Site selection method, device, equipment and storage medium

Abstract

The embodiment of the present application discloses a site selection method, device, equipment and storage medium, and the present application relates to artificial intelligence technology. The method includes: obtaining address attribute information and asset attribute information of the desired site selection of the target user; determining a candidate area according to the address attribute information, dividing the candidate area according to a preset area division rule to obtain M sub-areas; obtaining the sub-areas M i Population characteristics information and obtain sub-region M i Transaction feature information of sub-area M i The population characteristics information, transaction characteristics information and asset attribute information are identified to obtain the sub-region M i According to the matching degrees corresponding to the M sub-areas, the target site selection area of ​​the target user is determined from the M sub-areas. Through this application, the target site selection area can be determined quickly and accurately for the target user, thereby improving the site selection efficiency.

Description

Technical Field

[0001] The present application relates to the field of machine learning technology, and in particular to a site selection method, device, equipment and storage medium. Background Art

[0002] In recent years, the traditional offline retail industry has been hit hard by e-commerce and is facing unprecedented challenges. By choosing a better store address, users' offline shopping experience can be improved and their interest in offline shopping can be enhanced, so as to better conduct offline business.

[0003] The current site selection plan is based on manual research and collection of single site selection data, and the site selection area required by the user is determined in combination with the user's site selection requirements. The data used to determine the site selection area is relatively simple and manual site selection is time-consuming and labor-intensive, resulting in low site selection accuracy and efficiency. Summary of the invention

[0004] The technical problem to be solved by the embodiments of the present application is to provide a site selection method, device, equipment and storage medium, which can quickly and accurately determine the target site selection area for the target user and improve the site selection efficiency.

[0005] An embodiment of the present application provides a site selection method, including:

[0006] Obtaining address attribute information and asset attribute information of the target user's desired location;

[0007] Determine a candidate area according to the address attribute information, and divide the candidate area into M sub-areas according to a preset area division rule, where M is a positive integer;

[0008] Get sub-region M i The population characteristics information of the sub-region M i Transaction feature information of sub-area M i Belongs to M sub-areas, i is a positive integer less than or equal to M;

[0009] For sub-region M i The population characteristics information, transaction characteristics information and asset attribute information are identified to obtain the sub-region M i The matching degree of sub-region M i The matching degree of the sub-region M is used to reflect i The matching degree with the target users’ expected location;

[0010] According to the matching degrees corresponding to the M sub-areas respectively, the target location area of ​​the target user is determined from the M sub-areas.

[0011] Among them, transaction characteristic information includes regional travel costs;

[0012] Get sub-region M i Transaction characteristics information, including:

[0013] Get the sub-region M i The road type corresponding to the road is determined according to the road type. i The passage damping parameter of

[0014] Determine the sub-area M according to the traffic damping parameter i The travel time cost;

[0015] Get sub-region M i The traffic mode within the area is determined according to the traffic mode. i toll costs;

[0016] For sub-region M i The travel time cost and toll cost are summed to obtain the sub-area M i regional travel costs.

[0017] Among them, transaction characteristic information includes industry distribution information;

[0018] Get sub-region M i Transaction characteristics information, including:

[0019] Get the sub-region M i The business transaction data corresponding to the N industries in , where N is a positive integer;

[0020] According to industry N j Business transaction data to determine industry N j Industry output value; Industry N j Belongs to N industries, j is a positive integer less than or equal to N;

[0021] The industrial output values ​​corresponding to N industries are summed up to obtain the sub-region M i Regional output value;

[0022] Get Industry N j The ratio of the industrial output value to the regional output value is used to determine the ratios corresponding to the N industries as the sub-region M. i Industry distribution information.

[0023] Among them, transaction characteristic information includes user consumption capacity;

[0024] Get sub-region M i Transaction characteristics information, including:

[0025] Determine sub-area M i Whether there is housing transaction information of the user in the database;

[0026] If the sub-region M i If there is user housing transaction information in the sub-area M i The user housing transaction information in the sub-area M is determined i The consumption capacity of users;

[0027] If the sub-region M i If there is no user housing transaction information in the M sub-areas, then obtain the information related to sub-area M from M sub-areas. i Adjacent adjacent sub-regions, obtain the user consumption capacity of the adjacent sub-regions, and the weighting coefficients corresponding to the adjacent sub-regions, and use the weighting coefficients to weight the user consumption capacity of the adjacent sub-regions to obtain the sub-region M i consumer spending power.

[0028] Among them, for the sub-region M i The population characteristics information, transaction characteristics information, and asset attribute information are used to identify the sub-region M i The matching degree includes:

[0029] Call the target site identification model to identify the sub-region M i The population characteristic information and transaction characteristic information are converted into vectors to obtain the sub-region M i The population feature vector and transaction feature vector are used to convert the asset attribute information into a vector to obtain the asset attribute vector;

[0030] For sub-region M i The population feature vector and transaction feature vector are concatenated to obtain the sub-region M i The regional feature vector of

[0031] Get sub-region M i The vector distance between the regional feature vector and the asset attribute vector;

[0032] Determine the sub-region M based on the vector distance i degree of matching.

[0033] Wherein, according to the matching degrees corresponding to the M sub-areas respectively, the target site selection area of ​​the target user is determined from the M sub-areas, including:

[0034] According to the matching degrees corresponding to the M sub-regions, the candidate region is divided into contour lines to obtain a plurality of first candidate site selection regions; the matching degrees of any two sub-regions in all sub-regions covered by the boundary of the first candidate site selection region are the same;

[0035] Obtaining the regional center points respectively corresponding to the plurality of first candidate site selection areas, and adjusting the plurality of first candidate site selection areas based on the regional center points respectively corresponding to the plurality of first candidate site selection areas to obtain a plurality of adjusted first candidate site selection areas, wherein there is no overlapping portion between any two adjusted first candidate site selection areas within the plurality of adjusted first candidate site selection areas;

[0036] Obtaining first region scores respectively corresponding to the plurality of adjusted first candidate site selection regions, where the first region score is the sum of the matching degrees of all sub-regions covered by the adjusted first candidate site selection region;

[0037] According to the first area scores respectively corresponding to the multiple adjusted first candidate site selection areas, the target site selection area of ​​the target user is determined from the M sub-areas.

[0038] Wherein, according to the first area scores respectively corresponding to the multiple adjusted first candidate site selection areas, determining the target site selection area of ​​the target user from the M sub-areas includes:

[0039] According to the first area scores respectively corresponding to the multiple adjusted first candidate site selection areas, the candidate areas are divided into contour lines to obtain multiple second candidate site selection areas, and the first area scores of any two adjusted first candidate site selection areas in all the adjusted first candidate site selection areas covered by the boundaries of the second candidate site selection areas are the same;

[0040] The second area scores corresponding to the multiple second candidate site selection areas are obtained, and the second candidate site selection area with the highest second area score among the multiple second candidate site selection areas is determined as the target site selection area. The second area score is the sum of the matching degrees of all sub-areas covered by the second candidate area.

[0041] An embodiment of the present application provides a site selection device, including:

[0042] The first acquisition module is used to acquire the address attribute information and asset attribute information of the desired site of the target user;

[0043] A region division module is used to determine a candidate region according to address attribute information, and divide the candidate region into M sub-regions according to a preset region division rule, where M is a positive integer;

[0044] The second acquisition module is used to acquire the sub-area M i The population characteristics information of the sub-region M i Transaction feature information of sub-area M i Belongs to M sub-areas, i is a positive integer less than or equal to M;

[0045] Identification module, used for sub-region M iThe population characteristics information, transaction characteristics information and asset attribute information are identified to obtain the sub-region M i The matching degree of sub-region M i The matching degree of the sub-region M is used to reflect i The matching degree with the target users’ expected location;

[0046] The determination module is used to determine the target site selection area of ​​the target user from the M sub-areas according to the matching degrees corresponding to the M sub-areas respectively.

[0047] Among them, transaction characteristic information includes regional travel costs;

[0048] The second acquisition module includes:

[0049] The first determining unit is used to obtain the sub-area M i The road type corresponding to the road is determined according to the road type. i The passage damping parameter of

[0050] The second determining unit is used to determine the sub-area M according to the traffic damping parameter i The travel time cost;

[0051] The third determining unit is used to obtain the sub-area M i The traffic mode within the area is determined according to the traffic mode. i toll costs;

[0052] The summing unit is used to sum the sub-area M i The travel time cost and toll cost are summed to obtain the sub-area M i regional travel costs.

