A method and device for generating address information

Abstract

The present invention discloses an address information generation method and device, and relates to the field of computer technology. A specific implementation of the method includes: obtaining online object demand data and offline geographic environment data; using a clustering algorithm to aggregate the online object demand data and the offline geographic environment data respectively to obtain initial aggregated data points; and determining final aggregated data points based on the initial aggregated data points. This implementation can solve the problem of inaccurate addresses and low efficiency of offline store selection in the prior art.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and device for generating address information. Background Art

[0002] With the development of e-commerce technology, large e-commerce companies have accumulated a lot of technical strength, and at the same time, they have been loved by consumers with relatively low prices and fast and convenient services, and have accumulated a lot of online data. However, offline stores also have their incomparable advantages. For some low-priced goods, high-frequency purchases, or daily urgent goods, consumers prefer to buy them in offline stores, which can save shipping costs and get the required goods faster.

[0003] For e-commerce companies, by using the large amount of offline data accumulated in the early stage and site selection technology to develop offline experience stores, they can increase the sales channels of goods and fill the gap of low online sales of some items. At the same time, it is also of great significance for brand communication.

[0004] The location of stores is the primary problem faced by e-commerce companies in developing offline smart stores. If the location is not appropriate, it will cause problems such as high management costs and insufficient customer flow. E-commerce companies can use the large amount of online data that has been accumulated, the geographical distribution of commodity demand, and the geographical environment data to select areas with concentrated demand, dense traffic, and convenient transportation to select offline smart store locations.

[0005] In the process of implementing the present invention, the inventors found that there are at least the following problems in the prior art:

[0006] At present, there are two main mainstream technologies for site selection of e-commerce enterprises: one is to collect geographic environment data (offline data), estimate the possible average daily turnover of offline smart stores after opening (average daily traffic * store entry rate * customer unit price), and then subtract the corresponding operating costs, and select the site based on the principle of maximizing profits. The other is to use the previous online data of e-commerce enterprises, estimate the average daily turnover through online data, and then select the site based on the principle of maximizing profits.

[0007] However, pure online data or offline data do not fully reflect consumer demand: using only offline data cannot take advantage of the online data that e-commerce companies have accumulated, and when e-commerce companies integrate online processes into offline operations, they may not be able to adapt to the local environment. Using only online data may result in the selected stores not meeting offline needs, as online data cannot fully record all relevant geographical environment data. Summary of the invention

[0008] In view of this, an embodiment of the present invention provides a method and device for generating address information, which can solve the problem of inaccurate and low efficiency of address selection of offline stores in the prior art.

[0009] To achieve the above-mentioned purpose, according to one aspect of an embodiment of the present invention, a method for generating address information is provided, comprising acquiring online object demand data and offline geographic environment data; aggregating the online object demand data and the offline geographic environment data respectively using a clustering algorithm to obtain initial clustered data points; and determining final clustered data points based on the initial clustered data points.

[0010] Optionally, determining final clustered data points according to the initial clustered data points includes:

[0011] Calculating the distance between the online object demand data point and the initial aggregation data point to determine the classification of the online object demand data point; and calculating the distance between the offline geographic environment demand data point and the aggregation data point to determine the classification of the offline geographic environment demand data point; wherein the online object demand data includes the online object demand data point;

[0012] The final aggregated data points are obtained based on the online object demand data point classification and the offline geographic environment demand data point classification.

[0013] Optionally, calculating the distance between the online object demand data point and the initial clustered data point to determine the classification of the online object demand data point includes:

[0014] Calculate the distance between each online object demand data point and the initial clustered data point;

[0015] According to the distance, a weighted distance is calculated to determine a clustered data point that is closest to the online object demand data point as a classification of the online object demand data point;

[0016] In addition, calculating the distance between the offline geographic environment demand data point and the aggregated data point to determine the classification of the offline geographic environment demand data point includes:

[0017] Calculate the distance between each offline geographic environment demand data point and the initial aggregation data point;

[0018] According to the distance, a weighted distance is calculated to determine the clustered data point closest to the offline geographic environment demand data point as the classification of the offline geographic environment demand data point.

[0019] Optionally, the step of obtaining final aggregated data points according to the classification of online object demand data points and offline geographic environment demand data points includes:

[0020] For each online object demand data point classification location information, calculate the centroid of all online object demand data points within a preset radius; similarly, for each offline geographic environment demand data point classification location information, calculate the centroid of all offline geographic environment demand data points within a preset radius;

[0021] The final clustered data points are obtained according to the centroid of all online object demand data points and the centroid of all offline geographic environment demand data points.

[0022] Optionally, according to the online object demand data point classification and the offline geographic environment demand data point classification, the aggregated data points are iteratively updated until a preset condition is met to obtain the final aggregated data points.

