Gate address identical judgment method and device, computer equipment and storage medium

Abstract

The invention discloses a gate address similarity judgment method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining to-be-matched gate address data and gate address library data; performing district division on the to-be-matched gate address data and the gate address library data; performing address matching and / or latitude and longitude matching on the to-be-matched gate address data and the gate address library data in the same area; if matching fails, key positioning information in the to-be-matched door address data is extracted; and determining whether the to-be-matched door address data is covered or not based on the door address library data and the key positioning information. In the matching process, searching is only needed in the corresponding area, comprehensive searching in the whole gate address library is avoided, and the matching efficiency is remarkably improved. The method can accurately judge the addresses with different expressions but actually the same address, and effectively improves the matching accuracy in combination with latitude and longitude matching. And main point judgment is carried out on uncovered data, each key element of the gate address is comprehensively considered, and the reliability of gate address matching is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a method, apparatus, computer device and storage medium for judging the identity of door addresses. Background Art

[0002] Existing door address matching technologies usually adopt relatively simple and direct methods. A common method is to directly perform a full-scale comparison of address strings for all door address data to be matched in the entire door address library without any prior data partitioning or screening. This method has many problems when faced with a large amount of door address data. First, each match requires traversing the entire door address library, resulting in extremely low matching efficiency and consuming a large amount of time and computing resources. Second, in terms of address matching, relying solely on simple string comparison, it is impossible to accurately identify addresses with different expressions but actually pointing to the same location, resulting in low matching accuracy. Moreover, when judging whether a door address is covered, there is a lack of comprehensive consideration of precise location information such as longitude and latitude. Only relying on address matching, it is impossible to handle the situation where the addresses are the same but the actual locations are deviated, making the reliability of door address matching insufficient. Summary of the Invention

[0003] Based on this, it is necessary to provide a method, apparatus, computer device and storage medium for judging the identity of door addresses to solve at least one of the above-mentioned problems existing in the prior art.

[0004] In a first aspect, a method for judging the identity of door addresses is provided, including:

[0005] Obtaining the door address data to be matched and the door address library data;

[0006] Performing area division on the door address data to be matched and the door address library data;

[0007] Performing address matching and / or longitude and latitude matching on the door address data to be matched and the door address library data in the same area;

[0008] If the matching fails, extracting the key positioning information in the door address data to be matched;

[0009] Based on the door address library data and the key positioning information, determining whether the door address data to be matched is covered.

[0010] In one embodiment, the performing address matching and / or longitude and latitude matching on the door address data to be matched and the door address library data in the same area includes:

[0011] Respectively performing component recognition on the door address data to be matched and the door address library data in the same area to determine whether the addresses match based on the recognition results; and / or

[0012] Determine the distance between the longitude and latitude coordinates of the to-be-matched door address data in the same area and the longitude and latitude coordinates of the door address database data, so as to determine whether the longitude and latitude are matched based on the distance.

[0013] In one embodiment, the separately performing component recognition on the to-be-matched door address data and the door address database data in the same area to determine whether the addresses are matched based on the recognition results includes:

[0014] Perform component recognition on the to-be-matched door address data and the door address database data in the same area respectively through an address structuring model to obtain the key components corresponding to the to-be-matched door address data and the key components corresponding to the door address database data;

[0015] Compare the key components corresponding to the to-be-matched door address data and the key components corresponding to the door address database data one by one;

[0016] If the comparison is consistent, the matching is successful; otherwise, the matching fails.

[0017] In one embodiment, the separately performing component recognition on the to-be-matched door address data and the door address database data in the same area includes:

[0018] Perform word segmentation processing on the to-be-matched door address data and the door address database data in the same area respectively to obtain words or phrases;

[0019] Perform part-of-speech tagging on each word or phrase after word segmentation;

[0020] Match the to-be-matched door address data and the door address database data in the same area after part-of-speech tagging with a pre-constructed address template respectively.

