A real estate data cleaning and merging method, device and storage medium

Abstract

The present invention discloses a method, device and storage medium for cleaning and merging building data. The method obtains multiple POI information corresponding to each building name according to the building name in the second building data; obtains multiple POI information corresponding to each building address according to the building address in the second building data; merges the multiple POI information corresponding to the building name and the multiple POI information corresponding to the building address of the same building to obtain the POI information set of each building; selects a POI information from the POI information set of each building as the first POI information of each building; determines whether any two buildings are the same building according to the first POI information of each building, and removes the duplicate building data determined to be the same building in the second building data to obtain the third building data. The technical solution of the present invention realizes the efficient merging of building data and greatly reduces redundant data.

Description

Technical Field

[0001] The present invention relates to the technical field of data cleaning and merging, and in particular to a method, device and storage medium for cleaning and merging building data. Background Art

[0002] After the crawler completes the data crawling, clustering is performed based on the building name and building address to complete the data clustering under multiple data sources; at the same time, the business registration address of the enterprise is matched with the building address, and the relevant enterprises are associated with the corresponding building; thus supporting users to obtain data on buildings across the country and mine under building companies on the product side. In the existing technology, there are the following shortcomings when cleaning and merging building data:

[0003] (1) The same building has different names and addresses in each source, and the validity of the data is not ensured through data cleaning and data normalization;

[0004] (2) Ordinary data cleaning and grouping rules are inefficient, and since no corresponding recognition algorithm is introduced to identify and remove duplicates for the same real estate, there is a large amount of redundant data, which affects the subsequent application of the real estate data. Summary of the invention

[0005] The present invention provides a method, device and storage medium for cleaning and merging building data, which realizes efficient merging of building data and greatly reduces redundant data.

[0006] An embodiment of the present invention provides a method for cleaning and merging real estate data, comprising the following steps:

[0007] Acquire original building data, the building data including building name data and building address data of each building, and establish a mapping relationship between the building name data and the building address data of the same building;

[0008] The building data are screened according to the building name data to obtain first building data; the building address data in the first building data are subjected to first preprocessing to obtain second building data;

[0009] According to the building names in the second building data, multiple POI information corresponding to each building name is obtained; according to the building addresses in the second building data, multiple POI information corresponding to each building address is obtained;

[0010] According to the mapping relationship between the building name and the building address, multiple POI information corresponding to the building name and multiple POI information corresponding to the building address of the same building are merged to obtain a POI information set of each building;

[0011] After deleting the poi information that does not meet the first preset condition from the poi information sets of each real estate project, select one poi information from the poi information sets of each real estate project as the first poi information of each real estate project;

[0012] Judge whether any two real estate projects are the same real estate project according to the first poi information of each real estate project, and deduplicate the real estate project data judged to be the same real estate project in the second real estate project data to obtain the third real estate project data.

[0013] Further, filter the real estate project data according to the real estate project name data, specifically:

[0014] Delete the real estate project data whose real estate project name contains "front door", "front gate", "back door", "left door", "right door", "side door", "east gate", "south gate", "west gate", "north gate" and "gate number";

[0015] Delete the real estate project data whose real estate project name contains "parking";

[0016] Delete the real estate project data whose real estate project name contains "entrance and exit", "exit" or "entrance";

[0017] Delete the real estate project data whose real estate project name contains "investment promotion center" or "community";

[0018] Delete the real estate project data whose real estate project name contains "store" and does not contain "hotel".

[0019] Further, perform a first preprocessing on the real estate project address data in the first real estate project data, specifically:

[0020] Remove the special symbols in the real estate project address, and the special symbols include spaces, double quotes and single quotes;

[0021] Remove the parentheses and the content in the parentheses in the real estate project address;

[0022] According to the commas in the real estate project address, split the real estate project address into several sub-real estate project addresses, select one of the sub-real estate project addresses according to the preset selection logic and retain it, and delete the other sub-real estate project addresses;

[0023] Remove the numbers and the address information after the numbers after the character "number" in the real estate project address, and remove the letters and the address information after the letters after the character "number" in the real estate project address;

[0024] Remove the "self-compiled" and the address information after the "self-compiled" after the character "number" in the real estate project address, and there is no other character between the character "number" and the "self-compiled".

