +1) first grid areas in the first radiation range of the target business hall to form a grid area sequence G1,G2,…,GN。
As shown in FIG. 4, the grid area of the business hall H is G13The radiation radius L is 2 × L, and the number of first grid regions in the first radiation range is 25, which is G respectively1,G2,….,G25。
In the embodiment of the invention, the plurality of first grid areas in the first radiation range of the target business hall can be accurately determined, so that the accuracy of predicting the business scale of the target business hall is improved.
In S120, a grid score may be calculated using an index weighting method. The related indexes are determined according to business understanding and index screening technologies (including methods of correlation analysis, factor analysis, principal component analysis, attribute screening and the like), and the index weight is determined according to the importance of the indexes on the target (including various methods of importance scoring based on information entropy, importance scoring based on correlation, importance scoring based on Gini coefficient (GINI) and the like).
As an example, based on the telecommunication service understanding and service index screening techniques, implementation example service indexes and service index weights as described in table 1 are given. The business index data may be derived from mobile BMO data, research data, crawled public data. The basic example service indexes are classified into three levels according to different significances represented by the service indexes, the service index of each level is obtained by weighting the service index of the next level and the corresponding weight, and the grid score is determined by the first level service index and the weight thereof. The specific calculation formula is as follows:
where I is the grid score, IndexiIs the ith one-level index,
is the weight of the ith primary Index, m is the number of primary indexes, IndexijIs the jth secondary index under the ith primary index,
is the weight of the jth secondary index under the ith primary index, miIs the number of second-level indexes, Index, under the ith first-level IndexijkIs the kth tertiary index under the jth secondary index under the ith primary index,
is the kth tertiary index weight, m, under the jth secondary index under the ith primary indexijIs the number of the three-level indexes under the jth second-level index under the ith first-level index.
TABLE 1
In S130, the distance between the target business hall and each of the first grid areas may be a distance between any point in the grid area where the target business hall is located and any point in each of the first grid areas. Preferably, the distance between the center point of the grid area where the target business hall is located and the center point of each first grid area. The first traffic impact factor of each first grid area on the target business hall can be more accurately determined.
The first grid areas are reordered according to the sequence from small to large of the distance values, the grid areas with equal distances determine the ordering sequence according to the clockwise direction (up, right, down and left), and the order is obtainedThe grid region sequence of (A) is still marked as G1,G2,…,GNThe corresponding distance sequences are denoted as d1, d2, …, dN; recording the first traffic influence factor of each first grid area to the target business hall as f1,f2,…,fNThe specific calculation method is as follows:
if the first grid area is only in the first radiation range of the target business hall, the first traffic influence factor expression (3) of the first grid area to the target business hall is as follows:
fj＝Ij/dj (3)
wherein IjIs the grid score of the jth first grid region, djIs the distance from the jth first grid area to the target lobby.
If the first grid area is not only in the first radiation range of the target business hall but also in the second radiation range of the operated business hall, assuming that the first grid area is simultaneously in the second radiation ranges of p0 operated business halls, the expression (4) of the influence factor of the first grid area on the target business hall is as follows:
in S140, the first traffic impact factor is denoted as f1,f2,…,fNAnd inputting a pre-established traffic prediction model to obtain the traffic of the target business hall.
Specifically, the traffic prediction model may be set directly empirically. Preferably, the traffic prediction model is a prediction model established according to the traffic of the existing business hall in the geographical area to which the target business hall belongs and a second traffic influence factor of the second grid area on the existing business hall; the second grid area is a grid area in a second radiation range of the existing business hall, and the second radiation range is a range which takes the grid area where the existing business hall is located as the center and takes a second preset length as the radius. A traffic prediction model is established based on the traffic of the existing business hall currently operated, so that the collection of the early data becomes simpler, more convenient and more possible.
