Address data management method, device and medium

Abstract

The present application discloses an address data management method, device, and medium. The method includes: obtaining address data to be managed in a preset period; determining the five-level administrative division name of the address data; matching the five-level administrative division name according to the administrative division standard name table to determine the five-level administrative division standard name of the address data; determining the detailed address data corresponding to the five-level administrative division standard name in the address data; inputting the detailed address data into a pre-built detailed address data annotation neural network model to generate an annotation label for each character in the detailed address data; merging characters with the same annotation label to obtain a character combination; splitting the detailed address data according to the character combination to obtain a split result of the detailed address data; and verifying the split result of the detailed address data according to a pre-set data normalization rule to obtain normalized detailed address data. This improves data management efficiency.

Description

Technical Field

[0001] The present application relates to the field of data governance technology, and in particular to an address data governance method, device, and medium. Background Art

[0002] As the informatization process continues to improve across various industries, more and more business processes are being implemented within informatization systems, leading to an explosive growth in the amount of digital information. This influx of data into systems through data entry and business development presents both enormous potential for data value mining and numerous data quality issues. Properly processing and correcting data in the system and ensuring database quality are crucial to both data value mining and informatization projects themselves.

[0003] Improving the quality of address data is currently a crucial issue in grassroots governance. For both personal and real estate information, the address field is a crucial foundational field, crucial for applications such as home visits and linking people to properties.

[0004] However, due to the lack of standard basis for data entry in grassroots governance scenarios, different application scenarios and data sources have different rules for parsing and entering address data, resulting in very low consistency of address data in the database.

[0005] In addition, address information data is also highly complex, usually including five levels of administrative division names and multiple detailed address data fields such as roads, communities, building numbers, units, and household numbers. Each administrative division should have a standard name and code, but due to the specific circumstances of village mergers, name changes, and administrative division changes, there is a lack of unified standards for the standard names of administrative divisions in different times and systems, and there is no unified standard for the division and specific names of detailed address data.

[0006] Therefore, in the process of address data governance, data governance requires a lot of waste of manpower and material resources, resulting in low data governance efficiency. Summary of the Invention

[0007] The embodiments of the present application provide an address data management method, device, and medium for solving the problem of low address data management efficiency.

[0008] The embodiments of this application adopt the following technical solutions:

[0009] On the one hand, an embodiment of the present application provides an address data governance method, which includes: obtaining address data to be governed within a preset period; determining the five-level administrative division name of the address data; matching the five-level administrative division name according to a pre-purchased administrative division standard name table to determine the five-level administrative division standard name of the address data; the administrative division standard name table includes the five-level administrative division standard names corresponding to the preset area; in the address data, determining the detailed address data corresponding to the five-level administrative division standard name; inputting the detailed address data into a pre-built detailed address data annotation neural network model to generate an annotation label for each character in the detailed address data; merging characters with the same annotation label to obtain a character combination; splitting the detailed address data according to the character combination to obtain a split result of the detailed address data; verifying the split result of the detailed address data according to a pre-set data normalization rule to obtain normalized detailed address data; generating standardized address data corresponding to the address data according to the five-level administrative division standard name and the normalized detailed address data.

[0010] In one example, the five-level administrative division names are matched according to the pre-purchased standard name table of administrative divisions to determine the five-level administrative division standard name of the address data, specifically including: matching the five-level administrative division names according to the preset standard name table of administrative divisions to determine whether there are administrative division names that have not been matched for the first time; if so, matching the administrative division names that have not been matched for the first time in the administrative division standard name table according to preset regular matching rules to determine the five-level administrative division standard name of the address data.

[0011] In one example, according to the preset regular matching rule, the administrative division name that was not matched for the first time is matched in the administrative division standard name table to determine the fifth-level administrative division standard name of the address data, specifically including: according to the preset regular matching rule, the administrative division name that was not matched for the first time is matched in the administrative division standard name table to determine whether there is an administrative division name that was not matched for the second time; if so, according to a pre-constructed administrative division alias table, the administrative division name that was not matched for the second time is matched to determine the fifth-level administrative division standard name of the address data; the administrative division alias table includes the fifth-level administrative division alias corresponding to the fifth-level administrative division standard name in the preset area.

