CN114328766A - A method, device, medium and equipment for constructing a geographic knowledge graph database - Google Patents

Abstract

This article is about a method, device, medium and equipment for constructing a geographic knowledge graph database. The method includes: converting remote sensing images into geographic vector texts, obtaining POI data sets in an electronic map, and fusing the geographic vector texts with the POI data sets to generate textual data of geographic entity sets with geographic attributes; The textual data of the geographic entity set is imported into the Neo4j graph database and associated with the Mercator tile coordinates to construct a geographic knowledge graph database based on the tile index. Realize the association of geographic data and spatial information, and store geographic data and spatial information in a graph structure in a graph database, so as to achieve more accurate and efficient semantic query and search of geographic information.

Description

A method, device, medium and equipment for constructing a geographic knowledge graph database

technical field

This paper relates to a graph database, in particular to a method, device, medium and device for constructing a geographic knowledge graph database.

Background technique

The tile pyramid model is a multi-resolution hierarchical model. From the bottom layer to the top layer of the tile pyramid, the resolution becomes lower and lower, but the geographic extent of the representation remains unchanged. The tile pyramid model is a model based on the Web Mercator projection. The Mercator projection is an "equirectangular cylindrical projection". It is a mathematical transformation that projects the earth into a two-dimensional plane. The advantage of the Mercator projection is that it does not change the relative position of objects before and after the projection. The Web Mercator projection is a projection that simplifies the earth from an ellipsoid to a sphere. After performing the Web Mercator projection on the earth, the quadtree segmentation method is used to segment and layer the projected earth plane. Create a series of rectangular collections of different resolution levels. The rectangular set of each level consists of several tiles. When building a tile pyramid model, for each level of tile, start from the upper left corner of the map projection, cut from left to right, and top to bottom, and divide it into rectangular tiles of the same size. The number of tiles at level 0 is 1, that is, the entire map projection is regarded as one tile. From the first level, the tile matrix of the current level is formed by cutting each tile of the previous level into 2x2 tiles. In the related art, although tile coordinates can realize the mapping between positioning and latitude and longitude coordinates, they cannot provide information related to the geographic location of a geographic entity, such as the administrative region to which the target geographic entity belongs, and detailed information such as area.

At the same time, for remote sensing images, there are many geographic entities in remote sensing images, and these geographic entities have infinite latitude and longitude coordinates. In the process of establishing a map database, it is difficult to store so many latitude and longitude coordinates, and it is difficult to achieve more accurate , More efficient semantic query and search of geographic information.

SUMMARY OF THE INVENTION

In order to overcome the problems existing in the related technologies, this paper provides a method, device, medium and equipment for constructing a geographic knowledge graph database.

According to the first aspect of this article, a method for constructing a geographic knowledge graph database is provided, including:

Converting the remote sensing image into geographic vector text, the geographic vector text at least includes geographic entity identification information and corresponding latitude and longitude coordinates;

Obtain the POI data set in the electronic map, and the POI data set at least includes geographical attributes such as the name of the geographical entity, the location information of the feature entity, and the latitude and longitude coordinates of the feature entity;

Integrating the geographic vector text and the POI data set to generate textual data of a geographic entity set with geographic attributes;

Import the textual data of the geographic entity set into the Neo4j graph database, and associate with the Mercator tile coordinates to construct a geographic knowledge graph database based on the tile index.

The converting remote sensing image into geographic vector text includes:

Extracting geographic entities in the remote sensing images, and obtaining raster images related to the geographic entities;

According to the position of the geographic entity in the remote sensing image, assign the attribute related to the position to the geographic entity in the raster image, and generate the assigned raster data;

Convert the assigned raster data into geographic vector files;

Generate geographic vector text based on the geographic vector file.

The extracting the geographic entities in the remote sensing image, and acquiring the raster image includes:

splitting the remote sensing image into multiple sub-images;

Extract information for each sub-image and generate multiple sub-raster images;

The plurality of sub-raster images are spliced according to the positions of the corresponding sub-images to form a raster image with the same size as the remote sensing image.

The assigning the attribute related to the location to the geographic entity in the raster image includes:

converting the remote sensing image and the raster image into ASCII encoding;

Copy the coordinate information in the ASCII encoding of the remote sensing image to the corresponding geographic entity in the ASCII encoding of the raster image;

The ASCII code of the raster image to which the coordinate information is added is generated into the raster data after assignment.

