CN112069281B - Method and device for determining position of interest point, computer equipment and storage medium - Google Patents
Method and device for determining position of interest point, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112069281B CN112069281B CN202010934486.1A CN202010934486A CN112069281B CN 112069281 B CN112069281 B CN 112069281B CN 202010934486 A CN202010934486 A CN 202010934486A CN 112069281 B CN112069281 B CN 112069281B
- Authority
- CN
- China
- Prior art keywords
- grid
- grids
- interest
- area
- point
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/907—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/909—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Library & Information Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of data analysis, and provides a method, a device, computer equipment and a storage medium for determining a position of a point of interest, wherein the method comprises the following steps: acquiring the land characteristics of each grid to be selected, wherein the land characteristics are used for representing the attention degree of the grid to be selected; acquiring interference characteristics of each grid to be selected, wherein the interference characteristics are used for representing the influence degree between the grid to be selected and the selected grid; inputting the land characteristics and the interference characteristics of a plurality of grids to be selected into a preset evaluation model to obtain an evaluation value of each grid to be selected; and taking the target grid with the maximum evaluation value in the grids to be selected as the position of the target interest point. The method comprises the steps of carrying out grid division on an area map to which a target interest point belongs, and evaluating each grid according to land parcel characteristics of each divided grid and interference characteristics among the grids so as to determine the position of the target interest point from a plurality of grids in an area to be addressed.
Description
Technical Field
The invention relates to the technical field of data analysis, in particular to a method and a device for determining a position of a point of interest, computer equipment and a storage medium.
Background
A Point of interest (POI), also called Information Point, is a term in a geographic Information system, and generally refers to all geographic objects that can be abstracted as points, especially some geographic entities that are closely related to people's lives, such as schools, banks, restaurants, gas stations, hospitals, supermarkets, and so on. In the prior art, an effective method for determining the position of an interest point based on the regional characteristics of a regional map to which the interest point belongs does not exist.
Disclosure of Invention
The invention aims to provide a method, a device, a computer device and a storage medium for determining a position of a target interest point, which can determine the position of the target interest point from a plurality of grids in an area to be selected by carrying out grid division on an area map to which the target interest point belongs and evaluating each grid according to land parcel characteristics of each divided grid and interference characteristics among the grids.
In order to achieve the above purpose, the embodiment of the present invention adopts the following technical solutions:
in a first aspect, the present invention provides a method for determining a location of an interest point, where an area map to which a target interest point at a location to be determined belongs is divided into a plurality of grids in advance, each grid includes at most one interest point, and the plurality of grids include a plurality of grids to be selected where no interest point exists and a selected grid where an interest point exists, and the method includes: acquiring the land characteristics of each grid to be selected, wherein the land characteristics are used for representing the attention degree of the grid to be selected; acquiring interference characteristics of each grid to be selected, wherein the interference characteristics are used for representing the influence degree between the grid to be selected and the selected grid; inputting the land characteristics and the interference characteristics of a plurality of grids to be selected into a preset evaluation model to obtain an evaluation value of each grid to be selected; and taking the target grid with the maximum evaluation value in the grids to be selected as the position of the target interest point.
In a second aspect, the present invention provides an apparatus for determining a location of an interest point, where an area map to which a target interest point at a location to be determined belongs is pre-divided into a plurality of grids, each grid includes at most one interest point, and the plurality of grids include a plurality of grids to be selected where no interest point exists and a plurality of grids already selected where an interest point exists, the apparatus includes an obtaining module, an evaluating module, and a determining module, where the obtaining module is configured to: acquiring the land characteristics of each grid to be selected, wherein the land characteristics are used for representing the attention degree of the grid to be selected; acquiring interference characteristics of each grid to be selected, wherein the interference characteristics are used for representing the influence degree between the grid to be selected and the selected grid; the evaluation module is used for inputting the land characteristics and the interference characteristics of a plurality of grids to be selected into a preset evaluation model to obtain the evaluation value of each grid to be selected; the determination module is used for taking the target grid with the largest evaluation value in the candidate grids as the position of the target interest point.
In a third aspect, the present invention provides a computer apparatus comprising: one or more processors; a memory for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method for determining a location of interest as described above.
In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method for determining a location of interest as described above.
Compared with the prior art, the method and the device have the advantages that the grid division is carried out on the regional map to which the target interest point belongs, and each grid is evaluated according to the land parcel characteristics of each divided grid and the interference characteristics among the grids, so that the position of the target interest point is determined from a plurality of grids in the region to be addressed.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 shows a flowchart of a method for determining a location of interest according to an embodiment of the present invention.
Fig. 2 is a flowchart illustrating another method for determining a location of a point of interest according to an embodiment of the present invention.
Fig. 3 is a flowchart illustrating another method for determining a location of a point of interest according to an embodiment of the present invention.
Fig. 4 is a flowchart illustrating another method for determining a location of a point of interest according to an embodiment of the present invention.
