CN118378103B - Geographic information system data matching management method based on artificial intelligence - Google Patents
Geographic information system data matching management method based on artificial intelligence Download PDFInfo
- Publication number
- CN118378103B CN118378103B CN202410816028.6A CN202410816028A CN118378103B CN 118378103 B CN118378103 B CN 118378103B CN 202410816028 A CN202410816028 A CN 202410816028A CN 118378103 B CN118378103 B CN 118378103B
- Authority
- CN
- China
- Prior art keywords
- geographic information
- information data
- matched
- geographic
- target area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000007726 management method Methods 0.000 title claims abstract description 20
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 16
- 238000000034 method Methods 0.000 claims abstract description 48
- 238000013136 deep learning model Methods 0.000 claims abstract description 11
- 239000013598 vector Substances 0.000 claims description 39
- 230000008569 process Effects 0.000 claims description 32
- 238000013528 artificial neural network Methods 0.000 claims description 16
- 238000013527 convolutional neural network Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 claims description 4
- 238000005520 cutting process Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 abstract description 3
- 238000013523 data management Methods 0.000 abstract description 2
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000013439 planning Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009440 infrastructure construction Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000000547 structure data Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/042—Knowledge-based neural networks; Logical representations of neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Databases & Information Systems (AREA)
- Remote Sensing (AREA)
- Processing Or Creating Images (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a geographic information system data management method based on artificial intelligence, and relates to the technical field of data matching management. According to the geographic information system data matching management method based on artificial intelligence, feature extraction is carried out on a geographic information data set to be matched through a deep learning model, feature information of the geographic information data set to be matched is obtained, unmatched data pairs in the geographic information data set to be matched are identified through obtaining a target area geographic information data matching index, the unmatched data pairs in the geographic information data set to be matched are classified according to types and matching degrees, and a priority processing sequence is determined, so that efficient and accurate matching of the geographic information data is achieved, and unmatched data can be intelligently identified, classified and processed. The accuracy and the efficiency of data matching of the geographic information system are remarkably improved, the data matching precision is improved, and meanwhile, the integrity and the reliability of geographic information data are better maintained.
Description
Technical Field
The invention relates to the technical field of data management, in particular to a geographic information system data matching management method based on artificial intelligence.
Background
With the acceleration of the global urbanization process, urban population is continuously increased, urban scale is continuously enlarged, urban management and planning face great challenges, the application of a geographic information system in urban planning is increasingly wide, accurate and real-time geographic information support can be provided through efficient data matching and management, and scientific basis is provided for urban planning, land utilization, infrastructure construction and the like.
However, when the traditional geographic information system data matching management method is used for multi-source heterogeneous data, high-frequency data updating and geographic data with crossing, overlapping and other conditions, dynamic adaptability is lacked, and the data cannot be adapted to the change in time, so that the matching management result is inconsistent with the actual situation, and the problems of low processing efficiency and poor matching precision are solved.
Therefore, there is a need for an artificial intelligence-based data matching management method for a geographic information system to solve the above problems and improve data processing efficiency and matching accuracy.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a geographic information system data matching management method based on artificial intelligence, which solves the problems of the background art.
In order to achieve the above purpose, the invention is realized by the following technical scheme: a geographic information system data matching management method based on artificial intelligence comprises the following steps: s1, collecting geographic information data of a target area through a geographic information system, and preprocessing the data to obtain a geographic information data set to be matched; s2, extracting features of the geographic information data sets to be matched through a deep learning model, extracting spatial features, attribute features and topological relation features of the geographic information data sets to be matched, and obtaining feature information of the geographic information data sets to be matched; s3, carrying out feature matching on geographic position data, attribute features and topological features in the geographic information data set to be matched and geographic position data, attribute features and topological features in a geographic information system database respectively through a convolutional neural network and a word embedding model processed by natural language, and obtaining a target area geographic information data matching index; s4, comparing the geographic information data matching index of the target area with a preset matching index threshold value, identifying unmatched data pairs in the geographic information data set to be matched, and marking; s5, classifying unmatched data in the geographic information data set to be matched according to types and matching degrees, determining a priority processing sequence, generating an abnormal information report, and notifying a geographic information system data manager.