[0012] In one example, before matching the administrative division names that were not matched for the second time according to the pre-constructed administrative division alias table and determining the fifth-level administrative division standard name of the address data, the method also includes: obtaining the fifth-level administrative division alias corresponding to the fifth-level administrative division standard name within the preset area; establishing a first correspondence between the fifth-level administrative division standard name and the fifth-level administrative division alias; obtaining the latest historical merged multiple standard names corresponding to the fifth-level administrative division standard name, and the aliases corresponding to the latest historical merged multiple standard names; generating merged information of the five-level administrative division standard name based on the latest historical merged multiple standard names and the aliases corresponding to the latest historical merged multiple standard names; establishing a second correspondence between the five-level administrative division standard name and the merged information; and constructing the administrative division alias table based on the first correspondence and the second correspondence.

[0013] In one example, the administrative division name that was not matched for the second time is matched according to a pre-constructed administrative division alias table to determine the five-level administrative division standard name of the address data, specifically including: in the pre-constructed administrative division alias table, the administrative division name that was not matched for the second time is matched with multiple administrative division aliases to determine whether there is an administrative division name that was not matched for the third time; if so, the administrative division name that was not matched for the third time is matched according to the merge information to determine the five-level administrative division standard name of the address data.

[0014] In one example, before matching the five-level administrative division names according to the pre-purchased administrative division standard name table to determine the five-level administrative division standard name of the address data, the method also includes: obtaining the five-level administrative division standard name within a preset area; extracting multiple administrative division levels of the five-level administrative division standard name; and establishing the affiliation corresponding to the five-level administrative division standard name based on the multiple administrative division levels to construct the administrative division standard name table.

[0015] In one example, the five-level administrative division names are matched according to a pre-constructed standard name table of administrative divisions to determine whether there are administrative division names that were not matched the first time, specifically including: judging whether the level of the five-level administrative division name is missing; if so, if the missing level is not the lowest level, determining the next lower level of the missing level; in the pre-constructed standard name table of administrative divisions, determining the standard name of the missing level through the standard name and affiliation corresponding to the next lower level of the missing level; and completing the five-level administrative division name according to the standard name of the missing level.

[0016] In one example, before inputting the detailed address data into a pre-built detailed address data annotation neural network model and generating an annotation label for each character in the detailed address data, the method further includes: obtaining sample address data; determining the annotation label of the detailed address; the annotation label includes at least one of a street name, a community name, a unit building name, and a unit household name; and performing supervised training on the initial detailed address data annotation neural network model based on the sample address data and the annotation label to obtain the detailed address data annotation neural network model.

[0017] On the other hand, an embodiment of the present application provides an address data management device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: obtain address data to be managed within a preset period; determine the five-level administrative division name of the address data; match the five-level administrative division name according to a pre-purchased administrative division standard name table to determine the five-level administrative division standard name of the address data; the administrative division standard name table includes the five-level administrative division standard names corresponding to preset areas; In the address data, the detailed address data corresponding to the standard name of the five-level administrative division is determined; the detailed address data is input into a pre-built detailed address data annotation neural network model to generate an annotation label for each character in the detailed address data; characters with the same annotation label are merged to obtain a character combination; according to the character combination, the detailed address data is split to obtain a split result of the detailed address data; according to a pre-set data normalization rule, the split result of the detailed address data is verified to obtain normalized detailed address data; according to the five-level administrative division standard name and the normalized detailed address data, standardized address data corresponding to the address data is generated.

[0018] On the other hand, an embodiment of the present application provides a non-volatile computer storage medium for address data management, storing computer-executable instructions, wherein the computer-executable instructions are configured to: obtain the address data to be managed within a preset period; determine the five-level administrative division name of the address data; match the five-level administrative division name according to a pre-purchased administrative division standard name table to determine the five-level administrative division standard name of the address data; the administrative division standard name table includes the five-level administrative division standard names corresponding to the preset area; in the address data, determine the detailed address data corresponding to the five-level administrative division standard name; input the detailed address data into a pre-built detailed address data annotation neural network model to generate an annotation label for each character in the detailed address data; merge characters with the same annotation label to obtain a character combination; split the detailed address data according to the character combination to obtain a split result of the detailed address data; verify the split result of the detailed address data according to a pre-set data normalization rule to obtain normalized detailed address data; generate standardized address data corresponding to the address data according to the five-level administrative division standard name and the normalized detailed address data.