Fig. 5 illustrates an apparatus for determining a location of interest provided by an embodiment of the present invention.
Fig. 6 shows a block schematic diagram of a computer device provided by an embodiment of the present invention.
Icon: 10-a computer device; 11-a processor; 12-a memory; 13-a bus; 14-a communication interface; 100-means for determining a location of a point of interest; 110-an obtaining module; 120-an evaluation module; 130-a determination module; 140-update module.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
In the description of the present invention, it should be noted that if the terms "upper", "lower", "inside", "outside", etc. indicate an orientation or a positional relationship based on that shown in the drawings or that the product of the present invention is used as it is, this is only for convenience of description and simplification of the description, and it does not indicate or imply that the device or the element referred to must have a specific orientation, be constructed in a specific orientation, and be operated, and thus should not be construed as limiting the present invention.
Furthermore, the appearances of the terms "first," "second," and the like, if any, are used solely to distinguish one from another and are not to be construed as indicating or implying relative importance.
It should be noted that the features of the embodiments of the present invention may be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a flowchart illustrating a method for determining a location of a point of interest according to an embodiment of the present invention, where the method includes the following steps:
step S100, the land characteristics of each grid to be selected are obtained, wherein the land characteristics are used for representing the attention degree of the grid to be selected.
In this embodiment, firstly, a regional map to which a target interest point of a position to be determined belongs is divided into a plurality of grids in advance, the grid division can adopt a GeoHash algorithm, the algorithm is essentially a mode of spatial index, the basic principle is that the earth is understood as a two-dimensional plane, the plane is recursively decomposed into smaller sub-blocks, and each sub-block has the same code in a certain latitude and longitude range. According to different precisions, the segmentation level of the GeoHash is generally 1-12 levels, wherein 1-12 represents the length of a character string of grid coding, and the larger the length is, the higher the precision is, and the embodiment of the invention can adopt different segmentation levels according to actual needs, for example, the segmentation level of 7-level GeoHash is adopted, namely, the length of the character string is 7.
In this embodiment, the land parcel characteristics may be a one-dimensional index for measuring the attention of the grid to be selected, or may be a combination of multidimensional indexes. Such as the amount of people flowing within the candidate grid, the number of transit stations within the candidate grid, etc.
Step S110, obtaining an interference characteristic of each candidate grid, where the interference characteristic is used to characterize an influence between the candidate grid and the selected grid.
In this embodiment, the attention of the selected grid may affect the attention of the candidate grid in the area where the selected grid is located, and the interference feature is used to evaluate the influence between the candidate grid and the selected grid.
Step S120, the land characteristics and the interference characteristics of a plurality of grids to be selected are input into a preset evaluation model, and the evaluation value of each grid to be selected is obtained.
In this embodiment, the preset evaluation model is formed by training sample data in advance, the training data for training the preset evaluation model is the land parcel characteristics, the interference characteristics and the actual grid comprehensive values of a plurality of selected grids marked with preset labels, and the final output of the trained preset evaluation model is the evaluation value of each grid to be selected and a list of the grids to be selected sorted according to the evaluation value.
In step S130, the target grid with the largest evaluation value in the candidate grids is used as the position of the target interest point.
The method for determining the position of the interest point provided by the embodiment of the invention divides the grid of the regional map to which the target interest point belongs, and evaluates each grid according to the land parcel characteristics of each divided grid and the interference characteristics among the grids so as to determine the position of the target interest point from a plurality of grids in the region to be selected.
On the basis of fig. 1, an embodiment of the present invention further provides a specific implementation manner for obtaining the interference characteristic, please refer to fig. 2, fig. 2 shows a flowchart of another method for determining a location of a point of interest provided by the embodiment of the present invention, and step S110 includes the following sub-steps:
and a substep S110-10 of obtaining the number of the selected grids, the interest point areas of the selected grids, the first heat value of the selected grids and the second heat value of each grid to be selected.
In this embodiment, the area of the interest point of the selected grid may be the area of a building or an entity of a preset type characterized by the interest point in the selected grid. The first heat value and the second heat value may be flow data, such as a human flow, an upload flow, or a download flow, monitored by the corresponding grid within a preset time period.
And a substep S110-11 of calculating the area of the interest point of each grid to be selected according to the number of the selected grids, the area of the interest point of the selected grid, the first heat value and the second heat value, wherein the area of the interest point of the selected grid is the area of the interest point in the selected grid, and the area of the interest point of each grid to be selected is the area of the target interest point created in the grid to be selected.
In this embodiment, the types of entities represented by the points of interest of the candidate grid and the selected grid are the same in a specific application scenario, for example, the points of interest are gas stations or the points of interest are bus stations.
In this embodiment, the area of the interest point of the candidate grid is the area of the target interest point if the target interest point is created in the candidate grid. The candidate grids are different, and the second heat values of the candidate grids may also be different, so that the calculated interest point areas of the candidate grids may also be different.