Further, geographic information data of the target area are collected, data preprocessing is carried out, and the specific process of obtaining the geographic information data set to be matched is as follows: collecting geographic information data of a target area through a data source of a geographic information system, wherein the geographic information data comprises satellite image data, aviation image data and sensor data, and converting the satellite image data, the aviation image data and the sensor data into a unified data format; cutting the data according to the boundary of the target area, removing noise and error values in the geographic information data, and filling the missing values; and integrating the space information of the satellite image, the aerial image and the sensor data, and establishing a topological relation between geographic entities to form a geographic information data set to be matched.
Further, the specific process of extracting the spatial features, the attribute features and the topological relation features of the geographic information data set to be matched through the deep learning model and obtaining the feature information of the geographic information data set to be matched is as follows: the method comprises the steps of extracting spatial features of different scales of a geographic information data set to be matched through convolution operation of different levels by a convolution neural network, and obtaining geographic position data of the geographic information data set to be matched, wherein the geographic position data of the geographic information data set to be matched comprise a target area geographic position feature value and a geographic position image feature value; the method comprises the steps of taking attribute information of a geographic information data set to be matched as input through a fully-connected neural network, extracting attribute characteristics through processing of a fully-connected layer, and obtaining the attribute characteristics of the geographic information data set to be matched, wherein the attribute characteristics of the geographic information data set to be matched comprise geographic names of target areas, administrative division information and land utilization types; extracting topological relation features in the geographic information data set to be matched through a graph neural network, representing nodes by a target area road intersection and a connection point, and representing the target area road as an edge to obtain the topological features of the geographic information data set to be matched, wherein the topological features of the geographic information data set to be matched comprise the nodes and the edges of the target area; the characteristic information of the geographic information data set to be matched comprises geographic position data of the geographic information data set to be matched, attribute characteristics of the geographic information data set to be matched and topological characteristics of the geographic information data set to be matched.
Further, the specific process of performing feature matching on the geographic position data, the attribute features and the topological features in the geographic information data set to be matched with the geographic position data, the attribute features and the topological features in the geographic information system database is as follows: carrying out spatial feature matching on spatial relations between geographic position data in a geographic information data set to be matched and geographic position data in a geographic information system database through a convolutional neural network, and obtaining a target area geographic information data spatial matching index; matching attribute features in the geographic information data set to be matched with attribute features in a geographic information system database through a word embedding model processed by natural language to obtain a target region geographic information data attribute matching index; and matching the topological features in the geographic information data set to be matched with the topological features in the geographic information system database to obtain the topological matching index of the geographic information data of the target area.
Further, the specific process of obtaining the target area geographic information data space matching index is as follows: and comparing the geographic position characteristic value and the geographic position image characteristic value of the target area with the corresponding geographic characteristic values in a geographic information system database, obtaining the spatial similarity of geographic information data of the target area through calculating Euclidean distance and cosine similarity, and obtaining the spatial matching index of the geographic information data of the target area through comprehensive operation.
Further, the specific process of obtaining the target area geographic information data attribute matching index is as follows: converting the attribute characteristics of the geographic information data set to be matched into vector representation through a pre-trained word embedding model, calculating the similarity between the attribute characteristic vector of the geographic information data to be matched and the corresponding attribute characteristic vector in the geographic information system database, and obtaining the attribute matching index of the geographic information data of the target area.
Further, the specific process of obtaining the target area geographic information data topology matching index is as follows: the topological features of the geographic information data set to be matched are converted into vector representations by using a graph embedding technology, the similarity between the topological feature vectors of the geographic information data to be matched and the corresponding topological feature vectors in the geographic information system database is calculated, and comprehensive operation is carried out to obtain the topological matching index of the geographic information data of the target area.
Further, the specific process of obtaining the target area geographic information data matching index is as follows: and (3) distributing weights to the target area geographic information data space matching index, the target area geographic information data attribute matching index and the target area geographic information data topology matching index, and carrying out comprehensive operation to obtain the target area geographic information data matching index.
Further, the specific process of classifying the unmatched data in the geographic information data set to be matched according to the type and the matching degree and determining the priority processing sequence is as follows: classifying according to the mismatch of the spatial features, the attribute features and the topological relation, and carrying out priority processing and sorting according to the size of the target area geographic information data spatial matching index, the target area geographic information data attribute matching index and the target area geographic information data topological matching index.
The invention has the following beneficial effects:
(1) According to the geographic information system data matching management method based on artificial intelligence, feature extraction is carried out on the geographic information data set to be matched through the deep learning model, feature information of the geographic information data set to be matched is obtained, accuracy and efficiency of geographic information system data matching are remarkably improved, manual intervention is reduced, error rate in a manual processing process is reduced, overall processing efficiency and consistency are improved, and data matching precision is improved.
