CN117633140A - Urban geological investigation method based on big data cloud computing technology - Google Patents
Urban geological investigation method based on big data cloud computing technology Download PDFInfo
- Publication number
- CN117633140A CN117633140A CN202410101530.9A CN202410101530A CN117633140A CN 117633140 A CN117633140 A CN 117633140A CN 202410101530 A CN202410101530 A CN 202410101530A CN 117633140 A CN117633140 A CN 117633140A
- Authority
- CN
- China
- Prior art keywords
- geological
- urban
- sampling points
- features
- information
- 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.)
- Granted
Links
- 238000005516 engineering process Methods 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000011835 investigation Methods 0.000 title claims abstract description 12
- 238000005070 sampling Methods 0.000 claims abstract description 170
- 239000011159 matrix material Substances 0.000 claims description 78
- 239000013598 vector Substances 0.000 claims description 36
- 238000009826 distribution Methods 0.000 claims description 18
- 238000003062 neural network model Methods 0.000 claims description 16
- 238000013527 convolutional neural network Methods 0.000 claims description 14
- 238000011176 pooling Methods 0.000 claims description 14
- 239000011435 rock Substances 0.000 claims description 12
- 230000004913 activation Effects 0.000 claims description 8
- 239000000203 mixture Substances 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 8
- 239000000463 material Substances 0.000 claims description 6
- 229910052500 inorganic mineral Inorganic materials 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 claims description 4
- 239000011707 mineral Substances 0.000 claims description 4
- 230000000704 physical effect Effects 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 238000005755 formation reaction Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 description 18
- 238000004458 analytical method Methods 0.000 description 16
- 230000006870 function Effects 0.000 description 11
- 230000008569 process Effects 0.000 description 9
- 238000013528 artificial neural network Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000010276 construction Methods 0.000 description 5
- 230000000875 corresponding effect Effects 0.000 description 4
- 239000000284 extract Substances 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000000547 structure data Methods 0.000 description 3
- 230000004931 aggregating effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 239000000306 component Substances 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000003213 activating effect Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
- Y02A30/60—Planning or developing urban green infrastructure
Abstract
The application discloses a city geological investigation method based on big data cloud computing technology, and relates to the field of geological investigation. Firstly, obtaining geological information of a plurality of urban geological sampling points, then, respectively carrying out information coding on the geological information of the urban geological sampling points to obtain geological information coding features of the urban geological sampling points, then, constructing and extracting spatial topological features among the geological information of the urban geological sampling points, then, obtaining global geological features of the spatial topological urban geological sampling points based on the geological information coding features of the urban geological sampling points and the spatial topological features, and finally, determining whether urban geological conditions meet preset standards based on the global geological features of the spatial topological urban geological sampling points. In this way, it can be determined whether the urban geological conditions of the city meet the predetermined criteria.
Description
Technical Field
The present application relates to the field of geological investigation, and more particularly, to a method of urban geological investigation based on big data cloud computing technology.
Background
Urban subways are an efficient, environment-friendly and energy-saving urban traffic mode, but the construction of the urban subways needs to consider various factors, especially urban geological conditions. Urban geological conditions directly influence the design, construction and operation of urban subways. Therefore, accurate, comprehensive and rapid assessment of urban geology is an important link for urban subway construction feasibility analysis.
However, the traditional urban geological evaluation method mainly depends on manual sampling and expert opinion, and the method has the problems of limited sampling points, strong subjectivity and the like, and cannot evaluate urban geological conditions comprehensively and accurately.
Thus, an optimized solution is desired.
Disclosure of Invention
The present application has been made in order to solve the above technical problems. The application provides a city geological investigation method based on big data cloud computing technology, which can utilize artificial intelligence technology based on deep learning to perform feature extraction and joint analysis on geological information and space topology information of a plurality of city geological sampling points so as to judge whether city geological conditions of the city meet preset standards.
According to one aspect of the present application, there is provided a method of urban geological investigation based on big data cloud computing technology, comprising:
obtaining geological information of a plurality of urban geological sampling points;
respectively carrying out information coding on the geological information of a plurality of urban geological sampling points to obtain geological information coding characteristics of the plurality of urban geological sampling points;
constructing and extracting spatial topological features among geological information of a plurality of urban geological sampling points;
obtaining global geological features of the urban geological sampling points of the space topology based on geological information coding features and the space topology features of the urban geological sampling points of the plurality of cities;
and determining whether the urban geological conditions meet the predetermined criteria based on the global geological features of the spatial topological urban geological sampling points.
Geological information includes material composition, structure, architecture, physical properties, chemical properties, rock properties, mineral composition, production status and contact relationships of rock formations and rock masses.
Respectively carrying out information coding on the geological information of a plurality of urban geological sampling points to obtain geological information coding characteristics of the plurality of urban geological sampling points, and comprising the following steps:
respectively carrying out full-connection coding on the geological information of a plurality of urban geological sampling points to obtain geological information coding feature vectors of the plurality of urban geological sampling points;
and taking the geological information coding feature vectors of the plurality of urban geological sampling points as geological information coding features of the plurality of urban geological sampling points.
Constructing and extracting spatial topological features between geological information of a plurality of urban geological sampling points, comprising:
constructing a space topology matrix among geological information of a plurality of urban geological sampling points;
passing the space topology matrix through a space topology feature extractor based on a convolutional neural network model to obtain a space topology feature matrix;
and taking the space topology characteristic matrix as the space topology characteristic.
