Method and system for acquiring area to which address belongs by fusing multi-network map platform

Abstract

The invention provides a method and a system for acquiring an area to which an address belongs by fusing a plurality of network map platforms, and relates to the technical field of map localization, comprising the following steps: acquiring address or house number information, and establishing an area coordinate database; uploading the obtained address or house number information to a plurality of network map platforms for online query, and obtaining coordinate data fed back by the plurality of network map platforms; performing standard conversion on the coordinate data fed back by the plurality of network map platforms to generate latitude and longitude coordinates of the plurality of network map platforms; comparing and identifying the latitude and longitude coordinates of the plurality of network platforms, and judging the belonging areas and area codes; and counting the recognition accuracy of the region and the region code which are recognized and judged by the multi-network platform through a region coordinate database, and outputting a final recognition region. According to the method, data sources are expanded by fusing multiple pieces of network map data, and the recognition accuracy of the belonging area is enhanced through mutual cross validation.

Description

Technical Field

[0001] The present invention belongs to the technical field of map positioning, and in particular to a method and system for acquiring an address region by integrating multiple network map platforms. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] When conducting statistical work, a large number of unit addresses and resident house numbers will be divided into administrative regions. Food, express delivery, etc. also need to clarify the delivery area based on the address. At present, most of the regions to which the addresses belong are determined by manual recognition or single map recognition. However, the use of manual or single map recognition methods has the problem of a single data source, some addresses cannot be recognized, and the accuracy of the recognition cannot be verified, resulting in many recognition errors and low accuracy.

[0004] At the same time, the current map recognition method mainly uses computer technology through network maps to store and query addresses in digital form. Due to its spatial information visualization, storage cheapness, and virtualization characteristics, it has been widely used in daily travel, drone logistics distribution, agriculture and other fields. However, there are differences in the accuracy of longitude and latitude corresponding to addresses on different network maps, and there is a problem that users cannot select the network map with the most accurate longitude and latitude corresponding to the address when using the map, and cannot obtain the most accurate address information, which in turn affects the accuracy of the judgment of the area to which they belong.

[0005] Especially for smaller areas such as community and village-level areas, or customized regional data, or for some old addresses or addresses that are easily mistyped, most of them cannot accurately determine the exact area they belong to through the current network map. Therefore, when it is necessary to obtain the area to which an address belongs, how to expand the data source, improve the recognition accuracy of the area to which it belongs, and reduce the occurrence of errors has become a problem that needs to be solved. Summary of the invention

[0006] In order to overcome the above-mentioned deficiencies of the prior art, the present invention provides a method and system for obtaining the area to which an address belongs by integrating multiple network map platforms, which expands the data source by integrating multiple network map data and enhances the accuracy of identifying the area to which the address belongs by cross-validation.

[0007] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions: A first aspect of the present invention provides a method for acquiring an address region by integrating multiple network map platforms.

[0008] A method for obtaining the region to which an address belongs by integrating multiple network map platforms, comprising: Establish regional coordinate database; Obtain the address or house number information of the area to be confirmed; Upload the address or house number information of the area to be confirmed to multiple online map platforms for online query, and obtain the coordinate data fed back by multiple online map platforms; Perform unified standard conversion on the coordinate data fed back by multiple network map platforms to obtain the converted latitude and longitude coordinates of multiple network map platforms; Compare and identify the converted latitude and longitude coordinates of multiple network platforms with the regional coordinate database to determine the region and regional code; For the areas and area codes identified and judged by multiple network platforms, the recognition accuracy is calculated respectively, and the recognition area with the highest accuracy is output.

[0009] A second aspect of the present invention provides a system for acquiring an address region by integrating multiple network map platforms.