[0023] Optionally, according to the online object demand data point classification and the offline geographic environment demand data point classification, the aggregated data points are iteratively updated, including:

[0024] For each online object demand data point classification location information, calculate the centroid A of all online object demand data points within the preset radius 1 ′(x a1 ′,y a1 ′), B 1 ′(x b1 ′,y b1 ′), C 1 ′(x c1 ′,y c1 ′), D 1 ′(x d1 ′,y d1 ′)……; Similarly, for each offline geographic environment demand data point classification location information, calculate the centroid A of all offline geographic environment demand data points within the preset radius 1 ″(x a1 ″,y a1 ″)、B 1 ″(x b1 ″,y b1 ″)、C 1 ″(x c1 ″,y c1 ″)、D 1 ″(x d1 ″,y d1 ″)……;

[0025] Determine the clustered data points for the next iteration:

[0026] N 1 (x,y)=[N′ 1 (x′ n1 ,y′ n1 )+β×N″ 1 (x″n1 ,y″ n1 )]÷2

[0027] in:

[0028] N∈{A,B,C,D...}

[0029] When β>1: the impact of offline geographic environment demand data points is greater than the impact of online object demand data points;

[0030] When β<1: the impact of offline geographic environment demand data points is smaller than the impact of online object demand data points;

[0031] When β=1: the impact of offline geographic environment demand data points is equal to the impact of online object demand data points.

[0032] Optionally, the preset condition is: the distance between the aggregated data points after updating and the aggregated data points before updating is less than the error distance, or the number of cycles is greater than or equal to a set maximum number of cycles threshold.

[0033] Optionally, the clustering algorithm adopts a k-means clustering algorithm.

[0034] In addition, according to one aspect of an embodiment of the present invention, an address information generating device is provided, including an acquisition module for acquiring online object demand data and offline geographic environment data; a calculation module for respectively aggregating the online object demand data and the offline geographic environment data using a clustering algorithm to obtain initial clustered data points; and a selection module for determining final clustered data points based on the initial clustered data points.

[0035] Optionally, the selection module determines the final aggregated data points according to the initial aggregated data points, including:

[0036] Calculating the distance between the online object demand data point and the initial aggregation data point to determine the classification of the online object demand data point; and calculating the distance between the offline geographic environment demand data point and the aggregation data point to determine the classification of the offline geographic environment demand data point; wherein the online object demand data includes the online object demand data point;

[0037] The final aggregated data points are obtained based on the online object demand data point classification and the offline geographic environment demand data point classification.

[0038] Optionally, the selection module calculates the distance between the online object demand data point and the initial clustered data point to determine the classification of the online object demand data point, including:

[0039] Calculate the distance between each online object demand data point and the initial clustered data point;

[0040] According to the distance, a weighted distance is calculated to determine a clustered data point that is closest to the online object demand data point as a classification of the online object demand data point;

[0041] In addition, the calculation module calculates the distance between the offline geographic environment demand data point and the initial clustered data point to determine the classification of the offline geographic environment demand data point, including:

[0042] Calculate the distance between each offline geographic environment demand data point and the initial aggregation data point;

[0043] According to the distance, a weighted distance is calculated to determine the clustered data point closest to the offline geographic environment demand data point as the classification of the offline geographic environment demand data point.

[0044] Optionally, the selection module obtains final aggregated data points according to the online object demand data point classification and the offline geographic environment demand data point classification, including:

[0045] For each online object demand data point classification location information, calculate the centroid of all online object demand data points within a preset radius; similarly, for each offline geographic environment demand data point classification location information, calculate the centroid of all offline geographic environment demand data points within a preset radius;

[0046] The final clustered data points are obtained according to the centroid of all online object demand data points and the centroid of all offline geographic environment demand data points.

[0047] Optionally, the selection module iteratively updates the aggregated data points according to the online object demand data point classification and the offline geographic environment demand data point classification until a preset condition is met to obtain the final aggregated data points.

[0048] Optionally, the selection module iteratively updates the aggregated data points according to the online object demand data point classification and the offline geographic environment demand data point classification, including:

[0049] For each online object demand data point classification location information, calculate the centroid A of all online object demand data points within the preset radius 1 ′(x a1 ′,y a1 ′), B 1 ′(x b1 ′,y b1 ′), C 1 ′(x c1 ′,y c1 ′), D 1 ′(x d1 ′,y d1′)……; Similarly, for each offline geographic environment demand data point classification location information, calculate the centroid A of all offline geographic environment demand data points within the preset radius 1 ″(x a1 ″,y a1 ″)、B 1 ″(x b1 ″,y b1 ″)、C 1 ″(x c1 ″,y c1 ″)、D 1 ″(x d1 ″,y d1 ″)……;

[0050] Determine the clustered data points for the next iteration:

[0051] N 1 (x,y)=[N′ 1 (x′ n1 ,y′ n1 )+β×N″ 1 (x″ n1 ,y″ n1 )]÷2

[0052] in:

[0053] N∈{A,B,C,D...}

[0054] When β>1: the impact of offline geographic environment demand data points is greater than the impact of online object demand data points;

[0055] When β<1: the impact of offline geographic environment demand data points is smaller than the impact of online object demand data points;

[0056] When β=1: the impact of offline geographic environment demand data points is equal to the impact of online object demand data points.