The characteristic value of each position on the non-diagonal position in the space topology matrix is the space distance between two corresponding city geological sampling points.
The spatial topological feature extractor based on the convolutional neural network model comprises an input layer, a convolutional layer, an activation layer, a pooling layer and an output layer.
Obtaining global geological features of the spatial topological urban geological sampling points based on geological information coding features and spatial topological features of the plurality of urban geological sampling points, comprising:
the method comprises the steps that geological information coding feature vectors and space topological feature matrixes of a plurality of urban geological sampling points are subjected to a graph neural network model to obtain a global geological feature matrix of the space topological urban geological sampling points;
and taking the global geological feature matrix of the space topological urban geological sampling points as the global geological feature of the space topological urban geological sampling points.
Based on the global geological features of the spatial topological urban geological sampling points, determining whether the urban geological conditions meet the predetermined standard comprises:
performing feature distribution optimization on the global geological feature matrix of the space topology urban geological sampling points to obtain an optimized global geological feature matrix of the space topology urban geological sampling points;
and the optimized space topology urban geological sampling point global geological feature matrix is passed through a classifier to obtain a classification result, and the classification result is used for indicating whether urban geological conditions meet preset standards.
Compared with the prior art, the urban geological investigation method based on the big data cloud computing technology is characterized in that firstly geological information of a plurality of urban geological sampling points is obtained, then the geological information of the urban geological sampling points is respectively subjected to information coding to obtain geological information coding features of the urban geological sampling points, then spatial topological features among the geological information of the urban geological sampling points are constructed and extracted, then global geological features of the spatial topological urban geological sampling points are obtained based on the geological information coding features of the urban geological sampling points and the spatial topological features, and finally whether urban geological conditions accord with preset standards is determined based on the global geological features of the spatial topological urban geological sampling points. In this way, it can be determined whether the urban geological conditions of the city meet the predetermined criteria.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly introduced below, which are not intended to be drawn to scale in terms of actual dimensions, with emphasis on illustrating the gist of the present application.
FIG. 1 is a flow chart of a method of urban geological survey based on big data cloud computing technology according to an embodiment of the present application;
FIG. 2 is a schematic architecture diagram of a method of urban geological survey based on big data cloud computing technology according to an embodiment of the present application;
FIG. 3 is a flowchart of sub-step S120 of a method of urban geological survey based on big data cloud computing technology according to an embodiment of the present application;
FIG. 4 is a flowchart of sub-step S130 of a method of urban geological survey based on big data cloud computing technology according to an embodiment of the present application;
FIG. 5 is a flowchart of sub-step S140 of a method of urban geological survey based on big data cloud computing technology according to an embodiment of the present application;
FIG. 6 is a flowchart of sub-step S150 of a method of urban geological survey based on big data cloud computing technology according to an embodiment of the present application;
FIG. 7 is a block diagram of a city geological survey system based on big data cloud computing technology in accordance with an embodiment of the present application;
fig. 8 is an application scenario diagram of a city geological survey method based on big data cloud computing technology according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some, but not all embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present application without making any inventive effort, are also within the scope of the present application.
As used in this application and in the claims, the terms "a," "an," "the," and/or "the" are not specific to the singular, but may include the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
Although the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server. The modules are merely illustrative, and different aspects of the systems and methods may use different modules.
Flowcharts are used in this application to describe the operations performed by systems according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
Aiming at the technical problems, the technical conception of the method is to utilize an artificial intelligence technology based on deep learning to perform feature extraction and joint analysis on geological information and space topology information of a plurality of urban geological sampling points so as to judge whether urban geological conditions of the city meet preset standards.
Based on this, fig. 1 is a flowchart of a city geological survey method based on big data cloud computing technology according to an embodiment of the present application. Fig. 2 is a schematic architecture diagram of a city geological survey method based on big data cloud computing technology according to an embodiment of the present application. As shown in fig. 1 and 2, the urban geological survey method based on big data cloud computing technology according to the embodiment of the application includes the steps of: s110, obtaining geological information of a plurality of urban geological sampling points; s120, respectively carrying out information coding on the geological information of the plurality of urban geological sampling points to obtain geological information coding characteristics of the plurality of urban geological sampling points; s130, constructing and extracting spatial topological features among geological information of the urban geological sampling points; s140, obtaining global geological features of the space topological urban geological sampling points based on geological information coding features of the urban geological sampling points and the space topological features; and S150, determining whether the urban geological conditions meet a preset standard or not based on the global geological features of the space topological urban geological sampling points.
It should be appreciated that in step S110, by collecting geological information of a plurality of urban geological sampling points, geological data about different sites may be obtained, which may include information on material composition, structure, architecture, etc. In step S120, the geological information collected from the different urban geological sampling points is encoded and converted into a specific data representation, which is done for the purpose of facilitating subsequent data processing and analysis. In step S130, spatial relationships between the geological data may be revealed by constructing and extracting spatial topological features between the plurality of urban geological sampling points, which may include distances between the geological sampling points, proximity relationships, etc., to aid in analyzing the spatial distribution features of the geological data. In step S140, a data representation describing global geological features of the urban geological sampling points may be obtained in combination with geological information encoding features and spatial topological features. These global features may provide more comprehensive and comprehensive urban geological information, facilitating further analysis and judgment. In step S150, urban geological conditions are evaluated and judged according to global geological features of the spatial topological urban geological sampling points to determine whether the urban geological conditions meet predetermined standards, and the process can help a decision maker to know urban geological conditions, evaluate potential geological risks and take corresponding measures to manage and plan urban development.