[0021] In one embodiment, the determining the distance between the longitude and latitude coordinates of the to-be-matched door address data in the same area and the longitude and latitude coordinates of the door address database data to determine whether the longitude and latitude are matched based on the distance includes:

[0022] Extract the longitude and latitude coordinates from the to-be-matched door address data and the door address database data in the same area respectively;

[0023] Determine the distance between the longitude and latitude coordinates of the to-be-matched door address data in the same area and the longitude and latitude coordinates of the door address database data;

[0024] If the distance is greater than a preset distance threshold, the matching fails; otherwise, the matching is successful.

[0025] In one embodiment, before performing area division on the to-be-matched door address data and the door address database data, it further includes:

[0026] Obtain the identification information of the to-be-matched door address data;

[0027] Match the identification information with the corresponding identification information in the address library data;

[0028] If the match is successful, the address data to be matched has been covered;

[0029] If the match fails, perform the step of dividing the area of the address data to be matched and the address library data.

[0030] In one embodiment, determining whether the address data to be matched is covered based on the address library data includes:

[0031] Determine whether the key positioning information exists in the address library data;

[0032] If so, the address data to be matched is covered.

[0033] In a second aspect, there is provided an address comparison device, including:

[0034] An address data acquisition unit, configured to acquire address data to be matched and address library data;

[0035] An area division unit, configured to divide the area of the address data to be matched and the address library data;

[0036] A matching unit, configured to perform address matching and / or longitude and latitude matching on the address data to be matched and the address library data in the same area;

[0037] A key positioning information extraction unit, configured to extract the key positioning information in the address data to be matched if the match fails;

[0038] An address coverage determination unit, configured to determine whether the address data to be matched is covered based on the address library data and the key positioning information.

[0039] In a third aspect, there is provided a computer device, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor. When the processor executes the computer-readable instructions, the steps of the address comparison method as described above are implemented.

[0040] In a fourth aspect, there is provided a readable storage medium, where the readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the address comparison method as described above are implemented.

[0041] The above method, apparatus, computer device and storage medium for judging the identity of addresses, the implementation of the method includes: obtaining the address data to be matched and the address database data; dividing the area of the address data to be matched and the address database data; performing address matching and / or longitude and latitude matching on the address data to be matched and the address database data in the same area; if the matching fails, extracting the key positioning information in the address data to be matched; based on the address database data and the key positioning information, determining whether the address data to be matched is covered. In the embodiments of the present application, by dividing the area of all address data, only the corresponding area needs to be searched during matching, avoiding a comprehensive search in the entire address database, greatly saving time and computing resources, and significantly improving the matching efficiency. Using the address structured model to identify the components of the address, no longer limited to simple string comparison, can accurately judge addresses with different expressions but the same actuality, and at the same time combining longitude and latitude matching, comprehensively considering the address and location information, effectively improving the accuracy of matching. By combining address matching and longitude and latitude matching, and performing main point judgment on the uncovered data, all key elements of the address are comprehensively considered, greatly enhancing the reliability of address matching and more accurately determining whether the address data to be matched is covered. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments of the present invention. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings without creative efforts based on these drawings.

[0043] Figure 1 is a flowchart of a method for judging the identity of addresses in an embodiment of the present invention;

[0044] Figure 2 is a structural diagram of an apparatus for judging the identity of addresses in an embodiment of the present invention;

[0045] Figure 3 is a schematic diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the protection scope of the present invention.

[0047] In one embodiment, as Figure 1As shown, a method for judging the identity of door addresses is provided, including the following steps:

[0048] In step S110, the door address data to be matched and the door address database data are obtained;

[0049] Optionally, the user click operation or order data can be monitored. When a new user click operation or order data is monitored, the door address data to be matched can be extracted from the user click operation or order data. For example, when it is monitored that the user clicks on an interface element related to a certain location (such as a location marker on a map), the door address information related to this click position recorded by the system at this time is the door address data to be matched in the form of user click data. Or when the user places an order, the door address information such as the receiving address filled in belongs to the door address data to be matched in the form of order data.