[0025] Further, the POI information in the POI information set of each building that does not meet the first preset condition is deleted, specifically:

[0026] Deleting the POI information that does not contain the POI city name or POI type in the POI information set;

[0027] Delete the POI city name in the POI information set that is inconsistent with the city name of the corresponding building in the building data;

[0028] Delete the POI information in the POI information set whose POI type is not "real estate", "company enterprise; park", "shopping; shopping center", "hotel; star hotel", "company enterprise; other" or "shopping; shopping center".

[0029] Further, a POI information is selected from the POI information set of each building as the first POI information of each building, specifically:

[0030] Acquire the first longitude and latitude of the current building from the second building data, and calculate the first longitude and latitude distance score between the first longitude and latitude and the second longitude and latitude of each POI information in the POI information set of the current building;

[0031] Calculate the first edit distance similarity between the building name of the current building and the building names of each POI information in the POI information set of the current building;

[0032] Calculate the second edit distance similarity between the building address of the current building and the building addresses of each POI information in the POI information set of the current building;

[0033] Calculate the first total similarity score of each POI information in the POI information set of the current building, and select the POI information with the highest first total similarity score as the first POI information of the current building; the first total similarity score is the sum of the first longitude and latitude distance score, the first edit distance similarity and the second edit distance similarity.

[0034] Furthermore, whether any two buildings are the same building is determined based on the first POI information of each building, specifically:

[0035] Calculate the longitude and latitude distance between the first POI information of two buildings. When the longitude and latitude distance between the two buildings is greater than a first preset threshold, determine that the two buildings are not the same building; when the longitude and latitude distance between the two buildings is less than or equal to the first preset threshold, calculate the second longitude and latitude distance score between the first POI information of the two buildings;

[0036] Calculate the first edit distance similarity between the building name of the current building and the building names of each POI information in the POI information set of the current building;

[0037] Calculate the third edit distance similarity between the building names of the first POI information of the two buildings;

[0038] Calculate the fourth edit distance similarity between the building addresses of the first POI information of the two buildings;

[0039] Calculate the second total similarity score between the first POI information of the two buildings. When the second total similarity score is greater than the second preset threshold, it is judged to be the same building; when the second total similarity score is less than or equal to the preset threshold, it is judged to be not the same building; the second total similarity score is the sum of the second longitude and latitude distance score, the third edit distance similarity and the fourth edit distance similarity.

[0040] Further, when the first total similarity score is less than a third preset threshold, the POI information corresponding to the first total similarity score is deleted from the POI information set.

[0041] Another embodiment of the present invention provides a building data cleaning and merging device, including a building data acquisition module, a building data screening module, a POI information acquisition module, a POI information calculation module and a building data deduplication module;

[0042] The building data acquisition module is used to acquire original building data, the building data includes building name data and building address data of each building, and establish a mapping relationship between the building name data and building address data of the same building;

[0043] The building data screening module is used to screen the building data according to the building name data to obtain first building data; perform first preprocessing on the building address data in the first building data to obtain second building data;

[0044] The POI information acquisition module is used to acquire multiple POI information corresponding to each building name according to the building name in the second building data; acquire multiple POI information corresponding to each building address according to the building address in the second building data; and merge multiple POI information corresponding to the building name and multiple POI information corresponding to the building address of the same building according to the mapping relationship between the building name and the building address to obtain a POI information set for each building;

[0045] The POI information calculation module is used to delete the POI information that does not meet the first preset condition in the POI information set of each building, and then select a POI information from the POI information set of each building as the first POI information of each building;

[0046] The building data deduplication module is used to determine whether any two buildings are the same building according to the first POI information of each building, and to deduplicate the building data determined to be the same building in the second building data to obtain third building data.

[0047] Further, a POI information is selected from the POI information set of each building as the first POI information of each building, specifically:

[0048] Acquire the first longitude and latitude of the current building from the second building data, and calculate the first longitude and latitude distance score between the first longitude and latitude and the second longitude and latitude of each POI information in the POI information set of the current building;

[0049] Calculate the first edit distance similarity between the building name of the current building and the building names of each POI information in the POI information set of the current building;

[0050] Calculate the second edit distance similarity between the building address of the current building and the building addresses of each POI information in the POI information set of the current building;

[0051] Calculate the first total similarity score of each POI information in the POI information set of the current building, and select the POI information with the highest first total similarity score as the first POI information of the current building; the first total similarity score is the sum of the first longitude and latitude distance score, the first edit distance similarity and the second edit distance similarity.