[0019] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0020] By processing the five-level administrative division names and detailed address data in the address data separately, generating the five-level administrative division standard names and standardized detailed address data of the address data respectively, it is possible to generate standardized address data corresponding to the address data, thereby improving the quality of the address data and enhancing the availability of address information. In specific usage scenarios such as grassroots governance and personnel management, the role of standardized address data can be brought into play, thereby improving the efficiency and accuracy of address data governance. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solution of the present application, some embodiments of the present application will be described in detail below with reference to the accompanying drawings, in which:

[0022] Figure 1 A flowchart of an address data management method provided in an embodiment of the present application;

[0023] Figure 2 A schematic diagram of the structure of an address data management device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] To make the objectives, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0025] Some embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0026] Figure 1 This is a flowchart of an address data governance method provided in an embodiment of the present application. This method can be applied to various business areas, such as internet finance, e-commerce, instant messaging, gaming, and government affairs. Certain input parameters or intermediate results in this process allow for manual adjustment to help improve accuracy.

[0027] The analysis method involved in the embodiments of the present application can be implemented by a terminal device or a server, and the present application does not impose any special restrictions on this. For ease of understanding and description, the following embodiments are described in detail using a server as an example.

[0028] It should be noted that the server can be a single device or a system composed of multiple devices, that is, a distributed server, and this application does not make any specific restrictions on this.

[0029] Figure 1 The process in may include the following steps:

[0030] S101: Acquire address data to be managed within a preset period.

[0031] Among them, based on the user's operation, the address data of the specified business type is obtained from the address data management library. It should be noted that the address data management library stores address data of multiple business types, including address data uploaded for each business type in different time periods.

[0032] S102: Determine the five-level administrative division name of the address data.

[0033] In other words, extract the province name, city name, county name, township name, and village name from the address data. For example, through the keyword extraction model, extract the province, city, county, township, and village keywords respectively, and then obtain the names corresponding to the keywords.

[0034] S103: Match the five-level administrative division names according to a pre-purchased standard administrative division name table to determine the five-level administrative division standard name of the address data; the standard administrative division name table includes the corresponding five-level administrative division standard names in the preset area.

[0035] In some embodiments of the present application, when constructing the administrative division standard name table, the five-level administrative division standard names are obtained in a preset area. The preset area can be set according to actual needs, for example, the preset area is the national area.

[0036] Next, we extract multiple administrative division levels for the five-level administrative division standard names, i.e., the five administrative division levels. Finally, based on these multiple administrative division levels, we establish the affiliation relationships corresponding to the five-level administrative division standard names to construct a table of administrative division standard names. Affiliation refers to the affiliation between the levels to which each administrative division standard name belongs. For example, City B belongs to Province A. More intuitively, the table of administrative division standard names is shown in Table 1.

[0037] Table 1

[0038]

[0039] In Table 1, the name column refers to the name of the five-level administrative division standard, the level column refers to the level of the administrative division standard name, the code refers to the code of the administrative division standard name, and the pcode refers to the affiliation between the administrative division standard names.

[0040] In some embodiments of the present application, due to incomplete address data, it is considered to complete the names of the five-level administrative divisions.

[0041] Specifically, first determine whether the level of the five-level administrative division name is missing.

[0042] If the missing level is not the lowest level, determine the next lower level of the missing level. For example, if the missing level is province, the next lower level of the missing level is city.

[0043] Then, in the pre-built table of administrative division standard names, the standard name of the missing level is determined by the standard name corresponding to the next lower level and the affiliation relationship. For example, if the standard name of a city is City B, then based on the affiliation relationship, the province to which City B belongs is Province A.

[0044] Finally, the names of the five-level administrative divisions are completed based on the standard names of the missing levels.