In this embodiment, as a specific implementation manner, the following formula may be adopted to calculate the area of the interest point of the candidate grid:
And a substep S110-12 of obtaining the interference characteristic of each grid to be selected according to the number of the selected grids, the interest point area of each grid to be selected and the distance between each grid to be selected and the selected grids.
In this embodiment, the distance between each candidate mesh and the selected mesh may be a euclidean distance between the center position of the candidate mesh and the center position of the selected mesh, or a manhattan distance, or the like.
In this embodiment, as a specific implementation manner, the following formula may be adopted to calculate the interference characteristic of any candidate grid:
According to the method for determining the position of the interest point, provided by the embodiment of the invention, the area of the interest point of the selected grid is calculated according to the heat values of the selected grid and the to-be-selected grid and the area of the interest point of the selected grid, and the interference characteristic of the to-be-selected grid is further calculated according to the areas of the interest point of the selected grid and the to-be-selected grid and the distance between the areas of the interest point of the selected grid and the to-be-selected grid, so that the obtained interference characteristic is closer to an actual scene, and the accuracy of the position of the determined target interest point is.
On the basis of fig. 1, an embodiment of the present invention further provides a specific implementation manner of obtaining an evaluation value of a grid to be selected, please refer to fig. 3, where fig. 3 shows a flowchart of another method for determining a location of a point of interest provided by the embodiment of the present invention, and step S120 includes the following sub-steps:
and a substep S120-10, respectively inputting the land characteristics and the interference characteristics of the multiple candidate grids into the first model and the second model to obtain a first evaluation value of each candidate grid output by the first model and a second evaluation value of each candidate grid output by the second model.
In this embodiment, the first model may be a binary model, which may be trained by using a RandomForest random forest algorithm. The second model can be a sequencing model, can be trained by adopting a RankNet algorithm, and can be independently trained when the first model and the second model are trained, and the first model and the second model do not interfere with each other and can be simultaneously carried out.
And a substep S120-11, obtaining an evaluation value of the grid to be selected according to the first evaluation value and the second evaluation value of the same grid to be selected.
In this embodiment, the evaluation value of the candidate grid may be obtained by adding the first evaluation value and the second evaluation value of the candidate grid, or different weights may be set for the first evaluation value and the second evaluation value respectively according to an actual application scenario, and the evaluation value of the candidate grid is finally calculated according to the weights of the first evaluation value and the second evaluation value. For example, if the weight of the first evaluation value is the first weight and the weight of the second evaluation value is the second weight, the evaluation value of the grid to be selected is the first evaluation value + the first weight + the second evaluation value + the second weight.
According to the method for determining the position of the interest point, provided by the embodiment of the invention, the evaluation results of the first model and the second model are integrated, so that the final evaluation value of the grid to be selected is more reasonable, and the accuracy of the determined position of the target interest point is finally ensured.
It should be noted that sub-steps S110-10 to S110-12 in fig. 2 may replace step S110 in fig. 3 and 4, and sub-steps S120-10 to S120-11 in fig. 3 may replace step S120 in fig. 2 and 4.
In this embodiment, when a plurality of target interest points are provided, in order to take into account the influence of a target interest point of a currently determined position on a target interest point to be determined when determining the target interest point, so as to make the evaluation of all the target interest points more reasonable, an embodiment of the present invention further provides a method for updating interference characteristics of remaining candidate grids according to the target interest point of the determined position on the basis of fig. 1, please refer to fig. 4, where fig. 4 shows a flowchart of another method for determining a position of an interest point provided by the embodiment of the present invention, and the method further includes:
step S140: and updating the interference characteristics of the rest grids to be selected except the target grid in the multiple grids to be selected based on the target grid so as to determine the positions of other target interest points from the rest grids to be selected except the target grid based on the preset evaluation model again.
In this embodiment, when there are a plurality of target interest points, the target grid for which the target interest point has been determined may be used as a new selected grid, and when a next target interest point is determined, the interference characteristics of the current candidate grid are updated based on the new selected grid and the previous selected grid, so as to determine the positions of other target interest points from the current candidate grid.
According to the method for determining the positions of the interest points, provided by the embodiment of the invention, when a plurality of target interest points are provided, the influence of the target interest points with the current determined positions on the target interest points to be determined is also taken into consideration, so that the evaluation of all the target interest points is more reasonable.
The method for determining the position of the interest point described in the embodiment of the present invention may be applied to a scenario, for example, store addressing, where a reasonable position is selected for a store to be addressed in a preset area.
The existing store site selection method is generally based on the following theories: retail gravitation theory and business circle saturation theory.