[0050] Optionally, a large amount of door address data that has been sorted, reviewed, etc. and is considered accurate and effective is stored in the door address database. Door address data can be collected from multiple authoritative channels, such as the geographic information system data of government departments, the surveying and mapping results of professional surveying and mapping institutions, the data of map service providers, etc. A unified data entry standard and specification are established to uniformly stipulate the format, coding, naming, etc. of the door address data. Ensure that the entry personnel operate according to the standard to avoid data inconsistency or errors caused by human factors.

[0051] It should be noted that the door address data to be matched and the door address database data may include administrative region information (such as province, city, district), detailed address information (such as house number, road name, alley name, community name, building number, unit number, floor number, room number, etc.), geographic coordinate information (such as longitude and latitude), building information (the name of the building, type (such as residential building, commercial building, office building, school, hospital, etc.), surrounding environment information, etc.

[0052] In step S120, the door address data to be matched and the door address database data are divided into areas;

[0053] Optionally, the longitude and latitude of the door address data to be matched and the door address database data can be used as keys for connection. For example, the longitude and latitude coordinates of the door address data to be matched are (113.061426540945, 23.039234440162). Retaining two decimal places after the decimal point of the longitude and latitude, the key is constructed as: "113.06_23.03"; for the door address database data, the same key construction method is used, and each piece of door address database data corresponds to a key (an area). The door address data to be matched and the door address database data with the same key (in the same area) are connected.

[0054] Optionally, the appropriate size of the longitude and latitude grid can be determined according to the actual application scenario and accuracy requirements. For example, for the fine division of urban areas, a smaller grid interval can be set, such as 0.001 degrees. Then, based on the longitude and latitude coordinate system, the entire area can be divided into several regular grids according to the set grid size. Each grid can be uniquely identified by the longitude and latitude coordinates of its lower left corner or upper right corner. Traverse each record in the to-be-matched address data and the address database data, and determine the grid to which the record belongs according to its corresponding longitude and latitude coordinates. The to-be-matched address data and the address database data belonging to the same grid are regarded as being in the same area.

[0055] Optionally, obtain accurate administrative region boundary data from relevant departments or geographic information data providers. These data are usually stored in vector format and contain the boundary coordinate information of each administrative region. Then, traverse each record in the to-be-matched address data and the address database data, and judge which administrative region the record is located in according to its longitude and latitude coordinates. The to-be-matched address data and the address database data belonging to the same administrative region are regarded as being in the same area.

[0056] In step S130, perform address matching and / or longitude and latitude matching on the to-be-matched address data and the address database data in the same area;

[0057] Optionally, for the to-be-matched address data and the address database data in the same area, address matching and longitude and latitude matching can be performed. Address matching means that the component recognition can be respectively performed on the to-be-matched address data and the address database data in the same area through the address structuring model, and it is judged whether the to-be-matched address data and the address database data in the same area match based on the recognized components, which can effectively identify the similarity of addresses and avoid misjudgment caused by minor differences in address expressions. Longitude and latitude matching means that the longitude and latitude coordinates of the to-be-matched address data and the address database data in the same area are respectively extracted, and the distance between the two is calculated. If the distance is greater than the preset distance threshold, such as 100 meters, it is considered that the longitude and latitude are inconsistent. If the distance is less than or equal to the preset distance threshold, such as 100 meters, it is considered that the longitude and latitude are consistent. Longitude and latitude matching further verifies the consistency of the address data from the perspective of spatial position.

[0058] It should be noted that if both the address matching and the longitude and latitude matching are successful, it means that the to-be-matched address has been covered. That is, the to-be-matched address data is highly consistent with the data in the address database in terms of key information such as address and longitude and latitude, indicating that there is already a corresponding record for the to-be-matched address information in the address database, and there is no need to process it as a new address data.

[0059] In step S140, if the matching fails, extract the key positioning information in the to-be-matched address data;

[0060] Optionally, if either the address match or the latitude and longitude match fails, it indicates that the address data to be matched is not covered. At this time, for the address data to be matched that is not covered, its component analysis can be performed through the address structuring model, and key positioning information can be extracted.