[0052] Another embodiment of the present invention provides a readable storage medium, which includes a stored computer program. When the computer program is executed, the device where the readable storage medium is located is controlled to execute the real estate data cleaning and merging method described in any method embodiment of the present invention.

[0053] The embodiments of the present invention have the following beneficial effects:

[0054] The present invention provides a method, device and storage medium for cleaning and merging building data. The method obtains first building data by screening the building data according to the building name data; performs first preprocessing on the building address data in the first building data to obtain second building data; through the screening and preprocessing process, the initial cleaning of the original building data is achieved, and the validity of the building data is ensured. According to the building name in the second building data, multiple POI information corresponding to each building name is obtained; according to the building address in the second building data, multiple POI information corresponding to each building address is obtained; according to the first POI information of each building, it is determined whether any two buildings are the same building, and the building data determined to be the same building in the second building data are deduplicated to obtain third building data. That is, the present invention realizes accurate deduplication of building data by introducing POI technology, improves the cleaning efficiency of building data, and obtains accurate cleaning results of building data. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a flow chart of a real estate data cleaning and merging method provided by an embodiment of the present invention;

[0056] Figure 2 It is a structural diagram of a real estate data cleaning and merging device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] like Figure 1 As shown, a method for cleaning and merging real estate data provided by an embodiment of the present invention includes the following steps:

[0059] Step S101: Acquire original building data, which includes building name data and building address data of each building, and establish a mapping relationship between the building name data and building address data of the same building.

[0060] Step S102: Filter the building data according to the building name data to obtain first building data; perform first preprocessing on the building address data in the first building data to obtain second building data.

[0061] As one embodiment, step S102 includes the following sub-steps:

[0062] Sub-step S1021: Screen the property data according to the property name data, specifically:

[0063] Delete the property data whose property names contain "front door", "front gate", "back door", "left door", "right door", "side door", "east gate", "south gate", "west gate", "north gate" and "gate number";

[0064] Delete the property data whose property names contain "parking";

[0065] Delete the property data whose property names contain "entrance and exit", "exit" or "entrance";

[0066] Delete the property data whose property names contain "investment promotion center" or "community";

[0067] Delete the property data whose property names contain "store" and do not contain "hotel" to obtain the first property data.

[0068] Sub-step S1022: Perform a first preprocessing on the property address data in the first property data, specifically:

[0069] Remove the special symbols in the property address, and the special symbols include spaces, double quotes and single quotes;

[0070] Remove the brackets and the content in the brackets in the property address;

[0071] Split the property address into several sub-property addresses according to the commas in the property address, and select one of the sub-property addresses to retain according to the preset selection logic, and delete the other sub-property addresses;

[0072] Remove the numbers and the address information after the number and the letters and the address information after the letter after the word "number" in the property address; there can be other characters between the word "number" and the number after the word "number", and there can be other characters between the word "number" and the letter after the word "number";

[0073] Remove the "self-compiled" and the address information after the "self-compiled" after the word "number" in the property address, and there is no other character between the word "number" and the "self-compiled" to obtain the second property data.

[0074] Step S103: Obtain multiple poi information corresponding to each property name according to the property names in the second property data; obtain multiple poi information corresponding to each property address according to the property addresses in the second property data.

[0075] As one of the embodiments, Baidu Map is requested according to a building name in the second building data to obtain multiple POI information corresponding to the building name, and the first 10 POI information are taken from the multiple POI information; Baidu Map is requested according to the building address of the building name in the second building data to obtain multiple POI information corresponding to the building address, and the first 10 POI information from the multiple POI information are merged with the 10 POI information corresponding to the building name to obtain the POI information set of the current building.

[0076] Step S104: According to the mapping relationship between the building name and the building address, multiple POI information corresponding to the building name and multiple POI information corresponding to the building address of the same building are merged to obtain a POI information set of each building.

[0077] One of the POI information includes the following:

[0078]

[0079] Among them, "city":"Dongguan City" is the city name of the poi, and "poi_type":"Company Enterprise; Company" is the poi type.

[0080] Step S105: after deleting the POI information that does not meet the first preset condition in the POI information set of each building, select one POI information from the POI information set of each building as the first POI information of each building.