[0057] Optionally, the preset condition is: the distance between the aggregated data points after updating and the aggregated data points before updating is less than the error distance, or the number of cycles is greater than or equal to a set maximum number of cycles threshold.

[0058] Optionally, the clustering algorithm adopts a k-means clustering algorithm.

[0059] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, including:

[0060] one or more processors;

[0061] a storage device for storing one or more programs,

[0062] When the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any of the above-mentioned address information generation embodiments.

[0063] According to another aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored. When the program is executed by a processor, the method described in any of the above-mentioned address information generation embodiments is implemented.

[0064] One embodiment of the above invention has the following advantages or beneficial effects: because it adopts a technical means of combining the online order demand data of the e-commerce enterprise and the offline geographical environment data to generate offline store address information, the interests of the offline stores are maximized, and at the same time the brand effect of the e-commerce enterprise can be enhanced.

[0065] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with specific implementation examples. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0067] Figure 1 is a schematic diagram of the main process of the address information generating method according to an embodiment of the present invention;

[0068] Figure 2 is a schematic diagram of the main process of the address information generating method according to a reference embodiment of the present invention;

[0069] Figure 3 is a schematic diagram of main modules of an address information generating device according to an embodiment of the present invention;

[0070] Figure 4 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0071] Figure 5 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0072] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0073] Figure 1is a method for generating address information according to an embodiment of the present invention, such as Figure 1 As shown, the address information generating method includes:

[0074] Step S101, obtaining online object demand data and offline geographic environment data.

[0075] The online object demand data includes the order data of the online object and the longitude and latitude coordinate information corresponding to the order data, namely, the online object demand data point.

[0076] Step S102: clustering the online object demand data and the offline geographic environment data respectively using a clustering algorithm to obtain initial clustered data points.

[0077] The clustering algorithm is initialized to obtain initial clustered data points.

[0078] Step S103, determining the final clustered data points according to the initial clustered data points. The specific implementation process includes:

[0079] The online object demand data includes online object demand data points.

[0080] Step 1: Calculate the distance between the online object demand data point and the initial clustered data point to determine the classification of the online object demand data point; and calculate the distance between the offline geographic environment demand data point and the clustered data point to determine the classification of the offline geographic environment demand data point.

[0081] Preferably, when executing step one, the distance between each online object demand data point and the initial clustered data point can be calculated; based on the distance, a weighted distance is calculated to determine the clustered data point closest to the online object demand data point as the classification of the online object demand data point.

[0082] Similarly, the distance between each offline geographic environment demand data point and the initial clustered data point can be calculated; based on the distance, a weighted distance is calculated to determine the clustered data point closest to the offline geographic environment demand data point as the classification of the offline geographic environment demand data point.

[0083] Step 2: Classify the online object demand data points and the offline geographic environment demand data points to obtain the final aggregated data points.

[0084] Preferably, for each online object demand data point classification location information, the centroid of all online object demand data points within a preset radius is calculated; similarly, for each offline geographic environment demand data point classification location information, the centroid of all offline geographic environment demand data points within a preset radius is calculated;

[0085] Then, the final clustered data points are obtained according to the centroid of all online object demand data points and the centroid of all offline geographic environment demand data points.

[0086] Another preferred embodiment is to iteratively update the aggregated data points according to the online object demand data point classification and the offline geographic environment demand data point classification until the preset conditions are met to obtain the final aggregated data points. The specific implementation process includes:

[0087] When executing step 3, the centroid A of all online object demand data points within a preset radius can be calculated for the location information of each online object demand data point classification. 1 ′(x a1 ′,y a1 ′), B 1 ′(x b1 ′,y b1 ′), C 1 ′(x c1 ′,y c1 ′), D 1 ′(x d1 ′,y d1 ′)……; Similarly, for each offline geographic environment demand data point classification location information, calculate the centroid A of all offline geographic environment demand data points within the preset radius 1 ″(x a1 ″,y a1 ″)、B 1 ″(x b1 ″,y b1 ″)、C 1 ″(x c1 ″,y c1 ″)、D 1 ″(x d1 ″,y d1 ″)……;

[0088] Determine the clustered data points for the next iteration:

[0089] N 1 (x,y)=[N′ 1 (x′ n1 ,y′ n1 )+β×N″ 1 (x″ n1 ,y″ n1 )]÷2

[0090] in:

[0091] N∈{A,B,C,D...}

[0092] When β>1: the impact of offline geographic environment demand data points is greater than the impact of online object demand data points;

[0093] When β<1: the impact of offline geographic environment demand data points is smaller than the impact of online object demand data points;

[0094] When β=1: the impact of offline geographic environment demand data points is equal to the impact of online object demand data points.