Further, the process of establishing the traffic prediction model may include: determining a second traffic influence factor of each second grid area on the existing business hall according to the grid value of each second grid area and the distance between the existing business hall and each second grid area; and taking the business volume of the existing business hall and each second business volume influence factor as sample data, and establishing a business volume prediction model by using a preset algorithm.
Specifically, the process of establishing the traffic prediction model may include the following steps:
step 1, a target geographic area is defined according to the position of a target business hall, for example, a city to which the target business hall belongs is taken as the target geographic area;
step 2, dividing the target geographic area into grid areas with the size of L multiplied by L by means of an ArcGIS tool, numbering the grid areas and calculating grid scores of the grid areas;
step 3, screening out the existing business halls currently operating in the target geographic area according to the attribution area of the target business halls, and numbering H the existing business halls on the assumption that p existing business halls currently operating in the target geographic area exist1,H2,…,Hp；
Step 4, calculating step 3 to select stable business volume V of the existing business hall1,V2,…,VpThe stable traffic V is calculated as follows in equation (5):
wherein, ViIs the ith business hall stable traffic still in operation, q is the number of months tracked, vijActual traffic volume of the ith operating business hall in the jth month;
step 5, using ArcGIS tool or other tools to convert the address information of the existing operating business hall selected in step 3 into coordinate points (x)1,y1),(x2,y2),…,(xp,yp)；
Step 6, determining the grid area G where the operating existing business hall selected in the step 3 is located1,G2,…,GpThe specific method may be the above-described determination method of the grid area where the target business hall is located.
Step 7, taking L to n to L as the radiation radius of the existing business hall, and step 6, the grid area G of the existing business hall1,G2,…,GpOn the basis, a second grid area within a second radiation range of each operating existing business hall is defined. According to the radiation radius definition L ═ N ×, the number of the second grid regions in the second radiation range of each operating existing business hall is N ═ 2N + 1. Thus, a grid sequence (G) within the second radiation range of p operating business halls is obtained11,G12,…,G1N),(G21,G22,…,G2N),…,(Gp1,Gp2,…,GpN)；
Step 8, calculating the distance between the second grid area determined in step 7 and the corresponding radiation existing business hall by using a plane two-point distance formula, wherein the distance between the second grid area and the existing business hall is defined as the distance between the central point of the second grid area and the central point of the grid area where the existing business hall is located, and the distance between the grid area where the existing business hall is located and the grid area itself is defined as l0L/10. Obtaining a grid-business hall distance sequence (d) in a second radiation range of the operation business hall11,d12,…,d1N),(d21,d22,…,d2N),…,(dp1,dp2,…,dpN). The distance between two points in a plane equation (6) is as follows:
wherein, PA，PBAre two points in a plane, the coordinates are respectively (x)A,yA) And (x)B,yB)。
In the step 9, the step of performing the step,and 7, reordering the second grid area sequences and the corresponding distance sequences in the second radiation range of the operated existing business hall obtained in the steps 7 and 8 according to the sequence that the distance between the operated existing business hall and the second grid area in the second radiation range is from small to large, and determining the ordering sequence of the second grid area with the same distance with the existing business hall according to the clockwise direction (up, right, down and left). The resulting reordered sequence of grids and distances can be used to follow the original labeling method (G)11,G12,…,G1N),(G21,G22,…,G2N),…,(Gp1,Gp2,…,GpN) And (d)11,d12,…,d1N),(d21,d22,…,d2N),…,(dp1,dp2,…,dpN) Wherein d isi1<＝di2<＝…<＝diNI is 1,2, …, p. The second grid area G can be known according to the definition of the distance between the existing business hall and the second grid area1j,G2j,…,GpjRespectively to its existing business hall H1,H2,…,HpAre equidistant, i.e. d1j＝d2j＝…＝dpj，j＝1,2,…,N。
Step 10, according to the grid score of the second grid area and the distance from the second grid area to the existing radiation business hall in the steps 2 and 9, calculating a second traffic influence factor of the second grid area to the existing business hall in the grid sequence in the step 9, and recording the second traffic influence factor as (f)11,f12,…,f1N),(f21,f22,…,f2N),…,(fp1,fp2,…,fpN). The second traffic impact factor calculation method is as follows:
if a second grid area is only within a second radiation range of an operating existing lobby, the second traffic impact factor for the existing lobby that the second grid area radiates is the grid score divided by the distance of the second grid area from the existing lobby, i.e.:
fij＝Ij/dij (7)
whereinIjIs the jth grid index in the radiation range of the ith business hall;
if a second grid area is simultaneously within the second radiation range of two or more existing lobbies, assume that second grid area j is in p0 operating lobbies H1,H2,…Hp0In the radiation range, the influence factor of the second grid area on the ith existing business hall is as follows:
and 11, sequencing the second traffic influence factors from near to far according to the distance between the grid and the business hall.