The generating geographic vector text based on the geographic vector file includes:

converting the geographic vector file into a feature set in geojson format;

Convert the feature collection in the geojson format to geographic vector text.

The fusion of the geographic vector text and the POI dataset includes:

The latitude and longitude coordinates of the geographic entities in the geographic vector text are matched with the coordinates in the POI data set, and if the matching is successful, the geographic attributes in the POI data set are copied to the vector text corresponding to the geographic entities.

The associating the textual data of the geographic entity set with the Mercator tile coordinates includes:

traverse each row of data in the geographic entity set;

According to the latitude and longitude coordinates in each row of data, determine whether the Mercator tile corresponding to the latitude and longitude coordinates exists;

If the Mercator tile corresponding to the latitude and longitude coordinates does not exist, a Mercator tile is created; if there is a Mercator tile corresponding to the latitude and longitude coordinates, the geographic entity corresponding to the latitude and longitude coordinates A geographic attribute is associated to the Mercator tile.

According to another aspect of this paper, an apparatus for constructing a geographic knowledge graph database is provided, comprising:

A remote sensing image conversion module for converting remote sensing images into geographic vector text, where the geographic vector text includes geographic entities and corresponding latitude and longitude coordinates;

The POI data acquisition module is used to acquire the POI data set in the electronic map, and the POI data set at least includes geographical attributes such as the name of the geographic entity, the location information of the feature entity, and the latitude and longitude coordinates of the feature entity;

A data fusion module, for merging the geographic vector text and the POI data set to generate textual data of a geographic entity set with geographic attributes;

The import module imports the textual data of the geographic entity set into the Neo4j graph database, and associates it with the coordinates of the Mercator tile to construct a geographic knowledge graph database based on the Mercator tile index.

According to another aspect of this document, there is provided a computer-readable storage medium on which a computer program is stored, and when the computer program is executed, implements the steps of a method for constructing a geographic knowledge graph database.

According to another aspect of this document, a computer device is provided, comprising a processor, a memory and a computer program stored on the memory, wherein the processor implements the construction of a geographic knowledge graph database when the processor executes the computer program steps of the method.

This paper integrates the POI data set crawled from the electronic map into the geographic vector text converted from remote sensing images, and then imports the geographic vector text into the Neo4j map database, and associates it with the coordinates of the Mercator tile, so as to construct a Mercator-based model based on Mercator. A tile-indexed geographic knowledge graph database. It can realize the transformation of the infinite number of latitude and longitude coordinates into the infinite number of tile coordinate descriptions, so as to solve the problem that infinite number of latitude and longitude coordinates are difficult to store. In this way, the association between geographic data and spatial information is realized, and geographic data and spatial information are represented in a graph structure and stored in a graph database, so as to achieve more accurate and efficient semantic query and search of geographic information.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not limiting.

Description of drawings

The accompanying drawings, which form a part hereof, are used to provide a further understanding of this document, and the illustrative embodiments and their descriptions herein are used to explain this document and do not constitute an undue limitation to this document. In the attached image:

Fig. 1 is a flow chart of a method for constructing a geographic knowledge graph database according to an exemplary embodiment.

Fig. 2 is a block diagram of an apparatus for constructing a geographic knowledge graph database according to an exemplary embodiment.

Fig. 3 is a block diagram of a computer device for constructing a geographic knowledge graph database according to an exemplary embodiment

Detailed ways

In order to make the purposes, technical solutions and advantages of the embodiments herein more clear, the technical solutions in the embodiments herein will be clearly and completely described below with reference to the accompanying drawings in the embodiments herein. Some examples, but not all examples. Based on the embodiments herein, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the scope of protection herein. It should be noted that, the embodiments herein and the features in the embodiments may be arbitrarily combined with each other under the condition of no conflict.

In the traditional technology, people can only determine the geospatial distribution and environmental conditions of the target entity through remote sensing images, but cannot obtain more detailed information. For example, for a building in a remote sensing image, people cannot know its specific geographic attributes through the remote sensing image, such as the name of the building, the area of the building, the administrative area to which the building belongs, and the names of surrounding roads and other geographic information.

