A network site selection method and device

Abstract

The present invention discloses a method and device for selecting a network site, and relates to the field of computer technology. A specific implementation of the method includes obtaining a map spatial index list based on map data; obtaining attribute information, calculating the spatial index code corresponding to the attribute information, and merging it into the map spatial index list; obtaining the longitude and latitude data of the existing target network point, performing spatial index coding, and merging it into the map spatial index list merged with the spatial index code corresponding to the attribute information; according to the merged map spatial index list, obtaining the recommended network point address information through a preset machine learning model. Therefore, the implementation of the present invention can solve the problem that the existing method can only compare each location selected by the user to obtain a more suitable location, and cannot directly and quickly inform the location of the location when the user does not select an address.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a network site selection method and device. Background Art

[0002] The existing site selection system outputs the predicted future revenue of the location based on the location selected by the user. For example, if the user enters two locations on the map, the system will get the longitude and latitude points selected by the user, and then estimate the future revenue of the point if it is used as a bank branch based on the population and economic data around the longitude and latitude points. Then, based on the comparison of operating data such as revenue, the system will tell the user which point is more suitable as a bank branch in the future.

[0003] In the process of implementing the present invention, the inventors found that there are at least the following problems in the prior art:

[0004] The data cannot be put into the map index, so the only way to find the surrounding data for modeling is to perform a range search when the user enters the location. At the same time, similar locations (locations with similar historical data) cannot be compared, and temporary calculations are performed when the user enters the location, which leads to a poor user experience. Summary of the invention

[0005] In view of this, the embodiments of the present invention provide a network site selection method and device, which can solve the problem that the existing method can only compare each location selected by the user to obtain a more suitable site selection location, and cannot directly and quickly inform the site selection location when the user does not select an address.

[0006] To achieve the above-mentioned purpose, according to one aspect of an embodiment of the present invention, a method for network site selection is provided, including calculating all spatial index points based on map data to obtain a map spatial index list; wherein each spatial index code in the spatial index list represents a map location; obtaining attribute information, and calculating the spatial index code corresponding to the attribute information according to the longitude and latitude data corresponding to the attribute information; merging the spatial index code corresponding to the attribute information into the map spatial index list; obtaining the longitude and latitude data of existing target network points, performing spatial index coding, and merging them into the map spatial index list merged with the spatial index code corresponding to the attribute information; and obtaining the recommended network address information through a preset machine learning model according to the merged map spatial index list.

[0007] Optionally, according to the merged map space index list, the recommended network point address information is obtained through a preset machine learning model, including:

[0008] According to the merged map spatial index list, the network point information of the location corresponding to the spatial index code is obtained through a preset machine learning model;

[0009] The similarity between the target area and the position corresponding to the spatial index code is calculated, and the network point information corresponding to the position of the spatial index code with the highest similarity is recommended.

[0010] Optionally, according to the merged map spatial index list, after obtaining the network point information of the location corresponding to the spatial index code through a preset machine learning model, it includes:

[0011] According to the merged map spatial index list, calculating the correlation coefficient of each column of the network point information corresponding to the spatial index code;

[0012] Based on the preset target attribute information, the spatial index codes are sorted by correlation coefficients;

[0013] A preset number of spatial index codes are obtained, the similarity between the target area and the position corresponding to the spatial index code is calculated, and the network point information of the position corresponding to the spatial index code with the highest similarity is recommended.

[0014] Optionally include:

[0015] Based on the number of geographical points of interest, the spatial index codes are sorted by correlation coefficient.

[0016] Optionally include:

[0017] According to the merged map spatial index list, the network point information of the position corresponding to the spatial index code is obtained through a preset gradient boosting algorithm or a boosting tree model.

[0018] Optionally, calculating the similarity between the target area and the position corresponding to the spatial index code includes:

[0019] The similarity between the target area and the corresponding position of the spatial index encoding is calculated through cosine similarity or neural network model.

[0020] Optionally include:

[0021] The attribute information includes population data, number of geographical location points of interest, and business data.