[0081] As one embodiment, step S105 includes the following sub-steps:

[0082] Sub-step S1051: deleting the POI information in the POI information set of each building that does not meet the first preset condition, specifically:

[0083] Deleting the POI information that does not contain the POI city name or POI type in the POI information set;

[0084] Delete the POI city name in the POI information set that is inconsistent with the city name of the corresponding building in the building data;

[0085] Delete the POI information in the POI information set whose POI type is not "real estate", "company enterprise; park", "shopping; shopping center", "hotel; star hotel", "company enterprise; other" or "shopping; shopping center".

[0086] After the deletion operation in the sub-step S1051, if the number of POI information of the same building is 0, the building information is deleted, and the building information includes the building name, building address and other information related to the building.

[0087] Sub-step S1052: Obtain the first longitude and latitude of the current building from the second building data, and calculate the first longitude and latitude distance score between the first longitude and latitude and the second longitude and latitude of each POI information in the POI information set of the current building; specifically, calculate the first distance d between the first longitude and longitude and the second longitude and longitude, if the first distance exceeds 2 kilometers, delete the POI information, if the first distance does not exceed 2 kilometers, the first longitude and longitude distance score = (1-d / 2000).

[0088] Calculate the first edit distance similarity between the building name of the current building and the building names of each POI information in the POI information set of the current building;

[0089] Calculate the second edit distance similarity between the building address of the current building and the building addresses of each POI information in the POI information set of the current building;

[0090] Calculate the first total similarity score of each POI information in the POI information set of the current building, and select the POI information with the highest first total similarity score as the first POI information of the current building; the first total similarity score is the sum of the first longitude and latitude distance score, the first edit distance similarity and the second edit distance similarity.

[0091] When the first total similarity score is less than a third preset threshold, the POI information corresponding to the first total similarity score is deleted from the POI information set; preferably, if the first total similarity score is less than 2, the POI information is deleted, and if the first total similarity score is greater than or equal to 2, the POI information with the highest first total similarity score is selected as the first POI information of the current building.

[0092] Step S106: Determine whether any two buildings are the same building according to the first POI information of each building, remove duplicates from the building data determined to be the same building in the second building data, and obtain third building data.

[0093] As one embodiment, judging whether any two buildings are the same building according to the first POI information of each building is as follows:

[0094] Calculate the longitude and latitude distance s between the first POI information of two buildings. When the longitude and latitude distance of the two buildings is greater than a first preset threshold, it is determined that the two buildings are not the same building; when the longitude and latitude distance of the two buildings is less than or equal to the first preset threshold, calculate the second longitude and latitude distance score between the first POI information of the two buildings; preferably, the second longitude and latitude distance score = (1-s / 2000).

[0095] Calculate the first edit distance similarity between the building name of the current building and the building names of each POI information in the POI information set of the current building;

[0096] Calculate the third edit distance similarity between the building names of the first POI information of the two buildings;

[0097] Calculate the fourth edit distance similarity between the building addresses of the first POI information of the two buildings;

[0098] Calculate the second total similarity score between the first POI information of the two buildings. When the second total similarity score is greater than the second preset threshold, it is determined that they are the same building; when the second total similarity score is less than or equal to the preset threshold, it is determined that they are not the same building; the second total similarity score is the sum of the second longitude and latitude distance score, the third edit distance similarity and the fourth edit distance similarity. Preferably, the second preset threshold is 2.5.

[0099] like Figure 2 As shown, another embodiment of the present invention provides a building data cleaning and merging device, including a building data acquisition module, a building data screening module, a POI information acquisition module, a POI information calculation module and a building data deduplication module;

[0100] The building data acquisition module is used to acquire original building data, the building data includes building name data and building address data of each building, and establish a mapping relationship between the building name data and building address data of the same building;

[0101] The building data screening module is used to screen the building data according to the building name data to obtain first building data; perform first preprocessing on the building address data in the first building data to obtain second building data;

[0102] The POI information acquisition module is used to acquire multiple POI information corresponding to each building name according to the building name in the second building data; acquire multiple POI information corresponding to each building address according to the building address in the second building data; and merge multiple POI information corresponding to the building name and multiple POI information corresponding to the building address of the same building according to the mapping relationship between the building name and the building address to obtain a POI information set for each building;

[0103] The POI information calculation module is used to delete the POI information that does not meet the first preset condition in the POI information set of each building, and then select a POI information from the POI information set of each building as the first POI information of each building;

[0104] The building data deduplication module is used to determine whether any two buildings are the same building according to the first POI information of each building, and to deduplicate the building data determined to be the same building in the second building data to obtain third building data.