This paper provides a method for constructing a geographic knowledge graph database. FIG. 1 is a flowchart of a method for constructing a geographic knowledge graph database according to an exemplary embodiment. Referring to FIG. 1, the method for constructing a geographic knowledge graph database includes:

Step S11, convert the remote sensing image into geographic vector text, and the geographic vector text at least includes geographic entity identification information and corresponding latitude and longitude coordinates;

Step S12, obtains the POI data set in the electronic map, and the POI data set at least includes geographical attributes such as the name of the geographical entity, the location information of the feature entity, and the latitude and longitude coordinates of the feature entity;

Step S13, the geographic vector text and POI data set are fused, and the textual data of the geographic entity set with geographic attributes is generated;

Step S14, import the textual data of the geographic entity set into the Neo4j graph database, and associate with the Mercator tile coordinates to construct a geographic knowledge graph database based on the Mercator tile index.

In step S11, in order to add geographic information to the remote sensing image, the remote sensing image is first converted into geographic vector text. In the geographic vector text, each row is related information of a geographic entity, including at least the identification information of the geographic entity, and the latitude and longitude coordinates. . Of course, the category, code, size and other information of the geographic entity can also be included. For example, after converting a remote sensing image into geographic vector text, the geographic entity is a road in the remote sensing image. For each road, it is described by a line in the geographic vector text. Each line can identify the number, category, temporary Name, latitude and longitude coordinates and other information. Of course, only the geographic entity identification information (for example, the road number) and the latitude and longitude coordinates can be listed. Whether other information is included is not limited in this article.

In one embodiment, converting remote sensing imagery to geographic vector text includes:

Extract geographic entities in remote sensing images, and obtain raster images related to geographic entities;

According to the position of the geographic entity in the remote sensing image, assign the attribute related to the position to the geographic entity in the raster image, and generate the assigned raster data;

Convert the assigned raster data into geographic vector files;

Generate geographic vector text based on geographic vector files.

Perform feature recognition on remote sensing images, identify which are buildings, which are roads, and which are vegetation in the remote sensing images, and output corresponding raster images according to the targets to be identified and the corresponding target categories. For example, in road identification, it is only necessary to identify which pixels in the remote sensing image are roads and which pixels are non-roads. In the identified raster image, red can be used to represent roads, and black can be used to represent non-roads. The raster image at this time is 2-value graph. In some cases, roads and buildings can also be identified at the same time. In the identified raster image, red represents roads, yellow represents buildings, and black represents background. This article only illustrates the raster map by way of example, and the listed colors and entities do not constitute a limitation on the method in this article. Through feature recognition, the original remote sensing image is turned into a raster image marked with each pixel category, and the format is generally PNG. However, in the raster image, although the geographic entities in the image are identified, in the process of converting the remote sensing image to the raster image, the raster image does not obtain the location information in the remote sensing image, so it is necessary to put the geographic entity in the remote sensing image. Locations in the imagery are assigned to geographic entities in the raster image. Then, on the basis of the assigned raster image, the geographic vector text corresponding to the remote sensing image can be generated.

For feature recognition of remote sensing images, deep learning algorithms can be used to input remote sensing images into a trained machine learning model to quickly output corresponding raster images. However, because remote sensing images are generally relatively large and limited by the current level of computer equipment, it is necessary to take corresponding measures when identifying remote sensing images. In one embodiment, extracting geographic entities in a remote sensing image, and obtaining a raster image includes: dividing the remote sensing image into multiple sub-images; extracting information from each sub-image, and generating the same number of multiple sub-raster images; Multiple sub-raster images are spliced according to the positions of the corresponding sub-images to form a raster image with the same size as the remote sensing image. The storage format of remote sensing images is generally GeoTIFF format. When the machine model performs feature recognition, in order to prevent memory overflow, the remote sensing image is first divided into several sub-images in GeoTIFF format. For example, in this embodiment, the number of pixels of each sub-image is 512*512. Perform feature recognition on each sub-image to generate multiple sub-raster images of the same size as the sub-images. The format of the sub-raster images is PNG. The multiple sub-raster images are spliced according to the positions of the corresponding sub-images. It is a raster image of the same size as the remote sensing image.

