Address standardization method and system based on knowledge base

Abstract

The invention discloses an address standardization method and system based on a knowledge base, and belongs to the technical field of natural language processing. Standard addresses are segmented and divided, and entity information including administrative division, roads, building groups and building numbers is extracted; performing multi-name entity identification according to the longitude and latitude range of the address so as to improve the accuracy and real-time performance of address conversion; therefore, automatic conversion of the non-standard address is realized, and the non-standard address is associated with the standard address. According to the invention, the accuracy and real-time performance of address standardization can be improved, so that refined, efficient and informatization construction of social governance is promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of natural language processing, and in particular to a knowledge base-based address standardization method and system. Background Art

[0002] At present, the sources of social governance address data are diverse, such as department sharing, grassroots collection and other methods, which also lead to inconsistent address data quality and the inability to achieve association with standard addresses, which has a great impact on further improving public security management and enhancing public services. The significance of non-standard address conversion is to improve the level of social governance refinement, improve the efficiency of social governance work, promote information construction, and serve the people's livelihood and enterprise development. In order to pursue the geographical scope, the existing address standardization methods often standardize national addresses, which results in low address conversion accuracy, non-standard addresses, and inability to update in a timely manner. Summary of the invention

[0003] The technical task of the present invention is to address the above shortcomings and provide a knowledge base-based address standardization method and system, which can improve the accuracy and real-time performance of address standardization, and thus promote the refinement, efficiency and informatization of social governance.

[0004] The technical solution adopted by the present invention to solve its technical problem is:

[0005] A knowledge base-based address standardization method divides standard addresses into segments and extracts entity information including administrative divisions, roads (streets), building groups (communities), and building numbers; multiple name entity recognition is performed according to the latitude and longitude range of the address to improve the accuracy and real-time performance of address conversion; thereby achieving automatic conversion of non-standard addresses and associating them with standard addresses, so that they can be applied to multiple fields such as social governance, public security management, and public services.

[0006] This method can combine the standardized addresses formulated by the government, divide the standard addresses into segments, extract entities such as administrative divisions, roads (streets), building groups (communities), building numbers, etc., and can perform multi-name entity recognition based on the latitude and longitude ranges. This can improve the accuracy and real-time performance of address standardization.

[0007] Furthermore, the implementation of the method includes the following steps:

[0008] Standard address parsing: Parse the input standard address into multiple parts, including administrative divisions, roads, building groups, building numbers, room numbers, etc.

[0009] Construction of longitude, latitude and place name knowledge base: collect place names and their longitude and latitude in the region to form a knowledge base;

[0010] Non-standard address resolution: The input non-standard address is resolved into different parts, mainly based on the structure of the non-standard address itself and the standard address matching;

[0011] Address conversion: The non-standard address divided into different parts is matched with the standard address and the address in the place name knowledge base to form a standard address.

[0012] Furthermore, standard address parsing parses the input standard address and outputs it in json format;

[0013] The longitude and latitude and place name knowledge base is constructed by collecting place names and their longitude and latitude in the area through Tiandi Map or other open platforms, and outputting them in JSON format.

[0014] Furthermore, the standard address parsing is completed by combining the hidden Markov model with the string matching method; the hidden Markov model is a directed graph model. In the word segmentation algorithm, the hidden Markov model can learn from massive amounts of data and identify names of people, places, new words on the Internet, etc. one by one; on this basis, the various components in the standard address can be parsed out by manually screening common place name prefixes, suffixes, formats, etc., combined with regular expressions.

[0015] Furthermore, the non-standard address parsing first performs text cleaning, including operations such as unifying digital formats, converting simplified and traditional Chinese characters, and removing stop words, to obtain text in a normal format; then, word segmentation is performed using a method similar to standard address parsing. For the extracted word segments, address matching in the address library is performed, and typos and other operations are performed to obtain more accurate components.

[0016] Furthermore, the knowledge base is constructed as follows:

[0017] The standard address knowledge base is obtained by parsing the standard address, and each named entity and the relationship between them are recorded in JSON format;

[0018] The knowledge base of previously used place names obtains the place names and longitude and latitude information in the region by collecting open data, such as the APIs of Tiandi Map and Amap. First, the named entities existing in the standard address knowledge base are extracted, and their longitude and latitude are recorded. Then, other names of the standard place names, including former names and common names, are matched through the longitude and latitude to form a knowledge base of previously used place names.

[0019] Furthermore, the address conversion:

[0020] The components of the parsed non-standard address are matched with the entities in the standard address knowledge base and the previously used place name knowledge base to obtain the address level of each component, and finally these standardized components are spliced ​​into standard place names according to the level.