H1(V1:f11,f12,…,f1N),H2(V2:f21,f22,…,f2N),…,Hp(Vp:fp1,fp2,…,fpN) As step 9 illustrates, a sequence of grid areas (G) within the radiation range of an existing office is operated11,G12,…,G1N),(G21,G22,…,G2N),…,(Gp1,Gp2,…,GpN) The distances from the grid areas arranged at the same position of each subsequence to the corresponding radiation business hall are equal, namely the grid area G1j,G2j,…,Gpj(j ═ 1,2, …, N) to its radiation business hall H, respectively1,H2,…,HpAre equal. Thus, according to the position number of the grid region in the subsequence, N variables g can be defined1,g2,…,gNThe N variables are used as independent variables, the service volume of the operating business hall is used as an independent variable, and H is used as a reference valuei(Vi:fi1,fi2,…,fiN) And i is 1,2, …, and p is sample data, and a regression prediction model is established. The linear regression prediction model results were as follows:
V＝a1g1+a2g2+…+aNgN+a0 (9)
wherein, gjIs an argument of the grid definition of the j-th position in the grid sequence of the operating existing business hall, ajThe jth argument, a0Is a constant.
Besides linear regression, various regression analysis algorithms such as generalized regression, neural network regression, support vector machine and the like can be used for modeling.
In the embodiment of the invention, the influence factor of the grid area on the radiation business hall is defined, so that a relation model between the grid area and the business hall business volume is established, and the predicted business volume of the target business hall not only comprises the business volume of other channels around the target business hall after the target business hall is operated, but also comprises the newly increased business volume of the target business hall due to the establishment and propaganda of the target business hall.
Fig. 5 is a schematic structural diagram of a business size prediction apparatus for a business hall according to an embodiment of the present invention. As shown in fig. 5, the business scale prediction apparatus in the business hall according to the embodiment of the present invention includes the following modules:
a first grid area determining module 201, configured to determine, according to the location information of the target business hall, a plurality of first grid areas within a first radiation range of the target business hall; the first grid areas are determined by carrying out grid division on a target geographic area corresponding to the position information;
a grid score determining module 202, configured to determine a grid score of each first grid region according to the service index and the service index weight corresponding to each first grid;
the first traffic impact factor determining module 203 is configured to determine a first traffic impact factor of each first grid area on the target business hall according to the grid score of each first grid area and the distance between the target business hall and each first grid area;
the prediction module 204 is configured to input the plurality of first traffic impact factors into a pre-established traffic prediction model to obtain a traffic prediction result of the target business hall.
The business hall service scale prediction device provided by the embodiment of the invention is based on the grid and big data technology, firstly determines the grid and the influence value of the grid on the service volume, and then converts the grid value into the influence factor of the grid on the service volume of the business hall, thereby establishing the relationship between the service volume of the business hall and the grid in the radiation range. The method and the device can improve the accuracy of business scale prediction of the business hall.
In an embodiment, the first grid area determining module 201 is specifically configured to:
determining a grid area where the target business hall is located according to the position information of the target business hall;
determining a plurality of first grid areas within a first radiation range of the target business hall according to the grid area where the target business hall is located; the first radiation range is a range which takes a grid area where the target business hall is located as a center and takes a first preset length as a radius.