[0045] It should be noted that when the missing level is the lowest level, it is necessary to query the village name to which the detailed address data belongs in the detailed address data affiliation table based on the detailed address data. The detailed address data affiliation table includes the village name to which the detailed address standard data belongs.

[0046] In some embodiments of the present application, when matching the fifth-level administrative division names and determining the fifth-level administrative division standard names of the address data, it is necessary to consider the situation where the fifth-level administrative division names cannot be successfully matched in the administrative division standard name table because they are not standard names.

[0047] Specifically, first, the five-level administrative division names are matched according to the preset administrative division standard name table to determine whether there are administrative division names that have not been matched the first time.

[0048] If so, according to the preset regular matching rules, the administrative division name that was not matched the first time is matched in the administrative division standard name table to determine the fifth-level administrative division standard name of the address data.

[0049] It should be noted that if there is no administrative division name that was not matched the first time, step S104 is executed.

[0050] Furthermore, according to the preset regular matching rules, the administrative division names that are not matched for the first time are matched in the administrative division standard name table to determine whether there are administrative division names that are not matched for the second time.

[0051] If so, the administrative division names that were not matched the second time are matched according to the pre-constructed administrative division alias table to determine the fifth-level administrative division standard name of the address data; the administrative division alias table includes the fifth-level administrative division aliases corresponding to the fifth-level administrative division standard names within the preset area.

[0052] Among them, when constructing the administrative division alias table, the fifth-level administrative division alias corresponding to the fifth-level administrative division standard name is obtained within the preset area.

[0053] Then, the first correspondence between the standard names of the five-level administrative divisions and the aliases of the five-level administrative divisions is established.

[0054] Then, the latest historical merged multiple standard names corresponding to the five-level administrative division standard names and the aliases corresponding to the latest historical merged multiple standard names are obtained. Merged information of the five-level administrative division standard names is generated based on the latest historical merged multiple standard names and the aliases corresponding to the latest historical merged multiple standard names.

[0055] Then, a second correspondence is established between the standard names of the five-level administrative divisions and the merged information. Finally, an administrative division alias table is constructed based on the first correspondence and the second correspondence.

[0056] It should be noted that if there is no administrative division name that is not matched for the second time, step S104 is executed.

[0057] Among them, in the pre-constructed administrative division alias table, the administrative division name that is not matched for the second time is matched with multiple administrative division aliases to determine whether there is an administrative division name that is not matched for the third time.

[0058] If so, the administrative division names that were not matched for the third time are matched based on the merge information to determine the standard names of the five-level administrative divisions of the address data.

[0059] It should be noted that if there is no administrative division name that has not been matched for the third time, step S104 is executed.

[0060] S104: Determine the detailed address data corresponding to the standard name of the five-level administrative division in the address data.

[0061] Detailed address data includes street name, community name, unit building name, and unit household name.

[0062] S105: Inputting the detailed address data into a pre-built detailed address data annotation neural network model to generate an annotation label for each character in the detailed address data.

[0063] It should be noted that the label of each character is unique.

[0064] In some embodiments of the present application, when constructing a detailed address data annotation neural network model, sample address data is first obtained.

[0065] Then, a label of the detailed address is determined; the label includes at least one of a street name, a community name, a unit building name, and a unit household name.

[0066] Then, supervised training is performed on the initial detailed address data labeling neural network model based on the sample address data and the labeling labels to obtain the detailed address data labeling neural network model.

[0067] S106: Merge characters with the same label to obtain a character combination.

[0068] For example, if the labels of AB characters are both cell names, then AB is merged to obtain the AB cell.

[0069] S107: Split the detailed address data according to the character combination to obtain a split result of the detailed address data.

[0070] S108: Verify the splitting result of the detailed address data according to a pre-set data normalization rule to obtain normalized detailed address data.

[0071] For example, data normalization rules include number formats, affix content, etc. For example, Arabic numerals are not allowed in street names and they need to be converted to Chinese to express numbers.

[0072] S109: Generate standardized address data corresponding to the address data according to the five-level administrative division standard name and the standardized detailed address data.