[0095] Furthermore, the preset condition is that the distance between the aggregated data points after updating and the aggregated data points before updating is less than the error distance, or the number of cycles is greater than or equal to a set maximum number of cycles threshold.

[0096] According to the various embodiments above, it can be seen that the address information generation method can find the best commodity gathering point through the aggregation of online commodity demand data. And, combined with offline geographical environment information, the best store location is adjusted. In addition, the present invention also provides a margin for manual site selection. By adjusting the parameters, the total number of stores finally determined by the address information generation technology can be slightly more than the final plan. Finally, the final store is screened by considering social factors.

[0097] Figure 2 : is a schematic diagram of the main process of the address information generation method according to a reference embodiment of the present invention, and the address information generation method may include:

[0098] Step S201, obtaining online object demand data and offline geographic environment data.

[0099] In an embodiment, order data of online objects may be collected to reflect the demand for the objects through the online order data. Preferably, online objects may also be selected and the selected objects may be used as objects that can be sold in offline stores.

[0100] Furthermore, the longitude and latitude coordinates of the object in the selected store location area (i.e., the longitude and latitude coordinates corresponding to the total sales of the object in the store location area) are obtained, and the total online sales of each object in the area during a preset period are counted. The longitude and latitude coordinates of the store location area are accurate to three decimal places. For example, see Table 1, where each object (in this embodiment, the object is represented as a commodity) is represented as a data row. Each row is regarded as a data point. For the i-th data point, the longitude is x. i , latitude is y i , the total profit of the product (which can be the unit profit multiplied by the total sales volume) is w i , preferably, the data points with a total profit of 0 can be removed.

[0101] In addition, the goods are represented by SKU, and the full name of SKU is Stock Keeping Unit, which is the unit of measurement for inventory in and out, which can be in pieces, boxes, pallets, etc. SKU is a necessary method for logistics management of large chain supermarkets or distribution centers. It has now been extended to the abbreviation of the unified number of goods. Each product has a unique SKU number.

[0102] For example, if you need to select a location for a smart store in Beijing, you can query historical data and count the order data of all relevant objects in Beijing in the past two years to get the following historical commodity demand statistics.

[0103] It should be noted that the higher the accuracy of longitude and latitude during statistics, the less likely it is that the same type of objects will be clustered, and the larger the amount of order data used to assist in generating address information; the lower the accuracy of longitude and latitude, the smaller the amount of data. However, a large amount of data does not necessarily mean a good result for the algorithm. Preferably, the longitude and latitude coordinates with three decimal places, that is, the order data with a radius of about 0.15KM will be considered as data from the same location.

[0104] Table 1 Historical commodity demand data statistics

[0105] Product SKU <![CDATA[Longitude (x i )]]> <![CDATA[Latitude (y i )]]> <![CDATA[Total profit (w i )]]> 10000001 116.353 39.983 5 10000001 116.345 40.662 3 10000002 116.125 39.112 8 … … … … 89245922 116.349 39.024 1

[0106] In addition, the offline geographical environment data obtained is information data of relatively large customer flow in the store address area, wherein the information data includes longitude, latitude and customer flow weight of each coordinate set according to customer flow.

[0107] For example, areas with large passenger flow, such as subway information, business district information, and residential area information, and more detailed information such as subway stations (as shown in Table 2: For each subway station, the longitude and latitude coordinates are obtained through the online map API, and different weights v are set according to the passenger flow of each subway station. j . ), bus stops, residential areas, etc.

[0108] Table 2 Statistics of subway distribution data

[0109] Subway station number Subway Station Name <![CDATA[Longitude (x j )]]> <![CDATA[Latitude (y j )]]> <![CDATA[Passenger flow weight (v j ) <!-- 6 -->]]> 1 By sea 116.569 39.789 5 2 Xiaocun 116.454 39.840 1 3 Wudaokou 116.344 39.998 10 … … … … …

[0110] Step S202, initializing the k-means algorithm to obtain initial clustered data points.

[0111] Among them, the k-means algorithm, that is, the k-means clustering algorithm, is a representative of typical prototype-based objective function clustering methods. It uses a certain distance from the data point to the prototype as the optimized objective function and uses the method of finding the extreme value of the function to obtain the adjustment rules of iterative operations.