[0061] Among them, the key positioning information may include key information such as roads, communities, villages, and business districts.

[0062] In step S150, based on the address database data and the key positioning information, it is determined whether the address data to be matched is covered.

[0063] It should be noted that if the key positioning information is covered, it means that there is already a corresponding record for the address information to be matched in the address database, and there is no need to process it as new address data. If the key positioning information is not covered, the address data to be matched may be regarded as new information that needs to be further processed or entered into the address database.

[0064] Optionally, the key positioning information extracted from the address data to be matched can be queried in the address database data. For example, the address data to be matched is "No. 1388, F Road" and the city is "XX City", and its main point is extracted as "F Road". Query the key positioning information of the road in the address database data where the road is "F Road" and the city is "XX City". If the query is successful, it means that the main point of the address data to be matched is covered.

[0065] The embodiment of the present application provides a method for judging the identity of addresses. The implementation of the method includes: obtaining the address data to be matched and the address database data; performing area division on the address data to be matched and the address database data; performing address matching and / or latitude and longitude matching on the address data to be matched and the address database data in the same area; if the matching fails, extracting the key positioning information in the address data to be matched; based on the address database data and the key positioning information, determining whether the address data to be matched is covered. In the embodiment of the present application, by performing area division on all address data, only the corresponding area needs to be searched during matching, avoiding a comprehensive search in the entire address database, greatly saving time and computing resources, and significantly improving the matching efficiency. Using the address structuring model to identify the components of the address, it is no longer limited to simple string comparison, and can accurately judge addresses with different expressions but the same actuality. At the same time, combined with latitude and longitude matching, considering address and location information comprehensively, the accuracy of matching is effectively improved. By combining address matching and latitude and longitude matching, and performing main point judgment on the uncovered data, all key elements of the address are comprehensively considered, greatly enhancing the reliability of address matching and more accurately determining whether the address data to be matched is covered.

[0066] In an embodiment of the present application, the address matching and / or longitude and latitude matching of the to-be-matched door address data and the door address database data in the same area includes:

[0067] Conduct component recognition on the to-be-matched door address data and the door address database data in the same area respectively, so as to determine whether the addresses match based on the recognition results; and / or

[0068] Determine the distance between the longitude and latitude coordinates of the to-be-matched door address data in the same area and the longitude and latitude coordinates of the door address database data, so as to determine whether the longitude and latitude match based on the distance.

[0069] Optionally, obtain the to-be-matched door address data and the door address database data from the same area, and the obtained to-be-matched door address data and the door address database data are complete and relatively standardized in format. Then, conduct component recognition on the to-be-matched door address data and the door address database data in the same area respectively to parse the address into multiple key components, such as province, city, district, road, house number, building name, floor, etc. Then, compare the key components of the to-be-matched door address data and the door address database data one by one, that is, province to province, city to city. If all key components can be matched or match within a reasonable error range, it is considered that the address matching is successful; as long as one key component does not match, it is determined that the address matching fails.

[0070] Optionally, obtain the to-be-matched door address data and the door address database data from the same area, and the obtained to-be-matched door address data and the door address database data are complete and relatively standardized in format. Then, extract the longitude and latitude coordinates respectively, and calculate the distance between the two based on their longitude and latitude coordinates. If the distance is greater than a preset distance threshold, such as 100 meters, it is considered that the longitude and latitude are inconsistent, that is, the matching fails. If the distance is less than or equal to the preset distance threshold, such as 100 meters, it is considered that the longitude and latitude are consistent, that is, the matching is successful.

[0071] In an embodiment of the present application, the conducting component recognition on the to-be-matched door address data and the door address database data in the same area respectively to determine whether the addresses match based on the recognition results includes:

[0072] Conduct component recognition on the to-be-matched door address data and the door address database data in the same area respectively through an address structuring model to obtain the key components corresponding to the to-be-matched door address data and the key components corresponding to the door address database data;

[0073] Compare the key components corresponding to the to-be-matched door address data and the key components corresponding to the door address database data one by one;

[0074] If the comparison is consistent, the matching is successful; otherwise, the matching fails.