[0053] Among them, transaction characteristic information includes industry distribution information;

[0054] The second acquisition module includes:

[0055] The first acquisition unit is used to acquire the i The business transaction data corresponding to the N industries in , where N is a positive integer;

[0056] The fourth determining unit is used to determine the j Business transaction data to determine industry N j Industry output value; Industry N j Belongs to N industries, j is a positive integer less than or equal to N;

[0057] The summing processing unit is used to sum the industrial output values ​​corresponding to the N industries to obtain the sub-region M i Regional output value;

[0058] The second acquisition unit is used to acquire industry N j The ratio of the industrial output value to the regional output value is used to determine the ratios corresponding to the N industries as the sub-region M. i Industry distribution information.

[0059] Among them, transaction characteristic information includes user consumption capacity;

[0060] The second acquisition module includes:

[0061] A judging unit, used to judge the sub-area M i Whether there is housing transaction information of the user in the database;

[0062] The fifth determining unit is used for determining the sub-region M i If there is user housing transaction information in the sub-area M i The user housing transaction information in the sub-area M is determined i The consumption capacity of users;

[0063] The weighted processing unit is used for sub-region M i If there is no user housing transaction information in the M sub-areas, then obtain the information related to sub-area M from M sub-areas. i Adjacent adjacent sub-regions, obtain the user consumption capacity of the adjacent sub-regions, and the weighting coefficients corresponding to the adjacent sub-regions, and use the weighting coefficients to weight the user consumption capacity of the adjacent sub-regions to obtain the sub-region M i consumer spending power.

[0064] The identification module includes:

[0065] Vector conversion unit, used to call the target site selection recognition model, for the sub-region M i The population characteristic information and transaction characteristic information are converted into vectors to obtain the sub-region M i The population feature vector and transaction feature vector are used to convert the asset attribute information into a vector to obtain the asset attribute vector;

[0066] Splicing unit, used to connect sub-region M i The population feature vector and transaction feature vector are concatenated to obtain the sub-region M i The regional feature vector of

[0067] The third acquisition unit is used to acquire the sub-region M i The vector distance between the regional feature vector and the asset attribute vector;

[0068] The sixth determining unit is used to determine the sub-region M according to the vector distance. i degree of matching.

[0069] The determination module includes:

[0070] The contour division unit is used to divide the candidate area into contour lines according to the matching degrees corresponding to the M sub-areas, so as to obtain a plurality of first candidate site selection areas; the matching degrees of any two sub-areas in all the sub-areas covered by the boundary of the first candidate site selection area are the same;

[0071] An adjustment unit is used to obtain regional center points corresponding to the plurality of first candidate site selection areas, and adjust the plurality of first candidate site selection areas based on the regional center points corresponding to the plurality of first candidate site selection areas to obtain a plurality of adjusted first candidate site selection areas, wherein there is no overlapping portion between any two of the plurality of adjusted first candidate site selection areas;

[0072] A fourth acquisition unit is used to acquire first region scores respectively corresponding to the plurality of adjusted first candidate site selection regions, where the first region score is the sum of the matching degrees of all sub-regions covered by the adjusted first candidate site selection region;

[0073] The seventh determination unit is used to determine the target site selection area of ​​the target user from the M sub-areas according to the first area scores respectively corresponding to the multiple adjusted first candidate site selection areas.

[0074] An embodiment of the present application provides a computer device, including: a processor and a memory;

[0075] The processor is connected to the memory, wherein the memory is used to store a computer program. When the computer program is executed by the processor, the computer device executes the method provided in the embodiment of the present application.

[0076] On the one hand, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. The computer program is suitable for being loaded and executed by a processor so that a computer device having the processor executes the method provided by the embodiment of the present application.

[0077] In one aspect, the present application provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the method provided in the present application.

[0078] In the embodiment of the present application, by obtaining the address attribute information and asset attribute information of the target user's desired location, determining the candidate area according to the address attribute information, and dividing the candidate area into smaller granularity areas according to the preset division rules, M sub-areas are obtained, which is conducive to mining more accurate detailed feature information of each sub-area and improving the accuracy of obtaining the target location area of ​​the target user. Further, the sub-area M can be obtained. i The population characteristics information and transaction characteristics information of the sub-region M i Belonging to the M sub-areas, for sub-area M i The population characteristics information, transaction characteristics information and asset attribute information are identified to obtain the sub-region M i The matching degree of this sub-region M i The matching degree of the sub-region M is used to reflect i The matching degree between the target user’s desired location. Then, through the sub-region M i The multi-dimensional information (such as demographic information, transaction information, and asset attribute information) of the sub-region M is determined i The matching degree of the target site selection area is determined based on the matching degree, which can improve the accuracy of the matching degree of each sub-area, thereby improving the accuracy of the site selection of the target site selection area of ​​the target user from the M sub-areas. At the same time, the process of obtaining the target site selection area does not require manual participation. According to the target user's desired site selection, the population characteristic information of each sub-area, and the transaction characteristic information, the target site selection area of ​​the target user can be quickly and accurately determined, thereby improving the efficiency of site selection. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0080] Figure 1 It is a schematic diagram of the architecture of a site selection system provided in an embodiment of the present application;

[0081] Figure 2 It is a flowchart of a site selection method provided in an embodiment of the present application;

[0082] Figure 3 is a schematic diagram of obtaining the toll cost of a sub-area provided in an embodiment of the present application;

[0083] Figure 4 It is a flowchart of another site selection method provided in an embodiment of the present application;

[0084] Figure 5 This is a schematic diagram of determining a target site selection area for a target user provided by an embodiment of the present application;

[0085] Figure 6 is a structural schematic diagram of a site selection device provided in an embodiment of the present application;

[0086] Figure 7 It is a structural diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0087] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0088] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0089] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0090] See Figure 1 , Figure 1 Schematic diagram of a site selection system provided in an embodiment of the present application. Figure 1 As shown, the site selection system may include a server 10 and a user terminal cluster. The user terminal cluster may include one or more user terminals, and the number of user terminals is not limited here. Figure 1 As shown, it may specifically include user terminal 100a, user terminal 100b, user terminal 100c, ..., user terminal 100n. Figure 1 As shown, the user terminal 100a, the user terminal 100b, the user terminal 100c, ..., the user terminal 100n can respectively establish a network connection with the server 10, so that each user terminal can exchange data with the server 10 through the network connection.

[0091] Each user terminal in the user terminal cluster may include: smart phones, tablet computers, laptop computers, desktop computers, wearable devices, smart homes, head-mounted devices, vehicle-mounted terminals and other smart terminals with site selection functions. Figure 1 Each user terminal in the user terminal cluster shown in FIG. 1 may be installed with a target application (i.e., an application client). When the application client runs in each user terminal, it may be respectively connected to the above-mentioned Figure 1 The servers 10 shown here interact with each other.

[0092] Among them, Figure 1 As shown, the server 10 can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, as well as big data and artificial intelligence platforms.

[0093] For ease of understanding, the embodiments of the present application can be Figure 1 A user terminal is selected from the multiple user terminals shown as the target user terminal, and the target user terminal may include: a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart TV, and other smart terminals with a site selection function. For example, for ease of understanding, the embodiment of the present application may Figure 1 The user terminal 100a shown is used as a target user terminal. The user terminal 100a can obtain the address attribute information and asset attribute information of the target user's expected site selection. The site selection expectation refers to the site selection requirement of the target user, such as where the target user wants to select a site, and the scale, budget, and commercial use of the site selection area. The user terminal 100a determines the candidate area based on the address attribute information of the target user's expected site selection, and divides the candidate area into M sub-areas according to a preset division rule. The preset division rule can refer to equal area division or unequal area division, etc. M is a positive integer, such as M can be 1, 2, 3... The user terminal 100a can obtain the population characteristic information and transaction characteristic information of each sub-area in the M sub-areas, and send the population characteristic information and transaction characteristic information of each sub-area, as well as the asset attribute information of the target user's expected site selection to the server 10. After receiving the population characteristic information and transaction characteristic information of each sub-area, as well as the asset attribute information sent by the user terminal 100a, the server 10 can perform a search on the sub-area M. i The population characteristics information, transaction characteristics information and asset attribute information are identified to obtain the sub-region M i The sub-region M i The matching degree of the sub-region M is used to reflecti The matching degree between the target user's expected location, sub-area M i Belong to M sub-areas, i is a positive integer less than or equal to M. The server 10 can determine the target site selection area of ​​the target user from the M sub-areas according to the matching degrees corresponding to the M sub-areas respectively. The server 10 can send the target site selection area to the user terminal 100a, and the user terminal 100a can output the target site selection area. In this way, the target site selection area can be determined quickly and accurately for the target user, and the efficiency of site selection can be improved.