[0112] As an embodiment, k initial clustering data points are randomly selected, that is, k data points are selected from offline geographic environment data points as initial clustering data points. Further, it can be set:

[0113] k The number of smart stores that need to be selected m Adjustment parameter u

[0114] Among them: u is the adjustment parameter, the purpose is to select m+u smart offline stores, and then comprehensively consider various external factors among all the selected stores (for example: popular business districts and popular shopping centers can increase the brand effect of enterprises). When u=0, it means no adjustment is made, and the k-means algorithm is fully trusted to generate address information.

[0115] In the above example, suppose you need to select 2 stores, set u = 2, then select A 0 (x a0 ,y a0 ), B 0 (x b0 ,y b0 ), C 0 (x c0 ,y c0 )、D 0 (x d0 ,y d0 ) The four points are the initial clustered data points.

[0116] Preferably, in order to make the algorithm converge quickly, a historical object demand point mapping may be performed first, and initial clustered data points may be selected in an area where demand points are densely clustered.

[0117] Step S203, calculating the distance between the online object demand data point and the initial clustered data point to determine the classification of the online object demand data point.

[0118] As an example, for each object demand data point i, the initial distance RA between each object demand data point and the selected initial aggregation data point is calculated by longitude and latitude. i0 , RB i0 ,RC i0 , RD i0 ……. And based on the initial distance, calculate the initial weighted distance RA i1 , RB i1 ,RC i1 , RD i1…… :

[0119] RA i1 =RA i0 / 1+α×w i )

[0120] The parameter α can be adjusted. The larger the α is, the more sensitive the address information is to profit. The range of α is (0, +∞). Preferably, α can be selected to be slightly larger than 1. i is the total profit.

[0121] According to the calculated initial weighted distance RA i1 , RB i1 ,RC i1 , RD i1 ..., select the initial clustering data point closest to the object demand data point i as the initial classification of the object demand data point i. For example, for the object demand data point i, RB is calculated. i1 is the minimum value, then the commodity demand data point is classified as B.

[0122] Step S204, calculating the distance between the offline geographic environment demand data point and the initial clustered data point to determine the classification of the offline geographic environment demand data point.

[0123] As an example, the algorithm of step S203 is used to calculate the latitude and longitude and the passenger flow weight (v i ) Calculate the initial weighted distance RA between the offline geographic environment demand data point j and the selected initial aggregation point j1 , RB j1 ,RC j1 , RD j1 ... And according to the initial weighted distance, for each offline geographical environment demand point j, according to the classification method of step S203, the initial classification of each offline geographical environment demand point j is calculated.

[0124] Step S205, iteratively updating the aggregated data points according to the online object demand data point classification and the offline geographic environment demand data point classification until the preset conditions are met to obtain the final aggregated data points.

[0125] As an embodiment, for the location information of each online object demand data point classification, the centroid of all online object demand data points within a radius of R is calculated (the average value is taken according to the coordinates), and is determined as A 1 ′(x a1 ′,y a1 ′), B 1 ′(x b1 ′,y b1 ′), C 1 ′(x c1 ′,y c1 ′), D 1 ′(x d1 ′,y d1′). Similarly, for each offline geographic environment demand data point classification location information, the centroid A is calculated 1 ″(x a1 ″,y a1 ″)、B 1 ″(x b1 ″,y b1 ″)、C 1 ″(x c1 ″,y c1 ″)、D 1 ″(x d1 ″,y d1 ″).

[0126] Among them, for the selection of R: first draw a map of the online object demand data points or the offline geographical environment demand data points, and then determine the value of R in combination with the map and the actual situation. Preferably, 5km can be selected initially, that is, the audience range of this store is set to customers within 5km. Subsequently, R can be adjusted through the data accumulated after the physical store opens, and then the address information of the new store can be calculated.

[0127] Then, determine the clustered data points for the next iteration:

[0128] N 1 (x,y)=[N′ 1 (x′ n1 ,y′ n1 )+β×N″ 1 (x″ n1 ,y″ n1 )÷2

[0129] in:

[0130] N∈{A,B,C,D...}

[0131] β can be equal to 1, slightly greater than 1, or slightly less than 1, where:

[0132] When β>1: the impact of offline geographic environment demand data points is greater than the impact of online object demand data points.

[0133] When β<1: the impact of offline geographic environment demand data points is smaller than the impact of online object demand data points.

[0134] When β=1: the impact of offline geographic environment demand data points is equal to the impact of online object demand data points.

[0135] Finally, according to the calculated new clustered data point A 1 ,B 1 ,C 1 ,D 1 ..., return to step S203 and iterate again to calculate A2 ,B 2 ,C 2 ,D 2 ……. When the loop is iterated and optimized and the preset conditions are met, the loop can be ended to obtain the final clustered data point, that is, the offline store location selected last. Among them, the optimization condition can be that the distance between the newly calculated clustered data point and the old clustered data point (the data cluster point obtained in the previous round of iteration) is less than the error distance S, or the number of cycles is greater than or equal to the set maximum number of cycles threshold T.