In the embodiment of the invention, the plurality of first grid areas in the first radiation range of the target business hall can be accurately determined, so that the accuracy of predicting the business scale of the target business hall is improved.
In an embodiment, the first traffic impact factor determining module 203 is specifically configured to:
the distance between the target business hall and each first grid area includes the distance between the center point of the grid area where the target business hall is located and the center point of each first grid area.
In the embodiment of the invention, the first traffic influence factor of each first grid area on the target business hall can be more accurately determined.
In one embodiment, the prediction module 204 is specifically configured to:
the business volume prediction model is established according to the business volume of the existing business hall in the geographic area of the target business hall and a second business volume influence factor of the second grid area on the existing business hall; the second grid area is a grid area in a second radiation range of the existing business hall, and the second radiation range is a range which takes the grid area where the existing business hall is located as the center and takes a second preset length as the radius.
In the embodiment of the invention, the traffic prediction model is established based on the existing business hall traffic currently operated, so that the collection of the early data becomes simpler and more convenient and possible.
In one embodiment, the prediction module 204 is specifically configured to:
determining a second traffic influence factor of each second grid area on the existing business hall according to the grid value of each second grid area and the distance between the existing business hall and each second grid area;
and taking the business volume of the existing business hall and each second business volume influence factor as sample data, and establishing a business volume prediction model by using a preset algorithm.
In the embodiment of the invention, the influence factor of the grid area on the radiation business hall is defined, so that a relation model between the grid area and the business hall business volume is established, and the predicted business volume of the target business hall not only comprises the business volume of other channels around the target business hall after the target business hall is operated, but also comprises the newly increased business volume of the target business hall due to the establishment and propaganda of the target business hall.
In one embodiment, the prediction module 204 is specifically configured to:
determining a grid area where the existing business hall is located according to the position information of the existing business hall; if the number of the grid areas nearest to the existing business hall is multiple, the grid area where the existing business hall is located is determined according to a preset rule.
According to the determination method of the grid areas where the business hall is located, provided by the embodiment of the invention, all grid areas can be traversed, the grid areas where different business halls are located are prevented from being the same, and the accuracy of business hall traffic prediction can be further improved.
In an embodiment, the first grid area determining module 201 is specifically configured to:
carrying out gridding division on a target geographic area to obtain a plurality of grid areas;
determining the grid value of each grid area according to the service index corresponding to each grid area and the service index weight;
and determining the position information of the target business hall according to the grid area with the maximum grid score.
In the embodiment of the invention, the grid score is used as the address selection basis of the target business hall, so that the service volume of the target business hall can be improved, and the cost is reduced.
Fig. 6 is a schematic structural diagram of a business size prediction apparatus of a business hall according to an embodiment of the present invention.
The business dimensioning apparatus in a business hall may comprise a processor 301 and a memory 302 in which computer program instructions are stored.
In particular, the processor 301 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured as one or more Integrated circuits implementing embodiments of the present invention.
The processor 301 realizes any of the business hall traffic size prediction methods in the above embodiments by reading and executing the computer program instructions stored in the memory 302.
In one example, the business hall traffic scale prediction apparatus may also include a communication interface 303 and a bus 310. As shown in fig. 6, the processor 301, the memory 302, and the communication interface 303 are connected via a bus 310 to complete communication therebetween.
The communication interface 303 is mainly used for implementing communication between modules, apparatuses, units and/or devices in the embodiment of the present invention.
The business hall business scale prediction device can execute the business hall business scale prediction method in the embodiment of the invention, thereby realizing the business hall business scale prediction method and the business hall business scale prediction device described in combination with fig. 1 and fig. 5.
In addition, in combination with the business scale prediction method in the foregoing embodiment, the embodiment of the present invention may provide a computer storage medium to implement. The computer storage medium having computer program instructions stored thereon; the computer program instructions, when executed by a processor, implement any of the business hall traffic scale prediction methods in the above embodiments.