[0105] As one embodiment, one POI information is selected from the POI information set of each building as the first POI information of each building, specifically:

[0106] Acquire the first longitude and latitude of the current building from the second building data, and calculate the first longitude and latitude distance score between the first longitude and latitude and the second longitude and latitude of each POI information in the POI information set of the current building;

[0107] Calculate the first edit distance similarity between the building name of the current building and the building names of each POI information in the POI information set of the current building;

[0108] Calculate the second edit distance similarity between the building address of the current building and the building addresses of each POI information in the POI information set of the current building;

[0109] Calculate the first total similarity score of each POI information in the POI information set of the current building, and select the POI information with the highest first total similarity score as the first POI information of the current building; the first total similarity score is the sum of the first longitude and latitude distance score, the first edit distance similarity and the second edit distance similarity.

[0110] Based on the above method embodiment, the present invention provides a corresponding readable storage medium embodiment;

[0111] Another embodiment of the present invention provides a readable storage medium, which includes a stored computer program. When the computer program is executed, the device where the readable storage medium is located is controlled to execute the real estate data cleaning and merging method as described in any method embodiment of the present invention.

[0112] Exemplarily, the computer program may be divided into one or more modules, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the terminal device.

[0113] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0114] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0115] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the terminal device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0116] Wherein, if the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium (i.e., the above-mentioned readable storage medium). Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0117] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0118] Those of ordinary skill in the art can understand and implement it without creative work. The above is a preferred embodiment of the present invention. It should be noted that for those of ordinary skill in the art, several improvements and modifications can be made without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention. Those of ordinary skill in the art can understand that all or part of the processes in the above embodiments can be implemented by instructing related hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above embodiments. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

Claims

1. A real estate data cleaning and merging method, characterized in that: The following steps are involved: Acquire original building data, the building data including building name data and building address data of each building, and establish a mapping relationship between the building name data and the building address data of the same building; The building data are screened according to the building name data to obtain first building data; the building address data in the first building data are subjected to first preprocessing to obtain second building data; According to the building names in the second building data, multiple POI information corresponding to each building name is obtained; According to the building address in the second building data, obtain multiple POI information corresponding to each building address; According to the mapping relationship between the building name and the building address, multiple POI information corresponding to the building name and multiple POI information corresponding to the building address of the same building are merged to obtain a POI information set of each building; After deleting the POI information that does not meet the first preset condition in the POI information set of each building, selecting a POI information from the POI information set of each building as the first POI information of each building; Determine whether any two buildings are the same building according to the first POI information of each building, remove duplicates from the building data determined to be the same building in the second building data, and obtain third building data; Select one POI information from the POI information set of each building as the first POI information of each building, specifically: Acquire the first longitude and latitude of the current building from the second building data, and calculate the first longitude and latitude distance score between the first longitude and latitude and the second longitude and latitude of each POI information in the POI information set of the current building; Calculate the first edit distance similarity between the building name of the current building and the building names of each POI information in the POI information set of the current building; Calculate the second edit distance similarity between the building address of the current building and the building addresses of each POI information in the POI information set of the current building; Calculate the first total similarity score of each POI information in the POI information set of the current building, and select the POI information with the highest first total similarity score as the first POI information of the current building; The first total similarity score is the sum of the first longitude and latitude distance score, the first edit distance similarity, and the second edit distance similarity.

2. The real estate data cleaning and merging method according to claim 1 is characterized in that: The real estate data is filtered according to the real estate name data, specifically: Delete the building data whose names contain "main gate", "front gate", "back gate", "left gate", "right gate", "side gate", "east gate", "south gate", "west gate", "north gate" and "number gate"; Delete the building data whose building names contain "parking"; Delete the building data containing "entrance and exit", "exit" or "entrance" in the building name; Delete the real estate data whose real estate names contain "investment center" or "community"; Delete the property data whose property names contain "shop" but not "hotel".