[0022] In addition, the present invention also provides a network site selection device, including an acquisition module, which is used to calculate all spatial index points based on map data to obtain a map spatial index list; wherein each spatial index code in the spatial index list represents a map location; obtain attribute information, and calculate the spatial index code corresponding to the attribute information according to the latitude and longitude data corresponding to the attribute information; merge the spatial index code corresponding to the attribute information into the map spatial index list; obtain the latitude and longitude data of the existing target network point, perform spatial index coding, and merge it into the map spatial index list merged with the spatial index code corresponding to the attribute information;

[0023] A processing module is used to obtain recommended network address information through a preset machine learning model based on the merged map space index list.

[0024] An embodiment of the above invention has the following advantages or beneficial effects: because it adopts a map data-based method to obtain a map spatial index list; obtains attribute information, calculates the spatial index code corresponding to the attribute information, and merges it into the map spatial index list; obtains the longitude and latitude data of the existing target network point, performs spatial index coding, and merges it into the map spatial index list merged with the spatial index code corresponding to the attribute information; according to the merged map spatial index list, a technical means for obtaining the recommended network point address information through a preset machine learning model is overcome, thereby overcoming the technical problem that the existing method can only compare each location selected by the user to obtain a more suitable site selection location, and cannot directly and quickly inform the site selection location when the user has not selected an address.

[0025] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0027] Figure 1 is a schematic diagram of the main process of the network site selection method according to the first embodiment of the present invention;

[0028] Figure 2 is a schematic diagram of the main process of the network site selection method according to the second embodiment of the present invention;

[0029] Figure 3 is a schematic diagram of the main process of the network site selection method according to the third embodiment of the present invention;

[0030] Figure 4 is a schematic diagram of main modules of a network point site selection device according to an embodiment of the present invention;

[0031] Figure 5 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0032] Figure 6 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0033] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0034] Figure 1 FIG. 1 is a schematic diagram of the main process of the network site selection method according to the first embodiment of the present invention. Figure 1 As shown, the network site selection method includes:

[0035] Step S101, based on the map data, calculate all spatial index points to obtain a map spatial index list. Obtain attribute information, and calculate the spatial index code corresponding to the attribute information according to the latitude and longitude data corresponding to the attribute information. Merge the spatial index code corresponding to the attribute information into the map spatial index list. Obtain the latitude and longitude data of the existing target network point, perform spatial index coding, and merge it into the map spatial index list merged with the spatial index code corresponding to the attribute information.

[0036] Each spatial index code in the spatial index list represents a map location.

[0037] In an embodiment, the spatial index may be geohash, a B-tree-based indexing method, an R-tree-based indexing method, etc. The geohash is an address encoding method that can encode two-dimensional spatial latitude and longitude data into a string.

[0038] In some embodiments, the attribute information includes population data, POI number, business data, etc. Further, based on the POI number (ie, the target attribute information may be the POI number), the geohash codes are sorted by correlation coefficient.

[0039] As a specific embodiment, after calculating all spatial index points based on map data, it is necessary to perform deduplication processing and then generate a map spatial index list. It should be noted that map data refers to existing network point data, and locations without network point data are not within the calculation range.

[0040] Then, according to the latitude and longitude data corresponding to the attribute information such as population data, number of POIs, business data, etc., the spatial index code corresponding to the attribute information is calculated, and then the spatial index code corresponding to the attribute information is merged into the data column behind the map spatial index list.

[0041] The existing outlets with good operations (with longitude and latitude data) are encoded with the same level of spatial index and merged into the merged map spatial index list to serve as the target value to be predicted by the machine learning model.

[0042] Step S102, obtaining recommended network point address information through a preset machine learning model according to the merged map space index list.

[0043] In some embodiments, the specific implementation process of step S102 may include: obtaining the network point information (e.g., the number of network points) of the position corresponding to the spatial index code through a preset machine learning model according to the merged map spatial index list. Calculating the similarity between the target area and the position corresponding to the spatial index code, and recommending the network point information of the position corresponding to the spatial index code with the highest similarity.

[0044] In a further embodiment, according to the merged map spatial index list, after obtaining the network point information of the location corresponding to the spatial index code through a preset machine learning model, it includes:

[0045] According to the merged map spatial index list, the correlation coefficient of each column and the network point information at the position corresponding to the spatial index code is calculated. Based on the preset target attribute information, the spatial index codes are sorted by correlation coefficient. A preset number of spatial index codes are obtained, and the similarity between the target area (the area without network points) and the position corresponding to the spatial index code is calculated, and the network point information at the position corresponding to the spatial index code with the highest similarity is recommended.