[0136] Specifically, the loop stop condition is:

[0137] distance(N q ,N q-1 )<S or q≥T

[0138] q: Number of cycles

[0139] S: Pre-set error distance

[0140] T: The maximum number of cycles threshold set in advance

[0141] Step S206, obtaining the selected address according to the finally determined clustered data points.

[0142] In the embodiment, k offline stores, i.e., the final determined clustered data points, are finally obtained through step S205, and then the number m of smart stores to be selected is finally determined according to the adjustment parameter u. In the above specific embodiment, two stores are finally selected from the four store addresses finally obtained by the k-means algorithm based on various factors.

[0143] In addition, the specific implementation content of the address information generating method described in the reference embodiment of the present invention has been described in detail in the above-mentioned address information generating method, so the repeated content will not be described here.

[0144] Figure 3 is an address information generating device according to an embodiment of the present invention, such as Figure 3 As shown, the address information generating device 300 includes an acquisition module 301, a calculation module 302 and a selection module 303. The acquisition module 301 acquires online object demand data and offline geographic environment data. Then, the calculation module 302 uses a clustering algorithm to aggregate the online object demand data and the offline geographic environment data respectively to obtain initial clustered data points. Finally, the selection module 303 determines the final clustered data points based on the initial clustered data points.

[0145] As a preferred embodiment, the selection module 303 determines the final aggregation data point based on the initial aggregation data point to obtain the selected address. The specific implementation process includes:

[0146] Step 1: Calculate the distance between the online object demand data point and the initial clustered data point to determine the classification of the online object demand data point; and calculate the distance between the offline geographic environment demand data point and the clustered data point to determine the classification of the offline geographic environment demand data point.

[0147] Preferably, when executing step one, the distance between each online object demand data point and the initial clustered data point can be calculated; based on the distance, a weighted distance is calculated to determine the clustered data point closest to the online object demand data point as the classification of the online object demand data point.

[0148] Similarly, the distance between each offline geographic environment demand data point and the initial clustered data point can be calculated; based on the distance, a weighted distance is calculated to determine the clustered data point closest to the offline geographic environment demand data point as the classification of the offline geographic environment demand data point.

[0149] Step 2: Classify the online object demand data points and the offline geographic environment demand data points to obtain the final aggregated data points.

[0150] Preferably, for each online object demand data point classification location information, the centroid of all online object demand data points within a preset radius is calculated; similarly, for each offline geographic environment demand data point classification location information, the centroid of all offline geographic environment demand data points within a preset radius is calculated;

[0151] Then, the final clustered data points are obtained according to the centroid of all online object demand data points and the centroid of all offline geographic environment demand data points.

[0152] Another preferred embodiment is to iteratively update the aggregated data points according to the online object demand data point classification and the offline geographic environment demand data point classification until the preset conditions are met to obtain the final aggregated data points. The specific implementation process includes:

[0153] When executing step 3, the centroid A of all online object demand data points within a preset radius can be calculated for the location information of each online object demand data point classification. 1 ′(x a1 ′,y a1 ′), B 1 ′(x b1 ′,y b1 ′), C 1 ′(x c1′,y c1 ′), D 1 ′(x d1 ′,y d1 ′)……; Similarly, for each offline geographic environment demand data point classification location information, calculate the centroid A of all offline geographic environment demand data points within the preset radius 1 ″(x a1 ″,y a1 ″)、B 1 ″(x b1 ″,y b1 ″)、C 1 ″(x c1 ″,y c1 ″)、D 1 ″(x d1 ″,y d1 ″)……;

[0154] Determine the clustered data points for the next iteration:

[0155] N 1 (x,y)=[N′ 1 (x′ n1 ,y′ n1 )+β×N″ 1 (x″ n1 ,y″ n1 )]÷2

[0156] in:

[0157] N∈{A,B,C,D...}

[0158] When β>1: the impact of offline geographic environment demand data points is greater than the impact of online object demand data points;

[0159] When β<1: the impact of offline geographic environment demand data points is smaller than the impact of online object demand data points;

[0160] When β=1: the impact of offline geographic environment demand data points is equal to the impact of online object demand data points.

[0161] Furthermore, the preset condition is that the distance between the aggregated data points after updating and the aggregated data points before updating is less than the error distance, or the number of cycles is greater than or equal to a set maximum number of cycles threshold.

[0162] It should be noted that the specific implementation content of the address information generating device of the present invention has been described in detail in the above-mentioned address information generating method, so the repeated content will not be described again here.