[0094] See also Figure 2 , Figure 2 is a flow chart of a site selection method provided in an embodiment of the present application. The site selection method can be executed by a computer device, which can be a server (such as the above-mentioned Figure 1 Server 10 in the example above) or a user terminal (such as the one described above) Figure 1 Any user terminal in a user terminal cluster), or a system consisting of a server and a user terminal, which is not limited in this application. Figure 2 As shown, the site selection method may include steps S101-S105.

[0095] S101, obtaining address attribute information and asset attribute information of a desired location of a target user.

[0096] Specifically, the computer device can determine the target site selection area of ​​the target user by analyzing the target user's desired site selection. In this way, the target site selection area can be determined quickly and accurately for the target user, thereby improving site selection efficiency and reducing labor costs. Specifically, the computer device can obtain the address attribute information and asset attribute information of the target user's desired site selection. The address attribute information may include the site selection location information of the target user's desired site selection, such as the target user wants to select a target site selection area in Nanshan District, Shenzhen. The asset attribute information may include the size of the target site selection area, the rental or purchase price, and the purpose of the area. For example, if the target user wants to select a 100m 2 In this area, the monthly rent is around 5,000-50,000 yuan, which can be used to open a clothing store.

[0097] S102, determining a candidate area according to the address attribute information, and dividing the candidate area according to a preset area division rule to obtain M sub-areas.

[0098] Specifically, the computer device can determine the candidate area according to the address attribute information, such as according to the site selection location information contained in the target user's desired site selection, the area indicated by the site selection location information is determined as the candidate area. If the target user wants to open a clothing store in Nanshan, Shenzhen, then Nanshan, Shenzhen can be determined as a candidate area. After the computer device determines the candidate area, it can divide the candidate area into regions according to the preset regional division rules to obtain M sub-regions. Among them, the preset regional division rules can refer to the regional division rules pre-set by the management personnel, such as equal area division rules, unequal area division rules and random division rules, etc., which can be set according to the specific situation. The area size of each sub-region can be set according to the specific situation, and the embodiment of the present application is not limited here. The computer device can divide the candidate area into equal areas to obtain M sub-regions with the same area. Of course, the computer device can also randomly divide the candidate area to obtain M sub-regions with different areas. M is a positive integer, such as M can take the value of 1,2,3... For example, after the computer equipment determines that Shenzhen Nanshan is a candidate area, it can divide the Shenzhen Nanshan area into equal areas and divide Shenzhen Nanshan into M basic grids of 100m*100m.

[0099] S103, obtaining sub-region M i The population characteristics information of the sub-region M i Transaction feature information.

[0100] Specifically, the computer device may obtain the sub-region M i Population characteristics information and obtain sub-region M i The transaction feature information of this sub-area M i Belongs to M sub-areas, i is a positive integer less than or equal to M, such as i can be 1, 2, 3... Sub-area M i The population characteristics information of the sub-region M may include i The number of permanent residents, floating population, population density, number of potential customers and population attribute information, etc. The population attribute information may include population gender information, population age information, population occupation information and population consumption preference information, etc. Sub-area M i The transaction feature information may include regional travel costs, industry distribution information (i.e. point of interest location quotient POI), user consumption capacity, regional type information, and regional evaluation weighting coefficient.

[0101] Optionally, the transaction feature information includes the regional travel cost, and the computer device obtains the sub-region M i The specific method of obtaining the transaction characteristic information of the sub-area M may include: obtaining i The target road type is determined according to the sub-area M iThe sub-area M is determined according to the traffic damping parameter. i The travel time cost of sub-area M is obtained i The traffic mode within the area is determined according to the traffic mode. i The toll cost for sub-area M i The travel time cost and toll cost are summed to obtain the sub-area M i regional travel costs.

[0102] Specifically, the computer device may obtain the sub-area M i The road type corresponding to the road in each sub-area can refer to the primary road type and the secondary road type, that is, the urban road network has various road types. The primary road refers to the road connecting the economic and political centers of various regions, leading to important industrial areas or transportation hubs. The secondary road refers to the road connecting specific administrative centers, transportation hubs, commercial areas, residential communities, industrial mining areas or tourist attractions, etc., located below the primary road. The target road type corresponding to each sub-area can refer to urban roads, highways, factory and mine roads, forest roads and rural roads. Among them, urban roads can include expressways, trunk roads, secondary trunk roads and branch roads. The speeds corresponding to different road types are different. For example, the speed of the expressway is 60-100km / h, and the speed of the branch road (i.e., the connecting line between the secondary trunk road and the neighborhood road (community road), which is mainly for service functions) is 20-40km / h. Therefore, the time spent on traveling in areas with different road types is different. The computer equipment can be based on the speed of the road belonging to the sub-area M. i The road type corresponding to the road determines the sub-area M i If it belongs to sub-area M i The road type indication sub-area M corresponding to the road i The faster the road speed in the sub-area M is, the faster the road speed in the sub-area M is. i The smaller the passage damping parameter is. For example, if it belongs to sub-area M i The road type corresponding to the road is an expressway (the vehicle speed on the expressway is 60-100 km / h), then the sub-area M can be determined i The smaller the passage damping parameter is. i The target road type indication sub-area M i The slower the road speed in the sub-area M is, the i The larger the passage damping parameter is. For example, if it belongs to sub-area M i The road type corresponding to the road is a branch road (the vehicle speed on the branch road is 20-40km / h), then the sub-area M can be determined i The larger the passage damping parameter.

[0103] Specifically, the computer device can determine the sub-area M according to the traffic damping parameter. i The travel time cost of the sub-area Mi is calculated based on the travel damping parameter. If the travel damping parameter is larger, the travel time cost is larger. If the travel damping parameter is smaller, the travel time cost is smaller. The formula for determining the travel time cost of the sub-area Mi according to the travel damping parameter can be shown as the following formula (1):

[0104]

[0105] Where, D in formula (1) ij represents the spatial distance from the starting sub-area to the target sub-area (i.e., from the starting point to the destination), R i represents the passage damping parameter to reach the target sub-area i, It represents the accumulation of distance and traffic damping parameters of all sub-areas traversed between target sub-area i and starting sub-area, and f represents the positive correlation between the minimum cumulative resistance and the process of overcoming resistance.

[0106] Specifically, the computer device can also obtain the sub-area M iThe mode of passage within the area can be a taxi mode, a walking mode, a bus mode, a subway mode, and a driving mode. Different modes of passage require different toll costs and passage efforts. Therefore, the computer device can determine the toll cost of the corresponding sub-area according to the mode of passage in each sub-area. Among them, the computer device obtains all bus stops, subway stations, and parking lots in the candidate area, takes all the bus stops, subway stations, and parking lots as the midpoint, and takes buffer surfaces with different radius ranges. For example, a buffer surface with a radius of 100m can be taken with a certain bus stop as the midpoint, a buffer surface with a radius of 200m, or a buffer surface with a radius of 500m. The computer device can set different toll costs required for different buffer surfaces. The larger the radius of the buffer surface, the larger the corresponding toll cost. For example, if the bus station is taken as the midpoint, the toll cost of the buffer surface with a radius of 100m can be 1 yuan, the toll cost of the buffer surface with a radius of 200m can be 1.5 yuan, and the toll cost of the buffer surface with a radius of 500m can be 2 yuan. If the subway station is taken as the midpoint, the toll cost of the buffer surface with a radius of 100m is 2 yuan, and the toll cost of the buffer surface with a radius of 500m is 2 yuan. It can be seen that the toll costs of the buffer surfaces with the same radius with different transportation stations as the center can be the same or different. Computer equipment can collect the corresponding relationship between the toll cost and the travel distance of a large number of passing customers, and determine the toll cost of each buffer surface corresponding to each transportation station (i.e., bus station, subway station and parking lot). The computer equipment takes all bus stops, subway stations and parking lots as the midpoint, takes buffer surfaces with different radius ranges, and determines the toll cost of each buffer surface. Then, the toll cost of each sub-area can be obtained. For example, when sub-area A is in a buffer surface with a radius of 100m centered on the bus stop, it can be determined that the toll cost of sub-area A is 1 yuan.