[0046] Preferably, the correlation coefficient between each column (each column in the geohash list represents different attribute information) and the grid point information at the corresponding position of the geohash code is calculated by the covariance formula as follows:

[0047]

[0048] Among them, Xi is a column of attribute information, and Yi is the point information (i.e., the number of points) at the corresponding position of the geohash code.

[0049] After calculating the correlation coefficient, the POI (geographic point of interest) number attribute in the geohash list is sorted. The sorting shows the correlation between different types of geographic points of interest and network information: For example:

[0050] 210207,Bath and massage services

[0051] 200103,Building / Office Building

[0052] 210216, Real estate agency services

[0053] 160100,Education

[0054] 130403,Newspaper Retail

[0055] 130201, cakes and bread retail

[0056] 210205,Beauty / Body

[0057] 150102,ATM

[0058] 150101,Bank

[0059] In this way, the more important attributes can be selected as the basis for predicting whether a network point should be built in a region.

[0060] It is also worth noting that, according to the merged map space index list, the network point information of the corresponding position of the geohash code is obtained through a preset gradient boosting algorithm (such as catboost) or boosting tree (such as XBGoost) model.

[0061] Among them, catboost is a gradient boosting algorithm library that can handle categorical features. XBGoos is a boosting tree model.

[0062] In addition, the similarity between the target area and the corresponding position of the geohash code can be calculated by cosine similarity or neural network model. Preferably, the neural network can be a DeepFM model, FNN, PNN, etc. Preferably, the present invention can adopt a DeepFM model. Among them, the DeepFM algorithm combines the advantages of factor decomposition machine and neural network in feature learning, and extracts low-order combined features and high-order combined features at the same time.

[0063] In summary, the method for selecting bank outlets creatively uses the geographic location index combined with the model in the bank outlets selection method, and can calculate the location through batch processing in the background, without the need for temporary calculation when the user inputs the location, thus improving the user experience and making the output results clear and easy to understand. In addition, the present invention uses the recommendation system algorithm, so that the system can directly calculate the location where the outlets should be built based on the existing data, without the need for the user to select the location first and then compare repeatedly, and the output results are very intuitive.

[0064] Figure 2 FIG. 1 is a schematic diagram of the main process of the network site selection method according to the second embodiment of the present invention. Figure 2 As shown, the network site selection method includes:

[0065] Step S201, based on the map data, calculate all geohash points to obtain a map geohash list.

[0066] Among them, each geohash code in the geohash list represents a map location.

[0067] Step S202, obtaining attribute information, and calculating the geohash code corresponding to the attribute information according to the latitude and longitude data corresponding to the attribute information.

[0068] Step S203: merge the geohash code corresponding to the attribute information into the map geohash list.

[0069] Step S204, obtaining the latitude and longitude data of the existing target network point, performing geohash coding, and merging it into the map geohash list that merges the geohash coding corresponding to the attribute information.

[0070] Step S205, according to the merged map geohash list, obtain the network point information of the location corresponding to the geohash code through a preset machine learning model.

[0071] Step S206, calculating the similarity between the target area and the position corresponding to the geohash code, and recommending the network point information of the position corresponding to the geohash code with the highest similarity.

[0072] Figure 3 FIG. 1 is a schematic diagram of the main process of the network site selection method according to the third embodiment of the present invention. Figure 3 As shown, the network site selection method includes:

[0073] Step S301, based on the map data, calculate all geohash points to obtain a map geohash list.

[0074] Among them, each geohash code in the geohash list represents a map location.

[0075] Step S302, obtaining attribute information, and calculating the geohash code corresponding to the attribute information according to the latitude and longitude data corresponding to the attribute information.

[0076] The attribute information includes population data, number of POIs, and business data.

[0077] Step S303: merge the geohash code corresponding to the attribute information into the map geohash list.

[0078] Step S304, obtaining the latitude and longitude data of the existing target network point, performing geohash coding, and merging it into the map geohash list that merges the geohash coding corresponding to the attribute information.

[0079] Step S305: According to the merged map geohash list, the network point information of the location corresponding to the geohash code is obtained through a preset catboost or XBGoost model.