Retail gravitation theory is the most basic theory of retail commercial siting, describing the attractiveness of the two cities a and b to the middle zone population, originally proposed by the american scholars leili. The basic assumption of retail gravitation theory is that business operation capacity of different cities is the same, traffic accessibility is the same, and the core idea is that the number of consumers in the middle zone that a city can attract depends on the population of the city and the distance from the city to the middle zone. The former reflects the business type completeness of the city, and the latter reflects the commute cost of the consumer. The retail gravitation theory is not only suitable for the commercial attractions analysis between two adjacent cities, but also suitable for the commercial attractions analysis between two business circles on a more microscopic scale, but is difficult to be suitable for analyzing a specific business state. The theory simplifies the influence factors of the trade circle and provides important cornerstones for the subsequent theoretical development. A common formula for this theory is:
wherein, BaIndicating the attraction of city a to the middle zone population, BbDenotes the attraction of city b to the middle zone population, PaRepresenting the population number, P, of city abDenotes the population number of city b, DaDenotes the distance, D, of the median to the city abDenotes the distance of the middle zone to city b, N denotes an empirical value of the sensitivity of the attraction factor, and N denotes an empirical value of the sensitivity of the distance factor.
Retail gravitation theory studies the comprehensive commercial attractiveness of multiple business states, while business district saturation theory reflects the attractiveness of a business district to potential investors of that business state by calculating a certain degree of business state saturation within the business district. The saturation level of the business state is determined by comparing the supply end and the demand end, wherein the supply end evaluates the total business area of the business state in the business circle, and the demand end evaluates the number of households in the business circle and the average household purchasing power. The theory is in direct contact with the theory of evaluating the operation performance of retailers through plateau effect, the regional competition relationship is characterized through the total business area, and an important thought is provided for quantifying regional competition patterns. A common formula for this theory is:
wherein the IRSiSaturation index, H, representing the measured stateiIndicating the number of households, RE, within a regioniRepresenting consumption of each household in the area in a measured state, RFiRepresenting the total state area of the measured states in the region.
The two theories have reference significance for macroscopic site selection of stores, but the site selection of stores under a micro scene cannot be reasonably recommended, and the dimension of site selection reference is too single, so that the requirement of comprehensive site selection of the existing commercial body cannot be met.
With the development of smart cities, data which can be referred to when shop site selection is carried out is more and more abundant, a conventional site selection scheme starts with observing whether the position of a target site is a hot business circle, the distance between the target site and a residential area, a school and a business area, factors such as surveyor traffic flow, traffic mode and the like, and a final result is obtained after expert scoring.
The embodiment is applied to the store site selection scene, and the best address of the store to be selected can be found from a plurality of grids in the area to be selected by carrying out grid division on the area to be selected to which the store to be selected belongs and evaluating each grid according to the land parcel characteristics of each divided grid and the interference characteristics among the grids.
The interest points in the above embodiments may be stores, the target interest points may be stores to be selected, the attention degree of the grid to be selected represented by the parcel characteristics may be a multidimensional index of the grid to be selected, and the multidimensional index may select index content related to a store front, such as a work-day average passenger flow volume, a weekend-day average passenger flow volume, a total monthly passenger flow volume, a night passenger flow volume, a visiting passenger flow age structure, the number of surrounding dining stores, the number of public facilities, the number of commuting sites, and the like, but is not limited to the above index, and may also be data obtained by performing intersection operation on the above indexes. The influence between grids characterized by the interference features may be competition strength between stores in the grids, the area of interest of the selected grid may be the area of the created stores in the selected grid, the heat value may be a combination of one or more of the above-mentioned multi-dimensional indexes, for example, the first hot value of the selected mesh may be the visited amount covered by the selected mesh, the second hot value of the candidate mesh may be the visited amount covered by the candidate mesh, the visited amount covered by the mesh may be obtained by positioning through communication between the mobile phone and the base station, or the visit amount can be the average daily traffic of the grid in a month, or the sum of the daily traffic of the grid in a year, or the average daily traffic of the grid in a year. Besides the people flow, the heat value can also be one or more of communication data, internet data, consumption data, traffic data, business volume data and even house price data, or the data can be obtained after cleaning or normalization processing is carried out on the data.
The specific processing procedure is exemplified by the location of a store in a business hall, and the division of the area grid to which the store belongs is briefly described as an example in table 1, and the specific details can refer to the detailed description in the above embodiment.
TABLE 1
| A11 | A12 | A13 |
| A21 | A22 | A23 |
| A31 | A32 | A33 |
Collectively A11, A12, A13 in Table 1; a21, a22, a 23; the number of the grids A31, A32 and A33 is 9, wherein A12 and A32 are selected grids with the store hall stores already established, and the rest are candidate grids without the store hall stores. The number of the target business hall stores is 2, namely a and b, namely two grids are required to be selected from the grids to be selected as addresses of the a and b business hall stores respectively.