[0107] Among them, the computer device can also determine that the basic toll cost of each sub-area is the same, and different weighting coefficients can be set according to different buffer surfaces. The larger the radius of the buffer surface, the larger the weighting number, and the smaller the radius of the buffer surface, the smaller the weighting coefficient. For example, the weighting coefficient of a buffer surface with a radius of 100m can be 1 / 80, the weighting coefficient of a buffer surface with a radius of 200m can be 1 / 70 yuan, and the weighting coefficient of a buffer surface with a radius of 500m can be 1 / 60 yuan, etc. In this way, the sum of the weighting coefficients in each sub-area can be obtained, and the product between the weighting coefficient and the basic toll cost can be obtained, and the product is used as the toll cost of the corresponding sub-area. The computer device obtains the sub-area M i After the travel time cost and toll cost are calculated, the sub-area Mi The travel time cost and toll cost are summed to obtain the sub-area M i regional travel costs.

[0108] like Figure 3 As shown, Figure 3 is a schematic diagram of obtaining the toll cost of a sub-area provided in an embodiment of the present application, such as Figure 3 As shown, the computer device can take the bus stop as the midpoint, take buffer surfaces with different radius ranges, and determine the weight coefficient corresponding to each buffer surface. Figure 3 As shown, buffer surface 30a refers to a buffer surface divided by bus stop B as the center and 100m as the radius, buffer surface 30b refers to a buffer surface divided by bus stop B as the center and 200m as the radius, and buffer surface 30c refers to a buffer surface divided by bus stop B as the center and 500m as the radius. The weighting coefficients corresponding to buffer surfaces of different radii are different, and can be determined based on the collected customer traffic data or by other methods, which is not limited in the present application embodiment.

[0109] Optionally, the transaction feature information includes industry distribution information, and the computer device obtains sub-area M i The specific method of obtaining the transaction feature information of the sub-area M may include: obtaining i The business transaction data corresponding to the N industries in j Business transaction data to determine industry N j Industry output value; Industry N j Belonging to N industries, j is a positive integer less than or equal to N, and the industrial output values ​​corresponding to the N industries are summed up to obtain the sub-area M i Get the regional output value of industry N j The ratio of the industrial output value to the regional output value is used to determine the ratios corresponding to the N industries as the sub-region M. i Industry distribution information.

[0110] Specifically, the computer device may obtain the sub-area M i The business transaction data corresponding to the N industries in the table, the N industries may refer to office, education, entertainment, accommodation and others, N is a positive integer, for example, N can be 1, 2, 3... j Business transaction data to determine industry N j The industrial output value of each of the N industries is summed up to get the industrial output value of the sub-region M i Get the regional output value of industry N j The ratio of the industrial output value to the regional output value is used to determine the ratios corresponding to the N industries as the sub-region M. iThe industry distribution information can refer to the location quotient of the point of interest, that is, the POI location quotient. The English name of POI refers to Point of Interest, that is, the industry that the target user is interested in. The location quotient refers to the ratio of the output value of a specific department in a region to the total industrial output value of the region and the proportion of the output value of the department in the total industrial output value of the country. If the location quotient is greater than 1, it can be considered that the industry is a specialized industry in the region. The larger the location quotient, the higher the level of specialization, and the smaller the location quotient, the lower the level of specialization. If the location quotient is close to 0, it is considered that the level of specialization of the industry is lower. We can obtain the POI location quotients corresponding to each industry, such as the POI location quotients corresponding to office, education, entertainment, accommodation, etc. By calculating the POI location quotient of each sub-region, we can quantify the information complexity and land use complexity of the space, mainly distinguish the roles of prosperous areas and urban villages, characterize the prosperity of the regional economy, and describe the highly concentrated characteristic locations of spatial sites. For example, Huaqiangbei in Shenzhen and Zhongguancun in Beijing are concentrated areas of electronic product wholesale and retail industries, and the POI location quotient of their electronic industries is close to 1. According to the POI location quotient, we can better provide a reference for site selection.

[0111] The formula for obtaining the industry distribution information of each sub-region by the computer device can be shown as the following formula (2):

[0112]

[0113] In formula (2), α represents the αth industry, β represents the βth region, and LQ αβ It refers to the location quotient of the αth industry interest point in the βth region, L αβ refers to the output value of the αth industry in the βth region, It refers to the total output value of all regions (i.e. m regions), It refers to the total output value of all industries (i.e., n industries) in the βth region. It refers to the total output value of all industries (i.e. n industries) in all regions (i.e. m regions), that is, m*n output value.

[0114] Optionally, the transaction feature information includes the user's spending capacity, the computer device acquires the sub-area M i The specific method of obtaining the transaction characteristic information may include: determining the sub-area M i Whether there is user housing transaction information in the sub-area M i If there is user housing transaction information in the sub-area M i The user housing transaction information in the sub-area M is determined i The consumption capacity of users in sub-area M iIf there is no user housing transaction information in the M sub-areas, then obtain the information related to sub-area M from M sub-areas. i Adjacent adjacent sub-regions, obtain the user consumption capacity of the adjacent sub-regions, and the weighting coefficients corresponding to the adjacent sub-regions, and use the weighting coefficients to weight the user consumption capacity of the adjacent sub-regions to obtain the sub-region M i consumer spending power.

[0115] Specifically, the computer device can determine the sub-area M i Whether there is user housing transaction information in the sub-area M, the user housing transaction information may include transaction data such as second-hand housing price transaction data, rental price transaction data, and new housing price transaction data. i If there is user housing transaction information in the data, the second-hand housing price, rental price, and new housing price can be determined from the user housing transaction information, and the user consumption capacity of the target user can be determined based on the rental price. For example, if the second-hand housing price, rental price, and new housing price are higher, it can be said that the price of the area is higher and the user consumption capacity of the target user is relatively high; if the second-hand housing price, rental price, and new housing price are lower, it can be said that the price of the area is lower and the user consumption capacity of the target user is relatively low. If the sub-area M i If there is no user housing transaction information in the M sub-areas, then obtain the information related to sub-area M from M sub-areas. i Adjacent adjacent sub-regions, obtain the user consumption capacity of the adjacent sub-regions, and the weighting coefficients corresponding to the adjacent sub-regions, and use the weighting coefficients to weight the user consumption capacity of the adjacent sub-regions to obtain the sub-region M i The consumption capacity of users in sub-area M i The number of adjacent adjacent sub-regions can be one or more. i When there are multiple adjacent sub-regions, the user consumption capacities corresponding to the multiple adjacent sub-regions can be obtained. The computer device can use the weighting coefficients corresponding to the multiple adjacent sub-regions to perform weighted processing on the user consumption capacities corresponding to the multiple adjacent sub-regions to obtain multiple weighted user consumption capacities. The computer device can average the multiple weighted user consumption capacities and determine the average of the multiple weighted user consumption capacities as the sub-region M. i The weighting coefficients corresponding to the multiple adjacent sub-areas can be calculated based on the user consumption capacity of the sub-area M. i The distance is determined by the distance sub-region M i The farther the adjacent sub-region is, the smaller its weight coefficient is. iThe closer the adjacent sub-region is, the greater its weight coefficient is. The computer device can obtain the user consumption capacity of each sub-region through Kriging interpolation. Since it is difficult to obtain the user housing transaction data of all sub-regions, the Kriging interpolation algorithm can be used to determine the sub-region without user housing transaction data based on the sub-region with known user consumption capacity.

[0116] Specifically, the computer device obtains the user consumption capacity of each sub-region by the Kriging interpolation method as shown in the following formula (3):

[0117]

[0118] Where z(s0) in formula (3) refers to the sub-region M i The consumption capacity of users in sub-area M i , γ i refers to the adjacent sub-region s i The weight coefficient, z(s i ) refers to the sub-area M i The adjacent sub-region s i consumer spending power.

[0119] Optionally, sub-area M i The transaction feature information may also include area type information. The computer device may i The area type information determines the sub-area M i The effectiveness of the sub-region M i If it is an invalid area, the sub-area M can be i Delete, that is, do not use it as a candidate area for the subsequent target site selection area. The area type information may include valid area types and invalid area types. Valid area types may be business districts, streets, and office areas, etc., and invalid area types may be rivers, tourist attractions, green plants, and parks, etc. For example, when the sub-area M i When the area type is park, the sub-area M i If it is determined to be an invalid area, the sub-area M can be i It is deleted from the M sub-areas, that is, it is not used as a candidate area for subsequent determination of the target site selection area.

