Land space optimization strategy generation method and system

Through structured learning Bayesian network and conditional random airport algorithm, analyzing land space resource data is generated and a dependency relationship diagram is solved, which solves the problems of low efficiency and inaccurateness in traditional land space planning, and realizes a more accurate land space optimization strategy generate.

CN119005385APending Publication Date: 2024-11-22ZHEJIANG UNIV OF FINANCE & ECONOMICS
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410922558.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-10
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

Traditional land space planning and management rely on manual experience, is inefficient, easy to miss, and is inaccurate, making it difficult to accurately model and quantify the complex dependencies between land space resource data.

Method used

The Bayesian network and conditional random field algorithm are used to analyze the interrelationship and conditional dependence between land and space resource data, generate a dependency relationship diagram, and generate a land space optimization strategy based on the graph and planning requirements.

Benefits of technology

It improves the accuracy and depth of the understanding of the relationship between land and space resource data and the analysis results, and provides more accurate and comprehensive decision-making support for geospatial planning.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119005385A_ABST
    Figure CN119005385A_ABST
Patent Text Reader

Abstract

The invention discloses a territorial space optimization strategy generation method and system. The method comprises the following steps: S1, acquiring territorial space resource data; s2, according to the territorial space resource data, obtaining a dependency relation graph among the territorial space resource data; and S3, generating a territorial space optimization strategy according to the requirement of territorial space planning and the dependency relation graph between the territorial space resource data. By adopting the technical scheme of the invention, the complex dependency relationship among the territorial space resource data can be modeled and quantified more accurately, and the understanding of the mutual relationship among the data is improved, so that the analysis result is more accurate and deep.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of spatial information technology, and in particular relates to a method and system for generating a national land space optimization strategy. Background Art

[0003] Traditional land space planning and management often rely on manual experience, which leads to problems such as low efficiency, omissions, and inaccuracy. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method and system for generating a national land space optimization strategy.

[0005] To achieve the above object, the present invention adopts the following technical solution:

[0006] A method for generating a national land space optimization strategy, comprising:

[0007] Step S1, obtaining land space resource data;

[0008] Step S2: obtaining a dependency relationship diagram between the land and space resource data according to the land and space resource data;

[0009] Step S3: Generate a national land space optimization strategy based on the requirements of national land space planning and the dependency relationship diagram between national land space resource data.

[0010] Preferably, the national land space resource data include: land use data, topographic data, climate and meteorological data, and remote sensing image data.

[0011] Preferably, in step S2, a structured learning Bayesian network and conditional random field algorithm are used to analyze the mutual relationships and conditional dependencies among land space resource data and generate a dependency relationship diagram.

[0012] Preferably, step S3 comprises:

[0013] According to the dependency relationship diagram between the land and space resource data and the requirements of land and space planning, the regional management data, terrain planning data and functional planning data of the land and space resource data are obtained;

[0014] According to the regional management data, terrain planning data and functional planning data of the national land space resource data, a national land space resource reasoning expression tree is obtained;

[0015] According to the inference expression tree of land and space resources, the land and space optimization strategy is obtained.

[0016] The present invention also provides a national land space optimization strategy generation system, comprising:

[0017] An acquisition device for acquiring land and space resource data;

[0018] A processing device, for obtaining a dependency relationship diagram between the land and space resource data based on the land and space resource data;

[0019] A generating device is used to generate a national land space optimization strategy based on the requirements of national land space planning and a dependency relationship diagram between national land space resource data.

[0020] Preferably, the national land space resource data include: land use data, topographic data, climate and meteorological data, and remote sensing image data.

[0021] Preferably, the processing device uses a structured learning Bayesian network and conditional random field algorithm to analyze the relationships and conditional dependencies between land and space resource data and generate a dependency relationship diagram.

[0022] Preferably, the generating device comprises:

[0023] The first processing module is used to obtain regional management data, terrain planning data and functional planning data of national land space resource data according to the dependency relationship diagram between national land space resource data and the requirements of land space planning;

[0024] The second processing module is used to obtain a land space resource reasoning expression tree based on the regional management data, terrain planning data and functional planning data of the land space resource data;

[0025] The third processing module is used to infer the expression tree based on the national land space resources and obtain the national land space optimization strategy.

[0026] The present invention obtains land and space resource data; obtains a dependency relationship diagram between land and space resource data based on the land and space resource data; generates a land and space optimization strategy based on the requirements of land and space planning and the dependency relationship diagram between land and space resource data. The present invention can more accurately model and quantify the complex dependency relationship between land and space resource data, improve the understanding of the relationship between data, and thus make the analysis results more accurate and in-depth. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0028] Figure 1 This is a flow chart of a method for generating a national land space optimization strategy according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0031] Embodiment 1:

[0032] like Figure 1 As shown, an embodiment of the present invention provides a method for generating a national land space optimization strategy, including:

[0033] Step S1, obtaining land space resource data;

[0034] Step S2: obtaining a dependency relationship diagram between the land and space resource data according to the land and space resource data;

[0035] Step S3: Generate a national land space optimization strategy based on the requirements of national land space planning and the dependency relationship diagram between national land space resource data.

[0036] As an implementation method of an embodiment of the present invention, the national land space resource data includes: land use data, topographic data, climate and meteorological data, and remote sensing image data.

[0037] Furthermore, the land use data include land use and corresponding boundaries, which are used to reflect the use of the surface at different times and in different spatial ranges; the topographic data include elevation, slope and aspect, which reflect the topographic characteristics of different regions; the climate and meteorological data include temperature, rainfall and wind direction, which reflect the climate and meteorological change patterns in different regions; the remote sensing image data include high-resolution satellite images, which reflect the real situation of the surface.

[0038] As an implementation method of an embodiment of the present invention, in step S2, a Bayesian network and conditional random field algorithm of structured learning are used to analyze the mutual relationship and conditional dependency between land and space resource data, and generate a dependency relationship graph; wherein the dependency relationship graph includes data nodes, associated edges, and conditional dependency indicators. By adopting the Bayesian network and conditional random field algorithm of structured learning, the method can accurately reveal and analyze the conditional probability relationship and dependency path between multi-band satellite remote sensing data, so that the mutual relationship and dependency between data are more deeply understood and quantified, significantly improving the accuracy and depth of data analysis. Especially in applications in the fields of environmental monitoring, urban development, and natural disasters, this method can provide more comprehensive and accurate analysis results.

[0039] Step S2 is specifically as follows:

[0040] S21: Based on the probability map model of land and space resource data, the covariance analysis method is used to evaluate the correlation between multiple bands and generate a correlation analysis report;

[0041] S22: Based on the correlation analysis report, a graph theory algorithm is used to construct a preliminary network structure and generate an initial network structure diagram;

[0042] S23: Based on the initial network structure diagram, the Bayesian network parameter estimation method is used to refine the probability relationship in the network and generate an optimized probability network diagram;

[0043] S24: Based on the optimized probabilistic network graph, the conditional random field algorithm is used to describe the conditional dependency relationship between multi-source data and generate a dependency relationship graph;

[0044] Covariance analysis methods include Pearson correlation coefficient and Spearman rank correlation coefficient. Graph theory algorithms include shortest path algorithm and network flow algorithm. Bayesian network parameter estimation methods include maximum likelihood estimation and Bayesian estimation. Conditional random field algorithms include linear chain conditional random field and graph structure conditional random field.

[0045] In step S21, the covariance analysis method is used to evaluate the correlation between multiple bands through the probability map model based on multi-band satellite remote sensing data. This process involves the use of Pearson correlation coefficient and Spearman rank correlation coefficient, two statistical methods that can effectively measure the linear or nonlinear correlation between different remote sensing data bands. Finally, a comprehensive correlation analysis report is generated, which reveals the degree of correlation between different data bands and provides important basic information for subsequent data processing.

[0046] In step S22, based on the obtained correlation analysis report, a graph theory algorithm is used to construct a preliminary initial network structure diagram. This step involves the application of shortest path algorithms and network flow algorithms, which help to reveal the structural relationship and mobility characteristics between data. This enables a clearer visualization and understanding of the complex relationship between multi-source remote sensing data, laying the foundation for further data processing.

[0047] In step S23, based on the generated initial network structure diagram, the Bayesian network parameter estimation method is used to refine the probability relationship in the network. In this step, maximum likelihood estimation and Bayesian estimation are used to accurately determine the probability distribution of each node and edge in the network. This not only enhances the accuracy of the network model, but also enables the model to better reflect the dependencies and correlations between actual data.

[0048] In step S24, based on the optimized probability network graph, the conditional random field algorithm is used to further describe the conditional dependencies between multi-source data. Here, linear chain conditional random fields and graph structure conditional random fields are used to accurately model and analyze the conditional dependencies between data. The completion of this step marks the generation of the dependency graph, which not only makes the complex interdependencies between data more intuitive and easy to understand, but also provides a solid foundation for subsequent data analysis and processing.

[0049] As an implementation of the embodiment of the present invention, step S3 includes:

[0050] According to the dependency relationship diagram between the land and space resource data and the requirements of land and space planning, the regional management data, terrain planning data and functional planning data of the land and space resource data are obtained;

[0051] According to the regional management data, terrain planning data and functional planning data of the land and space resource data, a land and space resource reasoning expression tree is obtained; wherein the land and space resource knowledge tree is used to indicate the relationship between the supervised learning atlas metadata corresponding to the land and space resource data of the land and space resource;

[0052] According to the inference expression tree of land and space resources, the land and space optimization strategy is obtained.

[0053] Furthermore, based on the land space resource reasoning expression tree, the land space optimization strategies include:

[0054] Displaying a land and space resource reasoning expression tree, wherein the land and space resource reasoning expression tree comprises a plurality of nodes, each node represents a logical point in the land and space resource reasoning expression tree and the planning reasoning expression tree, and the hierarchical connection relationship between the nodes represents the logical association between the corresponding logical points;

[0055] In response to a node optimization operation triggered for a land and space resource reasoning expression tree, an optimization strategy for at least one first node is obtained, and a candidate node is selected in the land and space resource reasoning expression tree, wherein the hierarchical level of the candidate node is not lower than any of the first nodes;

[0056] Traversing the candidate node and the corresponding secondary nodes, obtaining at least one planning intention node and the corresponding optimization result; wherein the planning intention node is: a node whose node display state is affected after executing the optimization strategy, and the optimization result is: node data after the candidate optimization strategy is executed with adaptive optimization;

[0057] Based on the optimization result of at least one planning intention node, the land space resource reasoning expression tree is re-rendered to obtain an updated land space resource reasoning expression tree.

[0058] Example 2:

[0059] The embodiment of the present invention also provides a national land space optimization strategy generation system, including:

[0060] An acquisition device for acquiring land and space resource data;

[0061] A processing device, for obtaining a dependency relationship diagram between the land and space resource data based on the land and space resource data;

[0062] A generating device is used to generate a national land space optimization strategy based on the requirements of national land space planning and a dependency relationship diagram between national land space resource data.

[0063] As an implementation method of an embodiment of the present invention, the national land space resource data includes: land use data, topographic data, climate and meteorological data, and remote sensing image data.

[0064] As an implementation method of an embodiment of the present invention, the processing device uses a structured learning Bayesian network and a conditional random field algorithm to analyze the mutual relationships and conditional dependencies between land and space resource data and generate a dependency relationship diagram.

[0065] As an implementation manner of an embodiment of the present invention, the generating device includes:

[0066] The first processing module is used to obtain regional management data, terrain planning data and functional planning data of national land space resource data according to the dependency relationship diagram between national land space resource data and the requirements of land space planning;

[0067] The second processing module is used to obtain a land space resource reasoning expression tree based on the regional management data, terrain planning data and functional planning data of the land space resource data;

[0068] The third processing module is used to infer the expression tree based on the national land space resources and obtain the national land space optimization strategy.

[0069] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A method for generating a national land space optimization strategy, characterized in that: include: Step S1, obtaining land space resource data; Step S2: obtaining a dependency relationship diagram between the land and space resource data according to the land and space resource data; Step S3: Generate a national land space optimization strategy based on the requirements of national land space planning and the dependency relationship diagram between national land space resource data.

2. The method for generating a national land space optimization strategy according to claim 1, characterized in that: National land space resource data include: land use data, topography data, climate and meteorology data, and remote sensing image data.

3. The method for generating a national land space optimization strategy according to claim 2, characterized in that: In step S2, the Bayesian network and conditional random field algorithm of structured learning are used to analyze the mutual relationship and conditional dependency among the land space resource data and generate a dependency relationship diagram.

4. The method for generating a national land space optimization strategy according to claim 3, characterized in that: Step S3 includes: According to the dependency relationship diagram between the land and space resource data and the requirements of land and space planning, the regional management data, terrain planning data and functional planning data of the land and space resource data are obtained; According to the regional management data, terrain planning data and functional planning data of the national land space resource data, a national land space resource reasoning expression tree is obtained; According to the inference expression tree of land and space resources, the land and space optimization strategy is obtained.

5. A national land space optimization strategy generation system, characterized in that: include: An acquisition device for acquiring land and space resource data; A processing device, for obtaining a dependency relationship diagram between the land and space resource data based on the land and space resource data; A generating device is used to generate a national land space optimization strategy based on the requirements of national land space planning and a dependency relationship diagram between national land space resource data.

6. The national land space optimization strategy generation system according to claim 5, characterized in that: National land space resource data include: land use data, topography data, climate and meteorology data, and remote sensing image data.

7. The national land space optimization strategy generation system according to claim 6, characterized in that: The processing device adopts the Bayesian network and conditional random field algorithm of structured learning to analyze the mutual relationship and conditional dependency among the land space resource data and generate a dependency relationship diagram.

8. The national land space optimization strategy generation system according to claim 7, characterized in that: The generating device comprises: The first processing module is used to obtain regional management data, terrain planning data and functional planning data of national land space resource data according to the dependency relationship diagram between national land space resource data and the requirements of land space planning; The second processing module is used to obtain a land space resource reasoning expression tree based on the regional management data, terrain planning data and functional planning data of the land space resource data; The third processing module is used to infer the expression tree based on the national land space resources and obtain the national land space optimization strategy.