[0163] Figure 4An exemplary system architecture 400 to which the address information generation method or address information generation device according to the embodiment of the present invention can be applied is shown. Figure 4 An exemplary system architecture 400 is shown to which the address information generating method or the address information generating device according to the embodiment of the present invention can be applied.

[0164] like Figure 4 As shown, system architecture 400 may include terminal devices 401, 402, 403, network 404 and server 405. Network 404 is used to provide a medium for communication links between terminal devices 401, 402, 403 and server 405. Network 404 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0165] Users can use terminal devices 401, 402, 403 to interact with server 405 through network 404 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 401, 402, 403, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples).

[0166] The terminal devices 401 , 402 , and 403 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0167] The server 405 may be a server that provides various services, such as a backend management server (only an example) that provides support for shopping websites browsed by users using the terminal devices 401, 402, and 403. The backend management server may analyze and process the received data such as product information query requests, and feed back the processing results (such as target push information, product information - only an example) to the terminal device.

[0168] It should be noted that the address information generating method provided in the embodiment of the present invention is generally executed by the server 405 , and accordingly, the address information generating device is generally disposed in the server 405 .

[0169] It should be understood that Figure 4 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0170] Reference below Figure 5 , which shows a schematic diagram of the structure of a computer system 500 of a terminal device suitable for implementing an embodiment of the present invention. Figure 5 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0171] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage part 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the system 500 are also stored. The CPU 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0172] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed, so that a computer program read therefrom is installed into the storage section 508 as needed.

[0173] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 509, and / or installed from the removable medium 511. When the computer program is executed by the central processing unit (CPU) 501, the above-mentioned functions defined in the system of the present invention are executed.

[0174] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0175] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0176] The modules involved in the embodiments of the present invention may be implemented by software or hardware. The modules described may also be set in a processor. For example, it may be described as follows: a processor includes an acquisition module, a calculation module, and a selection module. The names of these modules do not, in some cases, constitute limitations on the modules themselves.

[0177] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes: obtaining online object demand data and offline geographic environment data; using a clustering algorithm to aggregate the online object demand data and the offline geographic environment data respectively to obtain initial aggregated data points; and determining final aggregated data points based on the initial aggregated data points.

[0178] According to the technical solution of the embodiment of the present invention, because the technical means of combining the online order demand data of the e-commerce enterprise and the offline geographical environment data to generate the offline store address information is adopted, the benefits of the offline stores are maximized, and the brand effect of the e-commerce enterprise can be enhanced.

[0179] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for generating address information, characterized in that: include: Obtain online object demand data and offline geographic environment data; Using a clustering algorithm to aggregate the online object demand data and the offline geographic environment data respectively to obtain initial aggregated data points; According to the initial aggregated data points, final aggregated data points are determined, including: calculating the distance between the online object demand data points and the initial aggregated data points to determine the classification of the online object demand data points; and calculating the distance between the offline geographic environment demand data points and the aggregated data points to determine the classification of the offline geographic environment demand data points; wherein the online object demand data includes online object demand data points; and obtaining final aggregated data points based on the classification of the online object demand data points and the classification of the offline geographic environment demand data points.

2. The method according to claim 1, characterized in that Calculating the distance between the online object demand data point and the initial clustered data point to determine the classification of the online object demand data point includes: Calculate the distance between each online object demand data point and the initial clustered data point; According to the distance, a weighted distance is calculated to determine a clustered data point that is closest to the online object demand data point as a classification of the online object demand data point; In addition, calculating the distance between the offline geographic environment demand data point and the aggregated data point to determine the classification of the offline geographic environment demand data point includes: Calculate the distance between each offline geographic environment demand data point and the initial aggregation data point; According to the distance, a weighted distance is calculated to determine the clustered data point closest to the offline geographic environment demand data point as the classification of the offline geographic environment demand data point.

3. The method according to claim 1, characterized in that The method of obtaining final aggregated data points according to the classification of online object demand data points and offline geographic environment demand data points includes: For each online object demand data point classification location information, calculate the centroid of all online object demand data points within a preset radius; similarly, for each offline geographic environment demand data point classification location information, calculate the centroid of all offline geographic environment demand data points within a preset radius; The final clustered data points are obtained according to the centroid of all online object demand data points and the centroid of all offline geographic environment demand data points.

4. The method according to claim 1, characterized in that: According to the classification of online object demand data points and offline geographic environment demand data points, the aggregated data points are iteratively updated until the preset conditions are met to obtain the final aggregated data points.