[0120] S104, for sub-region M i The population characteristics information, transaction characteristics information and asset attribute information are identified to obtain the sub-region M i degree of matching.

[0121] Specifically, the computer device may perform i The population characteristics information, transaction characteristics information and asset attribute information are identified to obtain the sub-region Mi The matching degree of this sub-region M i The matching degree of the sub-region M is used to reflect i The degree of match between the target user's desired location.

[0122] Optionally, the computer device may call a target site selection recognition model, which may identify the sub-region M i The population characteristics information, transaction characteristics information, and asset attribute information are used to identify the sub-region M i The computer device can use the embedding layer in the target location model to select the sub-region M i The population characteristic information and transaction characteristic information are converted into vectors to obtain the sub-region M i The population feature vector and transaction feature vector of the asset attribute information are converted into vectors to obtain the asset attribute vector. The computer device can call the connection layer in the target site selection recognition model to identify the sub-area M i The population feature vector and transaction feature vector are concatenated to obtain the sub-region M i The computer device can call the hidden layer in the target site selection recognition model to obtain the sub-region M i The vector distance between the regional feature vector and the asset attribute vector is calculated, and the classification layer in the target site selection recognition model is used to identify the sub-region M. i The vector distance between the regional feature vector and the asset attribute vector is used to classify the sub-region M i For example, if the vector distance is larger, it can be determined that the matching degree is smaller; if the vector distance is smaller, it can be determined that the matching degree is larger.

[0123] Optionally, the computer device can obtain the regional evaluation weighted coefficient corresponding to each sub-region, determine the matching degree output by the above-mentioned target site selection identification model as the candidate matching degree, and perform weighted processing on the candidate matching degree of each sub-region through the regional evaluation weighted coefficient to obtain the matching degree of each sub-region. In this way, the advantages and disadvantages of each sub-region can be determined more accurately, so as to more accurately select a more accurate target site selection area for the user. Among them, the regional evaluation weighted coefficient corresponding to each sub-region can be evaluated by experienced experts. If the experienced experts find that the economic development of a sub-region is better and the address location is better based on experience, the regional evaluation weighted coefficient corresponding to the sub-region can be set higher. If the experienced experts find that the economic development of a sub-region is poor and the address location is inconvenient based on experience, the regional evaluation weighted coefficient corresponding to the sub-region can be set lower.

[0124] S105 , determining a target location selection area of ​​the target user from the M sub-areas according to the matching degrees corresponding to the M sub-areas respectively.

[0125] Specifically, the computer device determines the target site selection area of ​​the target user from the M sub-areas according to the matching degrees corresponding to the M sub-areas. The computer device may divide the candidate areas into contour lines according to the matching degrees corresponding to the M sub-areas, and obtain at least one first candidate site selection area, and the matching degrees of any two sub-areas in all sub-areas covered by the boundary of the first candidate site selection area are the same. The computer device may obtain the site selection score of each first candidate site selection area, and the site selection score of each first candidate site selection area may refer to the sum of the matching degrees of all sub-areas covered by the first candidate site selection area. The computer device may obtain the first candidate site selection area with the highest site selection score among multiple first candidate site selection areas, and determine all sub-areas covered by the first candidate site selection area with the highest site selection score as the target site selection area of ​​the target user.

[0126] In the embodiment of the present application, by obtaining the address attribute information and asset attribute information of the target user's desired location, determining the candidate area according to the address attribute information, and dividing the candidate area into smaller granularity areas according to the preset division rules, M sub-areas are obtained, which is conducive to mining more accurate detailed feature information of each sub-area, and is conducive to improving the accuracy of obtaining the target location area of ​​the target user. Further, the sub-area M can be obtained. i The population characteristics information and transaction characteristics information of the sub-region M i Belonging to the M sub-areas, for sub-area M i The population characteristics information, transaction characteristics information and asset attribute information are identified to obtain the sub-region M i The matching degree of this sub-region M i The matching degree of the sub-region M is used to reflect i The matching degree between the target user’s desired location. Then, through the sub-region M i The multi-dimensional information (such as demographic information, transaction information, and asset attribute information) of the sub-region M is determined i The matching degree of each sub-region can be improved, and the accuracy of the matching degree of each sub-region can be improved, so as to improve the accuracy of the location selection of the target user's target location region from the M sub-regions. In addition, this solution uses the target location identification model to identify the sub-region M. i The population characteristics information, transaction characteristics information and asset attribute information are identified to obtain the sub-region M i The matching degree can improve the accuracy of matching degree identification. At the same time, the process of obtaining the target site selection area does not require manual participation. According to the target user's expected site selection, the population characteristics information of each sub-area, and the transaction characteristics information, the target site selection area of ​​the target user can be determined quickly and accurately, thereby improving the efficiency of site selection.

[0127] See also Figure 4 , Figure 4 is a flow chart of a site selection method provided in an embodiment of the present application. The site selection method can be executed by a computer device, which can be a server (such as the above-mentioned Figure 1 Server 10 in the example above) or a user terminal (such as the one described above) Figure 1 Any user terminal in a user terminal cluster), or a system consisting of a server and a user terminal, which is not limited in this application. Figure 4 As shown, the site selection method may include steps S201-S208.

[0128] S201, obtaining address attribute information and asset attribute information of a desired location of a target user.

[0129] S202, determining a candidate area according to the address attribute information, and dividing the candidate area according to a preset area division rule to obtain M sub-areas.

[0130] S203, obtaining sub-region M i The population characteristics information of the sub-region M i Transaction feature information.

[0131] S204, for sub-region M i The population characteristics information, transaction characteristics information and asset attribute information are identified to obtain the sub-region M i degree of matching.

[0132] Specifically, the specific contents of steps S201-S204 in the embodiment of the present application can be referred to above Figure 2 The contents of steps S101-S104 in this embodiment of the present application will not be repeated here.

[0133] S205 , dividing the candidate area into contour lines according to the matching degrees corresponding to the M sub-areas, to obtain a plurality of first candidate site selection areas.

[0134] Specifically, the computer device can divide the candidate area into contour lines according to the matching degrees corresponding to the M sub-areas, and obtain multiple first candidate site selection areas, and the matching degrees of any two sub-areas in all sub-areas covered by the boundary of the first candidate site selection area are the same. Since the matching degree of the sub-areas covered from the prosperous area to the remote area gradually decreases, the contour line division method can be used to circle the sub-areas with matching degrees greater than the target matching degree to obtain multiple first candidate site selection areas. In this way, it is easier to determine the target site selection area of ​​the target user from the M sub-areas later.

[0135] S206, obtaining the regional center points respectively corresponding to the multiple first candidate site selection areas, and adjusting the multiple first candidate site selection areas based on the regional center points respectively corresponding to the multiple first candidate site selection areas to obtain multiple adjusted first candidate site selection areas.

[0136] Specifically, since the candidate area is divided according to the matching degrees corresponding to the M sub-areas, when multiple first candidate site selection areas are obtained, there may be overlaps or gaps between the first candidate site selection areas, which is not conducive to the selection of the target site selection area. Therefore, the computer device can obtain the regional center points corresponding to the multiple first candidate site selection areas, and adjust the multiple first candidate site selection areas based on the regional center points corresponding to the multiple first candidate site selection areas to obtain multiple adjusted first candidate site selection areas, and there is no overlapping part between any two adjusted first candidate site selection areas in the multiple adjusted first candidate site selection areas. Among them, the computer device can adjust the multiple first candidate site selection areas based on the regional center points corresponding to the multiple first candidate site selection areas to obtain multiple Thiessen polygons (i.e., Voronoi diagrams, which are composed of a set of continuous polygons composed of perpendicular bisectors connecting two adjacent points). Adjusting multiple first candidate site selection areas to obtain multiple Thiessen polygons can achieve the division of candidate areas into non-overlapping and non-gap Thiessen polygons (i.e., multiple adjusted first candidate site selection areas), so as to accurately determine the target site selection area of ​​the target user from the M sub-areas, thereby improving the accuracy of site selection. Among them, the method of adjusting multiple first candidate site selection areas to obtain multiple Thiessen polygons may include: a divide-and-conquer method (a Thiessen polygon division method), a scan line algorithm (a Thiessen polygon division method), and a triangulation algorithm (a Thiessen polygon division method).

[0137] S207, obtaining first area scores respectively corresponding to the plurality of adjusted first candidate site selection areas.