In one embodiment, assigning a location-related attribute to a geographic entity in the raster image includes:

Convert the remote sensing image and the corresponding raster image to ASCII code; copy the coordinate information in the ASCII code of the remote sensing image to the corresponding geographic entity in the ASCII code of the raster image; convert the ASCII code of the raster image with the coordinate information added Encoding generates assigned raster data. Convert the remote sensing image and raster image to ASCII code, and copy the geographic information in the ASCII code of the remote sensing image to the corresponding position in the ASCII code of the raster image according to the pixel position of the geographic entity in the remote sensing image, so that the Add geographic information to the identified geographic entities. In practical applications, in addition to assigning the location information in the remote sensing image to the identified geographic entities, other related attributes of the geographic entities can also be obtained in the raster image. Information such as the type of road endpoints (broken road or intersection), and for buildings, the area of the building can be obtained, and these related attribute information can also be added to the ASCII encoding of the raster image. The assigned raster data can be generated by ASCII encoding with added geographic information. In this embodiment, the assigned raster data is in tiff format.

Next, using the arcpy.RasterToPolygon_conversion method in the ArcPy Python toolkit, the assigned raster data can be converted into a geographic vector file. In this embodiment, the geographic vector file is in SHP format.

In order to obtain the geographic vector text, in one embodiment, generating the geographic vector text based on the geographic vector file includes: converting the geographic vector file into a feature set in geojson format; and converting the feature set in geojson format into geographic vector text. Shapefile is a Python package that can convert the shp format geographic vector file produced earlier into geojson format geographic text data. In order to facilitate subsequent operations, the geographic text data in geojson format is further converted into geographic vector text in CSV format. In vector text, each line of data represents a geographic entity, including the name, serial number, latitude and longitude of the geographic entity, and other related attributes. The geographic vector text is not only easy to observe, but also more convenient to add more information when supplementing the geographic entity in the future. additional information.

In step S12, the POI data set in the electronic map is obtained, for example, a crawler tool is used to crawl the POI data in the electronic map, and relevant information such as feature names, latitude and longitude coordinates, and provinces to which multiple geographic entities are obtained are obtained. Then, the relevant information of the geographic entities crawled in the electronic map can be supplemented into the geographic vector text, and the geographic vector text and POI datasets can be integrated.

In step S13, the geographic vector text obtained in the previous steps and the POI data in the electronic map are fused, thereby generating textual data of a geographic entity set with geographic attributes. In one embodiment, fusing the geographic vector text and the POI dataset includes: matching the latitude and longitude coordinates of the geographic entities in the geographic vector text with the coordinates in the POI dataset, and if the matching is successful, merging the POI dataset into the POI dataset. The geographic attributes of are copied into the vector text corresponding to the geographic entity. If there are matching latitude and longitude coordinates, it means that the target described in the electronic map and the geographic vector text is the same target and is the same geographic entity. Therefore, the geographic attributes corresponding to the latitude and longitude coordinates in the POI dataset can be copied to the geographic vector text corresponding to the same latitude and longitude. in the geographic entity. For example, in the data of a certain line in the geographic vector text, only the geographic entity in it can be identified as a road, the latitude and longitude coordinates where it is located, and a unique code is assigned, while the information such as the name of the road, the province where it is located, and the width of the road are not certain. . According to the latitude and longitude coordinates in the geographic vector text, the POI data can be matched. If the match is successful, it means that the road identified in the geographic vector text is also marked in the electronic map, and the information is more detailed. The geographic attributes corresponding to the latitude and longitude in the text are copied to the geographic vector text, and added to the corresponding positions of the attributes such as road name, province, and road width, so as to realize the integration of geographic vector text and POI datasets. According to the above method, after all geographic entities are fused, the textual data of the geographic entity set with geographic attributes is generated.

In step S14, the textual data of the geographic entity set is imported into the Neo4j graph database, and a graph database including the remote sensing image content is generated. The tile coordinates are added to the database, and the location information of geographic entities is represented by tile coordinates instead of latitude and longitude in the graph database, and a geographic knowledge graph database based on tile index is constructed.