5. The method according to claim 4, characterized in that According to the classification of online object demand data points and offline geographic environment demand data points, iteratively update the aggregated data points, including: For each online object demand data point classification location information, calculate the centroid A1′(x a1 ′,y a1 ′), B1′(x b1 ′,y b1 ′), C1′(x c1 ′,y c1 ′)、D1′(x d1 ′,y d1 ′)……; Similarly, for each offline geographic environment demand data point classification location information, calculate the centroid A1″(x a1 ″,y a1 ″)、B1″(x b1 ″,y b1 ″)、C1″(x c1 ″,y c1 ″)、D1″(x d1 ″,y d1 ″)……; Determine the clustered data points for the next iteration: N1(x,y)=[N′1(x′ n1 ,y′ n1 )+β×N ″ 1(x″ n1 ,y″ n1 )]÷2 in: N∈{A,B,C,D...} When β>1: the impact of offline geographic environment demand data points is greater than the impact of online object demand data points; When β<1: the impact of offline geographic environment demand data points is smaller than the impact of online object demand data points; When β=1: the impact of offline geographic environment demand data points is equal to the impact of online object demand data points.

6. The method according to claim 4, characterized in that The preset condition is: the distance between the aggregated data points after updating and the aggregated data points before updating is less than the error distance, or the number of cycles is greater than or equal to the set maximum number of cycles threshold.

7. The method according to any one of claims 1 to 6, characterized in that: The clustering algorithm adopts the k-means clustering algorithm.

8. An address information generating device, characterized in that: include: An acquisition module, used to acquire online object demand data and offline geographic environment data; A calculation module, used to aggregate the online object demand data and the offline geographic environment data respectively using a clustering algorithm to obtain initial aggregated data points; A selection module is used to determine the final clustered data points based on the initial clustered data points, including: calculating the distance between the online object demand data points and the initial clustered data points to determine the classification of the online object demand data points; and calculating the distance between the offline geographic environment demand data points and the clustered data points to determine the classification of the offline geographic environment demand data points; wherein the online object demand data includes online object demand data points; and obtaining the final clustered data points based on the classification of the online object demand data points and the classification of the offline geographic environment demand data points.

9. The device according to claim 8, characterized in that The selection module calculates the distance between the online object demand data point and the initial clustered data point to determine the classification of the online object demand data point, including: Calculate the distance between each online object demand data point and the initial clustered data point; According to the distance, a weighted distance is calculated to determine a clustered data point that is closest to the online object demand data point as a classification of the online object demand data point; In addition, the calculation module calculates the distance between the offline geographic environment demand data point and the initial clustered data point to determine the classification of the offline geographic environment demand data point, including: Calculate the distance between each offline geographic environment demand data point and the initial aggregation data point; According to the distance, a weighted distance is calculated to determine the clustered data point closest to the offline geographic environment demand data point as the classification of the offline geographic environment demand data point.

10. The device according to claim 8, characterized in that The selection module obtains the final aggregated data points according to the online object demand data point classification and the offline geographic environment demand data point classification, including: For each online object demand data point classification location information, calculate the centroid of all online object demand data points within a preset radius; similarly, for each offline geographic environment demand data point classification location information, calculate the centroid of all offline geographic environment demand data points within a preset radius; The final clustered data points are obtained according to the centroid of all online object demand data points and the centroid of all offline geographic environment demand data points.

11. The device according to claim 8, characterized in that The selection module iteratively updates the aggregated data points according to the online object demand data point classification and the offline geographic environment demand data point classification until the preset conditions are met to obtain the final aggregated data points.

12. The device according to claim 11, characterized in that The selection module iteratively updates the aggregated data points according to the online object demand data point classification and the offline geographic environment demand data point classification, including: For each online object demand data point classification location information, calculate the centroid A1′(x a1 ′,y a1 ′), B1′(x b1 ′,y b1 ′), C1′(x c1 ′,y c1 ′)、D1′(x d1 ′,y d1 ′)……; Similarly, for each offline geographic environment demand data point classification location information, calculate the centroid A1″(x a1 ″,y a1 ″)、B1″(x b1 ″,y b1 ″)、C1″(x c1 ″,y c1 ″)、D1″(x d1 ″,y d1 ″)……; Determine the clustered data points for the next iteration: N1(x,y)=[N′1(x′ n1 ,y′ n1 )+β×N″1(x″ n1 ,y″ n1 )]÷2 in: N∈{A,B,C,D...} When β>1: the impact of offline geographic environment demand data points is greater than the impact of online object demand data points; When β<1: the impact of offline geographic environment demand data points is smaller than the impact of online object demand data points; When β=1: the impact of offline geographic environment demand data points is equal to the impact of online object demand data points.

13. The device according to claim 11, characterized in that The preset condition is: the distance between the aggregated data points after updating and the aggregated data points before updating is less than the error distance, or the number of cycles is greater than or equal to the set maximum number of cycles threshold.

14. The device according to any one of claims 8 to 13, characterized in that: The clustering algorithm adopts the k-means clustering algorithm.

15. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

16. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images