[0073] It should be noted that although the embodiments of this application are based on Figure 1 Steps S101 to S109 are described in sequence, but this does not mean that steps S101 to S109 must be performed in a strict order. Figure 1 The order shown in FIG1 is to introduce and explain steps S101 to S109 in order to facilitate those skilled in the art to understand the technical solutions of the embodiments of the present application. In other words, in the embodiments of the present application, the order of steps S101 to S109 can be appropriately adjusted according to actual needs.

[0074] pass Figure 1 The method is to process the five-level administrative division names and detailed address data in the address data respectively, generate the five-level administrative division standard names and standardized detailed address data of the address data respectively, and generate standardized address data corresponding to the address data, so as to improve the quality of the address data and enhance the availability of address information. In specific usage scenarios such as grassroots governance and personnel management, the role of standardized address data is brought into play, thereby improving the efficiency and accuracy of address data governance.

[0075] Based on the same idea, some embodiments of the present application also provide devices and non-volatile computer storage media corresponding to the above methods.

[0076] Figure 2 A schematic diagram of the structure of an address data management device provided in an embodiment of the present application includes:

[0077] at least one processor; and,

[0078] a memory communicatively connected to the at least one processor; wherein,

[0079] The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to:

[0080] Obtain address data to be managed within a preset period;

[0081] Determine the five-level administrative division name of the address data;

[0082] Matching the five-level administrative division names according to a pre-purchased standard administrative division name table to determine the five-level administrative division name of the address data; the standard administrative division name table includes the corresponding five-level administrative division name within the preset area;

[0083] In the address data, determining the detailed address data corresponding to the standard name of the five-level administrative division;

[0084] Inputting the detailed address data into a pre-built detailed address data annotation neural network model to generate an annotation label for each character in the detailed address data;

[0085] Merge characters with the same label to obtain a character combination;

[0086] Splitting the detailed address data according to the character combination to obtain a split result of the detailed address data;

[0087] Verifying the splitting result of the detailed address data according to a pre-set data normalization rule to obtain normalized detailed address data;

[0088] Based on the five-level administrative division standard names and the standardized detailed address data, standardized address data corresponding to the address data is generated.

[0089] Some embodiments of the present application provide an address data management non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to:

[0090] Obtain address data to be managed within a preset period;

[0091] Determine the five-level administrative division name of the address data;

[0092] Matching the five-level administrative division names according to a pre-purchased standard administrative division name table to determine the five-level administrative division name of the address data; the standard administrative division name table includes the corresponding five-level administrative division name within the preset area;

[0093] In the address data, determining the detailed address data corresponding to the standard name of the five-level administrative division;

[0094] Inputting the detailed address data into a pre-built detailed address data annotation neural network model to generate an annotation label for each character in the detailed address data;

[0095] Merge characters with the same label to obtain a character combination;

[0096] Splitting the detailed address data according to the character combination to obtain a split result of the detailed address data;

[0097] Verifying the splitting result of the detailed address data according to a pre-set data normalization rule to obtain normalized detailed address data;

[0098] Based on the five-level administrative division standard names and the standardized detailed address data, standardized address data corresponding to the address data is generated.

[0099] The various embodiments in this application are described in a progressive manner. Similar portions between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the device and medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simple. For relevant portions, refer to the descriptions of the method embodiments.

[0100] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects to their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0101] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0102] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0103] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0104] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0105] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0106] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0107] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0108] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0109] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modifications, equivalent replacements, improvements, etc. made within the technical principles of the present application should fall within the scope of protection of the present application.