In one embodiment, associating the textual data of the geographic entity set with Mercator tile coordinates includes:

Traverse each row of data in the geographic entity set; according to the latitude and longitude coordinates in each row of data, determine whether the Mercator tile corresponding to the latitude and longitude coordinates exists; if the Mercator tile corresponding to the latitude and longitude coordinates does not exist, Then create a Mercator tile; if there is a Mercator tile corresponding to the latitude and longitude coordinates, associate the geographic attribute of the geographic entity corresponding to the latitude and longitude coordinates to the Mercator tile.

Convert the latitude and longitude coordinates in each line of the geographic vector text into the corresponding tile number, you can determine which tile the geographic entity corresponding to the latitude and longitude coordinates belongs to, and associate the geographic attributes corresponding to the latitude and longitude coordinates with the tile. , to realize the fusion of remote sensing image database and tile map.

Through the above embodiments, this paper integrates the POI data set crawled from the electronic map into the geographic vector text converted from remote sensing images, and then imports the geographic vector text into the Neo4j map database and associates it with the coordinates of the Mercator tile, thereby Build a geographic knowledge graph database based on tile index. It can realize the transformation of the infinite number of latitude and longitude coordinates into the infinite number of tile coordinate descriptions, so as to solve the problem that infinite number of latitude and longitude coordinates are difficult to store. In this way, the association between geographic data and spatial information is realized, and geographic data and spatial information are represented in a graph structure and stored in a graph database, so as to achieve more accurate and efficient semantic query and search of geographic information.

Fig. 2 is a block diagram of an apparatus for constructing a geographic knowledge graph database according to an exemplary embodiment. Referring to FIG. 2 , the apparatus for constructing a geographic knowledge graph database includes: a remote sensing image conversion module 201 , a POI data acquisition module 202 , a data fusion module 203 , and an import module 204 .

The remote sensing image conversion module 201 is configured to convert the remote sensing image into geographic vector text, where the geographic vector text includes geographic entities and corresponding latitude and longitude coordinates.

The POI data acquisition module 202 is configured to acquire a POI data set in the electronic map, where the POI data set at least includes geographical attributes such as the name of a geographic entity, the location information of the feature entity, and the latitude and longitude coordinates of the feature entity.

The data fusion module 203 is configured to fuse the geographic vector text and the POI data set to generate textual data of a geographic entity set with geographic attributes.

The import module 204 is configured to import the textual data of the geographic entity set into the Neo4j graph database, and associate it with the Mercator tile coordinates to construct a tile index-based geographic knowledge graph database.

FIG. 3 is a block diagram of a computer device 300 for constructing a geographic knowledge graph database according to an exemplary embodiment. For example, computer device 300 may be provided as a server. Referring to FIG. 3 , the computer device 300 includes a processor 301, and the number of the processors can be set to one or more as required. Computer device 300 also includes memory 302 for storing instructions executable by processor 301, such as application programs. The number of memories can be set to one or more as required. It can store one or more applications. The processor 301 is configured to execute instructions to execute the above-mentioned method for constructing a geographic knowledge graph database

As will be appreciated by those skilled in the art, the embodiments herein may be provided as a method, an apparatus (apparatus), or a computer program product. Accordingly, this document may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this document may take the form of a computer program product embodied on one or more computer-usable storage media having computer-usable program code embodied therein. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data , including but not limited to RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cartridges, magnetic tape, magnetic disk storage or other magnetic storage devices, or may be used for Any other medium that stores desired information and can be accessed by a computer, etc. In addition, communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and can include any information delivery media, as is well known to those of ordinary skill in the art .

Described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (apparatus) and computer program products according to embodiments herein. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The means implements the functions specified in one or more of the flowcharts and/or one or more blocks of the block diagrams

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

As used herein, the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that an article or device comprising a list of elements includes not only those elements, but also others not expressly listed elements, or elements inherent to the article or equipment. Without further limitation, an element defined by the phrase "comprising" does not preclude the presence of additional identical elements in the article or device comprising said element.

While the preferred embodiments have been described herein, additional changes and modifications to these embodiments may occur to those skilled in the art once the basic inventive concepts are known. Therefore, the appended claims are intended to be construed to include the preferred embodiment and all changes and modifications that fall within the scope of this document.

It will be apparent to those skilled in the art that various modifications and variations can be made in this document without departing from the spirit and scope of this document. Thus, provided that such modifications and variations herein come within the scope of the claims herein and their equivalents, it is intended that such modifications and variations are also included herein.