[0010] A system for obtaining an address region by integrating multiple network map platforms, comprising: The data acquisition module is configured to: establish a regional coordinate database; obtain the address or house number information of the area to be confirmed; The fusion query module is configured to: upload the address or house number information of the area to be confirmed to multiple network map platforms for online query, and obtain the coordinate data fed back by the multiple network map platforms; The coordinate conversion module is configured to: perform a unified standard conversion on the coordinate data fed back by multiple network map platforms to obtain the converted latitude and longitude coordinates of the multiple network map platforms; The comparison and identification module is configured to: compare and identify the converted latitude and longitude coordinates of multiple network platforms with the regional coordinate database to determine the region and region code; The statistical output module is configured to calculate the recognition accuracy of the areas and area codes identified and judged by multiple network platforms, and output the recognition area with the highest accuracy.

[0011] The third aspect of the present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in a method as described in the second aspect of the present invention are implemented.

[0012] A fourth aspect of the present invention provides a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in a method as described in the second aspect of the present invention.

[0013] A fifth aspect of the present invention provides a computer program product comprising instructions, which, when running on a computer, enables the computer program to implement the steps in a method as described in the second aspect of the present invention when executed by a processor.

[0014] One or more of the above technical solutions have the following beneficial effects: The present invention expands the data source by fusing multiple network map data; and realizes mutual cross-validation by combining data obtained from different network map platforms, thereby enhancing the accuracy of final area identification.

[0015] The present invention can identify and count the area codes determined by multiple network map platforms by establishing a regional coordinate database, and can calculate the recognition accuracy, thereby further improving the accuracy of regional recognition and reducing the probability of recognition errors.

[0016] The present invention can realize online query of the area to which a single address belongs and online query of the area to which a batch of addresses belong. In particular, it can realize accurate identification of smaller areas such as streets, towns, villages or customized area data, or some old addresses or addresses that are easily mistyped.

[0017] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0019] Figure 1 This is a flow chart of a method for obtaining an address region by integrating multiple network map platforms according to the first embodiment of the present invention; Figure 2 The present invention is a method for obtaining the area to which an address belongs by integrating multiple network map platforms in the first embodiment of the present invention, and a schematic diagram of displaying the identified area on a map. DETAILED DESCRIPTION

[0020] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0021] It should be noted that the terms used herein are for describing specific embodiments only and are not intended to be limiting of exemplary embodiments according to the present invention.

[0022] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0023] The overall idea proposed by the present invention is: to transmit the address or house number information to the online query interfaces of multiple network maps at the same time, obtain coordinate data fed back by multiple parties, and then perform standard conversion on each coordinate data to generate their own longitude and latitude coordinates. The system then compares and identifies each longitude and latitude coordinate with the regional coordinates, determines the region and regional code to which it belongs, and then statistically calculates the accuracy, and finally feeds back the correct result.

[0024] Embodiment 1 This embodiment discloses a method for obtaining the region to which an address belongs by integrating multiple network map platforms, which expands the data source by integrating multiple network map data and enhances the accuracy of identifying the region by cross-validation, including: Establish regional coordinate database; Obtain the address or house number information of the area to be confirmed; Upload the address or house number information of the area to be confirmed to multiple online map platforms for online query, and obtain the coordinate data fed back by multiple online map platforms; Perform unified standard conversion on the coordinate data fed back by multiple network map platforms to obtain the converted latitude and longitude coordinates of multiple network map platforms; Compare and identify the converted latitude and longitude coordinates of multiple network platforms with the regional coordinate database to determine the region and regional code; For the areas and area codes identified and judged by multiple network platforms, the recognition accuracy is calculated respectively, and the recognition area with the highest accuracy is output.

[0025] In order to explain this embodiment more clearly, Figure 1 As shown, the implementation process of the method for obtaining the region to which an address belongs by integrating multiple network map platforms can be specifically described as follows: Step 1: Establish a regional coordinate database.

[0026] In this embodiment, the regional coordinate database is established using the WSG84 international longitude and latitude coordinates.

[0027] In this embodiment, the established regional coordinate database specifically includes: jurisdiction code, regional name, regional coordinate set and regional address keyword.