[0075] Optionally, the to-be-matched address data and the address database data can be obtained from the same area, and the obtained to-be-matched address data and address database data are complete and relatively standardized in format. Then, the to-be-matched address data and the address database data in the same area can be respectively subjected to component recognition through a preset address structuring model to parse the address into multiple components. For example, "XX Building, No. XX, XX Road, C District, B City, A Province" can be decomposed into province (A), city (B City), district (C District), road name (XX Road), house number (XX No.), building name (XX Building), etc. Then, key components are determined among the multiple components, and the corresponding key components identified from the to-be-matched address data and the address database data are compared one by one. It should be noted that during the comparison process, possible expression differences need to be considered, such as the use of synonyms, abbreviations, etc. For example, "Beijing City" and "Beijing" should be regarded as the same provincial (municipal) component. If all key components can be matched or are in line within a reasonable error range, the address is considered to be successfully matched; as long as one key component does not match, it is determined that the address matching fails.

[0076] Among them, the address structuring model can be a machine learning model, which is trained through a large number of labeled address data to enable the model to learn the features and patterns of different components in the address. In practical applications, the model predicts the corresponding component types for each part according to the input address text. Or it can also be a deep learning model, such as BERT (Bidirectional Encoder Representations from Transformers). In the address structuring task, the BERT model is used to encode the address text, and then the subsequent classification layer is used to predict the address component categories to which each word or phrase belongs. Or it is a rule engine model, which parses and recognizes components of the address based on predefined component decomposition rules. These rules are formulated according to the common structures and grammatical characteristics of addresses. For example, different components are divided by judging specific keywords (such as "province", "city", "district", "road", "number", etc.) in the address.

[0077] Among them, the key components can include "road + house number", "community + building number", "village + geographical number", "business district + building number". A key component list can be pre-constructed, and then all the parsed components are grouped according to the key component list, and the grouped key component combinations are compared one by one. If there are multiple key component combinations, the key component combination with the highest priority can be selected according to the priority of the key component combination for priority matching. For example, when both "road + house number" and "community + building number" exist, if the priority of "road + house number" is higher than that of "community + building number", then "road + house number" is matched.

[0078] In an embodiment of the present application, the component recognition of the to-be-matched address data and the address database data in the same area respectively includes:

[0079] Perform word segmentation processing on the to-be-matched address data and the address database data in the same area respectively to obtain words or phrases;

[0080] Perform part-of-speech tagging on each word or phrase after word segmentation;

[0081] Match the to-be-matched address data and the address database data in the same area after part-of-speech tagging with the pre-constructed address template respectively.

[0082] Optionally, perform word segmentation processing on the to-be-matched address data and the address database data in the same area respectively, that is, split the address text into individual words or phrases. For example, for the address "No. 100, XX Road, XX District, XX City", it may be segmented into "XX City", "XX District", "XX Road", and "No. 100". Perform part-of-speech tagging on each word or phrase obtained after word segmentation to determine their grammatical roles and semantic categories in the address text. For example, "XX City" may be tagged as "place name-provincial administrative region", "XX District" as "place name-district administrative region", "XX Road" as "place name-road name", and "No. 100" as "house number". Match the to-be-matched address data and the address database data in the same area after part-of-speech tagging with the pre-constructed address template respectively. The address template is a standard pattern designed according to common address structures and components, such as the form of "[provincial administrative region][municipal administrative region][district administrative region][road name][house number]". Compare the address data with part-of-speech tagging with the template to see if it meets the structural and component requirements of the template. If it meets, the words or phrases obtained by word segmentation are used as key components.

[0083] In an embodiment of the present application, the determination of the distance between the longitude and latitude coordinates of the to-be-matched address data in the same area and the longitude and latitude coordinates of the address database data, so as to determine whether the longitude and latitude are matched based on the distance, includes:

[0084] Extract the longitude and latitude coordinates from the to-be-matched address data and the address database data in the same area respectively;

[0085] Determine the distance between the longitude and latitude coordinates of the to-be-matched address data in the same area and the longitude and latitude coordinates of the address database data;

[0086] If the distance is greater than the preset distance threshold, the matching fails; otherwise, the matching succeeds.