The addressing process for a is as follows:
firstly, the parcel characteristics and the interference characteristics of 7 grids of a11, a13, a21, a22, a23, a31 and a33 are obtained, and taking the heat value as an access amount as an example, the calculation process for calculating the interference characteristics of a11 may be: (1) acquiring the number of the selected grids (namely 2), the interest point areas of the selected grids (namely the area of a business hall store in A12 and the area of a business hall store in A32), the first heat value of the selected grids (namely the visited quantity covered by A12 and the visited quantity covered by A32), and the second heat value of the to-be-selected grids (namely the second heat value of A11); (2) calculating the area of the store hall of A11, namely the area of a when a is created in A11 according to the number 2 of the selected grids, the area of the store hall of A12, the area of the store hall of A32, the amount of visit covered by A12, the amount of visit covered by A32 and the second heat value of A11; (3) the interference signature of a11 was calculated from the number of selected grids 2, the area of the hall store in a12 and the area of the hall store in a32, the area of the hall store in a11 and the distance between a11 and a12, the distance between a11 and a 32.
Secondly, the land characteristics and the interference characteristics of the 7 grids A11, A13, A21, A22, A23, A31 and A33 are input into a preset evaluation model, and evaluation values of the 7 grids are obtained.
Finally, the maximum value among the evaluation values of 7 grids is taken as the address of a, and it is assumed here that a31 is the target grid, meaning that the address of a is selected in the a31 grid.
The addressing process of b is similar to that of a, except that the number of the selected grids at this time is 3(a12, a31 and a32), the grid to be selected is 6 grids of a11, a13, a21, a22, a23 and a33, when the interference characteristics of the 6 grids are calculated, calculation is needed according to the selected grid being 3, and at this time, the area of the store in the business hall in a31 is the area of the a building and the a31 calculated when the a addressing is performed. The rest of the processing procedure is similar to the processing procedure of a, and is not described in detail here.
It should be noted that, when the preset evaluation model is trained and the binary model is trained, the training data may be the land feature and the interference feature of the selected grid and the business hall income data marked with the classification label in the selected grid, for example, if the business hall income is greater than the preset threshold, the training data is marked as 1, which represents that the probability of selection is 1, otherwise, the training data is marked as 0, which represents that the probability of selection is 0. When training the ranking model, the training data may be the land features, the interference features of the selected grid, and the sequence numbers or values of the lobby income data ranked according to the lobby income data in the selected grid.
The method is used for performing store site selection, and meanwhile, the mutual influence among stores of indexes of multiple dimensions of grids in the area where the stores are located is considered, so that the site selection result obtained by the method is more reasonable, the site selection result is integrally more suitable for actual scene application, and meanwhile, the whole processing process is automatically completed by a computer based on a preset evaluation model, so that the limitation that the experience of the traditional theory is not reproducible is broken through, and the method is more beneficial to popularization and application.
In order to perform the corresponding steps in the above embodiments and various possible implementations, an implementation of the apparatus 100 for determining a location of a point of interest is given below. Referring to fig. 5, fig. 5 is a block diagram illustrating an apparatus 100 for determining a location of interest according to an embodiment of the present invention. It should be noted that the basic principle and the resulting technical effect of the apparatus 100 for determining a location of interest provided in the present embodiment are the same as those of the above embodiments, and for the sake of brief description, no reference is made in this embodiment.
The apparatus 100 for determining a location of interest includes an obtaining module 110, an evaluating module 120, a determining module 130, and an updating module 140.
An obtaining module 110, configured to: acquiring the land characteristics of each grid to be selected, wherein the land characteristics are used for representing the attention degree of the grid to be selected; and acquiring the interference characteristics of each grid to be selected, wherein the interference characteristics are used for representing the influence degree between the grid to be selected and the selected grid.
As a specific implementation manner, the obtaining module 110 is specifically configured to: acquiring the number of the selected grids, the area of interest points of the selected grids, a first heat value of the selected grids and a second heat value of each to-be-selected grid; calculating the area of the interest point of each grid to be selected according to the number of the selected grids, the area of the interest point of the selected grid, the first heat value and the second heat value, wherein the area of the interest point of the selected grid is the area of the interest point in the selected grid, and the area of the interest point of each grid to be selected is the area of the target interest point established in the grid to be selected; and obtaining the interference characteristics of each grid to be selected according to the number of the selected grids, the interest point area of each grid to be selected and the distance between each grid to be selected and the selected grids.
As a specific implementation manner, the obtaining module 110 is specifically configured to, when calculating the area of the point of interest of each candidate grid according to the number of the selected grids, the area of the point of interest of the selected grid, the first heat value, and the second heat value: using a formula
Calculating the area of the interest points of the grid to be selected, wherein SiRepresenting the area of interest point, popu, of the ith grid to be selectediRepresenting a second heat value of the ith candidate grid, n representing the number of the selected grids, j representing the jth selected grid, SjRepresents the area of interest point, popu, of the jth selected gridjRepresenting a first heat value of the jth selected grid.
As a specific implementation manner, the obtaining module 110 is specifically configured to, when obtaining the interference characteristic of each candidate grid according to the number of the selected grids, the interest point area of the selected grid, the interest point area of each candidate grid, and the distance between each candidate grid and the selected grid: using a formula
Calculating the interference characteristics of any candidate grid, wherein AiRepresenting the interference characteristics of the ith grid to be selected, n representing the number of the selected grids, k representing the coefficient for adjusting the parameter scale, j representing the jth selected grid, SjRepresenting the area of the point of interest of the jth selected grid, SiRepresents the area of interest point of the ith candidate grid, rijRepresents the ith waitingThe distance between the selected grid and the jth selected grid.