Specifically, in the technical scheme of the application, firstly, geological information of a plurality of urban geological sampling points is acquired, wherein the geological information comprises a material composition, a structure, physical properties, chemical properties, rock properties, mineral components, a production state and a contact relation of rock stratum and rock mass. It should be understood that urban geology is composed of different geological elements, and interactions exist between these geological elements, so that characteristics and rules of the urban geology are determined. The complexity and diversity of the urban geology can be reflected by acquiring the geological information, and the model is helped to fully understand and evaluate the actual situation of the urban geology, and even predict geological disasters and risks possibly encountered in the urban subway construction process.
And then, respectively carrying out full-connection coding on the geological information of the plurality of urban geological sampling points to obtain geological information coding feature vectors of the plurality of urban geological sampling points. That is, non-linear, unstructured geologic information is converted into dense feature vectors, thereby reducing the complexity and redundancy of the data. Specifically, full-concatenated coding is an unsupervised deep learning method that enables the hidden layer to capture the inherent structure and regularity of the input data by constructing a multi-layer neural network, mapping the input data to the hidden layer, and then reconstructing the input data from the hidden layer. Full-connection coding can effectively extract abstract features of geological information.
Accordingly, as shown in fig. 3, the step of respectively performing information encoding on the geological information of the plurality of urban geological sampling points to obtain geological information encoding features of the plurality of urban geological sampling points includes: s121, respectively performing full-connection coding on the geological information of the plurality of urban geological sampling points to obtain geological information coding feature vectors of the plurality of urban geological sampling points; and S122, taking the geological information coding feature vectors of the plurality of urban geological sampling points as geological information coding features of the plurality of urban geological sampling points.
It should be noted that, in step S121, the purpose of fully-connected encoding of the geological information of the plurality of urban geological sampling points is to obtain a geological information encoding feature vector of each urban geological sampling point, and this encoding feature vector can convert the original geological information into a vector representation with a fixed dimension for subsequent data processing and analysis. Full-connection coding is a common coding method, and the geological information of different sampling points is correlated by fully connecting the geological information of each urban geological sampling point with the geological information of other sampling points. This allows complex relationships and interactions between geologic information to be captured. With full-join encoding, the geologic information for each urban geologic sample may be represented as a fixed-length vector that contains features related to the geologic information for other samples. The coding feature vector can better reflect the comprehensive condition of urban geological features, and is beneficial to subsequent data analysis and model establishment. In other words, the fully-connected encoding in step S121 converts the geological information of the plurality of urban geological sampling points into encoded feature vectors, providing a more compact and comprehensive representation that provides a basis for subsequent geological data processing and analysis.
Then, constructing a space topology matrix among geological information of the plurality of urban geological sampling points, wherein the characteristic value of each position on the non-diagonal position in the space topology matrix is the space distance between two corresponding urban geological sampling points; and the space topology matrix passes through a space topology feature extractor based on a convolutional neural network model to obtain a space topology feature matrix. That is, spatial topological features are extracted to reflect correlations and effects between urban geological sampling points, thereby better describing the overall condition of the urban geology.
Accordingly, as shown in fig. 4, constructing and extracting spatial topological features between geological information of the plurality of urban geological sampling points includes: s131, constructing a space topology matrix among geological information of the urban geological sampling points; s132, the space topology matrix passes through a space topology feature extractor based on a convolutional neural network model to obtain a space topology feature matrix; and S133, taking the space topology feature matrix as the space topology feature. It should be understood that step S131, step S132, and step S133 are steps for constructing and extracting spatial topological features between geological information of a plurality of urban geological sampling points. The purpose of step S131 is to construct a spatial topology matrix between the geological information of the plurality of urban geological sampling points, which describes the spatial relationship between the sampling points, reflecting the information of distance, relative position, connectivity, etc. between them. By constructing a space topology matrix, the space relation of the geological sampling points can be converted into a structured representation form, and a foundation is provided for subsequent feature extraction and analysis. Step S132 uses a space topology feature extractor based on a convolutional neural network model to process the constructed space topology matrix to obtain a space topology feature matrix, wherein the feature matrix captures the space topology features among geological sampling points and can contain information such as distance, direction, connection relation and the like. By using the convolutional neural network model, the features can be effectively extracted and represented as a matrix form, which facilitates subsequent data processing and analysis. In summary, steps S131 and S132 are used to construct and extract spatial topological features between the geological information of multiple urban geological sampling points, respectively, to provide more comprehensive and comprehensive information for urban geological investigation and analysis.