It is to be understood that the invention is not limited to the specific arrangements and instrumentality described above and shown in the drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications and additions or change the order between the steps after comprehending the spirit of the present invention.
The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
It should also be noted that the exemplary embodiments mentioned in this patent describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
As described above, only the specific embodiments of the present invention are provided, and it can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present invention, and these modifications or substitutions should be covered within the scope of the present invention.
Claims (10)
1. A business scale prediction method for a business hall is characterized by comprising the following steps:
determining a plurality of first grid areas in a first radiation range of a target business hall according to the position information of the target business hall; the plurality of first grid areas are determined based on grid division of a target geographic area corresponding to the position information;
determining grid values of the first grid areas according to the service indexes and the service index weights corresponding to the first grid areas;
determining a first traffic influence factor of each first grid area on the target business hall according to the grid score of each first grid area and the distance between the target business hall and each first grid area;
inputting a plurality of first traffic influence factors into a pre-established traffic prediction model to obtain a traffic prediction result of the target business hall;
if the first grid area is only in the first radiation range of the target business hall, determining the expression of the first traffic influence factor of each first network area on the target business hall as follows:
fj＝Ij/dj
wherein, IjIs the grid score of the jth first grid region, djIs the distance from the jth first grid area to the target business hall;
if the first grid area is not only in the first radiation range of the target business hall, but also in the second radiation range of the operated business hall, determining the expression of the first traffic influence factor of each first network area on the target business hall as follows:
wherein, IjIs the grid score of the jth first grid region, djIs the jth firstThe distance from the grid area to the target business hall, p0 is the number of operated business halls, dijIs the distance from the ith operated lobby to the j first grid areas.
2. The business hall traffic scale prediction method of claim 1, wherein the determining a first grid area within a first radiation range of a target business hall according to the location information of the target business hall comprises:
determining a grid area where the target business hall is located according to the position information of the target business hall;
determining a plurality of first grid areas in a first radiation range of the target business hall according to the grid area where the target business hall is located; the first radiation range is a range which takes the grid area where the target business hall is located as the center and takes a first preset length as the radius.
3. The business hall traffic scale prediction method according to claim 1, wherein the distance between the target business hall and each of the first grid areas comprises a distance between a center point of the grid area where the target business hall is located and a center point of each of the first grid areas.
4. The business hall traffic scale prediction method according to claim 1, wherein the traffic prediction model is a prediction model established based on the traffic of an existing business hall in the geographic area to which the target business hall belongs and a second traffic impact factor of a second grid area on the existing business hall; the second grid area is a grid area in a second radiation range of the existing business hall, and the second radiation range is a range which takes the grid area where the existing business hall is located as a center and takes a second preset length as a radius.
5. The business hall traffic scale prediction method according to claim 4, wherein the establishment process of the traffic prediction model comprises:
determining a second traffic influence factor of each second grid area on the existing business hall according to the grid score of each second grid area and the distance between the existing business hall and each second grid area;
and establishing a traffic prediction model by using a preset algorithm by taking the traffic of the existing business hall and each second traffic influence factor as sample data.
6. The business hall traffic scale prediction method of claim 1, characterized in that the method further comprises:
determining a grid area where an existing business hall is located according to the position information of the existing business hall; and if a plurality of grid areas nearest to the existing business hall exist, determining the grid area where the existing business hall is located according to a preset rule.
7. The business hall traffic scale prediction method of claim 1, characterized in that the method further comprises:
gridding and dividing the target geographic area to obtain a plurality of grid areas;
determining grid scores of the grid areas according to the service indexes and the service index weights corresponding to the grid areas;
and determining the position information of the target business hall according to the grid area with the maximum grid score.
