A natural resource multi-objective collaborative optimization configuration method

Abstract

The application discloses a natural resource multi-target collaborative optimization configuration method, relates to the technical field of resource configuration systems, and comprises the following stages: 1) constructing a data warehouse system of natural resource optimization configuration; 2) constructing an index system of natural resource optimization configuration based on an evolutionary multi-target algorithm; 3) constructing a natural resource optimization configuration model; and 4) coupling a multi-target hybrid intelligent algorithm and a natural resource parallel optimization model of decision subject preferences. Through data warehouse theories and methods, the application solves the problems of sharing and using multi-source natural resource data and interconnecting and intercommunicating various data, adopts an optimization configuration model based on all factors, coordinates and unifies the overall structure and functions of spatial resources, establishes a method for systematically planning and deploying spatial resources, and provides a basis for natural resource strategic layout, ecological protection and restoration, new urbanization development and scientific and reasonable industrial layout.

Description

Technical Field

[0001] This invention relates to the field of resource allocation system technology, and in particular to a multi-objective collaborative optimization allocation method for natural resources. Background Technology

[0002] Natural resource data from the Dabie Mountains is characterized by diverse content, complex structure, and large volume, encompassing a variety of spatial and temporal data formats, including basic geographic data, remote sensing imagery, land surveys, land use approvals, farmland and basic farmland protection data, and socio-economic data related to natural resource allocation optimization. However, challenges exist in achieving multidimensional integrity, data fusion and sharing, and access to closely related data sets.

[0003] Geospatial elements are stored in GIS systems as independent layers. This paper proposes a method for optimizing natural resource allocation by batch extracting geospatial and non-spatial data and storing them in a unified data format. When performing calculations such as land space carrying capacity and suitability assessments and multi-objective collaborative optimization, natural resource allocation optimization requires the comprehensive use of geographic data and attribute data stored in different file systems. Therefore, this invention aims to study methods for connecting, fusing, and associating multi-file data. Summary of the Invention

[0004] Based on the background technology and the purpose of this invention, this application proposes a multi-objective collaborative optimization allocation method for natural resources, comprising the following stages:

[0005] (1) Construct a data warehouse system for the optimal allocation of natural resources;

[0006] (2) Construct an indicator system for the optimal allocation of natural resources based on evolutionary multi-objective algorithms;

[0007] (3) Construct a natural resource optimization allocation model;

[0008] (4) A parallel optimization model for natural resources that couples multi-objective hybrid intelligent algorithms with the preferences of decision-making subjects;

[0009] Furthermore, in stage (1), data warehouse technology is used to establish a big data support system for multi-source information integration oriented towards the optimal allocation of natural resources;

[0010] Stage (2) is based on natural resource endowment, rationally determines the evaluation object and selects the natural resource optimization allocation target, and adopts the intuition fuzzy set method to form a multi-objective natural resource optimization allocation model containing variables, objective function and constraints.

[0011] Stage (3) is to adopt a multi-objective Pareto efficient solution and use a data interval model based on cellular automata to improve a firefly optimization algorithm based on Chebyshev mapping, and form a natural resource optimization allocation model based on firefly multi-objective algorithm.

[0012] Phase (4) adopts a domain knowledge and data-driven intelligent group decision-making method, introduces the swarm intelligence optimization algorithm into the field of natural resource optimization allocation rule mining, supports the autonomous evaluation and deduction of intelligent decision-making, and provides a high-performance computing solution for data and task parallelism for natural resource optimization allocation.

[0013] Furthermore, the structure of a data warehouse system includes:

[0014] The data source layer includes two types of data sources: entity-aware data sources and abstract data source layers.

[0015] The data processing layer, in which the processing of entity perception data is achieved by using the perception acquisition layer and network transmission layer in the Internet of Things technology system, and finally the required data is loaded into the fast-changing attribute library; the processing process of the abstract data includes the following stages: (1) According to the time characteristics of the data information, it is divided into two categories, namely fast-changing attribute abstract data and stable attribute abstract data; (2) Stable attribute abstract data is loaded into a specific business subject library using traditional ETL data processing tools; (3) For fast-changing attribute abstract data, since its attribute information is rich in time characteristics and changes quickly, based on comprehensive reference to relevant literature on data warehouses, a custom ETL tool module is designed to reconstruct the data structure of its related attributes, separate and extract the key attributes required by the user from the original relation table, and then recombine them into one or more new relation sub-tables, and add new foreign keys in the parent table to establish the connection between the parent table and the sub-table, and finally load the sub-table into the fast-changing attribute library;

[0016] The data storage layer adds a rapidly changing attribute library as a host for current data to the data storage layer of the natural resource data warehouse; the data storage layer also includes a spatial data warehouse, a data mart, and a metadata database. The spatial data warehouse is composed of n business subject databases. Data in the spatial data warehouse is integrated into the rapidly changing attribute library and the metadata database, and is also transmitted to the data mart.

[0017] The application analysis layer comprises a multi-source information integrated natural resource data warehouse, a comprehensive integration server, and mobile terminals. This layer tightly integrates the server and mobile terminals through distributed computing technology and spatial analysis, mining, application modeling, and visualization technologies based on general geographic information. It utilizes core technologies such as interactive technology, map publishing technology, spatial analysis technology, and modeling technology to achieve operations and objectives such as project site selection, satellite imagery enforcement, land surveys, geological disaster monitoring, and farmland protection. Within this layer, an XML-based Web service is deployed on the server side to enable indirect interaction between the mobile GIS client and the data warehouse located on the server, achieving analytical applications.

[0018] Furthermore, entity perception data sources are spatial object information acquired through smartphones, tablets, and their related sensors; the spatial object information includes houses, vehicles, and land features.

[0019] Furthermore, abstract data sources refer to unstructured data generated after processing such as modeling according to different data production standards and related specifications of various departments; the unstructured data includes GIS data, relational database data, and data in different types of text formats; the different data of various departments include land use data, urban planning data, geological environment data, and economic and social data; the unstructured data includes MDB text format, DBF / MDF text format, DEM / DOM text format, DAT / MYD text format, and TXT text format.

[0020] Furthermore, in the data processing layer, intelligent readers are used to acquire entity perception data, and communication between the ONS server, EPC server, and intelligent readers is achieved through API interfaces.

[0021] Furthermore, the integrated server side is the convergence of ubiquitous internet networks, including GSM, TD-SCDMA, Internet, Intranet, WLAN, WPAN, etc.; the mobile terminal is a computer device that can be used while on the move, including mobile phones, laptops, tablets, POS machines, in-vehicle computers, etc.

[0022] Furthermore, the indicator system includes:

[0023] (i) Functionally synergistically optimized living, ecological, and production goals;

[0024] (ii) Structural resource allocation: arable land, forest land, grassland, water area, and construction;

[0025] (iii) Geographical elements include soil, climate, hydrology, vegetation, topography, and geology;

[0026] That is, to strive for an optimal comprehensive benefit through the rational combination of various natural resource assets.

[0027] Furthermore, living goals include material production, economic development, employment support, social security, transportation development, and housing security; ecological goals include coordination, sustainability, environmental purification, and resource supply; and production goals include suitability, compactness, and planning costs.

[0028] Furthermore, the natural resource optimization allocation model includes a multi-objective collaborative system for natural resource allocation, resource and environmental carrying capacity, multi-objective collaborative optimization evaluation indicators, multi-objective collaborative optimization evaluation models and methods, multi-objective optimization allocation model for natural resources, cellular automata, firefly optimization algorithm based on Chebyshev mapping, set of natural resource optimization allocation schemes, comparative analysis and evaluation of optimization allocation results, and decision support for natural resource allocation.

[0029] Furthermore, in stage (4), natural resource-related data, knowledge rule mining algorithms, domain knowledge bases, multi-objective collaborative intelligent optimization configuration models for natural resources, multi-objective collaborative hybrid intelligent algorithms based on decomposition mechanisms, and intelligent algorithms based on the MapReduce cloud computing platform are optimized.

[0030] The present invention has the following beneficial effects:

[0031] (1) Through data warehouse theory and methods, the problems of sharing and using multi-source natural resource data and interconnection of various types of data have been solved. An optimization allocation model based on all elements is adopted to coordinate and unify the overall structure and function of spatial resources, and to establish a method for systematic planning and allocation of spatial resources. This provides a basis for strategic layout of natural resources, ecological protection and restoration, new urbanization development and scientific and rational layout of industries, and can also provide some reference for other special planning studies.

[0032] (2) This invention addresses the contradictions and conflicts in the allocation of natural resources to a certain extent. It adopts multi-objective collaborative optimization and the theory of comparative advantage of natural resources, proposes a path for natural resource optimization and pattern reconstruction, realizes multi-objective collaborative optimization of spatial resources, and provides support for the sustainable use of natural resources.

[0033] (3) This invention overcomes the shortcomings of traditional methods that can only optimize the quantity and structure of natural resources, and realizes spatial optimization of natural resource allocation. It not only adjusts the structure of natural resources, but also allocates them in terms of spatial layout. This makes the allocation results more scientific and reasonable, and provides a more intuitive and clear reference for natural resource utilization planning.

[0034] (4) This invention establishes an scalable multi-objective system, which breaks through the limitations of the multi-objective system for optimizing the allocation of natural resources. At the same time, the allocation fully relies on the carrying capacity of resources and environment, greatly enriching the diversity of optimizing the allocation of natural resources, thereby improving the adaptability to complex scenarios in real-world situations. Attached Figure Description

[0035] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0036] Figure 1 This is a framework diagram of a multi-source information integration Dabie Mountain natural resource data warehouse system constructed according to Embodiment 2 of the present invention;

[0037] Figure 2 This is a framework diagram of an index system for optimizing the allocation of natural resources in the Dabie Mountains based on an evolutionary multi-objective algorithm, constructed according to Embodiment 3 of the present invention.

[0038] Figure 3 This is an organizational coupling diagram among the following components in Embodiment 4 of the present invention: multi-objective collaborative system for natural resource allocation, resource and environmental carrying capacity, multi-objective collaborative optimization evaluation index, multi-objective collaborative optimization evaluation model and method, multi-objective optimization allocation model for natural resources, cellular automata, firefly optimization algorithm based on Chebyshev mapping, set of optimization allocation schemes for natural resources, comparative analysis and evaluation of optimization allocation results, and decision support for natural resource allocation.

[0039] Figure 4 This is a flowchart of a parallel optimization model for natural resources in the Dabie Mountains that couples a multi-objective hybrid intelligent algorithm with the preferences of the decision-making subject, constructed according to Embodiment 5 of the present invention. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.

[0041] Example 1

[0042] This embodiment discloses a multi-objective collaborative allocation method for optimizing the allocation of natural resources (taking the natural resources of the Dabie Mountains region in China as the research object), which includes the following stages:

[0043] (1) Construct a data warehouse system for the optimal allocation of natural resources in the Dabie Mountains;

[0044] (2) Construct an indicator system for the optimal allocation of natural resources in the Dabie Mountains based on an evolutionary multi-objective algorithm;

[0045] (3) Construct an optimal allocation model for natural resources in the Dabie Mountains;

[0046] (4) A parallel optimization model of natural resources in Dabie Mountain that couples multi-objective hybrid intelligent algorithm with decision-making subject preferences.

[0047] In this embodiment,

[0048] (1) Using data warehouse technology, a big data support system for multi-source information integration for the optimal allocation of natural resources in the Dabie Mountains was established.

[0049] (2) Based on the natural resource endowment, the evaluation object is reasonably determined and the target of the optimal allocation of natural resources in Dabie Mountain is selected. The intuitive fuzzy set method is used to form a multi-objective Dabie Mountain natural resource optimal allocation model that includes variables, objective functions and constraints.

[0050] (3) A multi-objective Pareto efficient solution is adopted, and a data interval model based on cellular automata is used to improve a firefly optimization algorithm based on Chebyshev mapping, forming a solution scheme for the Dabie Mountain natural resource optimization allocation model based on the firefly multi-objective algorithm.

[0051] (4) Adopting domain knowledge and data-driven intelligent group decision-making methods, introducing swarm intelligence optimization algorithms into the field of natural resource optimization allocation rule mining, supporting the autonomous evaluation and deduction of intelligent decisions, and providing a high-performance computing solution with parallel data and tasks for the optimization allocation of natural resources in the Dabie Mountains.

[0052] Example 2

[0053] Based on Embodiment 1, Embodiment 2 discloses a Dabie Mountain natural resource data warehouse system that integrates multi-source information, such as... Figure 1 As shown, it specifically includes the following:

[0054] When addressing the practical business needs such as the allocation of natural resources in the Dabie Mountains, and considering the application trends of IoT technology, mobile internet technology, and their integration with GIS, LBS, GNSS, and RS, the architecture of the Dabie Mountains natural resource data warehouse is divided into four layers: data source layer, data processing layer, data storage layer, and application analysis layer.

[0055] Based on different data acquisition methods, the data sources of the Dabie Mountain Natural Resources Data Warehouse are divided into two categories: entity perception data sources and abstract data data sources.

[0056] Among them, entity perception data sources are spatial physical information obtained through smartphones, tablets and their related sensors. Specifically, spatial physical information includes houses, vehicles, and land features.

[0057] Abstract data sources refer to unstructured data generated after processing such as modeling according to different data production standards and related specifications of various departments. Examples include GIS data, relational database data, and data in various text formats. The different data from various departments include land use data, urban planning data, geological environment data, and economic and social data. Unstructured data includes MDB text formats, DBF / MDF text formats, DEM / DOM text formats, DAT / MYD text formats, and TXT text formats.

[0058] In the data processing layer of this embodiment, the processing of entity perception data is mainly achieved using the sensing acquisition layer and network transmission layer in the Internet of Things (IoT) technology system. Finally, the obtained required data is loaded into the fast-change attribute library. For example, if a smart reader is used to acquire entity perception data, communication between the ONS server, EPC server, and smart reader is achieved through the API interface (i.e., application programming interface).

[0059] The processing of abstract data classes can be mainly divided into the following three steps:

[0060] (1) First, based on the time characteristics of the data information, it is divided into two categories: rapidly changing attribute abstract data and stable attribute abstract data;

[0061] (2) Secondly, the stable attribute abstract data is loaded into a specific business entity library using traditional ETL data processing tools;

[0062] (3) Finally, for the rapidly changing attribute abstract data, since its attribute information is rich in time characteristics and changes rapidly, based on the comprehensive reference of relevant data warehouse literature, we designed to use a custom ETL tool module to reconstruct the data structure of its related attributes, separate and extract the key attributes required by the user from the original relation table (parent table), and then recombine them into one or more new relation sub-tables (sub-tables), and add new foreign keys to the parent table to establish the connection between the parent table and the sub-table, and finally load the sub-table into the rapidly changing attribute library.

[0063] In the data storage layer of this embodiment, to adapt to the characteristics of natural resource data in the Dabie Mountains, and referring to relevant literature on traditional data warehouse theories and technical methods, it is summarized that, compared to the traditional data warehouse storage layer, the data storage layer of a data warehouse integrating IoT and mobile GIS technologies mainly addresses the real-time acquisition, loading, storage, and updating of rapidly changing data (i.e., current data). The solution is to add a rapidly changing attribute library as the host for current data in the data storage layer of the natural resource data warehouse. In addition, the data storage layer also includes a spatial data warehouse, a data mart, and a metadata database. The spatial data warehouse consists of n business subject databases. Data in the spatial data warehouse is integrated into the rapidly changing attribute library and the metadata database, and is also transmitted to the data mart.

[0064] In this embodiment, the application analysis layer includes a comprehensive integration server for the Dabie Mountain Natural Resources Data Warehouse, which integrates multi-source information, and a mobile GIS client (mobile terminal). The comprehensive integration server is a fusion of ubiquitous internet networks, including GSM, TD-SCDMA, Internet, Intranet, WLAN, WPAN, etc. The mobile GIS client is a computer device that can be used while on the move, specifically including mobile phones, laptops, tablets, POS machines, vehicle computers, etc.

[0065] The application analysis layer closely integrates servers and mobile terminals through distributed computing technology and spatial analysis, mining, application modeling and visualization technologies of pan-geographic information. Specifically, it utilizes core technologies such as interactive technology, map publishing technology, spatial analysis technology and modeling technology to achieve operations and objectives such as project site selection, satellite imagery enforcement, land survey, geological disaster monitoring and farmland protection.

[0066] In the application analysis layer, an XML-based web service is deployed on the server side to enable indirect interaction between the mobile GIS client and the data warehouse on the server side, thereby achieving the effect of analysis application.

[0067] Example 3

[0068] like Figure 2 As shown in the figure, this embodiment constructs an index system for the optimal allocation of natural resources in the Dabie Mountains based on an evolutionary multi-objective algorithm.

[0069] The indicator system in this embodiment aims to coordinate the three major goals of life, ecology and production of natural resources in the Dabie Mountains, that is, to strive to achieve an optimal comprehensive benefit through the rational combination of various natural resource assets.

[0070] Based on the element-structure-function principle in systems theory, this study attempts to establish an organic connection between various functions and the spatial structure of the land, and systematically identifies and classifies the spatial functions of the land at different levels. Building upon this functional identification and classification, and with the optimization goal of balancing production, living conditions, and ecology, and using resource and environmental carrying capacity as a constraint on the allocation of natural resources in the Dabie Mountains, this study selects a series of indicators closely related to the natural resources, sectors, and industries of the Dabie Mountains using multi-source data such as socio-economic statistics, remote sensing data, and current land use. Employing the intuitionistic fuzzy set method, it constructs decision-making models for the priority use of each sub-region and each natural resource based on preference information. Indicators such as ecological protection red lines and basic farmland protection boundaries serve as supplementary constraints, forming a multi-objective Dabie Mountains natural resource optimization allocation model that includes variables, objective functions, and constraints.

[0071] The living objectives include material production, economic development, employment support, social security, transportation development, and housing security; the ecological objectives include coordination, sustainability, environmental purification, and resource supply; and the production objectives include suitability, compactness, and planning costs. The resource allocation within the structure includes arable land, forest land, grassland, water bodies, and construction. Geographical elements include soil, climate, hydrology, vegetation, topography, and geology.

[0072] Example 4

[0073] like Figure 3 As shown, this embodiment constructs a Dabie Mountain natural resource optimization allocation model, specifically involving a Dabie Mountain natural resource optimization allocation model based on the firefly multi-objective algorithm. This model includes a multi-objective collaborative system for natural resource allocation, resource and environmental carrying capacity, multi-objective collaborative optimization evaluation indicators, multi-objective collaborative optimization evaluation models and methods, a multi-objective natural resource optimization allocation model, cellular automata, a firefly optimization algorithm based on Chebyshev mapping, a set of natural resource optimization allocation schemes, comparative analysis and evaluation of optimization allocation results, and natural resource allocation decision support.

[0074] In this embodiment, resource and environmental carrying capacity is a social attribute that embodies and reflects the environmental system (whose structure and function are the root of its carrying capacity). It is the primary attribute considered in the multi-objective collaborative system for natural resource allocation and the multi-objective collaborative optimization evaluation index, and is fully relied upon in the allocation. The establishment of the multi-objective collaborative system for natural resource allocation in the Dabie Mountains is the foundation for establishing a multi-objective optimization allocation model for natural resources. The selection of multi-objective collaborative optimization evaluation indexes is a factor in the multi-objective collaborative system for natural resource allocation, and it determines the rationality and scientific nature of the optimization allocation. The multi-objective optimization allocation model for natural resources is the skeleton of the entire research, while the intelligent optimization algorithm is the core of this model, determining the generation of the natural resource optimization allocation scheme (set). The natural resource optimization allocation scheme (set) is the final goal and result of the research, while the evaluation model of the optimization results is the judgment method for evaluating the multi-objective collaborative system for natural resource allocation, the multi-objective collaborative optimization evaluation indexes, the optimization model, and the optimization effect of the intelligent algorithm, which has a direct impact on the decision-making choices of the decision-making body.

[0075] Considering the characteristics of multivariable, nonlinear, and highly conflicting multi-objective optimization allocation models for natural resources, a multi-objective Pareto efficient solution is adopted. Furthermore, an improved firefly optimization algorithm based on Chebyshev mapping is developed using a data interval model based on cellular automata, thus forming a solution scheme for the Dabie Mountains natural resource optimization allocation model based on the firefly multi-objective algorithm.

[0076] Example 5

[0077] like Figure 4 As shown, this embodiment discloses an intelligent group decision-making method and a Dabie Mountain natural resource optimization allocation model, including Dabie Mountain natural resource related data, knowledge rule mining algorithm, domain knowledge base, natural resource multi-objective collaborative intelligent optimization allocation model, multi-objective collaborative hybrid intelligent algorithm based on decomposition mechanism, and intelligent algorithm based on MapReduce cloud computing platform and optimization.

[0078] Among them, the configuration of the domain knowledge base relies on expert guidance and policies and regulations; the configuration model of multi-objective collaborative intelligent optimization of natural resources selects decision support suggestions based on the multi-objective collaborative optimization problem and optimization results of natural resources; the configuration of multi-objective collaborative hybrid intelligent algorithm based on decomposition mechanism relies on objective decomposition and collaboration and hybrid intelligent algorithm; furthermore, objective decomposition and collaboration depend on multi-objective collaborative system and decision subject preferences, and the hybrid intelligent algorithm comprehensively relies on MOEA / D, ant colony intelligence and preference algorithm.

[0079] Based on the above, and considering the current research status, research ideas, and methodological potential of land space optimization, this paper adopts a domain knowledge- and data-driven intelligent swarm decision-making method. It introduces swarm intelligence optimization algorithms into the field of natural resource optimization rule mining, supporting the autonomous evaluation and deduction of intelligent decisions, and providing a high-performance computing solution for data and task parallelism in the Dabie Mountains natural resource optimization. Finally, it summarizes and analyzes to form a theoretical and technical methodology system guiding the optimization of natural resource allocation in the Dabie Mountains. Furthermore, land space optimization is a data-intensive and computationally intensive multi-objective optimization problem. Due to the advantages of cloud computing in big data processing, cloud-based spatial heterogeneous data management and parallelization strategies for multi-objective intelligent optimization algorithms will also be the focus of this embodiment.

[0080] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A natural resource multi-objective collaborative optimization configuration method, characterized in that, The method comprises the following stages: constructing a data warehouse system of natural resource optimal allocation; constructing an index system of natural resource optimal allocation based on an evolutionary multi-objective algorithm; constructing a natural resource optimal allocation model; coupling a multi-objective hybrid intelligent algorithm and a natural resource parallel optimization model of decision subject preference; In stage (1), a data warehouse technology is adopted to establish a big data support system of multi-source information integration for natural resource optimal allocation; In stage (2), based on natural resource endowment, an evaluation object is reasonably determined, a natural resource optimal allocation target is selected, an intuitionistic fuzzy set method is adopted, and a multi-objective natural resource optimal allocation model containing variables, a target function and constraint conditions is formed; In stage (3), a multi-objective Pareto effective solution is adopted, a data interval model based on a cellular automaton is utilized, and a firefly optimization algorithm based on Chebyshev mapping is improved to form a natural resource optimal allocation model based on a firefly multi-objective algorithm; In stage (4), a field knowledge and data-driven intelligent group decision method is adopted, a group intelligent optimization algorithm is introduced into the field of natural resource optimal allocation rule mining, self-evaluation and deduction of intelligent decision are supported, and a high-performance computing scheme of data and task parallel is provided for natural resource optimal allocation.

2. The natural resource multi-objective collaborative optimization configuration method according to claim 1, characterized in that, The structure of the data warehouse system comprises: a data source layer comprising two types of entity-aware data sources and abstract data sources; a data processing layer, wherein the processing of entity-aware data is realized by using a sensing acquisition layer and a network transmission layer in an Internet of Things technology system, and finally the obtained required data is loaded into a fast-changing attribute database; the processing process of the abstract data sources comprises the following stages: (1) according to the time characteristics of data information, the data information is divided into two types, i.e., fast-changing attribute abstract data and stable attribute abstract data; (2) the stable attribute abstract data is loaded into a specific business subject database by using a traditional ETL data processing tool; (3) for the fast-changing attribute abstract data, since the attribute information is rich in time characteristics and changes rapidly, on the basis of comprehensively referring to relevant data warehouse literature, a self-defined ETL tool module is designed to reconstruct the data structure of the related attributes, the required key attributes of a user are separated and extracted from the original relation table, and then the key attributes are recombined into one or more new relation sub-tables, a new foreign key is added in the parent table to establish the connection between the parent table and the sub-tables, and finally the sub-tables are loaded into the fast-changing attribute database; a data storage layer, in which a fast-changing attribute database is added as a host of present situation data in the data storage layer of the natural resource data warehouse; the data storage layer further comprises a spatial data warehouse, a data mart and a meta-database, wherein the spatial data warehouse is composed of n business theme databases, and the data in the spatial data warehouse is integrated into the fast-changing attribute database and the meta-database on one hand, and is transmitted to the data mart on the other hand; The application analysis layer includes a multi-source information integrated natural resource data warehouse comprehensive integration server end and a mobile terminal, and the application analysis layer is closely combined with the server and the mobile terminal through distributed computing technology and spatial analysis, mining, application modeling and visualization technology of the pan-geographic information, and uses core technologies such as interactive technology, map publishing technology, spatial analysis technology and modeling technology to realize project site selection, photo enforcement, land survey, land disaster monitoring, cultivated land protection operation and purposes, and in the application analysis layer, the mobile GIS client and the server end data warehouse are indirectly interacted through the deployment of the xml-based Webservice on the server end, so that the analysis application is achieved.

3. The natural resource multi-objective collaborative optimization configuration method according to claim 2, characterized in that, The entity perception type data source is spatial physical information acquired by a smart phone, a tablet computer and related sensors thereof; and the spatial physical information includes houses, vehicles and ground objects.

4. The natural resource multi-objective collaborative optimization configuration method according to claim 2, characterized in that, The abstract data type data source is unstructured data generated after modeling processing according to different data production standards and related specifications of each department; the unstructured data includes GIS data, relational database data and data in different types of text formats; the data of each department includes land use data, urban planning data, geological environment data and economic and social data; and the unstructured data includes MDB text format, DBF / MDF text format, DEM / DOM text format, DAT / MYD text format and TXT text format.

5. The natural resource multi-objective collaborative optimization configuration method according to claim 2, characterized in that, In the data processing layer, an intelligent reader / writer is used to acquire the entity perception type data, and the mutual communication among the ONS server, the EPC server and the intelligent reader / writer is realized through an API interface.

6. The natural resource multi-objective collaborative optimization configuration method according to claim 2, characterized in that, The comprehensive integration server end is the fusion of the ubiquitous Internet, including GSM, TD-SCDMA, Internet, Intranet, WLAN and WPAN; and the mobile terminal is a computer device that can be used in movement, including a mobile phone, a notebook computer, a tablet computer, a POS machine and a vehicle-mounted computer.

7. The natural resource multi-objective collaborative optimization configuration method according to claim 1, characterized in that, The index system includes: functionally synergistically optimized life goals, ecological goals and production goals; structurally resource-configured cultivated land, forest land, grassland, water area and construction; geographical elements including soil, climate, hydrology, vegetation, terrain and geology; that is, through the reasonable combination of various natural resource asset elements, an optimal comprehensive benefit is strived to achieve.

8. The natural resource multi-objective collaborative optimization configuration method according to claim 7, characterized in that, The life goals include material production, economic development, employment support, social security, traffic development and residence security; the ecological goals include coordination, maintenance, environmental purification and resource supply; and the production goals include suitability, compactness and planning cost.

9. The natural resource multi-objective collaborative optimization configuration method of claim 1, wherein, The natural resource optimization configuration model includes a natural resource configuration multi-target synergy system, resource environment carrying capacity, a multi-target synergy optimization evaluation index, a multi-target synergy optimization evaluation model and method, a natural resource multi-target optimization configuration model, a cellular automaton, a firefly optimization algorithm based on Chebyshev mapping, a natural resource optimization configuration scheme set, optimization configuration result comparison analysis and evaluation and natural resource configuration decision support.

10. The natural resource multi-objective collaborative optimization configuration method of claim 1, wherein, In the stage (4), the natural resource related data, the knowledge rule mining algorithm, the domain knowledge base, the natural resource multi-objective collaborative intelligent optimization configuration model, the multi-objective collaborative hybrid intelligent algorithm based on decomposition mechanism, and the intelligent algorithm based on the MapReduce cloud computing platform are optimized.

Images