Wherein, in step S132, the spatial topology feature extractor based on the convolutional neural network model includes an input layer, a convolutional layer, an activation layer, a pooling layer, and an output layer. It is worth mentioning that convolutional neural network (Convolutional Neural Network, CNN) is a deep learning model, dedicated to processing data with a grid structure. The basic structure of the convolutional neural network comprises an input layer, a convolutional layer, an activation layer, a pooling layer and an output layer. The following are the functions and roles of the various layers: 1. input Layer (Input Layer): raw data is received as input, such as pixel values of an image or word vector representations of text. 2. Convolution layer (Convolutional Layer): features of the input data are extracted by a convolution operation. The convolution layer includes a plurality of convolution kernels (filters), each of which slides over the input data and computes a convolution operation, generating a Feature Map. 3. Activation Layer (Activation Layer): a nonlinear transformation is introduced and the output of the convolutional layer is processed by an activation function. Typical activation functions are ReLU (Rectified Linear Unit), sigmoid, tanh, etc. for introducing nonlinear features. 4. Pooling Layer (Pooling Layer): the space size of the feature map is reduced, and the number of parameters and the calculated amount are reduced. Common Pooling operations include Max Pooling (Max Pooling) and Average Pooling (Average Pooling), where the main features are extracted by performing an aggregation operation on the local area. 5. Output Layer (Output Layer): the characteristic representation of the previous hierarchy is converted into a final output result. The output layer may be a fully connected layer (Fully Connected Layer) or other suitable structure, depending on the particular task. The convolutional neural network gradually extracts abstract features of the input data through multi-layer convolutional, activating and pooling operations, and maps the features to final output results through a full connection layer.
Further, the plurality of urban geological sampling point geological information coding feature vectors and the space topological feature matrix are processed through a graph neural network model to obtain a space topological urban geological sampling point global geological feature matrix. Here, the graph neural network model can effectively process data of non-euclidean space, the connection relation between the urban geological sampling points is represented by the graph structure, the characteristic representation of the urban geological sampling points is learned by the neural network, and the urban geological conditions can be integrated in a transitive mode.
Accordingly, as shown in fig. 5, based on the plurality of urban geological sampling point geological information encoding features and the spatial topological feature to obtain a spatial topological urban geological sampling point global geological feature, the method comprises: s141, the urban geological sampling point geological information coding feature vectors and the space topological feature matrix are processed through a graph neural network model to obtain a space topological urban geological sampling point global geological feature matrix; and S142, taking the global geological feature matrix of the space topological urban geological sampling points as the global geological feature of the space topological urban geological sampling points. It should be understood that the purpose of step S141 is to pass the geological information encoding feature vectors and the spatial topological feature matrix of the plurality of urban geological sampling points through a neural network model to obtain a global geological feature matrix of the spatial topological urban geological sampling points. In particular, the graph neural network is a type of deep learning model that is specialized in processing graph structure data, in urban geological surveys, urban geological sampling points can be considered nodes of a graph, and the spatial topological relationships between them can be considered edges of the graph. Thus, by inputting the geologic information encoding feature vectors and the spatial topological feature matrices into the graphic neural network model, the ability of the graphic neural network model can be utilized to learn and capture complex relationships and global features between urban geologic sampling points. Through step S141, the neural network model of the map can perform joint modeling and learning on the geological information coding feature vector and the spatial topological feature matrix, extract global geological features of geological sampling points, and comprehensively consider geological information and spatial topological relation to reflect the overall features and modes of urban geology, so that the neural network model of the map can provide more comprehensive and comprehensive description and analysis of the urban geology, and support for subsequent geological risk assessment, resource planning and decision. In other words, step S141 processes the geological information encoding feature vector and the spatial topological feature matrix through the graph neural network model to obtain the global geological feature matrix of the spatial topological urban geological sampling point, thereby further enriching the characterization and analysis capability of geological data.
It is worth mentioning that the graph neural network (Graph Neural Network, GNN) is a machine learning model for processing graph structure data. Unlike conventional neural network models that process vector or sequence data, GNNs can effectively learn and represent relationships and global structures between nodes in the graph. The basic idea of the graph neural network is to update the representation of each node by iteratively aggregating the neighbor information of the nodes. In each iteration, the graph neural network updates the representation of the node according to the information of the neighbor nodes of the node, and then passes the updated representation to the next iteration. In this way, the representation of the node gradually merges the information of its surrounding nodes and is able to capture the features of the global graph structure. The core components of the graph neural network include node representation update functions and messaging mechanisms. The node representation update function defines how to update a representation of a node based on neighbor information of the node. The messaging mechanism defines how information is transferred and aggregated between nodes. Common graph neural network models include graph convolutional networks (Graph Convolutional Network, GCN), graph annotation force networks (Graph Attention Network, GAT), graph pooling networks (Graph Pooling Network), and the like. These models are widely used in different tasks and applications, such as node classification, graph generation, etc. In other words, the graph neural network model is a machine learning model capable of learning and representing graph structure data, and the relationships between the global features of the graph and the nodes are captured by iteratively aggregating neighbor information of the nodes to update the representation of the nodes.
And then, the global geological feature matrix of the spatial topological urban geological sampling points is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether urban geological conditions meet a preset standard.
Accordingly, as shown in fig. 6, determining whether the urban geological condition meets the predetermined criteria based on the global geological feature of the spatial topological urban geological sampling point includes: s151, performing feature distribution optimization on the global geological feature matrix of the space topology urban geological sampling points to obtain an optimized global geological feature matrix of the space topology urban geological sampling points; and S152, passing the optimized space topology urban geological sampling point global geological feature matrix through a classifier to obtain a classification result, wherein the classification result is used for indicating whether urban geological conditions meet preset standards.