[0021] The present invention also claims protection for a knowledge base-based address standardization system, comprising:

[0022] The standard address parsing module parses the input standard address into multiple parts, including administrative divisions, roads, building groups, building numbers, and room numbers;

[0023] The latitude and longitude and place name knowledge base construction module is used to collect place names and their longitude and latitude in the region to form a knowledge base;

[0024] The non-standard address parsing module is used to parse the input non-standard address into different parts, and parse it according to the structure of the non-standard address itself and the standard address matching;

[0025] The address conversion module forms a standard address by matching the non-standard address divided into different parts with the addresses in the standard address and place name knowledge base;

[0026] The system realizes address standardization through the above-mentioned knowledge base-based address standardization method.

[0027] The present invention also claims protection for a knowledge base-based address standardization device, comprising: at least one memory and at least one processor;

[0028] The at least one memory is used to store a machine-readable program;

[0029] The at least one processor is used to call the machine-readable program to implement the above method.

[0030] The present invention also claims protection for a computer-readable medium having computer instructions stored thereon, which, when executed by a processor, causes the processor to perform the above method.

[0031] Compared with the prior art, the knowledge base-based address standardization method and system of the present invention has the following beneficial effects:

[0032] The non-standard address conversion method proposed in the present invention significantly improves the accuracy and real-time performance of address standardization by finely segmenting standard addresses, integrating multi-dimensional entity recognition such as administrative divisions, roads, building groups and building numbers, and combining latitude and longitude range verification. The present invention not only optimizes the utilization efficiency of address data in social governance, but also promotes the precise connection between public security management and public services, which has a far-reaching impact on accelerating information construction, benefiting people's livelihood and enterprise development. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a flowchart of the data label system construction process provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0035] The embodiment of the present invention provides an address standardization method based on a knowledge base, which divides the standard address into segments and extracts entity information including administrative divisions, roads (streets), building groups (communities), and building numbers; multi-name entity recognition is performed according to the latitude and longitude range of the address to improve the accuracy and real-time performance of address conversion; thereby realizing automatic conversion of non-standard addresses and associating them with standard addresses, so as to be applied to multiple fields such as social governance, public security management, and public services.

[0036] With the rapid development of natural language processing and knowledge base technologies, the standardized processing of address data has become a key link in the intelligentization of social governance. With the diversification of information sources, address data has become non-standardized and fragmented, which poses a challenge to the efficiency and accuracy of social governance. Traditional address standardization methods are limited by the wide range of geographical scope, making it difficult to achieve efficient and accurate address conversion. Natural language processing technology can effectively parse complex address information through semantic analysis and entity recognition, while knowledge base technology provides support for standard address data. Combining the two, it is possible to achieve fine division and real-time updating of address data, which not only improves the accuracy of address standardization, but also provides strong technical support for the informatization and refinement of social governance.

[0037] The implementation of this method includes the following steps:

[0038] Standard address parsing: Parse the input standard address into multiple parts such as administrative divisions, roads, building complexes, building numbers, room numbers, etc., and output them in JSON format.

[0039] Construction of longitude, latitude and place name knowledge base: collect place names and their longitude and latitude in the area through Tiandi Map or other open platforms, and output them in JSON format.

[0040] Non-standard address resolution: The input non-standard address is resolved into different parts, mainly based on the structure of the non-standard address itself and the standard address matching.

[0041] Address conversion: The non-standard address divided into different parts is matched with the standard address and the address in the place name knowledge base to form a standard address.

[0042] in,

[0043] Standard address: A list of standardized place names with a rigorous structure and complete information published by a government or other official agency;

[0044] Administrative division: an area divided into different levels for the convenience of administrative management, down to the district or town level, such as Lixia District, Jinan City, Shandong Province;

[0045] Road: An optional item in a standard address, indicating the road where a building or complex of buildings is located, such as Langchao Road and Bole Road.

[0046] Building complex: a collection of interrelated buildings located in a certain area, such as a community or a village.

[0047] Building number: The number of the road or building complex where the building is located, such as Building 2.

[0048] Room number: The number of the building where the room is located, usually composed of the floor number and the room number, such as Conference Room 8 on the 17th floor.

[0049] The standard address parsing is completed by combining the hidden Markov model with the string matching method. The hidden Markov model is a directed graph model. In the word segmentation algorithm, the hidden Markov model can learn from massive amounts of data to identify names, place names, new words on the Internet, etc.; on this basis, the various components of the standard address can be parsed out by combining regular expressions with the common place name prefixes, suffixes, formats, etc. that are manually screened.

[0050] The non-standard address parsing first cleans the text, performs operations such as digital format unification, Chinese simplified and traditional conversion, and stop word removal to obtain text in a normal format; then, word segmentation is performed using a method similar to standard address parsing. For the extracted word segments, address matching in the address library is performed, and typos are corrected to obtain more accurate components.