[0080] Step S306, calculating the correlation coefficient of each column of the network point information corresponding to the position of the geohash code according to the merged map geohash list.

[0081] Step S307: sorting the geohash codes by correlation coefficient based on the preset target attribute information.

[0082] Among them, based on the number of POIs, the geohash codes are sorted by correlation coefficient.

[0083] Step S308: Obtain a preset number of geohash codes, and calculate the similarity between the target area and the position corresponding to the geohash code by using cosine similarity or DeepFM model.

[0084] Step S309: recommending the network point information of the location corresponding to the geohash code with the highest similarity.

[0085] Figure 4 Schematic diagram of main modules of the network site selection device according to an embodiment of the present invention. Figure 4 As shown, the network site selection device 400 includes an acquisition module 401 and a processing module 402. The acquisition module 401 calculates all spatial index points based on map data to obtain a map spatial index list; each spatial index code in the spatial index list represents a map location; obtains attribute information, and calculates the spatial index code corresponding to the attribute information according to the latitude and longitude data corresponding to the attribute information; merges the spatial index code corresponding to the attribute information into the map spatial index list; obtains the latitude and longitude data of the existing target network point, performs spatial index coding, and merges it into the map spatial index list merged with the spatial index code corresponding to the attribute information. The processing module 402 obtains the recommended network point address information through a preset machine learning model according to the merged map spatial index list.

[0086] Preferably, the attribute information includes population data, number of geographical location points of interest, and business data.

[0087] In some embodiments, the processing module 402 obtains the recommended network point address information through a preset machine learning model according to the merged map space index list, including:

[0088] According to the merged map spatial index list, the network point information of the position corresponding to the spatial index code is obtained through a preset machine learning model; the similarity between the target area and the position corresponding to the spatial index code is calculated, and the network point information of the position corresponding to the spatial index code with the highest similarity is recommended.

[0089] In a further embodiment, after the processing module 402 obtains the network point information of the location corresponding to the spatial index code through a preset machine learning model according to the merged map spatial index list, it includes:

[0090] According to the merged map spatial index list, the correlation coefficient of each column and the network point information at the position corresponding to the spatial index code is calculated; based on the preset target attribute information, the spatial index codes are sorted by the correlation coefficients; a preset number of spatial index codes are obtained, the similarity between the target area and the position corresponding to the spatial index code is calculated, and the network point information at the position corresponding to the spatial index code with the highest similarity is recommended.

[0091] In a preferred embodiment, the spatial index codes are sorted by correlation coefficient based on the number of POIs.

[0092] As some other embodiments, the processing module 402 obtains the network point information of the position corresponding to the spatial index code through a preset gradient boosting algorithm or boosting tree model according to the merged map spatial index list.

[0093] As some further embodiments, the processing module 402 calculates the similarity between the target area and the position corresponding to the spatial index code by using cosine similarity or a neural network model.

[0094] It should be noted that the network point site selection method and the network point site selection device described in the present invention have a corresponding relationship in terms of specific implementation contents, so the repeated contents will not be described again.

[0095] Figure 5 An exemplary system architecture 500 is shown to which the network site selection method or network site selection device according to the embodiment of the present invention can be applied.

[0096] like Figure 5 As shown, system architecture 500 may include terminal devices 501, 502, 503, a network 504 and a server 505. Network 504 is used to provide a medium for communication links between terminal devices 501, 502, 503 and server 505. Network 504 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0097] Users can use terminal devices 501, 502, 503 to interact with server 505 through network 504 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 501, 502, 503, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples).

[0098] The terminal devices 501, 502, 503 may be various electronic devices having a site selection screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0099] The server 505 may be a server that provides various services, such as a backend management server (only an example) that provides support for shopping websites browsed by users using the terminal devices 501, 502, and 503. The backend management server may analyze and process the received data such as product information query requests, and feed back the processing results (such as target push information, product information - only an example) to the terminal device.

[0100] It should be noted that the network point site selection method provided in the embodiment of the present invention is generally executed by the server 505 , and accordingly, the computing device is generally set in the server 505 .

[0101] It should be understood that Figure 5 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0102] Reference below Figure 6 , which shows a schematic diagram of the structure of a computer system 600 of a terminal device suitable for implementing an embodiment of the present invention. Figure 6 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0103] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the computer system 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0104] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal dot selector (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage section 608 as needed.