8. An apparatus for predicting business scale in a business hall, the apparatus comprising:
the first grid area determining module is used for determining a plurality of first grid areas in a first radiation range of the target business hall according to the position information of the target business hall; the plurality of first grid areas are determined based on grid division of a target geographic area corresponding to the position information;
the grid score determining module is used for determining the grid score of each first grid area according to the service index and the service index weight corresponding to each first grid;
a first traffic influence factor determining module, configured to determine a first traffic influence factor of each first grid area on the target business hall according to the grid score of each first grid area and a distance between the target business hall and each first grid area;
the prediction module is used for inputting a plurality of first traffic influence factors into a pre-established traffic prediction model to obtain a traffic prediction result of the target business hall;
if the first grid area is only in the first radiation range of the target business hall, determining the expression of the first traffic influence factor of each first network area on the target business hall as follows:
fj＝Ij/dj
wherein, IjIs the grid score of the jth first grid region, djIs the distance from the jth first grid area to the target business hall;
if the first grid area is not only in the first radiation range of the target business hall, but also in the second radiation range of the operated business hall, determining the expression of the first traffic influence factor of each first network area on the target business hall as follows:
wherein, IjIs the grid score of the jth first grid region, djIs the distance from the jth first grid area to the target business hall, p0 is the number of operated business halls, dijIs the distance from the ith operated lobby to the jth first grid area.
9. An apparatus for predicting business scale in a business hall, the apparatus comprising: a processor and a memory storing computer program instructions;
the processor, when executing the computer program instructions, implements the business hall traffic dimensioning method according to any one of claims 1-7.
10. A computer-readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the business hall traffic scale prediction method of any one of claims 1-7.
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 CN110188937A (en) | 2019-08-30 |
| CN110188937B true 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 (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015123487A1 (en) * | 2014-02-14 | 2015-08-20 | Tidd Nathan A | Selecting equity investments using quantitative multi-factor models |
-
2019
- 2019-05-23 CN CN201910433414.6A patent/CN110188937B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
|---|---|
| CN110188937A (en) | 2019-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110726418B (en) | Method, device and equipment for determining interest point region and storage medium | |
| KR102097426B1 (en) | Analysis method of fluidized population information capable of providing real-time fluidized population data by pcell algorithm | |
| CN103134505B (en) | Path planning system and method thereof | |
| US8983490B2 (en) | Locating a mobile device | |
| WO2020107712A1 (en) | Method for implementing antenna azimuth correction based on user data | |
| CN110020224B (en) | Correlation method, device, equipment and medium for map interest point data | |
| EP3364309B1 (en) | Account mapping method and device based on address information | |
| CN106055607B (en) | User visit prediction model establishment method and device and user visit prediction method and device | |
| CN111028016A (en) | Sales data prediction method and device and related equipment | |
| US11966424B2 (en) | Method and apparatus for dividing region, storage medium, and electronic device | |
| CN106780064B (en) | Region division method, device and network equipment | |
| CN104075720A (en) | Path planning device and method based on multiple prices | |
| JP2008077403A (en) | Evaluation device, method and program | |
| US20220357176A1 (en) | Methods and data processing systems for predicting road attributes | |
| CN106021290A (en) | Method for social network association excavation based on multi-scale geographic information | |
| CN111931077B (en) | Data processing method, device, electronic equipment and storage medium | |
| Lee et al. | Location recognition system using random forest | |
| CN107133689B (en) | Position marking method | |
| CN111475746A (en) | Method and device for mining point of interest, computer equipment and storage medium | |
| CN110674208B (en) | Method and device for determining position information of user | |
| CN114662774A (en) | City block vitality prediction method, storage medium and terminal | |
| Mathew et al. | Comparative assessment of geospatial and statistical methods to estimate local road annual average daily traffic | |
| CN112469116B (en) | Positioning method, positioning device, electronic equipment and computer readable storage medium | |
| CN110188937B (en) | Business hall business scale prediction method, device, equipment and storage medium | |
| CN116823535B (en) | Journey planning and intelligent navigation system based on multi-mode large model |
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 |