[0138] Specifically, the computer device may obtain the first area scores corresponding to the multiple adjusted first candidate site selection areas, and the first area score is the sum of the matching degrees of all sub-areas covered by the adjusted first candidate site selection area. The computer device may obtain the sub-areas covered by each adjusted first candidate site selection area, obtain the matching degree of the covered sub-areas, sum the matching degrees of all sub-areas covered by each adjusted first candidate site selection area, and obtain the first area score of each adjusted first candidate site selection area.

[0139] S208: Determine a target site selection area for the target user from the M sub-areas according to the first area scores respectively corresponding to the multiple adjusted first candidate site selection areas.

[0140] Specifically, the computer device may determine the target site selection area of ​​the target user from the M sub-areas according to the first area scores respectively corresponding to the multiple adjusted first candidate site selection areas.

[0141] Optionally, the specific method for the computer device to determine the target site selection area of ​​the target user from the M sub-areas according to the first area scores respectively corresponding to the multiple adjusted first candidate site selection areas may include: dividing the candidate area into contour lines according to the first area scores respectively corresponding to the multiple adjusted first candidate site selection areas to obtain multiple second candidate site selection areas, and the first area scores of any two adjusted first candidate site selection areas in all the adjusted first candidate site selection areas covered by the boundaries of the second candidate site selection areas are the same. Obtain the second area scores respectively corresponding to the multiple second candidate site selection areas, and determine the second candidate site selection area with the highest second area score among the multiple second candidate site selection areas as the target site selection area, and the second area score is the sum of the matching degrees of all sub-areas covered by the second candidate area.

[0142] Specifically, the computer device divides the candidate area into contour lines according to the first area scores corresponding to the multiple adjusted first candidate site selection areas, and obtains multiple second candidate site selection areas. Among them, due to the adjustment of the first candidate site selection area, the first candidate site selection areas do not have overlapping parts with each other, and the adjusted first candidate site selection area covers the entire candidate area without leaving any gaps. However, the matching degree of the sub-area covered by the first candidate site selection area is greater than or equal to the target matching. After adjusting the multiple first candidate site selection areas, the sub-area in each first candidate site selection area is changed. Therefore, according to the first area scores corresponding to the multiple adjusted first candidate site selection areas, the candidate area can be divided into contour lines to obtain multiple second candidate site selection areas. The computer device can obtain the second area scores corresponding to the multiple second candidate site selection areas, and determine the second candidate site selection area with the highest second area score among the multiple second candidate site selection areas as the target site selection area, and the second area score is the sum of the matching degrees of all sub-areas covered by the second candidate area.

[0143] Optionally, after the computer device obtains multiple second candidate site selection areas, it can adjust each second candidate site selection area to obtain an adjusted second candidate site selection area. The computer device can determine the area of ​​the adjusted first candidate site selection area occupied by the original boundary of the second candidate site selection area. If the area of ​​the adjusted first candidate site selection area occupied by the original boundary of the second candidate site selection area is greater than 1 / 2, the original boundary of the second candidate site selection area is used as the boundary of the adjusted second candidate site selection area; if the area of ​​the adjusted first candidate site selection area occupied by the original boundary of the second candidate site selection area is less than or equal to 1 / 2, the boundary of the adjusted first candidate site selection area is used as the boundary of the adjusted second candidate site selection area, thereby obtaining the adjusted second candidate site selection area. In this way, the adjusted second candidate site selection area can contain a relatively completed adjusted first candidate site selection area, which can facilitate the selection of the target site selection area.

[0144] like Figure 5 As shown, Figure 5 is a schematic diagram of determining a target site selection area for a target user provided by an embodiment of the present application, such as Figure 5 As shown, the computer device can divide the candidate area into M sub-areas, such as Figure 5 The computer device can obtain the matching degree corresponding to each sub-region, divide the candidate region into contour lines according to the matching degree of each sub-region, obtain multiple first candidate site selection regions, and obtain the regional center point of each first candidate site selection region, that is, Figure 5 According to the regional center point of each first candidate site selection area, multiple first candidate site selection areas are adjusted, that is, the candidate areas are divided to obtain multiple adjusted first candidate site selection areas, that is, Figure 5 After obtaining the plurality of adjusted first candidate site selection areas, the computer device can obtain the first area scores corresponding to the plurality of adjusted first candidate site selection areas, respectively, and the first area score refers to the sum of the matching degrees of all sub-areas covered by the adjusted first candidate site selection area. The computer device can divide the candidate area into contour lines according to the first area scores of the plurality of adjusted first candidate site selection areas, and obtain a plurality of second candidate site selection areas, such as Figure 5 The computer device can adjust each second candidate site selection area to obtain an adjusted second candidate site selection area 50e, such as Figure 5As shown, the computer device can determine the area of ​​the adjusted first candidate site selection area occupied by the original boundary of the second candidate site selection area. If the area of ​​the adjusted first candidate site selection area occupied by the original boundary of the second candidate site selection area is greater than 1 / 2, the original boundary of the second candidate site selection area is used as the boundary of the adjusted second candidate site selection area; if the area of ​​the adjusted first candidate site selection area occupied by the original boundary of the second candidate site selection area is less than or equal to 1 / 2, the boundary of the adjusted first candidate site selection area is used as the boundary of the adjusted second candidate site selection area. The computer device can obtain the second area score corresponding to each adjusted second candidate site selection area, and the second area score refers to the sum of the matching degrees of all sub-areas covered by the second selected site selection area, and determine the adjusted second candidate site selection area with the highest second area score among multiple adjusted second candidate site selection areas as the target site selection area of ​​the target user.

[0145] In the embodiment of the present application, by obtaining the address attribute information and asset attribute information of the target user's desired location, determining the candidate area according to the address attribute information, and dividing the candidate area into smaller granularity areas according to the preset division rules, M sub-areas are obtained, which is conducive to mining more accurate detailed feature information of each sub-area, and is conducive to improving the accuracy of obtaining the target location area of ​​the target user. Further, the sub-area M can be obtained. i The population characteristics information and transaction characteristics information of the sub-region M i Belonging to the M sub-areas, for sub-area M i The population characteristics information, transaction characteristics information and asset attribute information are identified to obtain the sub-region M i The matching degree of this sub-region M i The matching degree of the sub-region M is used to reflect i The matching degree between the target user’s desired location. Then, through the sub-region M i The multi-dimensional information (such as demographic information, transaction information, and asset attribute information) of the sub-region M is determined iThe matching degree of each sub-region can be determined, and then the target site selection area can be determined according to the matching degree, which can improve the accuracy of the matching degree of each sub-region, thereby improving the site selection accuracy of the target site selection area of ​​the target user determined from the M sub-regions. In addition, the embodiment of the present application can divide the candidate area into contour lines according to the matching degree of each sub-region, obtain multiple first candidate site selection areas, and adjust the multiple candidate site selection areas to obtain multiple adjusted first candidate site selection areas, so that there is no overlapping part between the multiple adjusted first candidate site selection areas, and no gap part is left for the entire area occupied by the candidate area, which can facilitate the candidate to determine the target site selection area and improve the site selection accuracy. At the same time, the process of obtaining the target site selection area does not require manual participation. According to the target user's expected site selection, the population characteristic information of each sub-region, and the transaction characteristic information, the target site selection area of ​​the target user can be quickly and accurately determined, thereby improving the efficiency of site selection.

[0146] See also Figure 6 , Figure 6 : is a schematic diagram of the structure of a site selection device provided in an embodiment of the present application. The site selection device may be a computer program (including program code) running in a computer device, for example, the site selection device is an application software; the site selection device may be used to execute the corresponding steps in the site selection method provided in an embodiment of the present application. Figure 6 As shown, the site selection device may include: a first acquisition model 11, a region division module 12, a second acquisition module 13, an identification module 14 and a determination module 15.

[0147] The first acquisition module 11 is used to acquire the address attribute information and asset attribute information of the desired site of the target user;

[0148] A region division module 12 is used to determine a candidate region according to the address attribute information, and divide the candidate region into M sub-regions according to a preset region division rule, where M is a positive integer;

[0149] The second acquisition module 13 is used to acquire the sub-area M i The population characteristics information of the sub-region M i Transaction feature information of sub-area M i Belongs to M sub-areas, i is a positive integer less than or equal to M;

[0150] The identification module 14 is used to identify the sub-area M i The population characteristics information, transaction characteristics information and asset attribute information are identified to obtain the sub-region M i The matching degree of sub-region M i The matching degree of the sub-region M is used to reflect i The matching degree with the target users’ expected location;

[0151] The determination module 15 is used to determine the target location area of ​​the target user from the M sub-areas according to the matching degrees corresponding to the M sub-areas respectively.