[0105] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the system of the present invention are executed.

[0106] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0107] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0108] The modules involved in the embodiments of the present invention may be implemented by software or hardware. The modules described may also be set in a processor. For example, it may be described as follows: a processor includes an acquisition module and a processing module. The names of these modules do not, in some cases, limit the modules themselves.

[0109] As another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently and not be assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes obtaining a map spatial index list based on map data; obtaining attribute information, calculating the spatial index code corresponding to the attribute information, and merging it into the spatial index list; obtaining the longitude and latitude data of the existing target network point, performing spatial index coding, and merging it into the map spatial index list merged with the spatial index code corresponding to the attribute information; according to the merged map spatial index list, obtaining the recommended network point address information through a preset machine learning model.

[0110] The technical solution according to the embodiment of the present invention can solve the problem that the existing method can only compare each location selected by the user to obtain a more suitable location, and cannot directly and quickly inform the location when the user does not select an address.

[0111] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for selecting a network site, characterized in that: include: Based on the map data, all spatial index points are calculated to obtain a map spatial index list; wherein each spatial index code in the spatial index list represents a map location; Acquire attribute information, and calculate the spatial index code corresponding to the attribute information according to the latitude and longitude data corresponding to the attribute information; merge the spatial index code corresponding to the attribute information into the map spatial index list; the attribute information includes population data, the number of geographical location points of interest, and business data; Obtain the latitude and longitude data of the existing target network point, perform spatial index coding, and merge it into the map spatial index list that merges the spatial index coding corresponding to the attribute information; The network point information of the position corresponding to the spatial index code is obtained through a preset machine learning model, and the correlation coefficient of each column with the network point information of the position corresponding to the spatial index code is calculated according to the merged map spatial index list; the spatial index codes are sorted according to the correlation coefficients based on the preset target attribute information; a preset number of spatial index codes are obtained, and the similarity between the target area and the position corresponding to the spatial index code is calculated, and the network point information of the position corresponding to the spatial index code with the highest similarity is recommended; each of the columns represents different attribute information; the target area is an area where no network point is set; the spatial index codes are sorted according to the correlation coefficients based on the preset target attribute information, including: sorting the spatial index codes according to the correlation coefficients based on the attribute of the number of geographical location interest points in the merged map spatial index list, and the sorting indicates the correlation between different types of geographical location interest points and the network point information.

2. The method according to claim 1, characterized in that include: According to the merged map spatial index list, the network point information of the position corresponding to the spatial index code is obtained through a preset gradient boosting algorithm or a boosting tree model.

3. The method according to claim 1, characterized in that Calculate the similarity between the target area and the corresponding position of the spatial index code, including: The similarity between the target area and the corresponding position of the spatial index encoding is calculated through cosine similarity or neural network model.

4. A network site selection device, characterized in that: include: The acquisition module is used to calculate all spatial index points based on the map data to obtain a map spatial index list; wherein each spatial index code in the spatial index list represents a map location; obtain attribute information, and calculate the spatial index code corresponding to the attribute information according to the latitude and longitude data corresponding to the attribute information; merge the spatial index code corresponding to the attribute information into the map spatial index list; obtain the latitude and longitude data of the existing target network point, perform spatial index coding, and merge it into the map spatial index list merged with the spatial index code corresponding to the attribute information; the attribute information includes population data, the number of geographical location points of interest, and business data; A processing module is used to obtain the network point information of the position corresponding to the spatial index code through a preset machine learning model, calculate the correlation coefficient of each column with the network point information of the position corresponding to the spatial index code according to the merged map spatial index list; sort the spatial index codes according to the correlation coefficient based on the preset target attribute information; obtain a preset number of spatial index codes, calculate the similarity between the target area and the position corresponding to the spatial index code, and recommend the network point information of the position corresponding to the spatial index code with the highest similarity; each of the columns represents different attribute information; the target area is an area where no network point is set; the spatial index codes are sorted according to the correlation coefficient based on the preset target attribute information, including: sorting the spatial index codes according to the correlation coefficient based on the attribute of the number of geographical location interest points in the merged map spatial index list, and the sorting indicates the correlation between different types of geographical location interest points and the network point information.

5. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 3.

6. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images