It should be understood that in step S151, by optimizing the feature distribution of the global geological feature matrix, the features may be adjusted and optimized to better reflect the features and modes of the urban geology, so that the performance and accuracy of the subsequent classifier may be improved. In step S152, the optimized global geological feature matrix is input into the classifier, so as to perform classification judgment on the urban geological conditions. The classifier can divide the urban geological conditions into two categories according to the preset standard, namely meeting the standard and not meeting the standard. The classification results may be provided to decision makers and related professionals for assessing compliance and risk levels of urban geological conditions. In summary, the function of step S151 is to optimize the feature distribution of the global geological feature matrix of the spatial topological urban geological sampling points, so as to obtain a better feature representation. The function of step S152 is to pass the optimized feature matrix through a classifier to obtain a classification result of whether the urban geological condition meets the predetermined standard. The steps are combined, so that comprehensive evaluation and judgment can be performed on urban geological conditions, and reference basis is provided for decision making and planning.
Here, the plurality of urban geological sampling point geological information encoding feature vectors express encoding features of geological information of respective urban geological sampling points, such that the plurality of urban geological sampling point geological information encoding feature vectors and the spatial topological feature are obtainedAfter the matrix passes through the map neural network model, the topological association expression based on the spatial topology of the plurality of urban geological sampling points can be further carried out on the coding features of the geological information of each urban geological sampling point, but the spatial topological urban geological sampling point global geological feature vector corresponding to the urban geological sampling point geological information coding feature vector is considered, for example, the row vector belongs to the feature expression independence of the map neural network model, and when the spatial topological urban geological sampling point global geological feature matrix integrally passes through the classifier, the spatial topological urban geological sampling point global geological feature matrix has distribution sparsification due to the feature expression independence of the spatial topological urban geological sampling point global geological feature vector. Therefore, when the global geological feature matrix of the space topological urban geological sampling point is subjected to class probability regression mapping through the classifier, the convergence from the global geological feature matrix of the space topological urban geological sampling point to the predetermined class probability class representation in the probability space is poor, and the accuracy of the classification result is affected. Based on the above, the application is applied to the global geological feature matrix of the space topological urban geological sampling pointsAnd (5) optimizing.
Accordingly, in one example, in step S151, performing feature distribution optimization on the spatial topological urban geological sampling point global geological feature matrix to obtain an optimized spatial topological urban geological sampling point global geological feature matrix, including: performing feature distribution optimization on the global geological feature matrix of the space topological urban geological sampling points by using the following optimization formula to obtain the global geological feature matrix of the optimized space topological urban geological sampling points; wherein, the optimization formula is:
wherein,representing the global geological feature matrix of the spatial topological urban geological sampling points>Global geological feature matrix representing urban geological sampling points of the spatial topology>Position-by-position square of>Intermediate weight matrices trainable for parameters, e.g. global geological feature matrices based on urban geological sampling points of the spatial topology>Is initially set to be the global geological feature matrix of the geological sampling points of the space topology city>Is also +.>For all identity matrices with eigenvalues 1, < +.>Representing a transition matrix +.>Position-by-position squaring map representing the transition matrix,/->Representing matrix addition, ++>Representing the dot multiplication by position of the matrix, +.>And representing the optimized space topology urban geological sampling point global geological feature matrix.
Here, to optimize the spatial topological urban geological sampling point global geological feature matrixThe distribution uniformity and consistency of the sparse probability density in the whole probability space are realized by a tail distribution strengthening mechanism similar to the standard cauchy distribution type, so that the global geological feature matrix of the space topological urban geological sampling point is ≡>Distance type space distribution in a high-dimensional feature space is subjected to space angle inclination-based distance distribution optimization so as to realize the global geological feature matrix of the space topological urban geological sampling points>The distance between each local feature distribution is weakly correlated, thereby improving the global geological feature matrix of the spatial topological urban geological sampling point>The uniformity and consistency of the overall probability density distribution layer relative to regression probability convergence are improved, and the class probability convergence effect, namely the convergence speed of the classification result and the accuracy of the classification result, is improved.
Further, in step S152, the optimized spatial topology urban geological sampling point global geological feature matrix is passed through a classifier to obtain a classification result, where the classification result is used to indicate whether the urban geological condition meets a predetermined standard, and the method includes: expanding the global geological feature matrix of the optimized space topology urban geological sampling points into an optimized classification feature vector according to a row vector or a column vector; performing full-connection coding on the optimized classification feature vector by using a full-connection layer of the classifier to obtain a coding classification feature vector; and inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.
That is, in the technical solution of the present application, the labels of the classifier include that the urban geological condition meets a predetermined standard (first label), and that the urban geological condition does not meet a predetermined standard (second label), where the classifier determines, through a soft maximum function, to which classification label the optimized spatial topology urban geological sampling point global geological feature matrix belongs. It should be noted that the first tag p1 and the second tag p2 do not include a manually set concept, and in fact, during the training process, the computer model does not have a concept of "whether the urban geological condition meets the predetermined standard", which is simply that there are two kinds of classification tags and the probability that the output feature is under the two kinds of classification tags, that is, the sum of p1 and p2 is one. Therefore, the classification result of whether the urban geological condition meets the preset standard is actually converted into the classified probability distribution conforming to the natural rule through classifying the labels, and the physical meaning of the natural probability distribution of the labels is essentially used instead of the language text meaning of whether the urban geological condition meets the preset standard.