(2) According to the geographic information system data matching management method based on artificial intelligence, the geographic information data matching index of the target area is obtained, the unmatched data pairs in the geographic information data set to be matched are identified, the unmatched data pairs in the geographic information data set to be matched are classified according to types and matching degrees, the priority processing sequence is determined, efficient and accurate matching of the geographic information data is achieved, and the unmatched data can be intelligently identified, classified and processed. The method not only greatly improves the efficiency and accuracy of data processing, but also can timely generate abnormal information reports and inform related personnel, thereby better maintaining the integrity and reliability of geographic information data.
Of course, it is not necessary for any one product to practice the invention to achieve all of the advantages set forth above at the same time.
Drawings
FIG. 1 is a flow chart of a geographic information system data matching management method based on artificial intelligence.
FIG. 2 is a flow chart of the method for obtaining the geographic information data matching index of the target area.
Detailed Description
The embodiment of the application solves the problems of low processing efficiency and poor matching precision when facing to multi-source heterogeneous data, high-frequency data updating, crossing, overlapping and other geographic data through an artificial intelligence-based geographic information system data matching management method.
The problems in the embodiment of the application have the following general ideas:
And collecting geographic information data of the target area through a geographic information system, and preprocessing the data to obtain a geographic information data set to be matched.
And extracting the characteristics of the geographic information data set to be matched through the deep learning model, extracting the spatial characteristics, the attribute characteristics and the topological relation characteristics of the geographic information data set to be matched, and obtaining the characteristic information of the geographic information data set to be matched.
And respectively carrying out feature matching on the geographic position data, the attribute features and the topological features in the geographic information data set to be matched and the geographic position data, the attribute features and the topological features in the geographic information system database through a convolutional neural network and a word embedding model processed by natural language, and obtaining a target area geographic information data matching index.
And comparing the target area geographic information data matching index with a preset matching index threshold value, identifying unmatched data pairs in the geographic information data set to be matched, and marking.
And classifying unmatched data in the geographic information data set to be matched according to the type and the matching degree, determining a priority processing sequence, generating an abnormal information report, and notifying a geographic information system data manager.
Referring to fig. 1, the embodiment of the invention provides a technical scheme: a geographic information system data matching management method based on artificial intelligence comprises the following steps: s1, collecting geographic information data of a target area through a geographic information system, and preprocessing the data to obtain a geographic information data set to be matched; s2, extracting features of the geographic information data sets to be matched through a deep learning model, extracting spatial features, attribute features and topological relation features of the geographic information data sets to be matched, and obtaining feature information of the geographic information data sets to be matched; s3, carrying out feature matching on geographic position data, attribute features and topological features in the geographic information data set to be matched and geographic position data, attribute features and topological features in a geographic information system database respectively through a convolutional neural network and a word embedding model processed by natural language, and obtaining a target area geographic information data matching index; s4, comparing the geographic information data matching index of the target area with a preset matching index threshold value, identifying unmatched data pairs in the geographic information data set to be matched, and marking; s5, classifying unmatched data in the geographic information data set to be matched according to types and matching degrees, determining a priority processing sequence, generating an abnormal information report, and notifying a geographic information system data manager.
In this embodiment, deep learning is a machine learning method, and the core idea is to learn the feature representation of data through a multi-level neural network model. These models consist of multiple neural network layers, each of which transforms or processes the data to progressively extract an abstract feature representation of the data. The deep learning model is usually provided with a large number of parameters, and the parameters can be automatically learned through a large-scale data set in the training process, so that the modeling and learning of the complex data relationship are realized; in step S4, the target area geographic information data matching index is an index calculated according to the similarity and the matching degree between different features, and is used for measuring the matching degree between the geographic information data to be matched and the geographic information system database. The preset matching index threshold is a threshold set according to specific application scenes and requirements and is used for judging whether the matching index reaches an expected matching standard or not. By comparing the matching index with a preset threshold, which data pairs are unmatched can be determined, and by setting the preset matching index threshold, unmatched data pairs in the geographic information data set to be matched can be automatically identified, so that manual check is not needed one by one, and time and labor cost are saved.