Claims (10)

1. A method for constructing a geographic knowledge base is characterized by comprising the following steps:

converting the remote sensing image into a geographic vector text, wherein the geographic vector text at least comprises geographic entity identification information and corresponding longitude and latitude coordinates;

the method comprises the steps of obtaining a POI data set in an electronic map, wherein the POI data set at least comprises geographic attributes such as geographic entity names, surface feature entity position information, surface feature entity longitude and latitude coordinates and the like;

fusing the geographic vector text and the POI data set to generate textual data of a geographic entity set with geographic attributes;

and importing the textual data of the geographic entity set into a Neo4j database, associating the textual data with coordinates of mercator tiles, and constructing a geographic knowledge database based on tile indexes.

2. The method for constructing a geographical knowledge base database according to claim 1, wherein said converting the remote sensing image into a geographical vector text comprises:

extracting a geographic entity in the remote sensing image, and acquiring a raster image related to the geographic entity;

according to the position of the geographic entity in the remote sensing image, assigning the attribute related to the position to the geographic entity in the raster image to generate assigned raster data;

converting the assigned raster data into a geographic vector file;

and generating geographic vector text based on the geographic vector file.

3. The method for constructing a geographical knowledge base database according to claim 2, wherein the extracting the geographical entities from the remote sensing image and obtaining the raster image comprises:

cutting the remote sensing image into a plurality of sub-images;

extracting information of each sub-image and generating a plurality of sub-grid images;

and splicing the plurality of sub-grid images according to the positions of the corresponding sub-images to form a grid image with the same size as the remote sensing image.

4. The method of constructing a geographical knowledge base database of claim 3, wherein said assigning attributes related to the location to geographical entities in the raster image comprises:

converting the remote sensing image and the raster image into an ASCI I code;

copying coordinate information in the ASCI I code of the remote sensing image to a corresponding geographic entity in the ASCI I code of the raster image;

and generating assigned raster data by ASCI I coding of the raster image added with the coordinate information.

5. The method of constructing a geographical knowledge base database according to claim 2, wherein said generating geographical vector text based on said geographical vector file comprises:

converting the geographic vector file into a feature set in a geojson format;

and converting the characteristic set in the geojson format into geographic vector text.

6. The method of constructing a geographical knowledge base database according to claim 1, wherein said fusing said geographical vector text and said POI data sets comprises:

and matching the longitude and latitude coordinates of the geographic entity in the geographic vector text with the coordinates in the POI data set, and copying the geographic attributes in the POI data set into the vector text corresponding to the geographic entity if the matching is successful.

7. The method of constructing a geographic knowledge base database according to claim 1, wherein said associating textual data of said set of geographic entities with mercator tile coordinates comprises:

traversing each row of data in the set of geographic entities;

determining whether the ink card tray tile corresponding to the longitude and latitude coordinates exists according to the longitude and latitude coordinates in each line of data;

if the ink card tray tile corresponding to the longitude and latitude coordinates does not exist, creating the ink card tray tile; and if the mercator tile corresponding to the longitude and latitude coordinates exists, associating the geographic attribute of the geographic entity corresponding to the longitude and latitude coordinates to the mercator tile.

8. A map knowledge base construction apparatus, comprising:

the remote sensing image conversion module is used for converting the remote sensing image into a geographic vector text, and the geographic vector text comprises a geographic entity and corresponding longitude and latitude coordinates;

the system comprises a POI data acquisition module, a map information acquisition module and a map information acquisition module, wherein the POI data acquisition module is used for acquiring a POI data set in an electronic map, and the POI data set at least comprises geographic attributes such as geographic entity names, surface feature entity position information, surface feature entity longitude and latitude coordinates and the like;

the data fusion module is used for fusing the geographic vector text and the POI data set to generate textual data of a geographic entity set with geographic attributes;

and the importing module is used for importing the textual data of the geographic entity set into a Neo4j database, associating the textual data with coordinates of the mercator tile and constructing a geographic knowledge database based on mercator tile indexes.

9. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed, implements the steps of the method according to any one of claims 1-8.

10. A computer arrangement comprising a processor, a memory and a computer program stored on the memory, characterized in that the steps of the method according to any of claims 1-8 are implemented when the computer program is executed by the processor.

Images