The evaluation module 120 is configured to input the land characteristics and the interference characteristics of the multiple candidate grids into a preset evaluation model, so as to obtain an evaluation value of each candidate grid.
As a specific embodiment, the preset evaluation model includes a first model and a second model, and the evaluation module 120 is specifically configured to: respectively inputting the land characteristics and the interference characteristics of a plurality of grids to be selected into a first model and a second model to obtain a first evaluation value of each grid to be selected output by the first model and a second evaluation value of each grid to be selected output by the second model; and obtaining the evaluation value of the grid to be selected according to the first evaluation value and the second evaluation value of the same grid to be selected.
And the determining module 130 is configured to use the target grid with the largest evaluation value in the candidate grids as the position of the target interest point.
And the updating module 140 is configured to update the interference characteristics of the remaining candidate grids, except for the target grid, of the multiple candidate grids based on the target grid, so as to determine the positions of the other target interest points from the remaining candidate grids, except for the target grid, based on the preset evaluation model again.
Based on the above-described method for determining a location of interest, an embodiment of the present invention further provides a block diagram of a computer device 10 for implementing the method for determining a location of interest in fig. 1 to 4, please refer to fig. 6, and fig. 6 shows a block diagram of the computer device 10 according to an embodiment of the present invention, where the computer device 10 includes a processor 11, a memory 12, a bus 13, and a communication interface 14. The processor 11 and the memory 12 are connected by a bus 13, and the processor 11 is communicatively connected to an external device via a communication interface 14.
The processor 11 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 11. The Processor 11 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components.
The memory 12 is used for storing a program, such as the apparatus 100 for determining a location of interest in fig. 5, the apparatus 100 for determining a location of interest includes at least one software functional module which can be stored in the memory 12 in a form of software or firmware (firmware), and the processor 11 executes the program after receiving an execution instruction to implement the method for determining a location of interest.
The Memory 12 may include a high-speed Random Access Memory (RAM) and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Alternatively, the memory 12 may be a storage device built in the processor 11, or may be a storage device independent of the processor 11.
The bus 13 may be an ISA bus, a PCI bus, an EISA bus, or the like. Fig. 6 is indicated by only one double-headed arrow, but does not indicate only one bus or one type of bus.
The present invention provides a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the method of determining a location of interest as described above.
In summary, embodiments of the present invention provide a method, an apparatus, a computer device, and a storage medium for determining a location of an interest point, where an area map to which a target interest point of a location to be determined belongs is divided into a plurality of grids in advance, each grid includes at most one interest point, and the grids include a plurality of grids to be selected where no interest point exists and a plurality of grids selected where an interest point exists, where the method includes: acquiring the land characteristics of each grid to be selected, wherein the land characteristics are used for representing the attention degree of the grid to be selected; acquiring interference characteristics of each grid to be selected, wherein the interference characteristics are used for representing the influence degree between the grid to be selected and the selected grid; inputting the land characteristics and the interference characteristics of a plurality of grids to be selected into a preset evaluation model to obtain an evaluation value of each grid to be selected; and taking the target grid with the maximum evaluation value in the grids to be selected as the position of the target interest point. Compared with the prior art, the method and the device have the advantages that the grid division is carried out on the regional map to which the target interest point belongs, and each grid is evaluated according to the land parcel characteristics of each divided grid and the interference characteristics among the grids, so that the position of the target interest point is determined from a plurality of grids in the region to be addressed.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (7)
1. A method for determining a position of a point of interest (POI) is characterized in that a regional map to which a target POI at a position to be determined belongs is divided into a plurality of grids in advance, at most one POI exists in each grid, the grids comprise a plurality of grids to be selected in which the POI does not exist and grids already selected in which the POI exists, and the method comprises the following steps:
acquiring the land characteristics of each grid to be selected, wherein the land characteristics are used for representing the attention degree of the grid to be selected;
acquiring the number of the selected grids, the interest point areas of the selected grids, a first heat value of the selected grids and a second heat value of each grid to be selected;
calculating the area of the interest point of each grid to be selected according to the number of the selected grids, the area of the interest point of the selected grid, the first heat value and the second heat value, wherein the area of the interest point of the selected grid is the area of the interest point in the selected grid, and the area of the interest point of each grid to be selected is the area of the target interest point in the grid to be selected;
obtaining an interference characteristic of each to-be-selected grid according to the number of the to-be-selected grids, the area of the interest points of each to-be-selected grid and the distance between each to-be-selected grid and the selected grid, wherein the interference characteristic is used for representing the degree of influence between the to-be-selected grid and the selected grid;
respectively inputting the land feature and the interference feature of the grids to be selected into a first model and a second model of a preset evaluation model to obtain a first evaluation value of each grid to be selected output by the first model and a second evaluation value of each grid to be selected output by the second model;
obtaining the evaluation value of the grid to be selected according to the first evaluation value and the second evaluation value of the same grid to be selected so as to obtain the evaluation value of each grid to be selected;
and taking the target grid with the maximum evaluation value in the candidate grids as the position of the target interest point.
