Natural resource comprehensive evaluation method and system based on big data

Abstract

The invention provides a natural resource comprehensive evaluation method and system based on big data, and belongs to the technical field of natural resource management and information technology crossing. The system is formed by sequentially connecting a data acquisition and fusion module, a comprehensive evaluation index calculation module, a dynamic weight determination module, a comprehensive evaluation analysis module and a three-dimensional visualization module. The method comprises the following steps: collecting and fusing multi-source heterogeneous data; calculating the index value of each evaluation unit; dynamically determining an index weight based on the data characteristics; carrying out comprehensive evaluation by adopting an innovative model coupled with coordination and balance correction; and finally, an interactive three-dimensional visual scene is generated. According to the method, the defects of single data, subjective weight and non-visual result in a traditional evaluation method are overcome, the technical effects of full-process automation, objective weight distribution, deep evaluation dimension and visual result display are realized, and the scientificity and decision support capability of comprehensive evaluation of natural resources are remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of interdisciplinary technology of natural resource management and information technology, specifically to a comprehensive evaluation method and system for natural resources based on big data. Background Technology

[0002] Traditional natural resource assessment methods typically face several inherent limitations. First, at the data level, most methods rely on data from a single source or type, such as using only remote sensing imagery or limited field survey data. This data isolation leads to a one-sided assessment perspective, making it difficult to comprehensively capture the complexity and systematic nature of natural resources. Second, at the assessment model level, the weights of core assessment indicators are often subjectively assigned based on expert experience or calculated using simple, fixed formulas. This method lacks responsiveness to actual data characteristics; when data quality or distribution changes, the weights cannot adaptively adjust, leading to discrepancies between the assessment results and the actual situation. Finally, at the result presentation level, assessment conclusions are often displayed in the form of static charts or two-dimensional maps, lacking spatial depth and dynamic interactivity, making it difficult for decision-makers to intuitively and quickly understand complex spatial relationships and the root of problems.

[0003] Therefore, there is an urgent need in this field for a technology and system that can integrate multi-source heterogeneous data, objectively and dynamically determine evaluation parameters, and deeply visualize the results, in order to overcome the above-mentioned technical bottlenecks and improve the scientific and precise level of natural resource management and decision-making.

[0004] To address this, a comprehensive evaluation method and system for natural resources based on big data is proposed. Summary of the Invention

[0005] The present invention aims to solve the problems mentioned in the background art by providing a comprehensive evaluation method and system for natural resources based on big data.

[0006] The specific technical solution is as follows: A comprehensive natural resource evaluation system based on big data includes: The data acquisition and fusion module is used to collect raw natural resource data from multiple heterogeneous data sources, and to clean, standardize and spatially register the raw data to generate multi-source fused data. The comprehensive evaluation index calculation module is connected to the data acquisition and fusion module. It is used to receive the multi-source fused data and calculate the index values ​​of each evaluation unit based on the preset comprehensive evaluation index system. The dynamic weight determination module, connected to the comprehensive evaluation index calculation module, is used to dynamically determine the weight of each index in the comprehensive evaluation index system based on the distribution characteristics and data quality of the multi-source fusion data. The comprehensive evaluation and analysis module is connected to the comprehensive evaluation index calculation module and the dynamic weight determination module, respectively, and is used to calculate the comprehensive evaluation results of natural resources based on the index values ​​and the weights using the comprehensive evaluation model. The 3D visualization module, connected to the comprehensive evaluation and analysis module, is used to combine the comprehensive evaluation results of natural resources with geospatial information to generate and render an interactive 3D visualization scene.

[0007] The aforementioned big data-based comprehensive natural resource evaluation system, wherein the data acquisition and fusion module specifically includes: Remote sensing data unit is used to acquire land cover, vegetation index and topographic data from satellite or airborne remote sensing platforms; The Internet of Things (IoT) monitoring data unit is used to acquire real-time environmental monitoring data from a sensor network deployed at natural resource sites. The socio-economic development data unit is used to obtain population, economic, and industrial activity data from government statistical departments and open internet platforms.

[0008] The aforementioned big data-based comprehensive evaluation system for natural resources includes a comprehensive evaluation index system pre-set in the comprehensive evaluation index calculation module, which includes at least three dimensions: ecological function index, resource carrying capacity index, and socio-economic impact index.

[0009] In the aforementioned comprehensive natural resource evaluation system based on big data, the dynamic weight determination module is specifically used for: Principal component analysis was used to reduce the dimensionality of the multi-source fusion data and extract principal component factors. The initial weights of each indicator are calculated and dynamically adjusted based on the variance contribution rate of each principal component factor and the signal-to-noise ratio of the corresponding indicator data.

[0010] In the aforementioned comprehensive evaluation system for natural resources based on big data, the comprehensive evaluation analysis module adopts a weighted summation model or a fuzzy comprehensive evaluation model.

[0011] In the aforementioned comprehensive natural resource evaluation system based on big data, the three-dimensional visualization module is further used for: In the interactive 3D visualization scene, different levels of the comprehensive evaluation results of natural resources are mapped using different colors, transparency, or height. In response to the user's spatial query operation, the system dynamically displays detailed indicator values ​​and weight information for the specified evaluation unit.

[0012] This invention also provides a comprehensive natural resource evaluation method based on big data, applied to the aforementioned comprehensive natural resource evaluation system based on big data, comprising the following steps: S1: Collect raw natural resource data from multiple heterogeneous data sources, and clean, standardize, and spatially register the raw data to generate multi-source fused data; S2: Based on the preset comprehensive evaluation index system, the multi-source fusion data is calculated to obtain the index values ​​of each evaluation unit; S3: Based on the distribution characteristics and data quality of the multi-source fusion data, dynamically determine the weight of each indicator in the comprehensive evaluation index system; S4: Based on the index values ​​and weights, a comprehensive evaluation model is used to calculate and generate a comprehensive evaluation result for natural resources; S5: Combine the comprehensive evaluation results of natural resources with geospatial information to generate and render an interactive three-dimensional visualization scene.

[0013] The aforementioned comprehensive natural resource evaluation method based on big data, wherein the dynamic determination of weights in step S3 specifically includes: S31: Principal component analysis is used to reduce the dimensionality of the multi-source fusion data and extract principal component factors. S32: Calculate and dynamically adjust the initial weights of each indicator based on the variance contribution rate of each principal component factor and the signal-to-noise ratio of the corresponding indicator data.

[0014] The aforementioned method for comprehensive evaluation of natural resources based on big data, wherein in step S4, the comprehensive evaluation model adopts a dynamically coupled weighted comprehensive evaluation model, and its comprehensive evaluation value S j The calculation formula is: ; in: S j This represents the comprehensive evaluation value of the j-th evaluation unit; n represents the total number of indicators; w i This represents the dynamic weight of the i-th index determined through step S32 in claim 8; x ij This represents the standardized value of the j-th evaluation unit on the ith index; , represents the average value of all indicators in the j-th evaluation unit; C j is the coordination adjustment coefficient for the j-th evaluation unit, and its value is determined by the coupling coordination degree between the indicators within the unit.

[0015] The present invention also provides a computing device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method.

[0016] The present invention has the following beneficial effects: 1. The evaluation basis has shifted from "isolated and one-sided" to "integrated and comprehensive": By systematically integrating multi-dimensional data such as remote sensing, IoT monitoring, and socio-economic data, data barriers have been broken down, and an unprecedented panoramic data view has been constructed, enabling evaluation conclusions to be built on a more solid and richer information foundation.

[0017] 2. The evaluation process has shifted from "subjective and static" to "objective and dynamic": The core innovation lies in changing the determination of indicator weights from relying on prior knowledge to being driven by the intrinsic characteristics of the data. The model can automatically adjust the weights according to the quality and distribution of the data, making the evaluation criteria no longer fixed but dynamically optimized according to the actual situation, greatly enhancing the objectivity and adaptability of the evaluation results.

[0018] 3. The evaluation focus has shifted from "quantitative accumulation" to "quality coordination": The innovative evaluation formula, in addition to calculating the overall level, further reveals the coordination and balance among various indicators within the system. This allows the evaluation results to not only answer the question of "good or bad," but also to further diagnose "whether it is healthy and sustainable," providing a deeper scientific basis for optimal resource allocation.

[0019] 4. Decision support moves from "abstract and obscure" to "intuitive and perceptible": The final evaluation results are deeply integrated with geospatial information and transformed into a three-dimensional scene that can be directly perceived and interacted with through three-dimensional visualization technology. This greatly reduces the difficulty of information interpretation, accelerates the decision-maker's cognitive process of complex situations, and makes management decisions more accurate and efficient. Attached Figure Description

[0020] Figure 1 A schematic diagram illustrating the architecture of a big data-based comprehensive evaluation system for natural resources provided in an embodiment of the present invention; Figure 2 A flowchart illustrating the big data-based comprehensive evaluation method for natural resources provided in this embodiment of the invention; Figure 3 A weight distribution diagram of a big data-based comprehensive evaluation system for natural resources provided in an embodiment of the present invention; Figure 4 A graph illustrating the calculation process of the comprehensive evaluation value of the big data-based comprehensive evaluation system for natural resources provided in this embodiment of the invention; Figure 5 The distribution map of the variance contribution rate of the principal component factors in the comprehensive evaluation system of natural resources based on big data provided in the embodiments of the present invention; Figure 6 The graph shows the impact of standardized values ​​of different indicators on the comprehensive score of the big data-based comprehensive evaluation system for natural resources provided in this embodiment of the invention. Detailed Implementation

[0021] The technical solution of the present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0022] The accompanying drawings are for illustrative purposes only and are schematic diagrams, not actual images. They should not be construed as limiting the scope of this application. To better illustrate the embodiments of the present invention, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual dimensions of the product. It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0023] In the accompanying drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components. In the description of the present invention, it should be understood that if terms such as "upper," "lower," "left," "right," "inner," and "outer" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, the terms used to describe positional relationships in the drawings are only for illustrative purposes and should not be construed as limiting the present application. For those skilled in the art, the specific meaning of the above terms can be understood according to the specific circumstances.

[0024] In the description of this invention, unless otherwise explicitly specified and limited, the term "connection" or similar designation indicating a connection between components should be interpreted broadly. For example, it can refer to a fixed connection, a detachable connection, or an integral part; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can refer to the internal communication between two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0025] Example 1 Reference Figure 1 and Figures 3-6 As shown, where, Figure 3 The weighting of the three indicators—vegetation coverage (0.5), soil fertility (0.3), and biodiversity (0.2)—is shown. Figure 4 The calculation path is presented as follows: basic score (0.81), average value (0.8), coordination adjustment coefficient (0.253), weighted dispersion (0.0034) to final comprehensive evaluation value (0.8107). Figure 5 Show the variance contribution rates of the three principal component factors (30%, 25%, 20%). Figure 6The linear contribution of standardized values ​​(range 0-1) of different indicators to the overall score was simulated, corresponding to vegetation cover (slope 0.5), soil fertility (slope 0.3), and biodiversity (slope 0.2), respectively. This embodiment provides a comprehensive natural resource evaluation system based on big data, including: a data acquisition and fusion module, a comprehensive evaluation indicator calculation module, a dynamic weight determination module, a comprehensive evaluation analysis module, and a three-dimensional visualization module, wherein: The data acquisition and fusion module is used to collect raw natural resource data from multiple heterogeneous data sources, and to clean, standardize and spatially register the raw data to generate multi-source fused data. The comprehensive evaluation index calculation module is connected to the data acquisition and fusion module, and is used to receive the multi-source fusion data and calculate the index values ​​of each evaluation unit based on the preset comprehensive evaluation index system. The dynamic weight determination module is connected to the comprehensive evaluation index calculation module and is used to dynamically determine the weight of each index in the comprehensive evaluation index system based on the distribution characteristics and data quality of the multi-source fusion data. The comprehensive evaluation and analysis module is connected to the comprehensive evaluation index calculation module and the dynamic weight determination module, respectively, and is used to calculate and generate a comprehensive evaluation result of natural resources based on the index values ​​and the weights using a comprehensive evaluation model. The 3D visualization module is connected to the comprehensive evaluation and analysis module and is used to combine the comprehensive evaluation results of natural resources with geospatial information to generate and render an interactive 3D visualization scene.

[0026] This solution constructs a complete system comprising five core modules: data fusion, indicator calculation, dynamic weighting, comprehensive evaluation, and visualization. It achieves integrated and automated processing of natural resources from data collection to result presentation. This solution overcomes the shortcomings of traditional evaluation methods, such as single data sources, fragmented processing flows, and excessive reliance on manual labor. It provides a systematic solution that significantly improves the overall efficiency and engineering practicality of comprehensive evaluation work.

[0027] Specifically, in this embodiment, the data acquisition and fusion module includes: Remote sensing data unit is used to acquire land cover, vegetation index and topographic data from satellite or airborne remote sensing platforms; The Internet of Things (IoT) monitoring data unit is used to acquire real-time environmental monitoring data from a sensor network deployed at natural resource sites. The socio-economic development data unit is used to obtain population, economic, and industrial activity data from government statistical departments and open internet platforms.

[0028] This scheme organically combines macro-level situational awareness, micro-level real-time monitoring, and the impact of human activities by specifically defining three heterogeneous data sources: remote sensing, the Internet of Things, and socio-economic data. This fusion of multi-dimensional data effectively broadens the information foundation for the evaluation, enabling the evaluation results to simultaneously reflect the intrinsic state of natural resources, their real-time changes, and the socio-economic pressures they are subject to, thereby enhancing the comprehensiveness and objectivity of the evaluation.

[0029] Specifically, in this embodiment, the comprehensive evaluation index system preset in the comprehensive evaluation index calculation module includes at least three dimensions: ecological function index, resource carrying capacity index, and socio-economic impact index.

[0030] This scheme breaks away from the limitations of previous approaches that focused solely on resource quantity or ecological aspects by constructing a three-dimensional indicator system encompassing ecology, resource carrying capacity, and socio-economic impacts. This multi-dimensional framework ensures a comprehensive assessment of the "attributes-capacity-value" of natural resources, enabling evaluation conclusions to support more comprehensive management decisions and avoiding decision-making biases caused by missing evaluation dimensions.

[0031] Specifically, in this embodiment, the dynamic weight determination module is used for: Principal component analysis was used to reduce the dimensionality of the multi-source fusion data and extract principal component factors. The initial weights of each indicator are calculated and dynamically adjusted based on the variance contribution rate of each principal component factor and the signal-to-noise ratio of the corresponding indicator data.

[0032] This scheme introduces a dynamic weight determination mechanism based on principal component analysis and data signal-to-noise ratio, so that the allocation of indicator weights no longer relies on subjective experience, but is objectively driven by the statistical characteristics and quality of the data itself. This method can adaptively highlight the role of key indicators while suppressing the influence of noisy and redundant indicators, thereby enhancing the scientific nature of the weight setting and the relevance of the evaluation results to the reality of the data.

[0033] Specifically, in this embodiment, the comprehensive evaluation analysis module uses a weighted summation model or a fuzzy comprehensive evaluation model.

[0034] This solution provides the system with flexibility to address different evaluation scenarios and needs by configuring multiple alternative comprehensive evaluation models (such as weighted summation and fuzzy comprehensive evaluation). For problems with clear data and well-defined rules, or problems with fuzzy data and gray areas, the most suitable model can be selected for processing, improving the system's applicability and solution accuracy.

[0035] Specifically, in this embodiment, the 3D visualization module is further used for: In the interactive 3D visualization scene, different levels of the comprehensive evaluation results of natural resources are mapped using different colors, transparency, or height. In response to the user's spatial query operation, the system dynamically displays detailed indicator values ​​and weight information for the specified evaluation unit.

[0036] This solution significantly lowers the barrier to interpreting professional data by mapping abstract evaluation data into intuitive visual elements such as color, transparency, and height, and supports interactive queries. Decision-makers can quickly locate problem areas and understand the level distribution in a three-dimensional spatial environment, thereby accelerating the transformation from analysis results to management insights.

[0037] Example 2 This embodiment provides a comprehensive natural resource evaluation method based on big data, applied to the big data-based comprehensive natural resource evaluation system in Embodiment 1, and includes the following steps: S1: Collect raw natural resource data from multiple heterogeneous data sources, and clean, standardize, and spatially register the raw data to generate multi-source fused data; S2: Based on the preset comprehensive evaluation index system, the multi-source fusion data is calculated to obtain the index values ​​of each evaluation unit; S3: Based on the distribution characteristics and data quality of the multi-source fusion data, dynamically determine the weight of each indicator in the comprehensive evaluation index system; S4: Based on the index values ​​and weights, a comprehensive evaluation model is used to calculate and generate a comprehensive evaluation result for natural resources; S5: Combine the comprehensive evaluation results of natural resources with geospatial information to generate and render an interactive three-dimensional visualization scene.

[0038] This solution provides a standardized operating procedure. This procedure links the disparate data processing, analysis, calculation, and visualization steps into a logically rigorous and repeatable automated pipeline, ensuring the standardization, traceability, and reproducibility of the evaluation process.

[0039] Specifically, in this embodiment, the dynamic determination of weights in step S3 includes: S31: Principal component analysis is used to reduce the dimensionality of the multi-source fusion data and extract principal component factors. S32: Calculate and dynamically adjust the initial weights of each indicator based on the variance contribution rate of each principal component factor and the signal-to-noise ratio of the corresponding indicator data.

[0040] The proposed method translates the specific steps for determining dynamic weights into executable operations. Its effect is to transform the aforementioned system advantages into methodological advantages, ensuring that at every stage of the process, the weights can be objectively and adaptively adjusted based on the actual input data, thereby guaranteeing the scientific nature of the evaluation at the methodological level.

[0041] Specifically, in this embodiment, in step S4, the comprehensive evaluation model adopts a dynamically coupled weighted comprehensive evaluation model, and its comprehensive evaluation value S j The calculation formula is: ; in: S j This represents the comprehensive evaluation value of the j-th evaluation unit; n represents the total number of indicators; w i This represents the dynamic weight of the i-th index determined through step S32 in claim 8; x ij This represents the standardized value of the j-th evaluation unit on the ith index; , represents the average value of all indicators in the j-th evaluation unit; C j Let be the coordination adjustment coefficient for the j-th evaluation unit, whose value is determined by the degree of coupling coordination among the indicators within that unit. .

[0042] By introducing a dynamically coupled weighted comprehensive evaluation formula, the traditional weighted summation is supplemented with consideration of the "coordination" and "balance" among the indicators within the evaluation unit. The effect is that the final evaluation value not only reflects the overall level of resources but also reveals the health and stability of its internal structure. This helps identify areas with high overall scores but reliant on individual indicators and potential imbalance risks, thereby guiding more forward-looking and structurally optimized management strategies.

[0043] The derivation of the formula: The purpose of this formula is to address the problem that traditional weighted summation models cannot reflect the synergistic or antagonistic effects between indicators. Its derivation follows a logic from simple to complex, and from general to specific: 1. Basic model selection: The most classic weighted summation model. As a foundation, it represents the "basic score" of the evaluation unit on each indicator.

[0044] 2. Introducing a "balanced development" correction factor: An ideal state of natural resources not only requires a high total score, but also coordinated development among various indicators to avoid the "weakest link effect" or internal imbalance where some indicators are extremely high while others are extremely low. Therefore, a correction term (1+Adjustment) is introduced. j Adjustments are made to the base score.

[0045] 3. Quantification of "Balance": This balance is quantified using the concept of weighted coefficient of variation. The traditional coefficient of variation is the standard deviation divided by the mean; this is improved to the concept of the ratio of the "weighted standard deviation" to the "weighted mean." (The formula contains...) This idea is reflected in the degree of dispersion of the indicator value around its average value after considering the weights. The lower the dispersion, the more balanced the development.

[0046] 4. Introducing "Coordination" Adjustment: Simple equilibrium may be a "low-level equilibrium," requiring a "high-level coordination." Therefore, a coordination adjustment coefficient C is introduced. j This coefficient draws inspiration from the coupling coordination degree model, calculating the geometric mean between all pairs of indicators. And according to their weight Weighted average is used to measure the degree to which indicators cooperate and develop together. j The larger the value, the stronger the synergistic effect between the indicators.

[0047] 5. Final Synthesis: Combining "balance" (represented by weighted dispersion) with "coordination" (represented by C) j The total correction is calculated by multiplying the base score by the coefficients (1 + coordination coefficient × balance measure). The final formula is: Overall Evaluation Value = Base Score × (1 + Coordination Coefficient × Balance Measure). This means that, given the same base score, an evaluation unit with internal coordination and balanced development will receive a higher final score.

[0048] Parameter Description S j : Comprehensive evaluation value. This is the final output of the formula, used to characterize the quality of the natural resource status of the j-th evaluation unit; a higher value is better.

[0049] w i Dynamic weights. These weights are derived from principal component analysis and signal-to-noise ratio calculations, ensuring the objectivity and data adaptability of the weight settings. This is crucial for integrating the formula with the overall scheme.

[0050] x ij Standardized index values ​​are dimensionless values ​​that have undergone preprocessing and standardization, allowing indices with different dimensions to be compared and calculated.

[0051] : Average value of unit indicators. Used to calculate the center position of all indicators within this evaluation unit.

[0052] C j Coordination adjustment coefficient. A core innovation parameter specifically used to quantify the strength of synergy among indicators within an evaluation unit. Its value ranges from 0 to 1; the closer to 1, the better the synergy.

[0053] Example usage: Suppose we are evaluating a piece of forest land (evaluation unit j) and select three indicators: vegetation coverage (X1), soil fertility (X2), and biodiversity (X3).

[0054] The dynamic weights are calculated to be: w1=0.5, w2=0.3, w3=0.2.

[0055] The standardized values ​​of the three indicators for this forest land are: x 1j =0.8,x 2j =0.9,x 3j =0.7.

[0056] Calculate the base score: 0.5×0.8+0.3×0.9+0.2×0.7=0.4+0.27+0.14=0.81.

[0057] Calculate the average value : (0.8+0.9+0.7) / 3=0.8.

[0058] Calculate the coordination adjustment coefficient C j : Calculate pairwise combinations : (X1,X2): ; (X1,X3): ; (X2,X3): ; C j =(0.329+0.237+0.194) / 3≈0.253.

[0059] Calculate the weighted dispersion (balance): Mole: 0.5²×(0.8-0.8)²+0.3²×(0.9-0.8)²+0.2²×(0.7-0.8)²=0+0.0009+0.0004=0.0013; Denominator: 0.5² + 0.3² + 0.2² = 0.25 + 0.09 + 0.04 = 0.38; Weighted dispersion = 0.0013 / 0.38 ≈ 0.0034; Calculate the final comprehensive evaluation value S j : S j =0.81×(1+0.253×0.0034)≈0.81×(1+0.00086)≈0.8107.

[0060] In this example, because the various indicators of the forest land are developing very evenly (with extremely low dispersion), the coordination brings a small positive gain.

[0061] Technical effect 1. Beyond simple weighting, reflecting the internal correlation of the system: This formula innovatively incorporates the coupling and coordination relationship between indicators into the comprehensive evaluation system, so that the evaluation results can not only reflect the "overall level" of resources, but also reveal the "health and coordination of its internal structure". The technical effect is significantly better than the traditional weighted summation.

[0062] 2. Enhance the differentiation of results and the guidance for decision-making: For regions with similar basic scores, this formula can further differentiate between the good and the bad by the differences in their internal coordination, and can provide managers with diagnostic information such as "whether the overall level is insufficient or the internal structure is unbalanced", thereby guiding them to take more targeted management measures (such as: whether to improve the whole or focus on improving the weak indicators).

[0063] 3. Deeply aligned with the overall plan: the core parameter w in the formula i The "dynamic weight determination" step, which is directly derived from the aforementioned claims, makes the formula no longer an isolated mathematical expression, but an organic component of the entire dynamic evaluation process based on big data analysis, thus enhancing the integrity and indivisibility of this solution.

[0064] Working principle and process: The formula works as follows within the system: 1. Data Input: Receives standardized indicator values ​​x from each evaluation unit via the upstream module. ij and dynamic weight w i .

[0065] 2. Basic Calculation: Calculate the basic weighted score for each evaluation unit. and indicator average .

[0066] 3. Coordination Analysis: Calculate the coordination adjustment coefficient C for each unit according to the formula. j This step essentially utilizes big data computing power to perform pairwise correlation analysis on all indicators.

[0067] 4. Balance analysis: Calculate the degree of dispersion of index values ​​after considering weights, as a measure of balance.

[0068] 5. Dynamic Synthesis: The base score, coordination coefficient, and balance measure are synthesized according to a formula, and the final output is a comprehensive evaluation value S that considers both the importance of the indicators and the internal coordination of the system. j .

[0069] 6. Output the results: S j It is then passed to the subsequent 3D visualization module for spatial display and analysis.

[0070] Example 3 This embodiment provides a computing device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the computer program to implement the steps of the big data-based comprehensive natural resource evaluation method in Embodiment 2.

[0071] By programming the aforementioned methods and deploying them on computing devices, the effect is to transform abstract methodologies into tangible, stable, and operational technological products. This ensures that the evaluation method can be executed efficiently and reliably in various computing environments in software form, enabling the industrial application and widespread promotion of the technical solution.

[0072] Specifically, in this embodiment, the fuzzy comprehensive evaluation model is suitable for scenarios where the indicator boundaries are unclear and there is fuzziness. It transforms the indicator values ​​into a fuzzy evaluation set through a membership function, and then combines the weights for comprehensive judgment.

[0073] The steps for constructing a fuzzy comprehensive evaluation model are as follows: Step 1: Determine the evaluation factor set U Suppose the evaluation index system contains n indicators: U={u1,u2,…,u n}; For example: u1 = vegetation cover, u2 = soil fertility, u3 = biodiversity... Step 2: Determine the comment set V Suppose the evaluation results are divided into m levels: V={v1,v2,…,v m} For example: V={Excellent, Good, Average, Poor}

[0074] Step 3: Construct the membership matrix R For each indicator u i Determine its membership degree r to each rating level. ik This forms a fuzzy relation matrix: ; Step 4: Determine the weight vector W Use dynamic weights to determine the weights of the module output: W=[w1,w2,…,w n ]; Step 5: Perform fuzzy synthesis calculations The comprehensive evaluation vector B is calculated using fuzzy operators (such as weighted average type). ; in For fuzzy composition operators, the weighted average model is commonly used: ; in: This is the k-th element in the comprehensive evaluation vector; it represents the membership degree of the evaluated object as a whole to the k-th rating level (such as "Excellent", "Good", "Average", "Poor"); it is a value between 0 and 1. The closer the value is to 1, the higher the degree to which the evaluated object as a whole belongs to that rating level; all Construct a comprehensive evaluation vector This vector describes the fuzzy distribution of the final evaluation result of the evaluation object.

[0075] k is the index of the comment level, used to traverse the sequence number of each preset comment level, k=1, 2, ...,m. When m=4, k=1 can be defined as "Excellent", k=2 as "Good", k=3 as "Average", and k=4 as "Poor".

[0076] n represents the total number of indicators, the total number of indicator items participating in the comprehensive evaluation. This is the same meaning of n as in the weighted summation model.

[0077] i is the index of the indicator, used to traverse the sequence number of each evaluation indicator i = 1, 2, ..., n.

[0078] w i The weight of the i-th indicator represents the relative importance of the i-th indicator in the comprehensive evaluation system, and is generated by the dynamic weight determination module. Membership degree is a core parameter in fuzzy comprehensive evaluation. It represents the degree to which the measured value of the i-th indicator is considered to belong to the k-th evaluation level; it is calculated using the membership function. The membership function acts as a bridge, converting the precise value of an indicator (e.g., vegetation cover = 0.85) into a vector (e.g., (0.8, 0.2, 0, 0)) representing the degree of conformity to each fuzzy level (excellent, good, average, poor). 10 ≤ ≤1, and for a single index i, the sum of its membership degrees across all levels is typically 1.

[0079] Step 6: Result Determination The final evaluation level is determined based on the principle of maximum membership or the weighted average method, i.e., final level = selected b. k The grade with the highest value is used as the final evaluation result.

[0080] In summary, this invention generates multiple synergistic technological effects by constructing a complete technological closed loop from data to decision-making: 1. The evaluation basis has shifted from "isolated and one-sided" to "integrated and comprehensive": By systematically integrating multi-dimensional data such as remote sensing, IoT monitoring, and socio-economic data, data barriers have been broken down, and an unprecedented panoramic data view has been constructed, enabling evaluation conclusions to be built on a more solid and richer information foundation.

[0081] 2. The evaluation process has shifted from "subjective and static" to "objective and dynamic": The core innovation lies in changing the determination of indicator weights from relying on prior knowledge to being driven by the intrinsic characteristics of the data. The model can automatically adjust the weights according to the quality and distribution of the data, making the evaluation criteria no longer fixed but dynamically optimized according to the actual situation, greatly enhancing the objectivity and adaptability of the evaluation results.

[0082] 3. The evaluation focus has shifted from "quantitative accumulation" to "quality coordination": The innovative evaluation formula, in addition to calculating the overall level, further reveals the coordination and balance among various indicators within the system. This allows the evaluation results to not only answer the question of "good or bad," but also to further diagnose "whether it is healthy and sustainable," providing a deeper scientific basis for optimal resource allocation.

[0083] 4. Decision support moves from "abstract and obscure" to "intuitive and perceptible": The final evaluation results are deeply integrated with geospatial information and transformed into a three-dimensional scene that can be directly perceived and interacted with through three-dimensional visualization technology. This greatly reduces the difficulty of information interpretation, accelerates the decision-maker's cognitive process of complex situations, and makes management decisions more accurate and efficient.

[0084] Working principle: The working principle of this invention follows a progressive, data-driven logical pipeline: 1. Multi-source data perception and fusion: The system first extensively perceives raw data from different platforms in the sky and on the ground. These heterogeneous data are processed through cleaning, standardization, and spatial registration, and then unified onto the same spatiotemporal reference to form a regular and computable "multi-source fusion data base map".

[0085] 2. Dynamic Indicator Quantification and Weight Allocation: Based on a pre-set multi-dimensional indicator system, the system extracts specific values ​​for each evaluation unit from the fused data base map. Simultaneously, the dynamic weight determination module performs in-depth data analysis, extracting key information structures through principal component analysis and automatically calculating the indicator weights that best reflect the current data characteristics, in conjunction with the data signal-to-noise ratio.

[0086] 3. Comprehensive Analysis of Coupling and Coordination: The comprehensive evaluation and analysis module receives indicator values ​​and dynamic weights, and uses an innovatively designed dynamic coupling weighting model for calculation. This model not only performs conventional weighted summarization, but more importantly, it internally calculates the degree of coordination and development balance among the indicators, and uses this structural information as correction factors to synthesize the final comprehensive evaluation value.

[0087] 4. Spatial Visualization Result Mapping: Finally, the 3D visualization module binds the abstract numerical evaluation values ​​with specific geographical locations. Through visual channels such as color, height, and transparency, the evaluation results are projected onto the 3D terrain model in a three-dimensional and realistic manner, forming an immersive digital twin scene that users can freely explore.

[0088] How to use: The operation and use of this system should follow these clear steps: 1. System Initialization and Data Preparation: After system deployment, users first configure the connection parameters for various data sources to ensure stable access for remote sensing data services, IoT data interfaces, and socio-economic databases. Simultaneously, based on the specific circumstances of the area to be evaluated, the composition of the comprehensive evaluation index system is set or fine-tuned.

[0089] 2. Automated Evaluation Process: Users initiate evaluation tasks through the system interface. The system will automatically execute the entire workflow: sequentially completing data collection and fusion, indicator calculation, dynamic weight determination, and comprehensive evaluation analysis. During this process, users do not need to intervene in complex internal calculations.

[0090] 3. 3D Visualization Exploration and Diagnosis: After calculation, the system automatically loads and renders a 3D visualization scene. Users can zoom, rotate, and translate within this scene to examine the overall layout of resources from different perspectives. By clicking on an evaluation unit of interest, users can immediately view its detailed indicator scores, weight allocation, and internal coordination analysis report, thereby achieving precise problem location and diagnosis.

[0091] 4. Results Output and Decision Support: Users can export evaluation reports of visualized scenes or key areas from specific perspectives for use in planning scheme development, project review, or as a direct basis for scientific decision-making. This system thus becomes a powerful decision support tool that spans the entire lifecycle of natural resource management.

[0092] The above are merely preferred embodiments of the present invention and are not intended to limit the implementation methods and protection scope of the present invention. Those skilled in the art should recognize that any equivalent substitutions and obvious changes made based on the description and illustrations of the present invention should be included within the protection scope of the present invention.

Claims

1. A comprehensive natural resource evaluation system based on big data, characterized in that, include: The data acquisition and fusion module is used to collect raw natural resource data from multiple heterogeneous data sources, and to clean, standardize and spatially register the raw data to generate multi-source fused data. The comprehensive evaluation index calculation module is connected to the data acquisition and fusion module. It is used to receive the multi-source fused data and calculate the index values ​​of each evaluation unit based on the preset comprehensive evaluation index system. The dynamic weight determination module, connected to the comprehensive evaluation index calculation module, is used to dynamically determine the weight of each index in the comprehensive evaluation index system based on the distribution characteristics and data quality of the multi-source fusion data. The comprehensive evaluation and analysis module is connected to the comprehensive evaluation index calculation module and the dynamic weight determination module, respectively, and is used to calculate the comprehensive evaluation results of natural resources based on the index values ​​and the weights using the comprehensive evaluation model. The 3D visualization module, connected to the comprehensive evaluation and analysis module, is used to combine the comprehensive evaluation results of natural resources with geospatial information to generate and render an interactive 3D visualization scene.

2. The comprehensive natural resource evaluation system based on big data according to claim 1, characterized in that, The data acquisition and fusion module specifically includes: Remote sensing data unit is used to acquire land cover, vegetation index and topographic data from satellite or airborne remote sensing platforms; The Internet of Things (IoT) monitoring data unit is used to acquire real-time environmental monitoring data from a sensor network deployed at natural resource sites. The socio-economic development data unit is used to obtain population, economic, and industrial activity data from government statistical departments and open internet platforms.

3. The comprehensive natural resource evaluation system based on big data according to claim 2, characterized in that, The comprehensive evaluation index system preset in the comprehensive evaluation index calculation module includes at least three dimensions: ecological function index, resource carrying capacity index, and socio-economic impact index.

4. The comprehensive natural resource evaluation system based on big data according to claim 3, characterized in that, The dynamic weight determination module is specifically used for: Principal component analysis was used to reduce the dimensionality of the multi-source fusion data and extract principal component factors. The initial weights of each indicator are calculated and dynamically adjusted based on the variance contribution rate of each principal component factor and the signal-to-noise ratio of the corresponding indicator data.

5. The comprehensive natural resource evaluation system based on big data according to claim 4, characterized in that, The comprehensive evaluation analysis module uses a weighted summation model or a fuzzy comprehensive evaluation model.

6. The comprehensive natural resource evaluation system based on big data according to claim 5, characterized in that, The 3D visualization module is also used for: In the interactive 3D visualization scene, different levels of the comprehensive evaluation results of natural resources are mapped using different colors, transparency, or height. In response to the user's spatial query operation, the system dynamically displays detailed indicator values ​​and weight information for the specified evaluation unit.

7. A comprehensive natural resource evaluation method based on big data, applied to the comprehensive natural resource evaluation system based on big data as described in any one of claims 1 to 6, characterized in that, Includes the following steps: S1: Collect raw natural resource data from multiple heterogeneous data sources, and clean, standardize, and spatially register the raw data to generate multi-source fused data; S2: Based on the preset comprehensive evaluation index system, the multi-source fusion data is calculated to obtain the index values ​​of each evaluation unit; S3: Based on the distribution characteristics and data quality of the multi-source fusion data, dynamically determine the weight of each indicator in the comprehensive evaluation index system; S4: Based on the index values ​​and weights, a comprehensive evaluation model is used to calculate and generate a comprehensive evaluation result for natural resources; S5: Combine the comprehensive evaluation results of natural resources with geospatial information to generate and render an interactive three-dimensional visualization scene.

8. The comprehensive evaluation method for natural resources based on big data according to claim 7, characterized in that, The dynamic determination of weights in step S3 specifically includes: S31: Principal component analysis is used to reduce the dimensionality of the multi-source fusion data and extract principal component factors. S32: Calculate and dynamically adjust the initial weights of each indicator based on the variance contribution rate of each principal component factor and the signal-to-noise ratio of the corresponding indicator data.

9. The comprehensive evaluation method for natural resources based on big data according to claim 8, characterized in that, In step S4, the comprehensive evaluation model adopts a dynamically coupled weighted comprehensive evaluation model, and its comprehensive evaluation value S j The calculation formula is: ； in: S j This represents the comprehensive evaluation value of the j-th evaluation unit; n represents the total number of indicators; w i This represents the dynamic weight of the i-th index determined through step S32 in claim 8; x ij This represents the standardized value of the j-th evaluation unit on the ith index; , represents the average value of all indicators in the j-th evaluation unit; C j is the coordination adjustment coefficient for the j-th evaluation unit, and its value is determined by the coupling coordination degree between the indicators within the unit.

10. A computing device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the big data-based comprehensive evaluation method for natural resources as described in any one of claims 7 to 9.

Images