It should be appreciated that the role of the classifier is to learn the classification rules and classifier using a given class, known training data, and then classify (or predict) the unknown data. Logistic regression (logistics), SVM, etc. are commonly used to solve the classification problem, and for multi-classification problems (multi-class classification), logistic regression or SVM can be used as well, but multiple bi-classifications are required to compose multiple classifications, but this is error-prone and inefficient, and the commonly used multi-classification method is the Softmax classification function.
In summary, a method for urban geological investigation based on big data cloud computing technology according to the embodiments of the present application is illustrated, which can determine whether urban geological conditions of the city meet predetermined criteria.
Fig. 7 is a block diagram of a city geological survey system 100 based on big data cloud computing technology in accordance with an embodiment of the present application. As shown in fig. 7, the urban geological survey system 100 based on big data cloud computing technology according to an embodiment of the present application includes: a geological information obtaining module 110 for obtaining geological information of a plurality of urban geological sampling points; the information encoding module 120 is configured to encode the geological information of the plurality of urban geological sampling points to obtain geological information encoding features of the plurality of urban geological sampling points; a spatial topological feature construction module 130 for constructing and extracting spatial topological features between geological information of the plurality of urban geological sampling points; a global geological feature acquisition module 140, configured to obtain a global geological feature of the spatial topological urban geological sampling point based on the geological information coding features of the plurality of urban geological sampling points and the spatial topological feature; and a city geological condition analysis module 150 for determining whether city geological conditions meet a predetermined criterion based on the spatial topology city geological sampling point global geological features.
In one example, in the above-described urban geological survey system 100 based on big data cloud computing technology, the geological information includes material composition, structure, architecture, physical properties, chemical properties, rock properties, mineral composition, production status of rock formations and rock mass, and contact relationships.
Here, it will be understood by those skilled in the art that the specific functions and operations of the respective modules in the above-described urban geological survey system 100 based on the big data cloud computing technology have been described in detail in the above description of the urban geological survey method based on the big data cloud computing technology with reference to fig. 1 to 6, and thus, repetitive descriptions thereof will be omitted.
As described above, the urban geological survey system 100 based on the big data cloud computing technology according to the embodiment of the present application may be implemented in various wireless terminals, such as a server or the like having an urban geological survey algorithm based on the big data cloud computing technology. In one example, the big data cloud computing technology based urban geological survey system 100 according to embodiments of the present application may be integrated into a wireless terminal as one software module and/or hardware module. For example, the big data cloud computing technology based urban geological survey system 100 may be a software module in the operating system of the wireless terminal, or may be an application developed for the wireless terminal; of course, the urban geological survey system 100 based on big data cloud computing technology can also be one of the many hardware modules of the wireless terminal.
Alternatively, in another example, the big data cloud computing technology based city geological survey system 100 and the wireless terminal may also be separate devices, and the big data cloud computing technology based city geological survey system 100 may be connected to the wireless terminal through a wired and/or wireless network and communicate interactive information in a agreed data format.
Fig. 8 is an application scenario diagram of a city geological survey method based on big data cloud computing technology according to an embodiment of the present application. As shown in fig. 8, in this application scenario, first, the geological information of a plurality of urban geological sampling points (for example, D illustrated in fig. 8) is acquired, and then, the geological information of the plurality of urban geological sampling points is input to a server (for example, S illustrated in fig. 8) in which a big data cloud computing technology-based urban geological survey algorithm is deployed, wherein the server is capable of processing the geological information of the plurality of urban geological sampling points using the big data cloud computing technology-based urban geological survey algorithm to obtain a classification result for indicating whether or not urban geological conditions meet a predetermined standard.
Further, it is worth mentioning that big data cloud computing technology refers to combining big data processing and storing capabilities with cloud computing technology to achieve efficient, scalable and economical big data processing and analysis. The cloud computing system utilizes a cloud computing resource pool, elastic expansion and distributed computing capacity to store, process and analyze large-scale data.
According to the big data cloud computing technology, data are stored in a distributed storage system on a cloud platform, a data processing task is decomposed into a plurality of parallel tasks, and parallel processing is performed by utilizing computing resources of a cloud computing cluster. This distributed computing approach can greatly increase the speed and efficiency of data processing.
Meanwhile, the big data cloud computing technology also provides the capability of elastic expansion, and the scale of computing resources can be automatically adjusted according to actual demands so as to cope with data processing tasks with different scales and complexity. Thus, the cost can be saved, and the performance and effect of data processing are ensured.
Big data cloud computing technology also provides various data processing and analysis tools, such as distributed file systems, distributed databases, data mining and machine learning tools, etc., to help users better manage and analyze large-scale data sets.
In summary, big data cloud computing technology combines the advantages of big data processing and cloud computing, providing an efficient, scalable and economical big data processing and analysis solution.
Furthermore, those skilled in the art will appreciate that the various aspects of the invention are illustrated and described in the context of a number of patentable categories or circumstances, including any novel and useful procedures, machines, products, or materials, or any novel and useful modifications thereof. Accordingly, aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The foregoing is illustrative of the present invention and is not to be construed as limiting thereof. Although a few exemplary embodiments of this invention have been described, those skilled in the art will readily appreciate that many modifications are possible in the exemplary embodiments without materially departing from the novel teachings and advantages of this invention. Accordingly, all such modifications are intended to be included within the scope of this invention as defined in the following claims. It is to be understood that the foregoing is illustrative of the present invention and is not to be construed as limited to the specific embodiments disclosed, and that modifications to the disclosed embodiments, as well as other embodiments, are intended to be included within the scope of the appended claims. The invention is defined by the claims and their equivalents.