[0152] Among them, transaction characteristic information includes regional travel costs;

[0153] The second acquisition module 13 includes:

[0154] The first determining unit 1301 is used to obtain the sub-region M i The road type corresponding to the road is determined according to the road type. i The passage damping parameter of

[0155] The second determining unit 1302 is used to determine the sub-area M according to the traffic damping parameter i The travel time cost;

[0156] The third determining unit 1303 is used to obtain the sub-region M i The traffic mode within the area is determined according to the traffic mode. i toll costs;

[0157] The summing unit 1304 is used to sum the sub-region M i The travel time cost and toll cost are summed to obtain the sub-area M i regional travel costs.

[0158] Among them, transaction characteristic information includes industry distribution information;

[0159] The second acquisition module 13 includes:

[0160] The first acquisition unit 1305 is used to acquire the sub-region M i The business transaction data corresponding to the N industries in , where N is a positive integer;

[0161] The fourth determining unit 1306 is used to determine the j Business transaction data to determine industry N j Industry output value; Industry N j Belongs to N industries, j is a positive integer less than or equal to N;

[0162] The summing processing unit 1307 is used to sum the industrial output values ​​corresponding to the N industries to obtain the sub-region M i Regional output value;

[0163] The second acquisition unit 1308 is used to acquire industry N j The ratio of the industrial output value to the regional output value is used to determine the ratios corresponding to the N industries as the sub-region M.i Industry distribution information.

[0164] Among them, transaction characteristic information includes user consumption capacity;

[0165] The second acquisition module 13 includes:

[0166] The judging unit 1309 is used to judge the sub-area M i Whether there is housing transaction information of the user in the database;

[0167] The fifth determining unit 1310 is configured to: i If there is user housing transaction information in the sub-area M i The user housing transaction information in the sub-area M is determined i The consumption capacity of users;

[0168] The weighted processing unit 1311 is used for i If there is no user housing transaction information in the M sub-areas, then obtain the information related to sub-area M from M sub-areas. i Adjacent adjacent sub-regions, obtain the user consumption capacity of the adjacent sub-regions, and the weighting coefficients corresponding to the adjacent sub-regions, and use the weighting coefficients to weight the user consumption capacity of the adjacent sub-regions to obtain the sub-region M i consumer spending power.

[0169] Wherein, the identification module 14 includes:

[0170] The vector conversion unit 1401 is used to call the target site selection recognition model to identify the sub-region M i The population characteristic information and transaction characteristic information are converted into vectors to obtain the sub-region M i The population feature vector and transaction feature vector are used to convert the asset attribute information into a vector to obtain the asset attribute vector;

[0171] The splicing unit 1402 is used to combine the sub-region M i The population feature vector and transaction feature vector are concatenated to obtain the sub-region M i The regional feature vector of

[0172] The third acquisition unit 1403 is used to acquire the sub-region M i The vector distance between the regional feature vector and the asset attribute vector;

[0173] The sixth determining unit 1404 is used to determine the sub-region M according to the vector distance. i degree of matching.

[0174] Wherein, the determination module 15 includes:

[0175] The contour division unit 1501 is used to divide the candidate area into contour lines according to the matching degrees corresponding to the M sub-areas, so as to obtain a plurality of first candidate site selection areas; the matching degrees of any two sub-areas in all the sub-areas covered by the boundary of the first candidate site selection area are the same;

[0176] An adjustment unit 1502 is used to obtain regional center points corresponding to the plurality of first candidate site selection areas, and adjust the plurality of first candidate site selection areas based on the regional center points corresponding to the plurality of first candidate site selection areas to obtain a plurality of adjusted first candidate site selection areas, wherein any two of the plurality of adjusted first candidate site selection areas have no overlapping parts;

[0177] A fourth acquisition unit 1503 is used to acquire first region scores respectively corresponding to the plurality of adjusted first candidate site selection regions, where the first region score is the sum of the matching degrees of all sub-regions covered by the adjusted first candidate site selection region;

[0178] The seventh determining unit 1504 is configured to determine a target site selection area for the target user from the M sub-areas according to the first area scores respectively corresponding to the plurality of adjusted first candidate site selection areas.

[0179] The seventh determining unit 1504 is specifically configured to:

[0180] According to the first area scores respectively corresponding to the multiple adjusted first candidate site selection areas, the candidate areas are divided into contour lines to obtain multiple second candidate site selection areas, and the first area scores of any two adjusted first candidate site selection areas in all the adjusted first candidate site selection areas covered by the boundaries of the second candidate site selection areas are the same;

[0181] The second area scores corresponding to the multiple second candidate site selection areas are obtained, and the second candidate site selection area with the highest second area score among the multiple second candidate site selection areas is determined as the target site selection area. The second area score is the sum of the matching degrees of all sub-areas covered by the second candidate area.

[0182] In addition, the description of the beneficial effects of adopting the same method will not be repeated here.

[0183] See also Figure 7 , Figure 7 Schematic diagram of the structure of a computer device provided in an embodiment of the present application. Figure 7As shown, the above-mentioned computer device 1000 may include: a processor 1001, a network interface 1004 and a memory 1005. In addition, the above-mentioned computer device 1000 may also include: a target user interface 1003, and at least one communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. Among them, the target user interface 1003 may include a display screen (Display), a keyboard (Keyboard), and the target user interface 1003 may optionally include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory, or it may be a non-volatile memory (non-volatile memory), such as at least one disk storage. The memory 1005 may optionally also be at least one storage device located away from the aforementioned processor 1001. As Figure 7 As shown, the memory 1005 as a computer-readable storage medium may include an operating system, a network communication module, a target user interface module, and a device control application program.

[0184] exist Figure 7 In the computer device 1000 shown, the network interface 1004 can provide a network communication function; the target user interface 1003 is mainly used to provide an input interface for the target user; and the processor 1001 can be used to call the device control application stored in the memory 1005 to achieve:

[0185] Obtaining address attribute information and asset attribute information of the target user's desired location;

[0186] Determine a candidate area according to the address attribute information, and divide the candidate area into M sub-areas according to a preset area division rule, where M is a positive integer;

[0187] Get sub-region M i The population characteristics information of the sub-region M i Transaction feature information of sub-area M i Belongs to M sub-areas, i is a positive integer less than or equal to M;

[0188] For sub-region M i The population characteristics information, transaction characteristics information and asset attribute information are identified to obtain the sub-region M i The matching degree of sub-region M i The matching degree of the sub-region M is used to reflect i The matching degree with the target users’ expected location;

[0189] According to the matching degrees corresponding to the M sub-areas respectively, the target location area of ​​the target user is determined from the M sub-areas.

[0190] It should be understood that the computer device 1000 described in the embodiment of the present application can execute the above Figure 2 or Figure 4 The description of the site selection method in the corresponding embodiment can also be performed as described above. Figure 6 The description of the site selection device in the corresponding embodiment will not be repeated here. In addition, the description of the beneficial effects of adopting the same method will not be repeated here.

[0191] In addition, it should be pointed out here that: the embodiment of the present application also provides a computer-readable storage medium, and the computer-readable storage medium stores a computer program executed by the aforementioned address selection device, and the computer program includes program instructions. When the processor executes the program instructions, it can execute the aforementioned Figure 2 or Figure 4 The description of the site selection method in the corresponding embodiment will therefore not be repeated here. In addition, the description of the beneficial effects of the same method will not be repeated. For technical details not disclosed in the computer-readable storage medium embodiment involved in this application, please refer to the description of the method embodiment of this application. As an example, program instructions may be deployed on a computing device for execution, or on multiple computing devices located at one location, or on multiple computing devices distributed at multiple locations and interconnected by a communication network. Multiple computing devices distributed at multiple locations and interconnected by a communication network can constitute a blockchain system.

[0192] In addition, it should be noted that: the embodiment of the present application also provides a computer program product or a computer program, which may include computer instructions, and the computer instructions may be stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor may execute the computer instructions, so that the computer device executes the above Figure 2 or Figure 4 The description of the site selection method in the corresponding embodiment will not be repeated here. In addition, the description of the beneficial effects of the same method will not be repeated. For technical details not disclosed in the computer program product or computer program embodiment involved in this application, please refer to the description of the method embodiment of this application.