Claims

1. A method for address data management, characterized in that: The method comprises: Obtain address data to be managed within a preset period; Determine the five-level administrative division name of the address data; Matching the five-level administrative division names according to a pre-purchased standard administrative division name table to determine the five-level administrative division name of the address data; the standard administrative division name table includes the corresponding five-level administrative division name within the preset area; In the address data, determining the detailed address data corresponding to the standard name of the five-level administrative division; Inputting the detailed address data into a pre-built detailed address data annotation neural network model to generate an annotation label for each character in the detailed address data; Merge characters with the same label to obtain a character combination; Splitting the detailed address data according to the character combination to obtain a split result of the detailed address data; Verifying the splitting result of the detailed address data according to a pre-set data normalization rule to obtain normalized detailed address data; Generate standardized address data corresponding to the address data according to the five-level administrative division standard name and the standardized detailed address data; The matching of the five-level administrative division names according to the pre-purchased standard administrative division name table to determine the five-level administrative division standard name of the address data specifically includes: Matching the five-level administrative division names according to a preset administrative division standard name table to determine whether there is an administrative division name that was not matched the first time; If so, according to a preset regular matching rule, the administrative division name that was not matched for the first time is matched in the administrative division standard name table to determine the fifth-level administrative division standard name of the address data; The step of matching the first unmatched administrative division name in the administrative division standard name table according to a preset regular matching rule to determine the five-level administrative division standard name of the address data specifically includes: According to a preset regular matching rule, the administrative division name that was not matched for the first time is matched in the administrative division standard name table to determine whether there is an administrative division name that was not matched for the second time; If so, the administrative division name that was not matched for the second time is matched according to the pre-constructed administrative division alias table to determine the fifth-level administrative division standard name of the address data; the administrative division alias table includes the fifth-level administrative division alias corresponding to the fifth-level administrative division standard name within the preset area.

2. The method according to claim 1, characterized in that Before matching the administrative division names that were not matched for the second time according to the pre-built administrative division alias table to determine the five-level administrative division standard name of the address data, the method further includes: In the preset area, obtaining the fifth-level administrative division alias corresponding to the fifth-level administrative division standard name; Establishing a first correspondence between the standard name of the fifth-level administrative division and the alias of the fifth-level administrative division; Obtaining the latest historical merged multiple standard names corresponding to the five-level administrative division standard name, and the aliases corresponding to the latest historical merged multiple standard names; Generate the merged information of the five-level administrative division standard names according to the multiple standard names merged in the latest history and the aliases respectively corresponding to the multiple standard names merged in the latest history; Establishing a second correspondence between the five-level administrative division standard name and the merged information; The administrative division alias table is constructed based on the first corresponding relationship and the second corresponding relationship.

3. The method according to claim 2, characterized in that The matching of the administrative division names that were not matched for the second time according to the pre-built administrative division alias table to determine the five-level administrative division standard name of the address data specifically includes: In the pre-constructed administrative division alias table, matching the administrative division name that was not matched for the second time with multiple administrative division aliases to determine whether there is an administrative division name that was not matched for the third time; If so, the administrative division name that was not matched for the third time is matched according to the merge information to determine the fifth-level administrative division standard name of the address data.

4. The method according to claim 1, wherein Before matching the five-level administrative division names according to the pre-purchased standard administrative division name table to determine the five-level administrative division standard name of the address data, the method further includes: In the preset area, obtain the standard names of the five-level administrative divisions; Extracting multiple administrative division levels of the five-level administrative division standard name; According to the multiple administrative division levels, the affiliation relationships corresponding to the five-level administrative division standard names are established to construct the administrative division standard name table.

5. The method according to claim 4, characterized in that The matching of the five-level administrative division names according to the pre-constructed administrative division standard name table to determine whether there is an administrative division name that has not been matched the first time specifically includes: Determine whether the level of the five-level administrative division name is missing; If so, if the missing level is not the lowest level, then determine the next lower level of the missing level; In the pre-constructed administrative division standard name table, the standard name of the missing level is determined by the standard name and affiliation corresponding to the next lower level of the missing level; The five-level administrative division names are completed according to the standard names of the missing levels.

6. The method according to claim 1, characterized in that Before inputting the detailed address data into a pre-built detailed address data annotation neural network model to generate an annotation label for each character in the detailed address data, the method further includes: Get sample address data; Determine a label for the detailed address; the label includes at least one of a street name, a community name, a building name, and a household name; According to the sample address data and the annotation labels, supervised training is performed on the initial detailed address data annotation neural network model to obtain the detailed address data annotation neural network model.

7. An address data management device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the address data management method described in any one of claims 1 to 6.

8. A non-volatile computer storage medium for address data management, storing computer-executable instructions, characterized in that: The computer executable instructions are capable of executing an address data management method as described in any one of claims 1-6.

Images