[0051] The knowledge base is constructed by:

[0052] The standard address knowledge base is obtained by parsing the standard address, and each named entity and the relationship between them are recorded in JSON format;

[0053] The knowledge base of previously used place names obtains the place names and longitude and latitude information in the region by collecting open data, such as the APIs of Tiandi Map and Amap. First, the named entities existing in the standard address knowledge base are extracted, and their longitude and latitude are recorded. Then, other names of the standard place names, including former names and common names, are matched through the longitude and latitude to form a knowledge base of previously used place names.

[0054] The address conversion:

[0055] The components of the parsed non-standard address are matched with the entities in the standard address knowledge base and the previously used place name knowledge base to obtain the address level of each component, and finally these standardized components are spliced ​​into standard place names according to the level.

[0056] In view of the problems that the address data sources in current social governance are diverse and of varying quality, and the existing address standardization methods have low accuracy and untimely updates due to the pursuit of national scope, this method provides a segmentation and multi-name entity recognition method based on government standardized addresses. It accurately extracts key information such as administrative divisions, roads, building groups and building numbers, and combines them with longitude and latitude ranges for identification, so as to improve the accuracy and real-time performance of address standardization, thereby promoting the refinement, efficiency and informatization of social governance.

[0057] The embodiment of the present invention also provides an address standardization system based on a knowledge base, including a knowledge base construction part and a standard address conversion part. The knowledge base construction part forms a standard address knowledge base and a used place name knowledge base through standard address resolution and non-quasi-address resolution; the standard address conversion part includes non-standard address segmentation, place name matching according to the place name knowledge base, non-standard address component division, and standard address splicing. The system realizes address standardization through the address standardization method based on the knowledge base described in the above embodiment.

[0058] The system includes:

[0059] The standard address parsing module parses the input standard address into multiple parts such as administrative divisions, roads, building complexes, building numbers, room numbers, etc., and outputs them in JSON format.

[0060] The latitude, longitude and place name knowledge base construction module collects place names and their longitude and latitude in the area through Tiandi Map or other open platforms, and outputs them in JSON format.

[0061] The non-standard address parsing module parses the input non-standard address into different parts, mainly based on the structure of the non-standard address itself and the standard address matching.

[0062] The address conversion module forms a standard address by dividing the non-standard address into different parts and matching it with the standard address and the address in the place name knowledge base.

[0063] The standard address parsing is completed by combining the hidden Markov model with the string matching method. The hidden Markov model is a directed graph model. In the word segmentation algorithm, the hidden Markov model can learn from massive amounts of data to identify names, place names, new words on the Internet, etc.; on this basis, the various components of the standard address can be parsed out by combining regular expressions with the common place name prefixes, suffixes, formats, etc. that are manually screened.

[0064] The non-standard address parsing first cleans the text, performs operations such as digital format unification, Chinese simplified and traditional conversion, and stop word removal to obtain text in a normal format; then, word segmentation is performed using a method similar to standard address parsing. For the extracted word segments, address matching in the address library is performed, and typos are corrected to obtain more accurate components.

[0065] The knowledge base is constructed by:

[0066] The standard address knowledge base is obtained by parsing the standard address, and each named entity and the relationship between them are recorded in JSON format;

[0067] The knowledge base of previously used place names obtains the place names and longitude and latitude information in the region by collecting open data, such as the APIs of Tiandi Map and Amap. First, the named entities existing in the standard address knowledge base are extracted, and their longitude and latitude are recorded. Then, other names of the standard place names, including former names and common names, are matched through the longitude and latitude to form a knowledge base of previously used place names.

[0068] The address conversion:

[0069] The components of the parsed non-standard address are matched with the entities in the standard address knowledge base and the previously used place name knowledge base to obtain the address level of each component, and finally these standardized components are spliced ​​into standard place names according to the level.

[0070] The embodiment of the present invention also provides a knowledge base-based address standardization device, comprising: at least one memory and at least one processor;

[0071] The at least one memory is used to store a machine-readable program;

[0072] The at least one processor is used to call the machine-readable program to implement the knowledge base-based address standardization method described in the above embodiment.

[0073] The embodiment of the present invention further provides a computer-readable medium, on which computer instructions are stored, and when the computer instructions are executed by a processor, the processor executes the address standardization method based on the knowledge base described in the above embodiment. Specifically, a system or device equipped with a storage medium can be provided, on which a software program code that implements the functions of any of the above embodiments is stored, and a computer (or CPU or MPU) of the system or device reads and executes the program code stored in the storage medium.

[0074] In this case, the program code itself read from the storage medium can realize the function of any one of the above-mentioned embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present invention.

[0075] The storage medium embodiments for providing the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), a magnetic tape, a non-volatile memory card, and a ROM. Alternatively, the program code can be downloaded from a server computer by a communication network.