[0193] It should be noted that, for the above-mentioned various method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0194] The steps in the method of the embodiment of the present application can be adjusted in order, combined and deleted according to actual needs.

[0195] The modules in the device of the embodiment of the present application can be merged, divided and deleted according to actual needs.

[0196] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0197] The above disclosure is only the preferred embodiment of the present application, which certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. A site selection method, characterized in that: include: Obtaining address attribute information and asset attribute information of the target user's desired location; Determine a candidate area according to the address attribute information, and divide the candidate area into M sub-areas according to a preset area division rule, where M is a positive integer; Get sub-region M i The population characteristics information of the sub-region M i The transaction feature information of the sub-area M i belongs to the M sub-areas, i is a positive integer less than or equal to M; the transaction feature information includes area type information; the sub-area M i The demographic information of the sub-region M i The number of permanent residents, the number of floating population, population density, the number of potential customers and population attribute information, wherein the population attribute information includes population gender information, population age information, population occupation information and population consumption preference information; According to the sub-area M i The area type information determines the sub-area M i The validity of the sub-region M i If it is a valid area, the target site selection recognition model is called to identify the sub-area M i The population characteristic information, transaction characteristic information and the asset attribute information are identified to obtain the sub-area M i The candidate matching degree is based on the sub-region M i The corresponding regional assessment weighting coefficient is i The candidate matching degrees are weighted to obtain the sub-region M i The matching degree of the sub-region M i The matching degree is used to reflect the sub-region M i The matching degree between the sub-area M and the desired location of the target user is i The corresponding regional assessment weighting coefficient is based on the experience of the experts in the sub-region M i Determined by the corresponding economic development status and address location; According to the matching degrees corresponding to the M sub-areas, the candidate area is divided into contour lines to obtain multiple first candidate site selection areas, and the regional center points corresponding to the multiple first candidate site selection areas are obtained. Based on the regional center points corresponding to the multiple first candidate site selection areas, the multiple first candidate site selection areas are adjusted to obtain multiple adjusted first candidate site selection areas, and the first regional scores corresponding to the multiple adjusted first candidate site selection areas are obtained. According to the first regional scores corresponding to the multiple adjusted first candidate site selection areas, the target site selection area of ​​the target user is determined from the M sub-areas; the matching degrees of any two sub-areas in all sub-areas covered by the boundaries of the first candidate site selection area are the same, and there is no overlapping part between any two adjusted first candidate site selection areas in the multiple adjusted first candidate site selection areas, and the first regional score is the sum of the matching degrees of all sub-areas covered by the adjusted first candidate site selection area.

2. The method according to claim 1, characterized in that The transaction characteristic information includes regional travel cost; The obtaining of the sub-region M i Transaction characteristics information, including: Get the sub-area M i The road type corresponding to the road is determined according to the road type. i The passage damping parameter of Determine the sub-area M according to the passage damping parameter i The travel time cost; Get the sub-region M i The passage mode within the area, and determining the sub-area M according to the passage mode i toll costs; For the sub-area M i The travel time cost and toll cost are summed to obtain the sub-area M i regional travel costs.

3. The method according to claim 1, characterized in that The transaction characteristic information includes industry distribution information; The obtaining of the sub-region M i Transaction characteristics information, including: Get the sub-area M i The business transaction data corresponding to the N industries in , where N is a positive integer; According to the industry N j The business transaction data determines the industry N j The industrial output value of the industry N j belongs to the N industries, j is a positive integer less than or equal to N; The industrial output values ​​corresponding to the N industries are summed up to obtain the sub-region M i Regional output value; Get the industry N j The ratio of the industrial output value of the N industries to the regional output value is determined as the ratio of the industrial output value of the N industries to the regional output value. i Industry distribution information.

4. The method according to claim 1, characterized in that: The transaction characteristic information includes the user's spending capacity; The obtaining of the sub-region M i Transaction characteristics information, including: Determine the sub-area M i Whether there is housing transaction information of the user in the database; If the sub-region M i If there is user housing transaction information in the sub-area M i The user housing transaction information in the sub-area M is determined i The consumption capacity of users; If the sub-region M i If there is no user housing transaction information in the M sub-areas, then obtain the information related to the sub-area M from the M sub-areas. i The adjacent adjacent sub-regions are obtained, the user consumption capacity of the adjacent sub-regions and the weighting coefficients corresponding to the adjacent sub-regions are obtained, and the user consumption capacity of the adjacent sub-regions is weighted by using the weighting coefficients to obtain the sub-region M i consumer spending power.

5. The method according to claim 1, characterized in that The sub-area M i The population characteristic information and transaction characteristic information of the sub-region M are identified by using the asset attribute information. i The candidate matching degree includes: For the sub-area M i The population characteristic information and transaction characteristic information are vectorized to obtain the sub-region M i The population feature vector and the transaction feature vector are used to perform vector conversion on the asset attribute information to obtain an asset attribute vector; For the sub-area M i The population feature vector and transaction feature vector are concatenated to obtain the sub-region M i The regional feature vector of Get the sub-region M i The vector distance between the regional feature vector and the asset attribute vector; Determine the sub-region M according to the vector distance i Candidate matching degree.

6. The method according to claim 1, characterized in that The determining the target site selection area of ​​the target user from the M sub-areas according to the first area scores respectively corresponding to the plurality of adjusted first candidate site selection areas comprises: According to the first area scores respectively corresponding to the multiple adjusted first candidate site selection areas, the candidate areas are divided into contour lines to obtain multiple second candidate site selection areas, and the first area scores of any two adjusted first candidate site selection areas in all the adjusted first candidate site selection areas covered by the boundaries of the second candidate site selection areas are the same; Obtain the second area scores corresponding to the multiple second candidate site selection areas respectively, and determine the second candidate site selection area with the highest second area score among the multiple second candidate site selection areas as the target site selection area, wherein the second area score is the sum of the matching degrees of all sub-areas covered by the second candidate site selection area.

7. A site selection device, characterized in that: include: The first acquisition module is used to acquire the address attribute information and asset attribute information of the desired site of the target user; A region division module, used to determine a candidate region according to the address attribute information, and divide the candidate region into M sub-regions according to a preset region division rule, where M is a positive integer; The second acquisition module is used to acquire the sub-area M i The population characteristics information of the sub-region M i The transaction feature information of the sub-area M i belongs to the M sub-areas, i is a positive integer less than or equal to M; the transaction feature information includes area type information; the sub-area M i The demographic information of the sub-region M i The number of permanent residents, the number of floating population, population density, the number of potential customers and population attribute information, wherein the population attribute information includes population gender information, population age information, population occupation information and population consumption preference information; An identification module is used to identify the sub-area M i The area type information determines the sub-area M i The validity of the sub-region M i If it is a valid area, the target site selection recognition model is called to identify the sub-area M i The population characteristic information, transaction characteristic information and the asset attribute information are identified to obtain the sub-area M i The candidate matching degree is based on the sub-region M i The corresponding regional assessment weighting coefficient is i The candidate matching degrees are weighted to obtain the sub-region M i The matching degree of the sub-region M i The matching degree is used to reflect the sub-region M i The matching degree between the sub-area M and the desired location of the target user is i The corresponding regional assessment weighting coefficient is based on the experience of the experts in the sub-region M i Determined by the corresponding economic development status and address location; A determination module is used to divide the candidate area into contour lines according to the matching degrees respectively corresponding to the M sub-areas to obtain multiple first candidate site selection areas, obtain the regional center points respectively corresponding to the multiple first candidate site selection areas, adjust the multiple first candidate site selection areas based on the regional center points respectively corresponding to the multiple first candidate site selection areas to obtain multiple adjusted first candidate site selection areas, obtain the first regional scores respectively corresponding to the multiple adjusted first candidate site selection areas, and determine the target site selection area of ​​the target user from the M sub-areas according to the first regional scores respectively corresponding to the multiple adjusted first candidate site selection areas; the matching degrees of any two sub-areas in all sub-areas covered by the boundaries of the first candidate site selection area are the same, there is no overlapping part between any two adjusted first candidate site selection areas in the multiple adjusted first candidate site selection areas, and the first regional score is the sum of the matching degrees of all sub-areas covered by the adjusted first candidate site selection area.

8. A computer device, characterized in that: include: Processor and memory; The processor is connected to a memory, wherein the memory is used to store a computer program, and the processor is used to call the computer program so that the computer device executes the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded and executed by a processor, so that a computer device having the processor executes the method according to any one of claims 1 to 6.

Images