Specifically, geographic information data of a target area are collected, data preprocessing is carried out, and the specific process of obtaining a geographic information data set to be matched is as follows: collecting geographic information data of a target area through a data source of a geographic information system, wherein the geographic information data comprises satellite image data, aviation image data and sensor data, and converting the satellite image data, the aviation image data and the sensor data into a unified data format; cutting the data according to the boundary of the target area, removing noise and error values in the geographic information data, and filling the missing values; and integrating the space information of the satellite image, the aerial image and the sensor data, and establishing a topological relation between geographic entities to form a geographic information data set to be matched.
In this embodiment, the geographic information data may be from a variety of sources, including satellite imagery, aerial imagery, sensor data, and the like. These data have different formats and resolutions, so it is necessary to consider how they are integrated into a unified data format at the time of acquisition; the boundaries of the target region may not be exactly coincident with the coverage of the data source, and therefore the data needs to be cropped to match the range of the target region. When integrating the space information of satellite images, aerial images and sensor data, topological relations among geographic entities need to be established, and subsequent data analysis and matching tasks are facilitated.
Specifically, the spatial features, attribute features and topological relation features of the geographic information data set to be matched are extracted through a deep learning model, and the specific process of obtaining the feature information of the geographic information data set to be matched is as follows: the method comprises the steps of extracting spatial features of different scales of a geographic information data set to be matched through convolution operation of different levels by a convolution neural network, and obtaining geographic position data of the geographic information data set to be matched, wherein the geographic position data of the geographic information data set to be matched comprise a target area geographic position feature value and a geographic position image feature value; the method comprises the steps of taking attribute information of a geographic information data set to be matched as input through a fully-connected neural network, extracting attribute characteristics through processing of a fully-connected layer, and obtaining the attribute characteristics of the geographic information data set to be matched, wherein the attribute characteristics of the geographic information data set to be matched comprise geographic names of target areas, administrative division information and land utilization types; extracting topological relation features in the geographic information data set to be matched through a graph neural network, representing nodes by a target area road intersection and a connection point, and representing the target area road as an edge to obtain the topological features of the geographic information data set to be matched, wherein the topological features of the geographic information data set to be matched comprise the nodes and the edges of the target area; the feature information of the geographic information data set to be matched comprises geographic position data of the geographic information data set to be matched, attribute features of the geographic information data set to be matched and topological features of the geographic information data set to be matched.
In this embodiment, the convolutional neural network is a deep learning model dedicated to processing image data, and is used to process the image data, and to extract characteristic representations of the data through different levels of convolutional operations. Here, extracting spatial features of the geographic information dataset, local and global features in the geographic data may be captured using convolution operations of different scales, wherein the geographic location data may include target region geographic location feature values and geographic location image feature values; fully connected neural networks are commonly used to process structured data, extracting a characteristic representation of the data through multiple fully connected layers. The attribute characteristics of the geographic information data set are extracted by using the fully-connected neural network, attribute information can be used as input, and attribute characteristic representation is obtained through the processing of the fully-connected layer, wherein the attribute characteristics comprise geographic names, administrative division information and land utilization types; the graph neural network is specially used for processing graph structure data, and can effectively capture the relation between nodes. Here, the topological relation features in the geographical information dataset are extracted using a graph neural network, the road intersections and the connection points are represented as nodes, and the roads are represented as edges, thereby obtaining the topological features of the geographical information dataset.
Specifically, the specific process of performing feature matching on the geographic position data, the attribute features and the topological features in the geographic information data set to be matched with the geographic position data, the attribute features and the topological features in the geographic information system database is as follows: carrying out spatial feature matching on spatial relations between geographic position data in a geographic information data set to be matched and geographic position data in a geographic information system database through a convolutional neural network, and obtaining a target area geographic information data spatial matching index; matching attribute features in the geographic information data set to be matched with attribute features in a geographic information system database through a word embedding model processed by natural language to obtain a target region geographic information data attribute matching index; and matching the topological features in the geographic information data set to be matched with the topological features in the geographic information system database to obtain the topological matching index of the geographic information data of the target area.
In this embodiment, the convolutional neural network is used to perform spatial feature extraction and matching on the geographic location data in the geographic information data set to be matched and the geographic location data in the geographic information system database; calculating the matching degree of the geographic information data set to be matched and geographic position data in a database by using cosine similarity or other similarity indexes through the feature vectors extracted by the convolutional neural network to obtain a spatial matching index; the word embedding model processed by natural language is used for processing attribute characteristics in the geographic information data set to be matched with attribute characteristics in the geographic information system database. The word embedding model is used for converting attribute features of geographic information into vector representations, and then calculating attribute matching indexes through vector similarity. And extracting topological features in the geographic information data set to be matched by using the graph neural network, and matching the topological features with the topological features in the database. The graph neural network is used for learning the topological structure of the geographic information data set, and calculating a topological matching index through the feature vectors of the nodes and the edges.