[0087] Optionally, extract the longitude and latitude coordinates from the to-be-matched door address data and the door address database data in the same area. The longitude and latitude coordinates are a set of values used to accurately determine a position on the Earth's surface, and each door address data usually contains the corresponding longitude and latitude information. For example, if the longitude and latitude coordinates of the to-be-matched door address data are (121.314726311243, 31.07101033333) and the longitude and latitude coordinates of the door address database data are (121.314395293983, 31.070564232869), then the distance calculated by distance calculation methods such as the Haversine formula, the cosine theorem method, etc. is 58.84m, which is less than 100m, so it is considered that these two pairs of longitude and latitude coordinates match the same.

[0088] In an embodiment of the present application, before dividing the to-be-matched door address data and the door address database data into areas, it further includes:

[0089] Obtain the identification information of the to-be-matched door address data;

[0090] Match the identification information with the corresponding identification information of the door address database data;

[0091] If the match is successful, the to-be-matched door address data has been covered;

[0092] If the match fails, perform the step of dividing the to-be-matched door address data and the door address database data into areas.

[0093] Optionally, the identification information can be the unique ID corresponding to the address data. For example, if the to-be-matched door address data is "No. XX, XX Street, XX District, XX City, XX Province", its corresponding unique ID is "000000001", and there is a piece of data in the door address database as "XX Street, XX City, XX Province", and its corresponding unique ID is also "000000001". If the unique IDs are the same, the match is successful. At this time, it means that the to-be-matched door address data has been covered and no subsequent processing is required. If the match fails, divide the to-be-matched door address data and the door address database data into areas.

[0094] In an embodiment of the present application, determining whether the to-be-matched door address data is covered based on the door address database data includes:

[0095] Determine whether the key positioning information exists in the door address database data;

[0096] If so, the to-be-matched door address data is covered.

[0097] Optionally, the key location information may be the main point in the address, such as main location information like roads, residential communities, villages, business districts, etc. For example: The address data to be matched is "No. 1388, Road F", and the city is "XX City", and its main point is extracted as "Road F". Query the road main point with "Road F" and the city of "XX City" in the address database. If the query is successful, it means that the main point of the address data to be matched is covered.

[0098] In the embodiments of the present application, by dividing all address data into regions, only searching within the corresponding region during matching avoids a comprehensive search in the entire address database, greatly saving time and computing resources and significantly improving the matching efficiency. Using the address structuring model to identify the components of the address, no longer limited to simple string comparison, can accurately judge addresses with different expressions but the same actual meaning. At the same time, combined with latitude and longitude matching, comprehensively considering the address and location information, effectively improves the accuracy of matching. By combining address matching and latitude and longitude matching, and judging the main point of the uncovered data, all key elements of the address are comprehensively considered, greatly enhancing the reliability of address matching and more accurately determining whether the address data to be matched is covered.

[0099] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0100] In one embodiment, a device for judging the identity of addresses is provided, and this device for judging the identity of addresses corresponds one-to-one with the method for judging the identity of addresses in the above embodiments. As Figure 2 shown, this device for judging the identity of addresses includes an address data acquisition unit 10, a region division unit 20, a matching unit 30, a key location information extraction unit 40, and an address coverage determination unit 50. The detailed description of each functional module is as follows:

[0101] The address data acquisition unit 10 is used to acquire the address data to be matched and the address database data;

[0102] The region division unit 20 is used to divide regions for the address data to be matched and the address database data;

[0103] The matching unit 30 is used to perform address matching and / or latitude and longitude matching on the address data to be matched and the address database data in the same region;

[0104] The key location information extraction unit 40 is used to extract the key location information in the address data to be matched if the matching fails;

[0105] The address coverage determination unit 50 is used to determine whether the address data to be matched is covered based on the address database data and the key location information.

[0106] In an embodiment of the present application, the matching unit 30 is further configured to:

[0107] Perform component recognition on the to-be-matched address data and the address database data in the same area respectively, so as to determine whether the addresses match based on the recognition results; and / or

[0108] Determine the distance between the longitude and latitude coordinates of the to-be-matched address data and the longitude and latitude coordinates of the address database data in the same area, so as to determine whether the longitude and latitude match based on the distance.

[0109] In an embodiment of the present application, the matching unit 30 is further configured to:

[0110] Perform component recognition on the to-be-matched address data and the address database data in the same area respectively through an address structuring model, so as to obtain the key components corresponding to the to-be-matched address data and the key components corresponding to the address database data;

[0111] Compare the key components corresponding to the to-be-matched address data and the key components corresponding to the address database data one by one;

[0112] If the comparison is consistent, the matching is successful; otherwise, the matching fails.

[0113] In an embodiment of the present application, the matching unit 30 is further configured to:

[0114] Perform word segmentation processing on the to-be-matched address data and the address database data in the same area respectively, so as to obtain words or phrases

[0115] Perform part-of-speech tagging on each word or phrase after word segmentation;

[0116] Match the to-be-matched address data and the address database data in the same area after part-of-speech tagging with a pre-constructed address template respectively.

[0117] In an embodiment of the present application, the matching unit 30 is further configured to:

[0118] Extract the longitude and latitude coordinates from the to-be-matched address data and the address database data in the same area respectively;

[0119] Determine the distance between the longitude and latitude coordinates of the to-be-matched address data and the longitude and latitude coordinates of the address database data in the same area;

[0120] If the distance is greater than a preset distance threshold, the matching fails; otherwise, the matching is successful.

[0121] In an embodiment of the present application, the device further includes an identification matching unit, configured to:

[0122] Obtain the identification information of the to-be-matched door address data;

[0123] Match the identification information with the identification information corresponding to the door address library data;

[0124] If the match is successful, the to-be-matched door address data has been covered;

[0125] If the match fails, perform the step of dividing the to-be-matched door address data and the door address library data into areas.

[0126] In an embodiment of the present application, the door address coverage determination unit 50 is further configured to:

[0127] Determine whether the key positioning information exists in the door address library data;

[0128] If so, the to-be-matched door address data is covered.

[0129] In the embodiments of the present application, by dividing all door address data into areas, only the corresponding area needs to be searched during matching, avoiding a comprehensive search in the entire door address library, greatly saving time and computing resources, and significantly improving the matching efficiency. Using the address structuring model to identify the components of the address, it is no longer limited to simple string comparison, and can accurately judge addresses with different expressions but the same actual meaning. At the same time, combined with latitude and longitude matching, comprehensively considering the address and location information, effectively improving the accuracy of matching. By combining address matching and latitude and longitude matching, and making a main point judgment on the uncovered data, all key elements of the door address are comprehensively considered, greatly enhancing the reliability of the door address matching and more accurately determining whether the to-be-matched door address data is covered.

[0130] For the specific limitations of the door address identity determination device, reference can be made to the limitations of the door address identity determination method in the above text, which will not be elaborated here. Each module in the above door address identity determination device can be implemented in whole or in part through software, hardware, and their combinations. The above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0131] In one embodiment, a computer device is provided. The computer device can be a terminal device, and its internal structure diagram can be as Figure 3As shown in the figure. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a readable storage medium. The readable storage medium stores computer-readable instructions. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer-readable instructions are executed by the processor, a method for judging the same door address is implemented. The readable storage medium provided in this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.

[0132] In an embodiment of the present application, a computer device is provided, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor. When the processor executes the computer-readable instructions, the steps of the method for judging the same door address as described above are implemented.

[0133] In an embodiment of the application, a readable storage medium is provided. The readable storage medium stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps of the method for judging the same door address as described above are implemented.

[0134] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through computer-readable instructions. The computer-readable instructions can be stored in a non-volatile readable storage medium or a volatile readable storage medium. When the computer-readable instructions are executed, they can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or an external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0135] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0136] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for determining the sameness of a gate address, characterized in that: The method comprises: Obtaining the gate address data to be matched and the gate address library data; Dividing the to-be-matched gate address data and the gate address library data into zones; Performing address matching and / or longitude and latitude matching on the to-be-matched gate address data and gate address library data in the same area; If the match fails, extract the key positioning information in the to-be-matched door address data; Based on the gate address library data and the key positioning information, determine whether the gate address data to be matched is covered.

2. The method for determining the same door address as claimed in claim 1, characterized in that: The address matching and / or longitude and latitude matching of the to-be-matched gate address data and the gate address library data in the same area includes: Respectively perform component identification on the to-be-matched gate address data and gate address library data in the same area, so as to determine whether the addresses match based on the identification results; and / or Determine the distance between the longitude and latitude coordinates of the gate address data to be matched and the longitude and latitude coordinates of the gate address library data in the same area, so as to determine whether the longitude and latitude match based on the distance.

3. The door address identification method as claimed in claim 2, characterized in that: The component identification is performed on the to-be-matched gate address data and the gate address library data in the same area respectively, so as to determine whether the addresses match based on the identification results, including: Using the address structured model, component identification is performed on the to-be-matched gate address data and the gate address library data in the same area to obtain key components corresponding to the to-be-matched gate address data and key components corresponding to the gate address library data; The key components corresponding to the to-be-matched portal address data and the key components corresponding to the portal address library data are compared one by one; If the comparison is consistent, the match is successful, otherwise, the match fails.

4. The method for determining the same door address as claimed in claim 3, characterized in that: The component identification of the to-be-matched gate address data and the gate address library data in the same area respectively includes: Perform word segmentation on the matching gate address data and gate address database data in the same area to obtain words or phrases Perform part-of-speech tagging on each word or phrase after word segmentation; The to-be-matched door address data and door address library data in the same area after part-of-speech tagging are matched with the pre-built address templates respectively.

5. The method for determining the same door address as claimed in claim 2, characterized in that: The determining of the distance between the longitude and latitude coordinates of the to-be-matched gate address data and the longitude and latitude coordinates of the gate address database data in the same area, and determining whether the longitude and latitude match based on the distance, includes: Extracting longitude and latitude coordinates from the to-be-matched gate address data and the gate address library data respectively in the same area; Determine the distance between the longitude and latitude coordinates of the to-be-matched gate address data and the longitude and latitude coordinates of the gate address database data in the same area; If the distance is greater than a preset distance threshold, the match fails; otherwise, the match succeeds.

6. The method for determining the same door address as claimed in claim 1, characterized in that: Before dividing the to-be-matched gate address data and the gate address library data into zones, the method further includes: Obtaining identification information of the gate address data to be matched; Matching the identification information with the identification information corresponding to the gate address library data; If the match is successful, the gate address data to be matched has been covered; If the matching fails, the step of dividing the gate address data to be matched and the gate address library data into zones is performed.

7. The method for determining the same door address as claimed in claim 1, characterized in that: The determining, based on the gate address library data, whether the gate address data to be matched is covered includes: Determine whether the key positioning information exists in the portal address database data; If so, the gate address data to be matched is overwritten.

8. A door address identification device, characterized in that: The device comprises: A gate address data acquisition unit, used to acquire the gate address data to be matched and the gate address library data; A zone division unit, used for performing zone division on the gate address data to be matched and the gate address library data; A matching unit, used for performing address matching and / or longitude and latitude matching on the to-be-matched gate address data and gate address library data in the same area; A key positioning information extraction unit, used to extract the key positioning information in the to-be-matched gate address data if the matching fails; The gate address coverage determination unit is used to determine whether the gate address data to be matched is covered based on the gate address library data and the key positioning information.

9. A computer device comprising a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, characterized in that: When the processor executes the computer-readable instructions, the steps of the gate address identification method as described in any one of claims 1 to 7 are implemented.

10. A readable storage medium storing computer-readable instructions, characterized in that: When the computer-readable instructions are executed by a processor, the steps of the gate address identification method as described in any one of claims 1 to 7 are implemented.

Images