[0076] In addition, it should be clear that the functions of any of the above embodiments can be implemented not only by executing the program code read by the computer, but also by enabling an operating system operating on the computer to complete part or all of the actual operations based on instructions from the program code.

[0077] In addition, it can be understood that the program code read from the storage medium is written to a memory provided in an expansion board inserted into the computer or written to a memory provided in an expansion unit connected to the computer, and then based on the instructions of the program code, a CPU installed on the expansion board or the expansion unit is enabled to perform part or all of the actual operations, thereby realizing the functions of any of the above-mentioned embodiments.

[0078] The present invention is shown and described in detail above through the accompanying drawings and preferred embodiments. However, the present invention is not limited to these disclosed embodiments. Based on the above multiple embodiments, those skilled in the art can know that the code review methods in the above different embodiments can be combined to obtain more embodiments of the present invention, and these embodiments are also within the protection scope of the present invention.

Claims

1. A method for address standardization based on a knowledge base, characterized in that: The standard address is divided into segments to extract entity information including administrative divisions, roads, building groups, and building numbers; multi-name entity recognition is performed based on the latitude and longitude range of the address to improve the accuracy and real-time performance of address conversion; thereby achieving automatic conversion of non-standard addresses and associating them with standard addresses.

2. The method for address standardization based on a knowledge base according to claim 1, characterized in that: The implementation of this method includes the following steps: Standard address parsing: Parse the input standard address into multiple parts, including administrative division, road, building group, building number, and room number; Construction of longitude, latitude and place name knowledge base: collect place names and their longitude and latitude in the region to form a knowledge base; Non-standard address analysis: parse the input non-standard address into different parts, and analyze it according to the structure of the non-standard address itself and the standard address matching; Address conversion: The non-standard address divided into different parts is matched with the standard address and the address in the place name knowledge base to form a standard address.

3. The method for address standardization based on a knowledge base according to claim 2, characterized in that: Standard address parsing: parse the input standard address and output it in json format; The longitude and latitude and place name knowledge base is constructed by collecting place names and their longitude and latitude in the area through Tiandi Map or other open platforms, and outputting them in JSON format.

4. The method for address standardization based on a knowledge base according to claim 2, characterized in that: The standard address parsing is accomplished by combining a hidden Markov model with a string matching method. In the word segmentation algorithm, the hidden Markov model learns from massive amounts of data to identify names of people, places, and new words on the Internet. On this basis, each component of the standard address is parsed by manually screening common place name prefixes, suffixes, and formats in combination with regular expressions.

5. The method for address standardization based on a knowledge base according to claim 2 or 4, characterized in that: The non-standard address parsing first performs text cleaning, including operations such as digital format unification, Chinese simplified and traditional conversion, and stop word removal, to obtain text in a normal format; Then, word segmentation is performed. For the extracted word segmentation, the address in the address database is matched and typos are corrected to obtain more accurate components.

6. The method for address standardization based on a knowledge base according to claim 2 or 3, characterized in that: The knowledge base is constructed by: The standard address knowledge base is obtained by parsing the standard address, and each named entity and the relationship between them are recorded in JSON format; The former place names knowledge base obtains the place names and longitude and latitude information in the region by collecting open data; first, the named entities existing in the standard address knowledge base are extracted, and their longitude and latitude are recorded, and then the other names of the standard place names, including former names and common names, are matched through the longitude and latitude to form a former place names knowledge base.

7. The method for address standardization based on a knowledge base according to claim 6, characterized in that: The address conversion: The components of the parsed non-standard address are matched with the entities in the standard address knowledge base and the previously used place name knowledge base to obtain the address level of each component, and finally these standardized components are spliced ​​into standard place names according to the level.

8. An address standardization system based on a knowledge base, characterized in that: include: The standard address parsing module parses the input standard address into multiple parts, including administrative divisions, roads, building groups, building numbers, and room numbers; The latitude and longitude and place name knowledge base construction module is used to collect place names and their longitude and latitude in the region to form a knowledge base; The non-standard address parsing module is used to parse the input non-standard address into different parts, and parse it according to the structure of the non-standard address itself and the standard address matching; The address conversion module forms a standard address by matching the non-standard address divided into different parts with the addresses in the standard address and place name knowledge base; The system realizes address standardization through the knowledge base-based address standardization method described in any one of claims 1 to 7.

9. An address standardization device based on a knowledge base, characterized in that: include: at least one memory and at least one processor; The at least one memory is used to store a machine-readable program; The at least one processor is used to call the machine-readable program to implement the method described in any one of claims 1 to 7.

10. A computer-readable medium, characterized in that The computer readable medium stores computer instructions, which, when executed by a processor, cause the processor to execute the method according to any one of claims 1 to 7.

Images