Specifically, the specific process of obtaining the target area geographic information data space matching index is as follows: and comparing the geographic position characteristic value and the geographic position image characteristic value of the target area with the corresponding geographic characteristic values in a geographic information system database, obtaining the spatial similarity of geographic information data of the target area through calculating Euclidean distance and cosine similarity, and obtaining the spatial matching index of the geographic information data of the target area through comprehensive operation.
In this embodiment, euclidean distance is used to calculate the spatial similarity of the geographic location feature values, which are numbered sequentially 1,2,3. Vectorizing the characteristic value of the geographic position image of the target area to obtain the characteristic vector of the geographic position image of the target area, wherein the specific formula of the spatial matching index of the geographic information data of the target area is as follows:
In the method, in the process of the invention, Representing a target region geographic information data space matching index, for measuring the target region geographic information data space matching degree,Representing the geographic location characteristic value of the a-th target area,Representing the characteristic value of the geographic location of the a-th target area corresponding to the geographic information system database,Image feature vectors representing the geographic location of the target area,Representing the geographic location image feature vectors in the database,AndThe norms of FP and FQ are represented,Representation ofAndA represents the number value of the geographic position characteristic value of the target area, b represents the total number of the geographic position characteristic values of the target area, and the larger the spatial matching index of the geographic information data of the target area is, the higher the spatial matching degree of the geographic information data of the target area is.
Specifically, the specific process of obtaining the target area geographic information data attribute matching index is as follows: converting the attribute characteristics of the geographic information data set to be matched into vector representation through a pre-trained word embedding model, calculating the similarity between the attribute characteristic vector of the geographic information data to be matched and the corresponding attribute characteristic vector in the geographic information system database, and obtaining the attribute matching index of the geographic information data of the target area.
In this embodiment, through a Word embedded model Word2Vec model that is pre-trained, the model is trained on a large amount of text data, so that semantic relations between words can be captured, geographic names, administrative division information, land utilization types of a target area and corresponding geographic names, administrative division information and land utilization types in a geographic information system database are analyzed, and the semantic relations are converted into corresponding vectors; examples of the conversion of different attribute features in the geographic information dataset into vector representations by the pre-training Word embedding model Word2Vec model are as follows:
the specific formula of the target area geographic information data attribute matching index is as follows:
In the method, in the process of the invention, The method comprises the steps of representing a target area geographic information data attribute matching index, wherein the index is used for the target area geographic information data attribute matching degree, xz represents a feature vector of a geographic name of a target area, gh represents a feature vector of a geographic name in a geographic information system database, vx represents a feature vector of administrative division information of the target area, cb represents a feature vector of administrative division information in the geographic information system database, kc represents a feature vector of a land utilization type of the target area, and Yb represents a feature vector of the land utilization type in the geographic information system database.
Specifically, the specific process of obtaining the topological matching index of the geographic information data of the target area is as follows: the topological features of the geographic information data set to be matched are converted into vector representations by using a graph embedding technology, the similarity between the topological feature vectors of the geographic information data to be matched and the corresponding topological feature vectors in the geographic information system database is calculated, and comprehensive operation is carried out to obtain the topological matching index of the geographic information data of the target area.
In this embodiment, the intersection and the connection point of the target area road represent nodes, the target area road represents edges, the topological feature (nodes and edges) of the geographic information data set to be matched is converted into vector representation by the graph embedding technology, the embedded vectors of the nodes and edges are combined to form an overall topological feature vector, the feature vector of the target area graph is obtained, all the nodes and edges are extracted from the geographic information data set to be matched, the nodes and edges in the geographic information data set to be matched are represented as a set A, the nodes and edges in the geographic information system database are represented as a set B, and the specific formula of the topological matching index of the geographic information data of the target area is as follows:
In the method, in the process of the invention, Represents a target area geographic information data topology matching index for measuring the target area geographic information data topology matching degree, cp represents a feature vector of a target area graph,Feature vectors representing corresponding graphs in the database, A representing node and edge sets in the geographic information data set to be matched, B representing node and edge sets in the geographic information system database,Representing the number of intersection elements of set a and set B,The number of union elements representing the set A and the set B measures the matching degree of nodes and edges in the geographic information data set to be matched with nodes and edges in the geographic information system database.