3. The real estate data cleaning and merging method according to claim 2 is characterized in that: The first preprocessing is performed on the building address data in the first building data, specifically: Remove special symbols in the property address, where the special symbols include spaces, double quotes, and single quotes; Remove parentheses and the content within the parentheses in the property address; Split the property address based on commas in the property address to obtain several sub-property addresses, select one of the sub-property addresses according to a preset selection logic for retention, and delete the other sub-property addresses; Remove the numbers and the address information after the numbers after the character "No." in the property address, and remove the letters and the address information after the letters after the character "No." in the property address; Remove "Self-Compiled" and the address information after "Self-Compiled" after the character "No." in the property address, with no other characters intervening between the character "No." and "Self-Compiled".

4. The real estate data cleaning and merging method according to claim 3 is characterized in that: Delete poi information in the poi information set of each property that does not meet the first preset condition, specifically: Delete poi information in the poi information set that does not contain the poi city name or poi type; Delete those in the poi information set where the poi city name is inconsistent with the city name of the corresponding property in the property data; Delete poi information in the poi information set where the poi type is not "Real Estate", "Company; Park", "Shopping; Shopping Center", "Hotel; Star Hotel", "Company; Others", or "Shopping; Shopping Center".

5. The real estate data cleaning and merging method according to claim 1 is characterized in that: Judge whether any two properties are the same property according to the first poi information of each property, specifically: Calculate the longitude and latitude distance between the first poi information of two properties. When the longitude and latitude distance between the two properties is greater than the first preset threshold, it is judged that the two properties are not the same property; When the longitude and latitude distance between the two properties is less than or equal to the first preset threshold, calculate the second longitude and latitude distance score between the first poi information of the two properties; Calculate the first edit distance similarity between the property name of the current property and the property names of each poi information in the poi information set of the current property; Calculate the third edit distance similarity between the property names of the first poi information of two properties; Calculate the fourth edit distance similarity between the property addresses of the first poi information of two properties; Calculate the second total similarity score between the first poi information of the two properties. When the second total similarity score is greater than the second preset threshold, it is judged as the same property; when the second total similarity score is less than or equal to the preset threshold, it is judged as not the same property; The second total similarity score is the sum of the second longitude and latitude distance score, the third edit distance similarity, and the fourth edit distance similarity.

6. The real estate data cleaning and merging method according to any one of claims 1 to 5, characterized in that: When the first total similarity score is less than the third preset threshold, delete the poi information corresponding to the first total similarity score from the poi information set.

7. A real estate data cleaning and merging device, characterized in that: It includes a property data acquisition module, a property data screening module, a poi information acquisition module, a poi information calculation module, and a property data deduplication module; The building data acquisition module is used to acquire original building data, the building data includes building name data and building address data of each building, and establish a mapping relationship between the building name data and building address data of the same building; The building data screening module is used to screen the building data according to the building name data to obtain first building data; perform first preprocessing on the building address data in the first building data to obtain second building data; The POI information acquisition module is used to acquire multiple POI information corresponding to each building name according to the building name in the second building data; acquire multiple POI information corresponding to each building address according to the building address in the second building data; and merge multiple POI information corresponding to the building name and multiple POI information corresponding to the building address of the same building according to the mapping relationship between the building name and the building address to obtain a POI information set for each building; The POI information calculation module is used to delete the POI information that does not meet the first preset condition in the POI information set of each building, and then select a POI information from the POI information set of each building as the first POI information of each building; The real estate data deduplication module is used to determine whether any two real estates are the same real estate according to the first POI information of each real estate, and to dedupe the real estate data determined to be the same real estate in the second real estate data to obtain the third real estate data; The step of selecting a POI information from the POI information set of each building as the first POI information of each building is specifically: Acquire the first longitude and latitude of the current building from the second building data, and calculate the first longitude and latitude distance score between the first longitude and latitude and the second longitude and latitude of each POI information in the POI information set of the current building; Calculate the first edit distance similarity between the building name of the current building and the building names of each POI information in the POI information set of the current building; Calculate the second edit distance similarity between the building address of the current building and the building addresses of each POI information in the POI information set of the current building; Calculate the first total similarity score of each POI information in the POI information set of the current building, and select the POI information with the highest first total similarity score as the first POI information of the current building; The first total similarity score is the sum of the first longitude and latitude distance score, the first edit distance similarity, and the second edit distance similarity.

8. A readable storage medium, characterized in that: The readable storage medium includes a stored computer program. When the computer program is executed, the device where the readable storage medium is located is controlled to execute the real estate data cleaning and merging method as described in any one of claims 1 to 6.

Images