[0028] Among them, the regional address keywords serve as a supplementary verification function. They can also identify the areas to which some old addresses, addresses that are easily mistyped, and addresses whose coordinates cannot be fed back on multiple maps belong.

[0029] For example: Luokou and Luokou are the same address name but are easy to misspell; Beiyuan Road and Beiyuan Street are the old and new names of the same road.

[0030] In this embodiment, the specific process of establishing the regional coordinate database is as follows: The coordinate data of administrative regions at the provincial, municipal, and county levels are obtained using Tiantu Map, which is the WSG84 international standard coordinates. The coordinate data of smaller streets, towns, villages, or custom regions are obtained through map software to obtain the longitude and latitude coordinates of the regional boundary nodes, and the longitude and latitude coordinates of the regional boundary nodes are organized into the established regional coordinate database.

[0031] The regional address keywords include regular expressions of the house numbers, road names, community names, building names, etc. in the area.

[0032] The regional coordinate database specifically includes sample data as shown in Table 1.

[0033] Table 1 Sample data of regional coordinate database

[0034] By establishing its own regional coordinate data address database, it can be used for comparative analysis with the regions identified by multiple network platforms, and ultimately improve the overall recognition accuracy through cross-validation. In addition, the established regional coordinate database contains data such as regional address keywords, which can play a supplementary verification function. It can also identify the region to which some old addresses or addresses that are easily mistyped, as well as addresses that cannot provide coordinates on multiple maps, belong.

[0035] Step 2: Call the multi-map interface to query the address.

[0036] Obtain the address or house number information of the area to be confirmed; Upload the address or house number information of the area to be confirmed to multiple online map platforms for online query, and obtain the coordinate data fed back by multiple online map platforms.

[0037] In this embodiment, the multiple network map platforms specifically include: Amap, Baidu Map, Tencent Map, Tiandi Map and other network map platforms.

[0038] In this embodiment, when the acquired address or house number information is input, multiple network map platform interfaces will be connected to perform online query respectively, and coordinate data fed back by multiple network map platforms will be obtained. For example, to search for a place in Tianqiao District: Amap returns the coordinates 116.988270, 36.677881 (GCJ02 standard coordinates); Baidu Map returns the coordinates 116.987650, 36.677912 (GCJ02 standard coordinates); Tencent Maps returns the coordinates 116.986614, 36.678054 (GCJ02 standard coordinates); Tiandi Map returns the coordinates 116.981607, 36.677677 (WSG84 standard coordinates).

[0039] Step 3: Convert coordinates to international longitude and latitude.

[0040] The coordinate data fed back by multiple network map platforms are converted according to a unified standard to obtain the converted latitude and longitude coordinates of the multiple network map platforms.

[0041] In this embodiment, the coordinate data fed back by Amap, Baidu Map, and Tencent Map platforms are GCJ02 standard longitude and latitude coordinates, and the coordinate data fed back by Tiandi Map platform are WSG84 international longitude and latitude coordinates. This embodiment calls the GCJ02toWGS84 coordinate conversion formula to uniformly convert the coordinate data into WSG84 international longitude and latitude coordinates, and realizes a unified standard conversion of the coordinate data fed back by multiple network map platforms, which facilitates the subsequent rapid and effective judgment and comparison of the coordinate data of multiple network platforms with the regional coordinate data of the regional coordinate database.

[0042] Step 4: Determine the area to which the coordinates belong.

[0043] The converted latitude and longitude coordinates of multiple network platforms are compared and identified with the regional coordinate database to determine the region and regional code.

[0044] In this embodiment, the converted multiple map longitude and latitude coordinates are compared and identified with the regional coordinate database to determine the region and region code to which they belong. Specifically, the ST_CONTAINS function of the MYSQL database is called to determine whether the converted multiple map longitude and latitude coordinates are included in a certain region, and are compared with the coordinate set data of each regional node in the regional coordinate database respectively. At the same time, a regular expression comparison is performed with the regional address keyword to find the region where the address is located, and based on the search results, the region and region code where the multiple map feedback coordinates are located are output.