Claims (8)
1. A city geological investigation method based on big data cloud computing technology is characterized by comprising the following steps:
obtaining geological information of a plurality of urban geological sampling points;
respectively carrying out information coding on the geological information of the plurality of urban geological sampling points to obtain geological information coding characteristics of the plurality of urban geological sampling points;
constructing and extracting spatial topological features among the geological information of the urban geological sampling points;
obtaining global geological features of the space topological urban geological sampling points based on the geological information coding features of the urban geological sampling points and the space topological features;
and determining whether the urban geological conditions meet a predetermined standard based on the global geological features of the space topology urban geological sampling points.
2. The method of urban geological survey based on big data cloud computing technology of claim 1, wherein said geological information includes material composition, structure, architecture, physical properties, chemical properties, rock properties, mineral composition, production status of rock formations and rock mass and contact relationships.
3. The urban geological survey method based on big data cloud computing technology according to claim 2, wherein the step of respectively performing information encoding on the geological information of the plurality of urban geological sampling points to obtain geological information encoding features of the plurality of urban geological sampling points comprises the steps of:
respectively carrying out full-connection coding on the geological information of the plurality of urban geological sampling points to obtain geological information coding feature vectors of the plurality of urban geological sampling points;
and taking the geological information coding feature vectors of the plurality of urban geological sampling points as geological information coding features of the plurality of urban geological sampling points.
4. The method of urban geological survey based on big data cloud computing technology of claim 3, wherein constructing and extracting spatial topological features between geological information of the plurality of urban geological sampling points comprises:
constructing a space topology matrix among the geological information of the plurality of urban geological sampling points;
the space topology matrix passes through a space topology feature extractor based on a convolutional neural network model to obtain a space topology feature matrix;
and taking the spatial topological feature matrix as the spatial topological feature.
5. The urban geological survey method based on big data cloud computing technology according to claim 4, wherein the characteristic value of each position on the off-diagonal position in the spatial topology matrix is a spatial distance between two corresponding urban geological sampling points.
6. The method for urban geological survey based on big data cloud computing technology of claim 5, wherein said spatial topology feature extractor based on convolutional neural network model comprises an input layer, a convolutional layer, an activation layer, a pooling layer and an output layer.
7. The method of urban geological survey based on big data cloud computing technology of claim 6, wherein deriving spatial topological urban geological sampling point global geological features based on the plurality of urban geological sampling point geological information encoding features and the spatial topological features comprises:
the geological information coding feature vectors of the urban geological sampling points and the space topological feature matrix are processed through a graph neural network model to obtain a space topological urban geological sampling point global geological feature matrix;
and taking the global geological feature matrix of the spatial topological urban geological sampling points as the global geological feature of the spatial topological urban geological sampling points.
8. The method of urban geological survey based on big data cloud computing technology of claim 7, wherein determining whether urban geological conditions meet predetermined criteria based on global geological features of the spatial topological urban geological sampling points comprises:
performing feature distribution optimization on the global geological feature matrix of the space topology urban geological sampling points to obtain an optimized global geological feature matrix of the space topology urban geological sampling points;
and the optimized space topology urban geological sampling point global geological feature matrix is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether urban geological conditions meet preset standards.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410101530.9A CN117633140B (en) | 2024-01-25 | 2024-01-25 | Urban geological investigation method based on big data cloud computing technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410101530.9A CN117633140B (en) | 2024-01-25 | 2024-01-25 | Urban geological investigation method based on big data cloud computing technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117633140A true CN117633140A (en) | 2024-03-01 |
| CN117633140B CN117633140B (en) | 2024-04-16 |
Family
ID=90034199
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410101530.9A Active CN117633140B (en) | 2024-01-25 | 2024-01-25 | Urban geological investigation method based on big data cloud computing technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117633140B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050171700A1 (en) * | 2004-01-30 | 2005-08-04 | Chroma Energy, Inc. | Device and system for calculating 3D seismic classification features and process for geoprospecting material seams |
| CN114969325A (en) * | 2022-04-21 | 2022-08-30 | 武汉市测绘研究院 | Multi-element urban geological big data storage management and mining analysis system |
| US20230161061A1 (en) * | 2020-05-06 | 2023-05-25 | Exxonmobil Upstream Research Company | Structured representations of subsurface features for hydrocarbon system and geological reasoning |