Referring to fig. 2, a specific process for obtaining the matching index of the geographic information data of the target area is as follows: and (3) distributing weights to the target area geographic information data space matching index, the target area geographic information data attribute matching index and the target area geographic information data topology matching index, and carrying out comprehensive operation to obtain the target area geographic information data matching index.
In this embodiment, the specific formula of the target area geographic information data matching index is as follows:
In the method, in the process of the invention, Representing a target area geographic information data matching index, for measuring the degree of matching of the target area geographic information data,Data space matching index representing geographic information of the target area,Data attributes representing the geographic information of the target area match the index,Data topology matching index representing geographic information of the target area,A weight coefficient representing a target region geographic information data space matching index,A weight coefficient representing a target region geographic information data attribute matching index,And the weight coefficient is used for adjusting and balancing the importance of different matching indexes when calculating the matching indexes of the geographic information data of the target area. By adjusting the weight coefficient, the proportion of the matching indexes in different aspects in the overall matching indexes is more reasonable, so that specific matching requirements and actual conditions are met.
Specifically, the specific process of classifying the unmatched data in the geographic information data set to be matched according to the type and the matching degree and determining the priority processing sequence is as follows: classifying according to the mismatch of the spatial features, the attribute features and the topological relation, and carrying out priority processing and sorting according to the size of the target area geographic information data spatial matching index, the target area geographic information data attribute matching index and the target area geographic information data topological matching index.
In the embodiment, the data pairs with unmatched spatial characteristics, the data pairs with unmatched attribute characteristics and the data pairs with unmatched topological relations are respectively classified into different categories; and evaluating the matching degree of the unmatched data pairs of each category, wherein the unmatched degree can be measured by using indexes such as a target area geographic information data space matching index, a target area geographic information data attribute matching index, a target area geographic information data topology matching index and the like, and the priority processing sequence is determined according to the matching index of the unmatched data pairs of different categories. Typically, data pairs with lower matching indices may affect the accuracy and efficiency of data matching, and thus unmatched data pairs with lower matching indices may be preferentially processed.
In summary, the present application has at least the following effects:
According to the geographic information system data matching management method based on artificial intelligence, feature information of geographic information data sets to be matched is obtained, unmatched data pairs in the geographic information data sets to be matched are identified by obtaining geographic information data matching indexes of target areas, the unmatched data pairs in the geographic information data sets to be matched are classified according to types and matching degrees, and priority processing sequences are determined, so that efficient and accurate matching of the geographic information data is achieved, and unmatched data can be intelligently identified, classified and processed. The accuracy and the efficiency of data matching of the geographic information system are remarkably improved, the data matching precision is improved, and meanwhile, the integrity and the reliability of geographic information data are better maintained.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of systems, apparatuses (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of 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 a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (2)
1. The geographic information system data matching management method based on artificial intelligence is characterized by comprising the following steps of:
S1, collecting geographic information data of a target area through a geographic information system, and preprocessing the data to obtain a geographic information data set to be matched;
S2, extracting features of the geographic information data sets to be matched through a deep learning model, extracting spatial features, attribute features and topological relation features of the geographic information data sets to be matched, and obtaining feature information of the geographic information data sets to be matched;
s3, carrying out feature matching on geographic position data, attribute features and topological features in the geographic information data set to be matched and geographic position data, attribute features and topological features in a geographic information system database respectively through a convolutional neural network and a word embedding model processed by natural language, and obtaining a target area geographic information data matching index;
s4, comparing the geographic information data matching index of the target area with a preset matching index threshold value, identifying unmatched data pairs in the geographic information data set to be matched, and marking;
S5, classifying unmatched data in the geographic information data set to be matched according to types and matching degrees, determining a priority processing sequence, generating an abnormal information report, and notifying a geographic information system data manager;
the step S1 of collecting the geographic information data of the target area through the geographic information system and preprocessing the data to obtain a geographic information data set to be matched, comprising the following steps:
Collecting geographic information data of a target area through a data source of a geographic information system, wherein the geographic information data comprises satellite image data, aviation image data and sensor data, and converting the satellite image data, the aviation image data and the sensor data into a unified data format;
cutting the data according to the boundary of the target area, removing noise and error values in the geographic information data, and filling the missing values;
integrating the space information of the satellite image, the aerial image and the sensor data, establishing a topological relation between geographic entities, and forming a geographic information data set to be matched;
And in the step S2, extracting the spatial characteristics, the attribute characteristics and the topological relation characteristics of the geographic information data set to be matched through the deep learning model, and acquiring the characteristic information of the geographic information data set to be matched, wherein the method comprises the following steps:
the method comprises the steps of extracting spatial features of different scales of a geographic information data set to be matched through convolution operation of different levels by a convolution neural network, and obtaining geographic position data of the geographic information data set to be matched, wherein the geographic position data of the geographic information data set to be matched comprise a target area geographic position feature value and a geographic position image feature value;
The method comprises the steps of taking attribute information of a geographic information data set to be matched as input through a fully-connected neural network, extracting attribute characteristics through processing of a fully-connected layer, and obtaining the attribute characteristics of the geographic information data set to be matched, wherein the attribute characteristics of the geographic information data set to be matched comprise geographic names of target areas, administrative division information and land utilization types;
Extracting topological relation features in the geographic information data set to be matched through a graph neural network, representing nodes by a target area road intersection and a connection point, and representing the target area road as an edge to obtain the topological features of the geographic information data set to be matched, wherein the topological features of the geographic information data set to be matched comprise the nodes and the edges of the target area;
The characteristic information of the geographic information data set to be matched comprises geographic position data of the geographic information data set to be matched, attribute characteristics of the geographic information data set to be matched and topological characteristics of the geographic information data set to be matched;
in the step S3, feature matching is performed on the geographic position data, the attribute features and the topological features in the geographic information data set to be matched with the geographic position data, the attribute features and the topological features in the geographic information system database, including:
carrying out spatial feature matching on spatial relations between geographic position data in a geographic information data set to be matched and geographic position data in a geographic information system database through a convolutional neural network, and obtaining a target area geographic information data spatial matching index;
Matching attribute features in the geographic information data set to be matched with attribute features in a geographic information system database through a word embedding model processed by natural language to obtain a target region geographic information data attribute matching index;
matching the topological features in the geographic information data set to be matched with the topological features in the geographic information system database to obtain a target area geographic information data topological matching index;
the specific process of acquiring the target area geographic information data space matching index is as follows:
Comparing the geographic position characteristic value and the geographic position image characteristic value of the target area with corresponding geographic characteristic values in a geographic information system database, obtaining the geographic information data space similarity of the target area through calculating Euclidean distance and cosine similarity, and obtaining the geographic information data space matching index of the target area through comprehensive operation;
the specific process of acquiring the target area geographic information data attribute matching index is as follows:
Converting attribute features of the geographic information data set to be matched into vector representations through a pre-trained word embedding model, calculating similarity between the attribute feature vectors of the geographic information data to be matched and corresponding attribute feature vectors in a geographic information system database, and obtaining a target region geographic information data attribute matching index;
the specific process of obtaining the target area geographic information data topology matching index is as follows:
Converting the topological features of the geographic information data set to be matched into vector representations by using a graph embedding technology, calculating the similarity between the topological feature vectors of the geographic information data to be matched and the corresponding topological feature vectors in the geographic information system database, and comprehensively calculating to obtain the topological matching index of the geographic information data of the target area;
the specific process of obtaining the target area geographic information data matching index is as follows:
And (3) distributing weights to the target area geographic information data space matching index, the target area geographic information data attribute matching index and the target area geographic information data topology matching index, and carrying out comprehensive operation to obtain the target area geographic information data matching index.