2. The method for determining the location of a point of interest according to claim 1, wherein the step of calculating the area of a point of interest of each of the candidate grids according to the number of the selected grids, the area of a point of interest of the selected grids, the first heat value and the second heat value comprises:
using a formula
Calculating the area of the interest point of the grid to be selected, wherein SiRepresenting the area of interest point, popu, of the ith said grid to be selectediRepresenting a second heat value of the ith grid to be selected, n representing the number of the selected grids, j representing the jth grid to be selected, SjRepresents the area of interest point of said selected mesh, popujRepresenting a first heat value of a jth of said selected grid.
3. The method for determining the location of a point of interest according to claim 1, wherein the step of obtaining the interference characteristic of each candidate grid according to the number of the selected grids, the area of the point of interest of each candidate grid, and the distance between each candidate grid and the selected grid comprises:
using a formula
Calculating the interference characteristics of any grid to be selected, wherein AiRepresenting the interference characteristics of the ith grid to be selected, n representing the number of the selected grids, k representing the coefficient for adjusting the parameter scale, j representing the jth grid to be selected, SjRepresenting the area of interest point of said selected mesh j, SiRepresenting the area of interest point of the ith grid to be selected, rijRepresents the distance between the ith selected grid and the jth selected grid.
4. The method of determining a location of a point of interest of claim 1, the method further comprising:
and updating the interference characteristics of the rest grids to be selected except the target grid in the plurality of grids to be selected based on the target grid so as to determine the positions of other target interest points from the rest grids to be selected except the target grid based on the preset evaluation model again.
5. An apparatus for determining a location of a point of interest, wherein a map of an area to which a target point of interest of a location to be determined belongs is divided into a plurality of grids in advance, at most one point of interest exists in each of the grids, and the grids include a plurality of candidate grids in which no point of interest exists and selected grids in which a point of interest exists, the apparatus comprising:
an acquisition module to: acquiring the land characteristics of each grid to be selected, wherein the land characteristics are used for representing the attention degree of the grid to be selected; acquiring the number of the selected grids, the interest point areas of the selected grids, a first heat value of the selected grids and a second heat value of each grid to be selected; calculating the area of the interest point of each grid to be selected according to the number of the selected grids, the area of the interest point of the selected grid, the first heat value and the second heat value, wherein the area of the interest point of the selected grid is the area of the interest point in the selected grid, and the area of the interest point of each grid to be selected is the area of the target interest point in the grid to be selected; obtaining an interference characteristic of each to-be-selected grid according to the number of the to-be-selected grids, the area of the interest points of each to-be-selected grid and the distance between each to-be-selected grid and the selected grid, wherein the interference characteristic is used for representing the degree of influence between the to-be-selected grid and the selected grid;
an evaluation module to: respectively inputting the land feature and the interference feature of the grids to be selected into a first model and a second model of a preset evaluation model to obtain a first evaluation value of each grid to be selected output by the first model and a second evaluation value of each grid to be selected output by the second model; obtaining the evaluation value of the grid to be selected according to the first evaluation value and the second evaluation value of the same grid to be selected so as to obtain the evaluation value of each grid to be selected;
and the determining module is used for taking the target grid with the maximum evaluation value in the candidate grids as the position of the target interest point.
6. A computer device, characterized in that the computer device comprises:
one or more processors;
memory for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method of determining a location of interest according to any of claims 1-4.
7. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method of determining a location of interest according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010934486.1A CN112069281B (en) | 2020-09-08 | 2020-09-08 | Method and device for determining position of interest point, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010934486.1A CN112069281B (en) | 2020-09-08 | 2020-09-08 | Method and device for determining position of interest point, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112069281A CN112069281A (en) | 2020-12-11 |
| CN112069281B true CN112069281B (en) | 2021-06-18 |
Family
ID=73664231
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010934486.1A Active CN112069281B (en) | 2020-09-08 | 2020-09-08 | Method and device for determining position of interest point, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112069281B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI780540B (en) * | 2020-12-15 | 2022-10-11 | 中華電信股份有限公司 | System and method for intelligent commercial geography analysis and computer readable medium |
| TWI811603B (en) * | 2020-12-29 | 2023-08-11 | 司圖科技股份有限公司 | Poi tracking analysis system and people flow system |
| CN113220395A (en) * | 2021-05-07 | 2021-08-06 | 王云鹏 | Museum interaction method and system based on map display |
| CN113282828B (en) * | 2021-06-02 | 2024-03-26 | 万达信息股份有限公司 | Method and system for determining places where users are often, and electronic equipment |
| CN113254565B (en) * | 2021-06-21 | 2021-09-28 | 浙江口碑网络技术有限公司 | Region identification method and device, computer equipment and computer readable storage medium |
| CN114386536B (en) * | 2022-03-22 | 2022-07-01 | 腾讯科技（深圳）有限公司 | Region determination method, device, computing equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109241225A (en) * | 2018-08-27 | 2019-01-18 | 百度在线网络技术（北京）有限公司 | Point of interest competitive relation method for digging, device, computer equipment and storage medium |
| CN110070380A (en) * | 2018-01-24 | 2019-07-30 | 北京京东尚科信息技术有限公司 | Information generating method and device |
| CN110489669A (en) * | 2018-05-11 | 2019-11-22 | 中移(苏州)软件技术有限公司 | A kind of information-pushing method and device |
| US20200012680A1 (en) * | 2016-04-26 | 2020-01-09 | Toyota Jidosha Kabushiki Kaisha | Information collection system and information center |
| CN111274500A (en) * | 2020-01-15 | 2020-06-12 | 平安医疗健康管理股份有限公司 | Position information recommendation method and device, computer equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109460509A (en) * | 2018-10-12 | 2019-03-12 | 平安科技（深圳）有限公司 | User interest point appraisal procedure, device, computer equipment and storage medium |
| CN111274346A (en) * | 2020-01-21 | 2020-06-12 | 青梧桐有限责任公司 | Method, system, electronic device and readable storage medium for obtaining point of interest data |
-
2020
- 2020-09-08 CN CN202010934486.1A patent/CN112069281B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200012680A1 (en) * | 2016-04-26 | 2020-01-09 | Toyota Jidosha Kabushiki Kaisha | Information collection system and information center |
| CN110070380A (en) * | 2018-01-24 | 2019-07-30 | 北京京东尚科信息技术有限公司 | Information generating method and device |
| CN110489669A (en) * | 2018-05-11 | 2019-11-22 | 中移(苏州)软件技术有限公司 | A kind of information-pushing method and device |
| CN109241225A (en) * | 2018-08-27 | 2019-01-18 | 百度在线网络技术（北京）有限公司 | Point of interest competitive relation method for digging, device, computer equipment and storage medium |
| CN111274500A (en) * | 2020-01-15 | 2020-06-12 | 平安医疗健康管理股份有限公司 | Position information recommendation method and device, computer equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| Design and implementation of a POI collection and management system based on public map service;Yuanrong He等;《2016 Fourth International Conference on Ubiquitous Positioning, Indoor Navigation and Location Based Services (UPINLBS)》;20170109;第1-4页 * |
| 面向移动地图表达的POI动态综合方法研究;于艳平;《中国优秀硕士学位论文全文数据库 基础科学辑》;20130315(第3期);第A008-163页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112069281A (en) | 2020-12-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112069281B (en) | Method and device for determining position of interest point, computer equipment and storage medium | |
| US11238065B1 (en) | Systems and methods for generating and implementing knowledge graphs for knowledge representation and analysis | |
| Pei et al. | A new insight into land use classification based on aggregated mobile phone data | |
| CA3064137A1 (en) | Method and device for recommending information | |
| KR20190139130A (en) | Analysis method of fluidized population information capable of providing real-time fluidized population data by pcell algorithm | |
| CN109949063B (en) | Address determination method and device, electronic equipment and readable storage medium | |
| WO2017127592A1 (en) | System, method, and device for generating a geographic area heat map | |
| CN108717676B (en) | Multi-data fusion-based job and live space evaluation method and system under different scales | |
| CN111401692B (en) | Method for measuring urban space function compactness | |
| US11966424B2 (en) | Method and apparatus for dividing region, storage medium, and electronic device | |
| CN107666649A (en) | Personal property state evaluating method and device | |
| Siła-Nowicka et al. | Calibrating spatial interaction models from GPS tracking data: An example of retail behaviour | |
| Shoman et al. | A comparative analysis of gridding systems for point-based land cover/use analysis | |
| CN113627975A (en) | Store site selection method and device, computer equipment and storage medium | |
| CN116437291A (en) | Cultural circle planning method and system based on mobile phone signaling | |
| CN107784046A (en) | POI treating method and apparatus | |
| KR20140056828A (en) | Apparatus, method and computer readable recording medium for analyzing a floating population using a user terminal | |
| CN114693351A (en) | Information prediction method and device and electronic equipment | |
| Sinclair et al. | Assessing the socio-demographic representativeness of mobile phone application data | |
| CN109409959A (en) | A kind of user information analysis method, device, equipment and medium | |
| Nuzir et al. | Dynamic Land-Use Map Based on Twitter Data. | |
| CN112001384A (en) | Business circle identification method and equipment | |
| CN109670853B (en) | Method, device, equipment and readable storage medium for determining user characteristic data | |
| CN111523614B (en) | Cell similarity judging method and device | |
| Sila-Nowicka et al. | Calibrating spatial interaction models from GPS tracking data: An example of retail behaviour. |
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 |