| CN116245013A (en) * | 2022-12-29 | 2023-06-09 | 中国地质大学（武汉） | Geological prediction model construction method, modeling method, equipment and storage medium |
| CN116486030A (en) * | 2023-05-15 | 2023-07-25 | 中山大学 | Modeling method and related device of three-dimensional geologic body model based on surface image |
| CN116486025A (en) * | 2023-04-13 | 2023-07-25 | 济南市勘察测绘研究院 | Urban geological data processing platform based on big data cloud computing technology |
| US20230237221A1 (en) * | 2022-01-27 | 2023-07-27 | Huazhong University Of Science And Technology | Geologically constrained infrared imaging detection method and system for urban deeply-buried strip-like passage |
| CN116665067A (en) * | 2023-08-01 | 2023-08-29 | 吉林大学 | Ore finding target area optimization system and method based on graph neural network |
| CN116910611A (en) * | 2023-06-30 | 2023-10-20 | 湖南省三联环保科技有限公司 | Intelligent environment monitoring system and method based on big data |
| CN117237559A (en) * | 2023-11-10 | 2023-12-15 | 陕西天润科技股份有限公司 | Digital twin city-oriented three-dimensional model data intelligent analysis method and system |
-
2024
- 2024-01-25 CN CN202410101530.9A patent/CN117633140B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050171700A1 (en) * | 2004-01-30 | 2005-08-04 | Chroma Energy, Inc. | Device and system for calculating 3D seismic classification features and process for geoprospecting material seams |
| US20230161061A1 (en) * | 2020-05-06 | 2023-05-25 | Exxonmobil Upstream Research Company | Structured representations of subsurface features for hydrocarbon system and geological reasoning |
| US20230237221A1 (en) * | 2022-01-27 | 2023-07-27 | Huazhong University Of Science And Technology | Geologically constrained infrared imaging detection method and system for urban deeply-buried strip-like passage |
| CN114969325A (en) * | 2022-04-21 | 2022-08-30 | 武汉市测绘研究院 | Multi-element urban geological big data storage management and mining analysis system |
| CN116245013A (en) * | 2022-12-29 | 2023-06-09 | 中国地质大学（武汉） | Geological prediction model construction method, modeling method, equipment and storage medium |
| CN116486025A (en) * | 2023-04-13 | 2023-07-25 | 济南市勘察测绘研究院 | Urban geological data processing platform based on big data cloud computing technology |
| CN116486030A (en) * | 2023-05-15 | 2023-07-25 | 中山大学 | Modeling method and related device of three-dimensional geologic body model based on surface image |
| CN116910611A (en) * | 2023-06-30 | 2023-10-20 | 湖南省三联环保科技有限公司 | Intelligent environment monitoring system and method based on big data |
| CN116665067A (en) * | 2023-08-01 | 2023-08-29 | 吉林大学 | Ore finding target area optimization system and method based on graph neural network |
| CN117237559A (en) * | 2023-11-10 | 2023-12-15 | 陕西天润科技股份有限公司 | Digital twin city-oriented three-dimensional model data intelligent analysis method and system |
Non-Patent Citations (4)
| Title |
|---|
| HILLIER, MICHAEL 等: "Three-Dimensional Structural Geological Modeling Using Graph Neural Networks", MATHEMATICAL GEOSCIENCES, vol. 53, no. 8, 31 December 2021 (2021-12-31), pages 1725 - 1749, XP037622408, DOI: 10.1007/s11004-021-09945-x * |
| 胡伟;: "城市地质环境三维建模与可视化", 智能城市, no. 20, 28 October 2018 (2018-10-28) * |
| 郑坤;侯卫生;刘修国;: "城市三维地质调查数据库", 地球科学(中国地质大学学报), no. 05, 25 September 2006 (2006-09-25) * |
| 陈占龙;吕梦楼;吴亮;徐永洋;: "基于特征矩阵和关联图的空间场景相似性度量方法", 武汉大学学报(信息科学版), no. 07, 12 July 2016 (2016-07-12) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117633140B (en) | 2024-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109492099B (en) | Cross-domain text emotion classification method based on domain impedance self-adaption | |
| WO2022083624A1 (en) | Model acquisition method, and device | |
| CN110597735A (en) | Software defect prediction method for open-source software defect feature deep learning | |
| CN114092832B (en) | High-resolution remote sensing image classification method based on parallel hybrid convolutional network | |
| CN112685504B (en) | Production process-oriented distributed migration chart learning method | |
| CN111008337B (en) | Deep attention rumor identification method and device based on ternary characteristics | |
| CN114019370B (en) | Motor fault detection method based on gray level image and lightweight CNN-SVM model | |
| CN113378913A (en) | Semi-supervised node classification method based on self-supervised learning | |
| CN117237559B (en) | Digital twin city-oriented three-dimensional model data intelligent analysis method and system | |
| CN113989544A (en) | Group discovery method based on deep map convolution network | |
| CN114373092A (en) | Progressive training fine-grained vision classification method based on jigsaw arrangement learning | |
| CN113516019A (en) | Hyperspectral image unmixing method and device and electronic equipment | |
| CN108898157B (en) | Classification method for radar chart representation of numerical data based on convolutional neural network | |
| CN117633140B (en) | Urban geological investigation method based on big data cloud computing technology | |
| CN109614984A (en) | A kind of homologous image detecting method and system | |
| CN114265954B (en) | Graph representation learning method based on position and structure information | |
| CN115861664A (en) | Feature matching method and system based on local feature fusion and self-attention mechanism | |
| Zhang et al. | End‐to‐end generation of structural topology for complex architectural layouts with graph neural networks | |
| CN111768214A (en) | Product attribute prediction method, system, device and storage medium | |
| CN115174421B (en) | Network fault prediction method and device based on self-supervision unwrapping hypergraph attention | |
| CN116244484B (en) | Federal cross-modal retrieval method and system for unbalanced data | |
| CN117314892B (en) | Incremental learning-based continuous optimization method for solar cell defect detection | |
| CN117171413B (en) | Data processing system and method for digital collection management | |
| CN110210988B (en) | Symbolic social network embedding method based on deep hash | |
| CN117540247A (en) | Comprehensive decision method, system and medium for preference learning based on graph neural network |
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 |