[0045] Step 5: Statistically calculate the recognition accuracy.

[0046] For the areas and area codes identified and judged by multiple network platforms, the recognition accuracy is calculated respectively, and the recognition area with the highest accuracy is output.

[0047] To achieve cross-validation, the regional codes identified and judged by multiple network platforms are used as data sets. The frequency of occurrence of regional codes is counted, and the accuracy of multiple regional codes fed back is calculated. The higher the statistical frequency of a regional code, the higher the accuracy.

[0048] The specific calculation formula is as follows: If the statistical frequency data set has N data, The number of occurrences of a number is , the total number of digits is N, then the accuracy is calculated:

[0049] For example: using the feedback data of four online maps, namely Baidu Map, Amap, Tiandi Map and Tencent Map, and the feedback data of one address database keyword, the accuracy of each of these five data is statistically calculated.

[0050] The statistical frequency of a certain data is 5 times, and the accuracy = 5 / 5*100% = 100%; The statistical frequency of a certain data is 4 times, and the accuracy = 4 / 5*100% = 80%; The statistical frequency of a certain data is 0 times and the accuracy is 0%.

[0051] The recognition accuracy of the areas and area codes identified and judged by multiple network platforms is statistically analyzed through the regional coordinate database, and the final recognition area is output to achieve the integration of regional judgment results of multiple network platforms.

[0052] In this embodiment, by performing batch recognition of 4585 unit addresses to community and village levels and fusing multi-map data for statistical judgment, the regional recognition rate can be achieved to be over 98%. Through cross-validation, the recognition accuracy is greater than 60%, reaching over 85%.

[0053] As shown in Table 2, in the batch recognition of 4585 unit addresses to the community and village levels by integrating multi-map data, there is only one way to identify the area with an accuracy of less than 20% for 56 addresses, accounting for 1.22%, less than 2%. For the other more than 98% of the addresses, there are 2 to 5 ways to identify the area they belong to; and there are 87.11% of the areas identified by 3 ways with an accuracy of more than 60%, which is the sum of 34.35% with an accuracy of 100%, 32.93% with an accuracy of 80%, and 19.83% with an accuracy of 60%.

[0054] Table 2 Batch recognition accuracy statistics

[0055] Table 3 Schematic diagram of output results of batch recognition of address areas

[0056] Therefore, after integrating multi-map data for statistical judgment, we can first expand the data source through a variety of online map data; then combine the data obtained from different online map platforms to achieve mutual cross-validation and enhance the accuracy of the final area identification.

[0057] Embodiment 2 The purpose of this embodiment is to provide a system for obtaining an address region by integrating multiple network map platforms, including: The data acquisition module is configured to: establish a regional coordinate database; obtain the address or house number information of the area to be confirmed; The fusion query module is configured to: upload the address or house number information of the area to be confirmed to multiple network map platforms for online query, and obtain the coordinate data fed back by the multiple network map platforms; The coordinate conversion module is configured to: perform a unified standard conversion on the coordinate data fed back by multiple network map platforms to obtain the converted latitude and longitude coordinates of the multiple network map platforms; The comparison and identification module is configured to: compare and identify the converted latitude and longitude coordinates of multiple network platforms with the regional coordinate database to determine the region and region code; The statistical output module is configured to calculate the recognition accuracy of the areas and area codes identified and judged by multiple network platforms, and output the recognition area with the highest accuracy.

[0058] Embodiment 3 The purpose of this embodiment is to provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the program.

[0059] Embodiment 4 The purpose of this embodiment is to provide a computer-readable storage medium.

[0060] A computer-readable storage medium stores a computer program, which executes the steps of the above method when executed by a processor.

[0061] Embodiment 5 The purpose of this embodiment is to provide a computer program product containing instructions, which, when running on a computer, enables the computer to execute the methods and functions involved in any of the above embodiments.

[0062] The steps involved in the apparatus of the above embodiment correspond to the method embodiment 1, and the specific implementation method can refer to the relevant description part of embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood to include any medium that can store, encode or carry an instruction set for execution by a processor and enable the processor to execute any method in the present invention.

[0063] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0064] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A method for obtaining the region to which an address belongs by integrating multiple network map platforms, characterized in that: include: Establish regional coordinate database; Obtain the address or house number information of the area to be confirmed; Upload the address or house number information of the area to be confirmed to multiple online map platforms for online query, and obtain the coordinate data fed back by multiple online map platforms; Perform unified standard conversion on the coordinate data fed back by multiple network map platforms to obtain the converted latitude and longitude coordinates of multiple network map platforms; Compare and identify the converted latitude and longitude coordinates of multiple network platforms with the regional coordinate database to determine the region and regional code; For the areas and area codes identified and judged by multiple network platforms, the recognition accuracy is calculated respectively, and the recognition area with the highest accuracy is output.

2. A method for obtaining the region to which an address belongs by integrating multiple network map platforms as claimed in claim 1, characterized in that: Establish regional coordinate database with WSG84 international longitude and latitude coordinates; The establishment of the regional coordinate database specifically includes: jurisdiction code, regional name, regional coordinate set and regional address keywords.

3. A method for obtaining the region to which an address belongs by integrating multiple network map platforms as claimed in claim 2, characterized in that: The regional address keywords include regular expressions of house numbers in the area, road names, community names, and building names.

4. The method for obtaining the region to which an address belongs by integrating multiple network map platforms as claimed in claim 1, characterized in that: The unified standard conversion of the coordinate data fed back by multiple online map platforms is specifically: calling the GCJ02toWGS84 coordinate conversion formula to uniformly convert the coordinate data into WSG84 international longitude and latitude coordinates, thereby realizing the unified standard conversion of the coordinate data fed back by multiple online map platforms.

5. The method for obtaining the region to which an address belongs by integrating multiple network map platforms as claimed in claim 1, characterized in that: The described comparison and identification of the converted latitude and longitude coordinates of the multiple network platforms with the regional coordinate database is specifically as follows: calling the ST_CONTAINS function of the MYSQL database to determine whether the converted multiple map longitude and latitude coordinates are contained in a certain area, comparing them with the coordinate set data of each regional node in the regional coordinate database respectively, and performing regular expression comparison with the regional address keyword to find the area where the address is located, and outputting the area and area code where the multiple map feedback coordinates are located according to the search results.

6. The method for obtaining the region to which an address belongs by integrating multiple network map platforms as claimed in claim 1, characterized in that: The regions and region codes identified and judged by the multiple network platforms are respectively calculated for recognition accuracy, and the recognition region with the highest accuracy is output, specifically: In order to achieve cross-validation, the regional codes identified and judged by multiple network platforms are used as data sets. The frequency of regional codes is counted, and the accuracy of multiple regional codes fed back is calculated. The higher the statistical frequency of a regional code, the higher the accuracy: The specific calculation formula is as follows: ； Assume that the statistical frequency data set has N data, The number of occurrences of a number is , the total number of digits is N, calculate the accuracy.

7. A system for acquiring the area to which an address belongs that integrates multiple network map platforms, characterized in that: include: The data acquisition module is configured to: establish a regional coordinate database; obtain the address or house number information of the area to be confirmed; The fusion query module is configured to: upload the address or house number information of the area to be confirmed to multiple network map platforms for online query, and obtain the coordinate data fed back by the multiple network map platforms; The coordinate conversion module is configured to: perform a unified standard conversion on the coordinate data fed back by multiple network map platforms to obtain the converted latitude and longitude coordinates of the multiple network map platforms; The comparison and identification module is configured to: compare and identify the converted latitude and longitude coordinates of multiple network platforms with the regional coordinate database to determine the region and region code; The statistical output module is configured to calculate the recognition accuracy of the areas and area codes identified and judged by multiple network platforms, and output the recognition area with the highest accuracy.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method described in any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 6 are performed.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images