2. The geographical information system data matching management method based on artificial intelligence according to claim 1, wherein: the specific process of classifying the unmatched data in the geographic information data set to be matched according to the type and the matching degree and determining the priority processing sequence is as follows:
Classifying according to the mismatch of the spatial features, the attribute features and the topological relation, and carrying out priority processing and sorting according to the size of the target area geographic information data spatial matching index, the target area geographic information data attribute matching index and the target area geographic information data topological matching index.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410816028.6A CN118378103B (en) | 2024-06-24 | 2024-06-24 | Geographic information system data matching management method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410816028.6A CN118378103B (en) | 2024-06-24 | 2024-06-24 | Geographic information system data matching management method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118378103A CN118378103A (en) | 2024-07-23 |
| CN118378103B true CN118378103B (en) | 2024-09-06 |
Family
ID=91909027
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410816028.6A Active CN118378103B (en) | 2024-06-24 | 2024-06-24 | Geographic information system data matching management method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118378103B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104063466A (en) * | 2014-06-27 | 2014-09-24 | 深圳先进技术研究院 | Virtuality-reality integrated three-dimensional display method and virtuality-reality integrated three-dimensional display system |
| CN110472066A (en) * | 2019-08-07 | 2019-11-19 | 北京大学 | A kind of construction method of urban geography semantic knowledge map |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2389669A1 (en) * | 2009-01-21 | 2011-11-30 | Universiteit Gent | Geodatabase information processing |
| US9443005B2 (en) * | 2012-12-14 | 2016-09-13 | Instaknow.Com, Inc. | Systems and methods for natural language processing |
| CN112256888A (en) * | 2020-10-30 | 2021-01-22 | 南京师范大学 | Geographic knowledge acquisition method |
| CN112559747B (en) * | 2020-12-15 | 2024-05-28 | 北京百度网讯科技有限公司 | Event classification processing method, device, electronic equipment and storage medium |
| CN115984603A (en) * | 2022-11-24 | 2023-04-18 | 中国矿业大学 | Fine classification method and system for urban green land based on GF-2 and open map data |
| CN117893233A (en) * | 2023-11-23 | 2024-04-16 | 华东师范大学 | Regional industry value network analysis method based on heterogeneous graph structure learning |
-
2024
- 2024-06-24 CN CN202410816028.6A patent/CN118378103B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104063466A (en) * | 2014-06-27 | 2014-09-24 | 深圳先进技术研究院 | Virtuality-reality integrated three-dimensional display method and virtuality-reality integrated three-dimensional display system |
| CN110472066A (en) * | 2019-08-07 | 2019-11-19 | 北京大学 | A kind of construction method of urban geography semantic knowledge map |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118378103A (en) | 2024-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112270027B (en) | Paperless intelligent interactive examination method for city design based on entity model | |
| CN113434623B (en) | Fusion method based on multi-source heterogeneous space planning data | |
| CN114092832B (en) | High-resolution remote sensing image classification method based on parallel hybrid convolutional network | |
| CN108470022B (en) | Intelligent work order quality inspection method based on operation and maintenance management | |
| CN111428558A (en) | Vehicle detection method based on improved YO L Ov3 method | |
| CN109947881B (en) | POI weight judging method and device, mobile terminal and computer readable storage medium | |
| CN116503705B (en) | Fusion method of digital city multi-source data | |
| CN114840900B (en) | Automatic generation method of derivative BIM (building information modeling) component based on i-GBDT (generic block transformation) technology | |
| CN109583467B (en) | Electric power meteorological data fusion method and system | |
| CN116129262A (en) | Cultivated land suitability evaluation method and system for suitable mechanized transformation | |
| CN116720632A (en) | Engineering construction intelligent management method and system based on GIS and BIM | |
| CN115222988B (en) | Fine classification method for urban ground object PointEFF based on laser radar point cloud data | |
| CN115809833A (en) | Intelligent monitoring method and device for capital construction project based on portrait technology | |
| CN114661744A (en) | Terrain database updating method and system based on deep learning | |
| CN112015937B (en) | Picture geographic positioning method and system | |
| CN118378103B (en) | Geographic information system data matching management method based on artificial intelligence | |
| CN116541944B (en) | Carbon emission calculation method based on comprehensive oblique photography modeling model of transformer substation | |
| KR101545998B1 (en) | Method for Management Integration of Runoff-Hydraulic Model Data and System thereof | |
| CN117010373A (en) | Recommendation method for category and group to which asset management data of power equipment belong | |
| CN115272864A (en) | Real-scene three-dimensional building intelligent extraction method based on unmanned aerial vehicle aerial photography | |
| CN109816228A (en) | A kind of enterprise B IM technical application ability quantitative evaluation system and method | |
| CN118797088B (en) | Multi-source heterogeneous data matching method and device and electronic equipment | |
| CN118012977B (en) | AI and GIS fusion-based two-dimensional multi-mode data processing method | |
| CN117933030A (en) | Finite element calculation model modeling method, device, equipment and medium for power transmission tower | |
| CN115840829A (en) | Automatic retrieval method and device for difference part based on three-dimensional point cloud and BIM |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |