Door address coordinate error correction method and device, computer equipment and storage medium
By extracting and aggregating gate address features, coordinate clustering and prediction are performed, the error problem in the geographic name and geographic coordinate mapping library is solved, and the positioning accuracy and user experience are improved.
Patent Information
- Application Number
- CN202411870881.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-17
- Publication Date
- 2025-03-25
AI Technical Summary
In the prior art, there are errors in the mapping library of geographical names and geographic coordinates, resulting in low positioning accuracy and affecting user experience.
By obtaining the gate address characteristics of the target gate address, extracting the valid address information, aggregating the valid address information according to the name, performing coordinate clustering, obtaining adjacent gate addresses for coordinate prediction, and determining whether the gate address is incorrect.
It improves the accuracy of door address coordinates, enhances the generalization ability of error mining, and improves positioning accuracy and user experience.
Smart Images
Figure CN119691562A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing technology, and in particular to a gate address coordinate error correction method, device, computer equipment and storage medium. Background Art
[0002] With the development of mobile Internet and geographic information technology, people's daily lives have undergone tremendous changes. Navigation, logistics, taxi-hailing, etc. are all perfectly integrated with geographic information technology.
[0003] Geographic location coding is an important part of geographic information technology. For example, when a user takes a taxi, he enters a geographical name, XX University, and the taxi app needs to give the geographical coordinates (i.e. longitude and latitude) based on the geographical name XX University. Then it will navigate based on the geographical coordinates of XX University and the coordinates of the user. In logistics and freight, the freight APP also needs to give the coordinates of the loading and unloading locations provided in the user's order, and then plan the route.
[0004] Geolocation coding relies on the mapping of geographic names to geographic coordinates. There are generally two types of geographic names: POI (Point of Interest) and gate address (i.e. address). However, there are often some errors in the current mapping library of geographic names to geographic coordinates. For example, one geographic coordinate corresponds to multiple geographic names, or there are multiple ways to express geographic names. Using incorrect data will affect all subsequent processes, resulting in low positioning accuracy and affecting user experience. Summary of the invention
[0005] Based on this, it is necessary to provide a gate address coordinate error correction method, device, computer equipment and storage medium to address the above technical problems, so as to solve at least one problem existing in the above-mentioned prior art.
[0006] In a first aspect, a gate address coordinate error correction method is provided, comprising:
[0007] Acquire the door address characteristics of the target door address, and extract the valid address information from the door address characteristics;
[0008] Aggregating the valid address information according to the name to obtain a name-associated gate address set;
[0009] Performing coordinate clustering on the name-associated door address set to obtain a coordinate clustering result;
[0010] Acquire the adjacent gate addresses of the target gate address, and predict the coordinates of the target gate address based on the adjacent gate addresses to obtain the predicted coordinates of the target gate address;
[0011] Based on the gate address features, the coordinate clustering results and the predicted coordinates, it is determined whether the target gate address is incorrect.
[0012] In one embodiment, the coordinate clustering of the name-associated portal address set includes:
[0013] Determine the initial clustering distance parameter;
[0014] Based on the initial clustering distance parameter, coordinate clustering is performed on each name-associated door address set to obtain a cluster set;
[0015] When the cluster set does not meet the preset clustering condition, the initial cluster distance parameter is adjusted, and the coordinates of each name-associated door address set are clustered again based on the adjusted cluster distance parameter until the cluster set meets the preset clustering condition, and then clustering is stopped.
[0016] In one embodiment, the preset clustering condition includes:
[0017] The proportion of the number of elements in the largest cluster in the cluster set to the total number of elements is greater than a preset ratio threshold; or
[0018] The clustering distance parameter is greater than a preset distance parameter threshold.
[0019] In one embodiment, after performing coordinate clustering on the name-associated portal address set and obtaining the coordinate clustering result, the method includes:
[0020] The coordinate clustering result is corrected by the interest surface fence to merge the clustering points in the same fence.
[0021] In one embodiment, the target door address includes a door number, and obtaining the adjacent door address of the target door address includes:
[0022] When the house number is an odd number, obtaining the house address corresponding to the odd house number adjacent to the house number as the adjacent house address;
[0023] When the house number is an even number, the house address corresponding to the even house number adjacent to the house number is obtained as the adjacent house address.
[0024] In one embodiment, determining whether the target door address is incorrect based on the name-associated door address set, the coordinate clustering feature, and the predicted coordinates includes:
[0025] Inputting the door address features, coordinate clustering features and predicted coordinates into a pre-trained classification model for prediction processing;
[0026] Based on the prediction result output by the pre-trained classification model, it is determined whether the target door address is incorrect.
[0027] In one embodiment, extracting effective address information from the target gate address includes:
[0028] Performing structured segmentation on the target portal address;
[0029] The effective address information is extracted from the segmented target gate address, and the extracted effective address is normalized.
[0030] In a second aspect, a gate address coordinate error correction device is provided, comprising:
[0031] An effective address information extraction unit, used to obtain a door address feature of a target door address, and extract effective address information from the door address feature;
[0032] A name aggregation unit, used to aggregate the valid address information according to the name to obtain a name-associated gate address set;
[0033] A coordinate aggregation unit, used for performing coordinate clustering on the name-associated door address set to obtain a coordinate clustering result;
[0034] A coordinate prediction unit, used to obtain the adjacent gate addresses of the target gate address, and perform coordinate prediction on the target gate address based on the adjacent gate addresses to obtain the predicted coordinates of the target gate address;
[0035] The gate address error correction unit is used to determine whether the target gate address is incorrect based on the gate address characteristics, coordinate clustering results and the predicted coordinates.
[0036] In a third aspect, a computer device is provided, comprising a memory, a processor, and computer-readable instructions stored in the memory and running on the processor, wherein the processor implements the gate address coordinate error correction method as described above when executing the computer-readable instructions.
[0037] In a fourth aspect, a readable storage medium is provided, on which computer-readable instructions are stored, characterized in that when the computer-readable instructions are executed by a processor, the gate address coordinate error correction method as described above is implemented.
[0038] The above-mentioned gate address coordinate error correction method, device, computer equipment and storage medium, the method implementation includes: obtaining the gate address feature of the target gate address, extracting valid address information from the gate address feature; aggregating the valid address information according to the name to obtain a name-associated gate address set; performing coordinate clustering on the name-associated gate address set to obtain a coordinate clustering result; obtaining the adjacent gate addresses of the target gate address, predicting the coordinates of the target gate address based on the adjacent gate addresses, and obtaining the predicted coordinates of the target gate address; determining whether the target gate address is incorrect based on the gate address feature, the coordinate clustering result and the predicted coordinates. In the embodiment of the present application, after the gate address is aggregated by name, the coordinates are clustered for each name-associated gate address set, and the surrounding gate address information is introduced to predict the current gate address, which adds more features, and error mining can also be performed for a smaller number of associated gate address clusters. The accuracy of the gate address is predicted based on the above clustering, surrounding gate addresses and other features, which improves the generalization ability of error mining. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0040] Figure 1 It is a flow chart of a gate address coordinate error correction method in one embodiment of the present application;
[0041] Figure 2 This is an implementation environment diagram of a coordinate clustering method in an embodiment of the present application;
[0042] Figure 3 It is a structural schematic diagram of a door address coordinate error correction device in one embodiment of the present application;
[0043] Figure 4 It is a schematic diagram of a computer device in one embodiment of the present application. DETAILED DESCRIPTION
[0044] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0045] In one embodiment, if Figure 1 As shown, a gate address coordinate error correction method is provided, comprising the following steps:
[0046] In step S110, the door address feature of the target door address is obtained, and the valid address information is extracted from the door address feature;
[0047] In the embodiment of the present application, the door address refers to an address, which mainly includes the following: No. XX, XX Road, Building XX, XX Community, No. XX, XX Village, etc. The door address database often stores multiple associated door addresses, such as No. 36, XX 2nd Road, City A, No. 36, XX 2nd Road, City A, etc.
[0048] Optionally, after obtaining the target gate address, the target gate address can be structured and segmented, for example, by using named entity recognition (bilstm+crf), etc. The target gate address can be segmented into local address information such as province, city, district, street, township, village, road, house number, community, building, POI (point of interest), etc.
[0049] Then, extract the valid address information from each segmented address local information. The valid address information refers to the lowest level address information, such as road + house number, community + building, village + number, etc. For example, the corresponding valid address information in the above example is: No. 36, XX 2nd Road, Building No. 5, XX Community, and No. 165, XX Village.
[0050] It should be noted that after extracting the valid address information, the valid address information may be normalized, for example, uppercase and lowercase letters, numbers, names, etc. may be rewritten in a unified format.
[0051] In step S120, the valid address information is aggregated according to the name to obtain a name-associated portal address set;
[0052] In the embodiment of the present application, all valid address information obtained is subjected to text clustering according to the name, and a name-associated address set in the same district or county can be obtained. Exemplarily, within the same district (or county), for all valid address information obtained, it is determined whether they are exactly the same. If so, they are represented as associated addresses and can be combined into a set. For example, XX Metal Products Company, No. 36, XX 2nd Road, No. 36, XX 2nd Road, XX 2nd Road, A City, etc. can be combined into a name-associated address set.
[0053] Among them, the name-associated portal address set may include multiple ones.
[0054] In step S130, coordinate clustering is performed on the name-associated portal address set to obtain a coordinate clustering result;
[0055] In an embodiment of the present application, a density clustering algorithm (DBSCAN) can be used to cluster the coordinates within a set of gate addresses associated with the same name. It is understandable that DBSCAN needs to specify a distance parameter for clustering. Due to the characteristics of the gate address itself, the distances of different gate addresses vary greatly. If the gate address (No. xx, xx Road) points to an AOI (area of interest) such as a logistics park or a community, since the range of this AOI is very large, DBSCAN needs to specify a larger distance parameter to achieve better clustering, otherwise the correct data cannot be clustered together. If the gate address points to an ordinary POI, such as a restaurant (No. xx, xx Road) or a building (Building xx, xx Community), this type of POI has a smaller range and needs to specify a smaller distance parameter, otherwise the wrong data will also be clustered together.
[0056] In step S140, the adjacent gate addresses of the target gate address are obtained, and the coordinates of the target gate address are predicted based on the adjacent gate addresses to obtain the predicted coordinates of the target gate address;
[0057] In the embodiment of the present application, the neighboring gate addresses of the target gate address can be obtained by recalling the gate address data of the surrounding gate addresses of the target gate address, for example, No. 36, XX 2nd Road, and No. 38, XX 2nd Road, No. 42, and No. 41, XX 2nd Road, etc., which are recalled in the surrounding area. Then, based on the neighboring gate addresses such as No. 38, XX 2nd Road, No. 42, and No. 41, XX 2nd Road, etc. recalled in the surrounding area, the corresponding coordinates of each neighboring gate address, such as the longitude and latitude coordinates, can be determined, and then the longitude and latitude coordinates of the target gate address can be predicted based on the longitude and latitude coordinates.
[0058] For example, the target gate address is No. 36, XX 2nd Road. The surrounding area recalls No. 38, XX 2nd Road (set as n38, longitude and latitude coordinates are lon38, lat38) and No. 42, XX 2nd Road (set as n42, longitude and latitude coordinates are lon42, lat42). The longitude and latitude prediction formula of No. 36, XX 2nd Road can be as follows:
[0059]
[0060] In step S150, based on the gate address features, the coordinate clustering results and the predicted coordinates, it is determined whether the target gate address is incorrect.
[0061] In an embodiment of the present application, a prediction model can be constructed, such as a binary classification prediction model, such as a gradient boosting tree (GBDT), and the name-associated gate address set, the coordinate clustering result, and the predicted coordinates are input into the prediction model for binary classification prediction, and the probability of correctness or error can be output, so that it can be determined whether the target gate address is correct, so as to achieve error correction processing of the target gate address. Alternatively, the name-associated gate address set, the coordinate clustering result, and the predicted coordinates can be comprehensively compared and analyzed to determine whether the target gate address is correct, thereby determining the wrong gate address.
[0062] In an embodiment of the present application, a gate address coordinate error correction method is provided, including: obtaining the gate address feature of the target gate address, extracting valid address information from the gate address feature; aggregating the valid address information according to the name to obtain a name-associated gate address set; performing coordinate clustering on the name-associated gate address set to obtain a coordinate clustering result; obtaining the adjacent gate addresses of the target gate address, predicting the coordinates of the target gate address based on the adjacent gate addresses, and obtaining the predicted coordinates of the target gate address; determining whether the target gate address is incorrect based on the gate address feature, the coordinate clustering result, and the predicted coordinates. In an embodiment of the present application, after the gate address is aggregated by name, coordinate clustering is performed on each name-associated gate address set, and the surrounding gate address information is introduced to predict the current gate address, which adds more features, and error mining can also be performed for a smaller number of associated gate address clusters. Based on the above clustering, surrounding gate address and other features, the accuracy of the gate address is predicted, which improves the generalization ability of error mining.
[0063] In one embodiment of the present application, the coordinate clustering of the name-associated portal address set includes:
[0064] Determine the initial clustering distance parameter;
[0065] Based on the initial clustering distance parameter, coordinate clustering is performed on each name-associated door address set to obtain a cluster set;
[0066] When the cluster set does not meet the preset clustering condition, the initial cluster distance parameter is adjusted, and the coordinates of each name-associated door address set are clustered again based on the adjusted cluster distance parameter until the cluster set meets the preset clustering condition, and then clustering is stopped.
[0067] Optionally, the density clustering algorithm (DBSCAN) can be used to cluster the coordinates within the set of gate addresses associated with the same name. Understandably, DBSCAN needs to specify a distance parameter for clustering. Due to the characteristics of the gate address itself, the distances of different gate addresses vary greatly. If the gate address (No. xx, xx Road) points to an AOI (area of interest) such as a logistics park or a community, since the range of this AOI is very large, DBSCAN needs to specify a larger distance parameter to achieve better clustering, otherwise the correct data cannot be clustered together. If the gate address points to an ordinary POI, such as a restaurant (No. xx, xx Road) or a building (Building xx, xx Community), this type of POI has a smaller range and needs to specify a smaller distance parameter, otherwise the wrong data will also be clustered together.
[0068] Therefore, if at least 60% of the gate addresses in a name-associated gate address set are correct, then more than 60% of the gate addresses in the associated gate address set can be clustered together. Therefore, an initial clustering distance parameter can be set first, for example, 30 meters, see Figure 2 , the gray solid circles represent clustering points, and the hollow circles represent clusters. During the clustering process, the clustering distance parameter in the previous clustering process can be continuously expanded, and the coordinates of each name-associated door address set are clustered again based on the expanded clustering distance parameter until the cluster set meets the preset clustering condition, and then the clustering is stopped.
[0069] In an embodiment of the present application, the preset clustering condition includes:
[0070] The proportion of the number of elements in the largest cluster in the cluster set to the total number of elements is greater than a preset ratio threshold; or
[0071] The clustering distance parameter is greater than a preset distance parameter threshold.
[0072] Optionally, clustering may be stopped when the number of elements in the largest cluster in the cluster set accounts for more than a preset ratio threshold, such as more than 60%. Alternatively, a clustering distance parameter threshold may be set, that is, when the clustering distance parameter reaches the clustering distance parameter threshold, such as 300 meters, clustering is stopped.
[0073] In an embodiment of the present application, after performing coordinate clustering on the name-associated portal address set and obtaining the coordinate clustering result, the method includes:
[0074] The coordinate clustering result is corrected by using the interest surface fence.
[0075] Optionally, the coordinate clustering results after aggregation can be corrected again through the interest surface fence. For example, if the target gate address points to a logistics park, an interest surface fence can be established based on the coordinate information of the logistics park to determine whether the clustering points in the coordinate clustering results are within the interest surface fence. The clustering points outside the coordinate fence of the interest surface can be excluded, and the clustering points in the same fence can be merged.
[0076] In one embodiment of the present application, the target door address includes a house number, and obtaining an adjacent door address of the target door address includes:
[0077] When the house number is an odd number, obtaining the house address corresponding to the odd house number adjacent to the house number as the adjacent house address;
[0078] When the house number is an even number, the house address corresponding to the even house number adjacent to the house number is obtained as the adjacent house address.
[0079] Optionally, when predicting the target gate address through the surrounding gate addresses, due to the habit of setting house numbers, many roads have odd and even numbers on both sides. Therefore, if the house number of the target gate address is odd, the two closest odd gate addresses can be selected to predict the coordinates of the target gate address. If the house number of the target gate address is even, the two closest even gate addresses can be selected to predict the coordinates of the target gate address.
[0080] In one embodiment of the present application, determining whether the target door address is incorrect based on the name-associated door address set, the coordinate clustering feature, and the predicted coordinates includes:
[0081] Inputting the door address features, coordinate clustering features and predicted coordinates into a pre-trained classification model for prediction processing;
[0082] Based on the prediction result output by the pre-trained classification model, it is determined whether the target door address is incorrect.
[0083] Optionally, a prediction model can be constructed, such as a binary classification prediction model, such as a gradient boosted tree (GBDT). The name-associated gate address set, coordinate clustering results, and predicted coordinates are input into the prediction model for binary classification prediction, and the probability of correctness or error can be output, so as to determine whether the target gate address is correct, so as to implement error correction processing for the target gate address.
[0084] In one embodiment of the present application, extracting effective address information from the target gate address includes:
[0085] Performing structured segmentation on the target portal address;
[0086] The effective address information is extracted from the segmented target gate address, and the extracted effective address is normalized.
[0087] Optionally, after obtaining the target door address, the target door address can be structured and segmented, for example, by using named entity recognition (bilstm+crf) and the like. The target door address can be segmented into local address information such as province, city, district, street, township, village, road, house number, community, building, POI (point of interest), etc. For example, XX Metal Products Company, No. 36, XX 2nd Road, City A. It will be segmented into: city: A; road: XX 2nd Road; road_number: No. 36; POI:: XX Metal Products Company.
[0088] For example, Building 5, XX District, XX Community, City B. It will be divided into: city: City B; ad_name: XX District; building: XX Community; building_number: Building 5.
[0089] For example, No. 165, XX Village, XX District, City C. It will be divided into: city: City C; ad_name: XX District; community:: XX Village; location_number: No. 165.
[0090] In the embodiment of the present application, after the name aggregation of the gate address, the coordinate clustering is performed on each name-associated gate address set, and the surrounding gate address information is introduced to predict the current gate address, adding more features. For a small number of associated gate address clusters, error mining can also be performed. Based on the above clustering, surrounding gate address and other features, the accuracy of the gate address is predicted, which improves the generalization ability of error mining.
[0091] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0092] In one embodiment, a gate address coordinate error correction device is provided, and the gate address coordinate error correction device corresponds to the gate address coordinate error correction method in the above embodiment. Figure 3 As shown, the gate address coordinate error correction device includes an effective address information extraction unit 10, a name aggregation unit 20, a coordinate aggregation unit 30, a coordinate prediction unit 40 and a gate address error correction unit 50. The functional modules are described in detail as follows:
[0093] The effective address information extraction unit 10 is used to obtain the door address characteristics of the target door address and extract the effective address information from the door address characteristics;
[0094] A name aggregation unit 20, configured to aggregate the valid address information according to the name to obtain a name-associated gate address set;
[0095] A coordinate aggregation unit 30 is used to perform coordinate clustering on the name-associated door address set to obtain a coordinate clustering result;
[0096] A coordinate prediction unit 40 is used to obtain the adjacent gate addresses of the target gate address, and perform coordinate prediction on the target gate address based on the adjacent gate addresses to obtain the predicted coordinates of the target gate address;
[0097] The gate address error correction unit 50 is used to determine whether the target gate address is incorrect based on the gate address characteristics, the coordinate clustering result and the predicted coordinates.
[0098] In one embodiment of the present application, the coordinate aggregation unit 30 is further used for:
[0099] Determine the initial clustering distance parameter;
[0100] Based on the initial clustering distance parameter, coordinate clustering is performed on each name-associated door address set to obtain a cluster set;
[0101] When the cluster set does not meet the preset clustering condition, the initial cluster distance parameter is adjusted, and the coordinates of each name-associated door address set are clustered again based on the adjusted cluster distance parameter until the cluster set meets the preset clustering condition, and then clustering is stopped.
[0102] In an embodiment of the present application, the preset clustering condition includes:
[0103] The proportion of the number of elements in the largest cluster in the cluster set to the total number of elements is greater than a preset ratio threshold; or
[0104] The clustering distance parameter is greater than a preset distance parameter threshold.
[0105] In one embodiment of the present application, the coordinate clustering correction unit includes:
[0106] The coordinate clustering result is corrected by using the interest surface fence.
[0107] In one embodiment of the present application, the target door address includes a door number, and the coordinate prediction unit 40 is further used to:
[0108] When the house number is an odd number, obtaining the house address corresponding to the odd house number adjacent to the house number as the adjacent house address;
[0109] When the house number is an even number, the house address corresponding to the even house number adjacent to the house number is obtained as the adjacent house address.
[0110] In one embodiment of the present application, the gate address error correction unit 50 is further used for:
[0111] Inputting the door address features, coordinate clustering features and predicted coordinates into a pre-trained classification model for prediction processing;
[0112] Based on the prediction result output by the pre-trained classification model, it is determined whether the target door address is incorrect.
[0113] In one embodiment of the present application, the effective address information extraction unit 10 is further used to:
[0114] Performing structured segmentation on the target portal address;
[0115] The effective address information is extracted from the segmented target gate address, and the extracted effective address is normalized.
[0116] In the embodiment of the present application, after the name aggregation of the gate address, the coordinate clustering is performed on each name-associated gate address set, and the surrounding gate address information is introduced to predict the current gate address, adding more features. For a small number of associated gate address clusters, error mining can also be performed. Based on the above clustering, surrounding gate address and other features, the accuracy of the gate address is predicted, which improves the generalization ability of error mining.
[0117] The specific definition of the gate address coordinate error correction device can be found in the definition of the gate address coordinate error correction method above, which will not be repeated here. Each module in the above-mentioned gate address coordinate error correction device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
[0118] In one embodiment, a computer device is provided. The computer device may be a terminal device, and its internal structure diagram may be as follows: Figure 4 As shown. 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 gate address coordinate error correction method is implemented. The readable storage medium provided in this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.
[0119] 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 gate address coordinate error correction method described above are implemented.
[0120] In an embodiment of the application, a readable storage medium is provided, wherein the readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the gate address coordinate error correction method as described above are implemented.
[0121] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through computer-readable instructions, and 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 may include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or 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 (DDRSDRAM), 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.
[0122] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by 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.
[0123] The embodiments described above 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 aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions 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 gate address coordinate error correction method, characterized in that: The method comprises: Acquire the gate address feature of the target gate address, and extract the valid address information from the target gate address; Aggregating the valid address information according to the name to obtain a name-associated gate address set; Performing coordinate clustering on the name-associated door address set to obtain a coordinate clustering result; Acquire the adjacent gate addresses of the target gate address, and predict the coordinates of the target gate address based on the adjacent gate addresses to obtain the predicted coordinates of the target gate address; Based on the gate address features, coordinate clustering results and predicted coordinates, determine whether the target gate address is incorrect.
2. The gate address coordinate error correction method according to claim 1, characterized in that: The coordinate clustering of the name-associated door address set includes: Determine the initial clustering distance parameter; Based on the initial clustering distance parameter, coordinate clustering is performed on each name-associated door address set to obtain a cluster set; When the cluster set does not meet the preset clustering condition, the initial cluster distance parameter is adjusted, and the coordinates of each name-associated door address set are clustered again based on the adjusted cluster distance parameter until the cluster set meets the preset clustering condition, and then clustering is stopped.
3. The gate address coordinate error correction method according to claim 2, characterized in that: The preset clustering conditions include: The proportion of the number of elements in the largest cluster in the cluster set to the total number of elements is greater than a preset ratio threshold; or The clustering distance parameter is greater than a preset distance parameter threshold.
4. The door address coordinate error correction method according to claim 1 or 2, characterized in that: After performing coordinate clustering on the name-associated portal address set to obtain the coordinate clustering result, the method includes: The coordinate clustering result is corrected by using the interest surface fence.
5. The gate address coordinate error correction method according to claim 1, characterized in that: The target door address includes a door number, and the step of obtaining an adjacent door address of the target door address includes: When the house number is an odd number, obtaining the house address corresponding to the odd house number adjacent to the house number as the adjacent house address; When the house number is an even number, the house address corresponding to the even house number adjacent to the house number is obtained as the adjacent house address.
6. The gate address coordinate error correction method according to claim 1, characterized in that: Based on the name-associated door address set, the coordinate clustering feature and the predicted coordinates, determining whether the target door address is incorrect includes: Inputting the door address features, coordinate clustering features and predicted coordinates into a pre-trained classification model for prediction processing; Based on the prediction result output by the pre-trained classification model, it is determined whether the target door address is incorrect.
7. The gate address coordinate error correction method according to claim 1, characterized in that: The extracting effective address information from the target gate address includes: Performing structured segmentation on the target portal address; The effective address information is extracted from the segmented target gate address, and the extracted effective address is normalized.
8. A door address coordinate error correction device, characterized in that: The device comprises: An effective address information extraction unit, used to obtain a door address feature of a target door address, and extract effective address information from the door address feature; A name aggregation unit, used to aggregate the valid address information according to the name to obtain a name-associated gate address set; A coordinate aggregation unit, used for performing coordinate clustering on the name-associated door address set to obtain a coordinate clustering result; A coordinate prediction unit, used to obtain the adjacent gate addresses of the target gate address, and perform coordinate prediction on the target gate address based on the adjacent gate addresses to obtain the predicted coordinates of the target gate address; The gate address error correction unit is used to determine whether the target gate address is incorrect based on the gate address characteristics, coordinate clustering results and the predicted coordinates.
9. A computer device comprising a memory, a processor, and computer-readable instructions stored in the memory and executed on the processor, characterized in that: When the processor executes the computer-readable instructions, the gate address coordinate error correction method as described in any one of claims 1 to 7 is implemented.
10. A readable storage medium having computer readable instructions stored thereon, characterized in that: When the computer-readable instructions are executed by a processor, the gate address coordinate error correction method as described in any one of claims 1 to 7 is implemented.